CN111859240A

CN111859240A - Picture exporting method, related device and storage medium

Info

Publication number: CN111859240A
Application number: CN202010762761.6A
Authority: CN
Inventors: 李龙彬
Original assignee: Tencent Technology Wuhan Co Ltd
Current assignee: Tencent Technology Wuhan Co Ltd
Priority date: 2020-07-31
Filing date: 2020-07-31
Publication date: 2020-10-30

Abstract

The application discloses a picture exporting method, which comprises the following steps: when a picture viewing instruction for a page to be identified is acquired, displaying M pictures contained in the page to be identified through a picture viewer; sending a target text identifier to a server so that the server determines target atlas identification information according to the target text identifier; if the target atlas identification information meets the picture export condition, displaying an atlas export interface on a picture viewer according to an atlas export request sent by a server; when the operation aiming at the atlas exporting interface is detected, exporting the N pictures in the page to be identified as the file corresponding to the target format. The application also provides a related device. According to the method and the device, whether the picture in the page can be derived or not can be intelligently decided, so that the reasonability of data derivation is increased, and the picture derivation efficiency is improved.

Description

Picture exporting method, related device and storage medium

Technical Field

The present application relates to the field of artificial intelligence, and in particular, to a method for exporting pictures, a related apparatus, and a storage medium.

Background

With the rapid development of the internet, the information on the network is more and more abundant, and the browser is more and more diversified. The browser page not only includes characters, but also includes a large number of pictures, and the pictures are popular with users because the information to be displayed can be visually displayed, so the pictures occupy very important positions in the webpage information.

At present, a mode of deriving a picture from a page is that a user selects a picture to be derived first in the page, a dialog box pops up after long-time pressing of the picture or clicking of the picture, then an option of saving the picture is clicked from the dialog box, and a browser responds to the selection of the user and saves the picture locally in a terminal device.

However, there are often many pictures on a page, and if a user wants to save the pictures, the user needs to perform the above operations for each picture separately, and the whole process is cumbersome, so that the efficiency of deriving the pictures is low.

Disclosure of Invention

The embodiment of the application provides a picture exporting method, a related device and a storage medium. Whether the pictures in the page can be exported or not is intelligently decided based on the identification information of the target atlas, so that the reasonability of data export is increased. Under the condition that the atlas can be exported, the picture on the page is exported to the file corresponding to the target format in the one-key export mode, and therefore the picture export efficiency is improved.

In view of the above, an aspect of the present application provides a method for deriving a picture, including:

when an image viewing instruction for a page to be identified is obtained, displaying M images contained in the page to be identified through an image viewer, wherein the image viewing instruction carries a target text identifier, the target text identifier is used for indicating a target text contained in the page to be identified, and M is an integer greater than or equal to 1;

sending a target text identifier to a server so that the server determines target atlas identification information according to the target text identifier;

if the target atlas identification information meets the picture export condition, displaying an atlas export interface on a picture viewer according to an atlas export request sent by a server, wherein the atlas export interface is used for exporting N pictures in M pictures, and N is an integer which is greater than or equal to 1 and less than or equal to M;

when the operation aiming at the atlas exporting interface is detected, exporting the N pictures in the page to be identified as the file corresponding to the target format.

Another aspect of the present application provides a method for deriving a picture, including:

receiving a target text identifier aiming at a page to be recognized, which is sent by terminal equipment, wherein the target text identifier is used for indicating a target text included in the page to be recognized, the page to be recognized comprises M pictures, and M is an integer greater than or equal to 1;

determining target atlas identification information according to the target text identification;

if the target atlas identification information meets the picture export condition, sending an atlas export request to the terminal equipment so that the terminal equipment displays an atlas export interface on a picture viewer according to the atlas export request sent by the server, and exporting N pictures in a page to be identified as files corresponding to the target format when the terminal equipment detects operation aiming at the atlas export interface, wherein the atlas export interface is used for exporting the N pictures in M pictures, and N is an integer which is greater than or equal to 1 and less than or equal to M.

Another aspect of the present application provides a picture deriving apparatus, including:

the display module is used for displaying M pictures contained in the page to be recognized through a picture viewer when a picture viewing instruction for the page to be recognized is acquired, wherein the picture viewing instruction carries a target text identifier which is used for indicating a target text contained in the page to be recognized, and M is an integer greater than or equal to 1;

the sending module is used for sending the target text identification to the server so that the server determines the target atlas identification information according to the target text identification;

the display module is further used for displaying an album export interface on the picture viewer according to an album export request sent by the server if the target album identification information meets the picture export condition, wherein the album export interface is used for exporting N pictures in the M pictures, and N is an integer which is greater than or equal to 1 and less than or equal to M;

and the export module is used for exporting the N pictures in the page to be identified into the file corresponding to the target format when the operation aiming at the atlas export interface is detected.

In one possible design, in one implementation of another aspect of an embodiment of the present application,

the export module is specifically used for displaying a first export interface and a second export interface when an operation aiming at the atlas export interface is detected;

if the operation aiming at the first export interface is detected, exporting the N pictures in the page to be identified as the files corresponding to the picture formats;

and if the operation aiming at the second export interface is detected, exporting the N pictures in the page to be identified as the file corresponding to the portable document format PDF.

In one possible design, in another implementation of another aspect of the embodiments of the present application, N is an integer greater than 1;

the export module is specifically used for receiving a picture ordering result which is sent by the server and aims at the N pictures when the operation aiming at the atlas export interface is detected;

and exporting the N sequenced pictures as files corresponding to the picture formats according to the picture sequencing result.

In one possible design, in another implementation of another aspect of an embodiment of the present application,

the display module is also used for displaying N pictures through the picture viewer if the target atlas identification information meets the picture export condition;

and the exporting module is further used for exporting the K pictures in the page to be identified as the file corresponding to the target format when the operation aiming at the K pictures is detected, wherein the K pictures are contained in the N pictures, and K is an integer which is greater than or equal to 1 and less than or equal to K.

the device comprises a receiving module, a processing module and a display module, wherein the receiving module is used for receiving a target text identifier which is sent by terminal equipment and aims at a page to be recognized, the target text identifier is used for indicating a target text included in the page to be recognized, the page to be recognized comprises M pictures, and M is an integer greater than or equal to 1;

the determining module is used for determining the identification information of the target atlas according to the target text identifier;

and the sending module is used for sending an atlas exporting request to the terminal equipment if the target atlas identification information meets the atlas exporting condition, so that the terminal equipment displays an atlas exporting interface on an atlas viewer according to the atlas exporting request sent by the server, and when the terminal equipment detects an operation aiming at the atlas exporting interface, exporting N pictures in a page to be identified as a file corresponding to a target format, wherein the atlas exporting interface is used for exporting the N pictures in M pictures, and N is an integer which is greater than or equal to 1 and less than or equal to M.

the determining module is specifically configured to obtain target atlas identification information if the target text identifier hits the text identifier library, where the target atlas identification information includes picture identification information corresponding to each of the M pictures, and the text identifier library includes at least one text identifier and atlas identification information corresponding to each text identifier.

the determining module is specifically used for acquiring M pictures if the target text identifier does not hit the text identifier library;

identifying the M pictures to obtain target atlas identification information, wherein the target atlas identification information comprises picture identification information corresponding to each picture in the M pictures;

and storing the target text identification and the target atlas identification information into a text identification library, wherein the text identification library comprises at least one text identification and the atlas identification information corresponding to each text identification.

the determining module is specifically used for acquiring picture identification information corresponding to the picture through the object identification model aiming at each picture in the M pictures, wherein the picture identification information comprises at least one of an object type, an object name and a keyword;

and acquiring target atlas identification information according to the picture identification information corresponding to each picture in the M pictures.

In one possible design, in another implementation manner of another aspect of the embodiment of the present application, the target atlas identification information includes picture identification information corresponding to each of the M pictures;

the determining module is further used for determining that the target atlas identification information meets the picture export condition if the association degree between the picture identification information of the N pictures and the target text meets the picture-text matching condition and the picture identification information of the N pictures meets the information safety condition after the target atlas identification information is determined according to the target text identifier, wherein the N pictures are contained in the M pictures;

or the like, or, alternatively,

after determining the target atlas identification information according to the target text identification, if the association degree between the picture identification information of the N pictures and the target text meets the picture-text matching condition, determining that the target atlas identification information meets the picture derivation condition;

or the like, or, alternatively,

after the target atlas identification information is determined according to the target text identification, if the picture identification information of the N pictures meets the information safety condition, the target atlas identification information is determined to meet the picture export condition.

the picture exporting device also comprises a processing module;

the processing module is used for clustering the N pictures according to the picture identification information corresponding to each picture in the N pictures to obtain N clustered pictures after the target atlas identification information is determined according to the target text identification and if the target atlas identification information meets the picture derivation condition;

the determining module is further used for determining the association degree between each picture and the target text according to the target text and the picture identification information corresponding to each picture in the N pictures;

the processing module is further used for sequencing the N clustered pictures according to the sequence of the relevance degrees from large to small to obtain a picture sequencing result;

and the sending module is further used for sending the picture sorting result to the terminal device, so that when the terminal device detects the operation aiming at the album export interface, the N sorted pictures are exported to be the files corresponding to the picture formats according to the picture sorting result.

Another aspect of the present application provides a terminal device, including: a memory, a transceiver, a processor, and a bus system;

wherein, the memory is used for storing programs;

a processor for executing the program in the memory, the processor for performing the above-described aspects of the method according to instructions in the program code;

the bus system is used for connecting the memory and the processor so as to enable the memory and the processor to communicate.

Another aspect of the present application provides a server, including: a memory, a transceiver, a processor, and a bus system;

wherein, the memory is used for storing programs;

Another aspect of the present application provides a computer-readable storage medium having stored therein instructions, which when executed on a computer, cause the computer to perform the method of the above-described aspects.

In another aspect of the application, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided by the various alternative implementations of the aspects described above.

According to the technical scheme, the embodiment of the application has the following advantages:

in the embodiment of the application, a picture exporting method is provided, when a picture viewing instruction for a to-be-identified page is acquired, a terminal device displays M pictures contained in the to-be-identified page through a picture viewer, sends a target text identifier to a server, so that the server determines target atlas identification information according to the target text identifier, if the target atlas identification information meets a picture exporting condition, the terminal device displays an atlas exporting interface on the picture viewer, and when an operation for the atlas exporting interface is detected, the terminal device exports N pictures in the to-be-identified page to files corresponding to a target format. By the mode, whether the picture in the page can be derived or not is intelligently decided based on the identification information of the target atlas, so that the reasonability of data derivation is improved. Under the condition that the atlas can be exported, the picture on the page is directly exported to the file corresponding to the target format in a one-key export mode, and a user does not need to save each picture on the page, so that the picture export efficiency is improved.

Drawings

FIG. 1 is a block diagram of an architecture of a picture derivation system according to an embodiment of the present application;

fig. 2 is a schematic interactive flow chart of a picture derivation method in an embodiment of the present application;

fig. 3 is a schematic diagram of an embodiment of a picture derivation method in an embodiment of the present application;

FIG. 4 is a schematic interface diagram of a page to be identified in the embodiment of the present application;

FIG. 5 is a schematic diagram illustrating an entry into a picture viewer through a page to be identified in an embodiment of the present application;

FIG. 6 is a schematic interface diagram of a picture viewer satisfying a picture export condition according to an embodiment of the present application;

FIG. 7 is a schematic interface diagram of a picture viewer in an embodiment of the present application under a condition that a picture export condition is not satisfied;

fig. 8 is a schematic diagram showing a first export interface and a second export interface in the embodiment of the present application;

FIG. 9 is a diagram illustrating an embodiment of a file exported as a picture format;

FIG. 10 is a diagram showing a file exported as a portable document format in an embodiment of the present application;

FIG. 11 is a diagram illustrating the sequential picture export of a portable document format file according to an embodiment of the present application;

FIG. 12 is a schematic diagram of manually selecting a derived picture in an embodiment of the present application;

fig. 13 is a schematic diagram of another embodiment of a picture derivation method in an embodiment of the present application;

FIG. 14 is a flowchart illustrating a process of determining whether an atlas meets the condition for deriving an atlas;

FIG. 15 is a schematic flow chart illustrating the ranking of an atlas in an embodiment of the application;

fig. 16 is a schematic diagram of an embodiment of a picture deriving device in an embodiment of the present application;

fig. 17 is a schematic diagram of another embodiment of the picture derivation apparatus in the embodiment of the present application;

fig. 18 is a schematic structural diagram of a terminal device in an embodiment of the present application;

fig. 19 is a schematic structural diagram of a server in the embodiment of the present application.

Detailed Description

The embodiment of the application provides a picture exporting method, device, equipment and storage medium based on Artificial Intelligence (AI). Whether the pictures in the page can be exported or not is intelligently decided based on the identification information of the target atlas, so that the reasonability of data export is increased. Under the condition that the atlas can be exported, the picture on the page is exported to the file corresponding to the target format in the one-key export mode, and therefore the picture export efficiency is improved.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "corresponding" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Whether on a browser page or an applet page, the relevant content is typically presented in a pictographic format. These pictures may be stored locally at the terminal device for subsequent use and viewing by the user. However, the number of pictures displayed on some pages is large, which requires the user to save each picture, resulting in very tedious operation. The picture exporting method provided by the application can well cope with the scenes, for example, 20 pictures exist on a page of a browser, and a user can directly export all the pictures on the page into files in a specified format by triggering a one-key exporting function. Furthermore, in consideration of the fact that pictures appearing on a page may have text-to-text inconsistency, pornography, violence or political sensitivity, the pictures need to be filtered and then exported. Furthermore, the exported pictures can be intelligently sequenced, so that the time for classifying and sequencing the pictures by a user is saved.

The method is applied to a picture export system shown in fig. 1, as shown in the figure, the picture export system includes a server and a terminal device, and a client is deployed on the terminal device. The server related to the application can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, Content Delivery Network (CDN), big data and an AI platform. The terminal device may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a palm computer, a personal computer, a smart television, a smart watch, and the like. The terminal device and the server may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein. The number of servers and terminal devices is not limited.

Referring to fig. 2 based on the picture export system shown in fig. 1, fig. 2 is an interactive flow diagram of a picture export method in the embodiment of the present application, and as shown in the figure, taking a browser installed on a terminal device as an example, specifically:

in step S1, the terminal device acquires a picture viewing instruction for the page to be recognized through the browser.

In step S2, the terminal device pulls up a picture viewer integrated in the browser in response to the picture viewing instruction, and displays the picture in the page to be recognized through the picture viewer.

In step S3, when the user opens the picture viewer, it indicates that the user is interested in the picture in the page to be recognized, and may want to derive the picture, so the terminal device also sends a picture viewing instruction to the server to trigger the server to perform recognition processing on the picture.

In step S4, the server determines whether the page to be recognized has been recognized based on the picture viewing command, and if so, directly obtains the target atlas identification information corresponding to the page to be recognized, and if not, executes step S41, step S42 and step S43. Specifically, in step S41, the server identifies each picture based on the AI technique, and obtains a picture identification result for each picture. In step S42, the server checks whether each picture is suitable for export, and for pictures that involve sensitive content, export will not be possible. In step S43, the pictures allowed to be exported are sorted.

In step S5, if the server determines that the target album identification information satisfies the picture derivation condition, it sends an album derivation request to the terminal device.

In step S6, the terminal device exposes an album derivation interface in the picture viewer according to the album derivation request.

In step S7, the user may export the picture in the page to be recognized as the file corresponding to the target format by clicking the atlas export interface.

It is to be appreciated that the present application is directed to AI technology, wherein AI is a theory, method, technique and application that utilizes a digital computer or a digital computer controlled machine to simulate, extend and extend human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, AI is an integrated technique of computer science that attempts to understand the essence of intelligence and produces a new intelligent machine that can react in a manner similar to human intelligence. AI is to study the design principles and implementation methods of various intelligent machines, so that the machine has the functions of perception, reasoning and decision making.

The AI technology is a comprehensive subject, and relates to the field of extensive technology, both hardware level technology and software level technology. The AI base technologies generally include technologies such as sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technologies, operating/interactive systems, mechatronics, and the like. The AI software technology mainly includes several directions, such as computer vision technology, speech processing technology, natural language processing technology, and machine learning/deep learning.

In the process of recognizing pictures, a Computer Vision (CV) technology is required, wherein the CV technology is a science for researching how to make a machine see, and further means that a camera and a Computer are used for replacing human eyes to perform machine Vision such as recognition, tracking and measurement on a target, and further performing graphic processing, so that the Computer is processed into an image more suitable for human eyes to observe or transmitted to an instrument to detect. As a scientific discipline, CV research-related theories and techniques attempt to build AI systems that can acquire information from images or multidimensional data. CV technology generally includes technologies such as image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, synchronous positioning, map construction, and the like, and also includes common biometric technologies such as face recognition, fingerprint recognition, and the like.

In the process of identifying a target file (such as a title and text content in a page), a Natural Language Processing (NLP) technology needs to be adopted, wherein the NLP technology is an important direction in the fields of computer science and AI. It studies various theories and methods that enable efficient communication between humans and computers using natural language. NLP is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language that people use everyday, so it is closely related to the research of linguistics. NLP techniques typically include text processing, semantic understanding, machine translation, robotic question and answer, knowledge mapping, and the like.

With the research and progress of the AI technology, the AI technology is researched and applied in a plurality of fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, unmanned aerial vehicles, robots, smart medical services, smart customer service, etc., and it is believed that with the development of the technology, the AI technology will be applied in more fields and exert more and more important values.

With reference to the above description, the solutions provided in the embodiments of the present application relate to CV technology and NLP technology of AI, and the following description will be made from the perspective of a terminal device on an AI-based picture derivation method in the present application, with reference to fig. 3, where an embodiment of an AI-based picture derivation method in the embodiments of the present application includes:

101. when a picture viewing instruction for a page to be identified is acquired, the terminal device displays M pictures contained in the page to be identified through a picture viewer, wherein the picture viewing instruction carries a target text identifier, the target text identifier is used for indicating a target text contained in the page to be identified, and M is an integer greater than or equal to 1;

in this embodiment, a to-be-identified page is displayed on a browser or other client of a terminal device, for convenience of description, please refer to fig. 4, where fig. 4 is an interface schematic diagram of the to-be-identified page in the embodiment of the present application, as shown in the figure, a target text and a picture are displayed in the to-be-identified page, where the target text may include a title and a text, the number of pictures is M, and M is an integer greater than or equal to 1.

The picture viewer may load all pictures in the page to be recognized, please refer to fig. 5, where fig. 5 is a schematic diagram of entering the picture viewer through the page to be recognized in the embodiment of the present application, as shown in fig. (a), a user may view a picture on the page to be recognized, and if the user is interested in a certain picture, the user may press the picture for a long time or double click the picture, and the like, thereby triggering a picture viewing instruction. The terminal device responds to the picture viewing instruction, calls up a picture viewer in the client, namely, enters an interface of the picture viewer shown in the diagram (B), and can display M pictures on the page to be identified on the picture viewer or only display N pictures which are allowed to be exported on the page to be identified on the picture viewer. The picture selected by the user can be displayed in an enlarged manner on the picture viewer, and other pictures are displayed in the form of thumbnails, however, the mode of displaying the picture by the picture viewer can be flexibly set, and the diagram (B) in fig. 5 is only one schematic diagram and should not be construed as limiting the present application.

102. The terminal equipment sends a target text identifier to the server so that the server determines target atlas identification information according to the target text identifier;

in this embodiment, after receiving the picture viewing instruction, the terminal device may further send a target text identifier to the server, where the picture viewing instruction carries the target text identifier corresponding to the target text, and the target text identifier have a unique corresponding relationship.

The server may first find target atlas identification information based on the target text identification, where the target atlas identification information may be one identification information for all pictures on the page to be identified.

Illustratively, the target atlas identification information is "1", that is, the M pictures on the page to be identified satisfy the picture derivation condition, and can be derived in full quantity. Or, the target atlas identification information is "0", that is, the M pictures on the page to be identified do not satisfy the picture export condition, and cannot be exported. In the above example, since the M pictures are determined as a whole, the target album identification information is only "1" or "0".

Illustratively, the target atlas identification information may also include picture identification information corresponding to each of the M pictures, and assuming that M is 20, the target atlas identification information includes 20 pieces of picture identification information. In one case, each picture identification information may be represented as "1" or "0", where "1" indicates that the picture may be derived and "0" indicates that the picture may not be derived. In another case, each picture identification information may include features of different dimensions, for example, at least one of an object category, an object name, and a keyword of the picture.

103. If the target atlas identification information meets the atlas exporting condition, the terminal device displays an atlas exporting interface on an atlas viewer according to an atlas exporting request sent by a server, wherein the atlas exporting interface is used for exporting N pictures in M pictures, N is an integer which is greater than or equal to 1 and less than or equal to M;

in this embodiment, based on the above description, after obtaining the target atlas identification information, the server needs to determine whether the target atlas identification information meets an atlas derivation condition, and if the target atlas identification information meets the atlas derivation condition, the server sends an atlas derivation request to the terminal device, where the atlas derivation request indicates that the terminal device is allowed to derive an atlas on a page to be identified, and then the terminal device responds to the atlas derivation request and displays an atlas derivation interface on the atlas viewer. On the contrary, if the picture export request is not satisfied, the server may send a prompt that the export of the album fails to the terminal device, and the terminal device may display a prompt of "picture on the page is not exportable", or display a prompt of "illegal content exists on the page, and is not exportable", and the like.

Illustratively, if the target album identification information is "1", that is, the picture derivation condition is satisfied, the server may transmit an album derivation request indicating that N pictures can be derived to the terminal device, where N is M. If the target atlas identification information is "0", that is, the picture derivation condition is not satisfied, the server may send a prompt to the terminal device that the atlas derivation has failed.

Illustratively, if it is determined that N pieces of picture identification information therein are "1" based on the target album identification information, i.e., the picture derivation condition is satisfied, the server may send an album derivation request indicating that N pieces of pictures can be derived to the terminal device, at which time N ≦ M. If it is determined that the M picture identification information are all "0", i.e., the picture derivation condition is not satisfied, based on the target album identification information, the server may send a prompt to the terminal device that the album derivation has failed.

It can be understood that the above-mentioned manner for determining whether the target atlas identification information meets the picture derivation condition is only an illustration, and other manners may also be adopted for determination in the actual process, and the following embodiments will also be described.

104. When the operation aiming at the atlas exporting interface is detected, the terminal equipment exports N pictures in the page to be identified as the file corresponding to the target format.

In this embodiment, if the target album identification information satisfies the image export condition, the terminal device exports the request according to the album sent by the server, for convenience of description, please refer to fig. 6, fig. 6 is an interface schematic diagram of the image viewer satisfying the image export condition in the embodiment of the present application, as shown in the figure, K1 indicates an album export interface, and when a user triggers an operation (for example, a click, a double click, a long press, or the like) on the album export interface, the terminal device can respond to the operation of the user and export N images in the page to be identified as a file corresponding to the target format. The target Format includes, but is not limited to, a picture Format, a Portable Document Format (PDF), a spreadsheet Format (excel), a word processing Format (word), a video Format, and the like.

If the target atlas identification information does not satisfy the atlas derivation conditions, then the atlas derivation interface is not exposed on the picture viewer, meaning that the user cannot derive pictures on the page to be identified. For convenience of introduction, please refer to fig. 7, where fig. 7 is an interface schematic diagram of a picture viewer that does not satisfy a picture export condition in the embodiment of the present application, and as shown in the figure, only M pictures on a page to be identified are shown on the picture viewer, but the pictures cannot be exported.

In the embodiment of the application, an AI-based picture export method is provided, wherein when a picture viewing instruction for a to-be-identified page is acquired, a terminal device displays M pictures contained in the to-be-identified page through a picture viewer, sends a target text identifier to a server, so that the server determines target atlas identification information according to the target text identifier, if the target atlas identification information meets a picture export condition, the terminal device displays an atlas export interface on the picture viewer, and when an operation for the atlas export interface is detected, the terminal device exports N pictures in the to-be-identified page as a file corresponding to a target format. By the mode, whether the picture in the page can be derived or not is intelligently decided based on the identification information of the target atlas, so that the reasonability of data derivation is improved. Under the condition that the atlas can be exported, the picture on the page is directly exported to the file corresponding to the target format in a one-key export mode, and a user does not need to save each picture on the page, so that the picture export efficiency is improved.

Optionally, on the basis of the embodiment corresponding to fig. 3, in an optional embodiment provided in the embodiment of the present application, when an operation directed to an album export interface is detected, the terminal device exports N pictures in a page to be identified as a file corresponding to a target format, which specifically includes the following steps:

when the operation aiming at the atlas exporting interface is detected, the terminal equipment displays the first exporting interface and the second exporting interface;

if the operation aiming at the first export interface is detected, exporting N pictures in the page to be identified as a file corresponding to the picture format by the terminal equipment;

and if the operation aiming at the second export interface is detected, exporting the N pictures in the page to be identified to a file corresponding to the portable document format PDF by the terminal equipment.

In this embodiment, a manner of exporting a picture into a file with a different format is introduced, so as to improve convenience of using the picture by a user, the picture of the target text can be exported and stored in a PDF file or a picture file, and the user can conveniently search the picture under the target text in a centralized manner.

Specifically, when the user triggers an operation (e.g., single click, double click, long press, etc.) on the atlas lead-out interface, the terminal device may respond to the user's operation and then expose the first lead-out interface and the second lead-out interface. For convenience of understanding, please refer to fig. 8, fig. 8 is a schematic diagram illustrating a first export interface and a second export interface in the embodiment of the present application, and as shown in the figure, the first export interface is indicated by K2, and when a user triggers an operation through the first export interface, the terminal device may export N pictures in the page to be identified as a file corresponding to the picture format. The instruction of K3 is a second export interface, and when the user triggers an operation through the second export interface, the terminal device may export N pictures in the page to be identified as a file corresponding to the PDF. Indicated by K4 is a "save" button that the user can save a picture-formatted file or a PDF-formatted file after clicking. Indicated by K5 is a "share" button, and after clicking the "share" button, the user can share the picture-formatted file or the PDF-formatted file to his or her own friends, or to other social platforms. Indicated at K6 is a "cancel" button, which when clicked by the user, cancels the exporting of the picture, exits the picture viewer, and returns to the browser interface (or other client interface).

Referring to fig. 9, fig. 9 is a schematic diagram of a file exported in a picture format in an embodiment of the present application, as shown in the figure, N pictures may be stored in a local album of a terminal device, and a user views the exported pictures in the album. The picture format includes, but is not limited to, Bitmap (BMP) format, Graphics Interchange Format (GIF), Joint Photographic Experts Group (JPEG), Portable Network Graphics (PNG) format, and the like, and is not limited herein.

Referring to fig. 10, fig. 10 is a schematic diagram of a portable document format file exported in the embodiment of the present application, as shown in the figure, N pictures can be exported to a PDF file, the pictures can be viewed after the PDF file is opened, and operations such as page turning operation or scaling adjustment can be performed on the PDF file.

Secondly, in the embodiment of the application, a mode for exporting the picture into files with different formats is provided, and through the mode, a user can select the format of the exported picture according to the actual situation, for example, if the user wants to export an independent picture, the user can select the exported picture into the format of the picture, so that the user can conveniently view and use a single picture subsequently. For another example, if the user wants to view and use the pictures collectively, the user can select the pictures to be exported as PDF, so that the user can call the pictures or view the pictures at one time conveniently, and thus, the flexibility of picture processing is improved.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in the embodiments of the present application, N is an integer greater than 1;

when the operation aiming at the atlas exporting interface is detected, the terminal equipment exports N pictures in the page to be identified as a file corresponding to the target format, and the method specifically comprises the following steps:

when the operation aiming at the atlas exporting interface is detected, the terminal equipment receives a picture sorting result aiming at N pictures sent by the server;

and the terminal equipment exports the N ordered pictures as files corresponding to the picture formats according to the picture ordering result.

In this embodiment, a manner of exporting pictures in sequence is introduced, that is, an exported file may show N exported pictures in a certain order, and when N is equal to 1, that is, it is not necessary to aggregate and sort 1 picture, therefore, in this embodiment of the present application, a case where N is greater than 1 is taken as an example, and when a server determines that target atlas identification information meets a picture export condition, N pictures may be sorted.

Specifically, assume that there are 12 pictures on the page to be identified, i.e., M is 12. When it is determined that the target atlas identification information meets the picture derivation condition, the number of derivable pictures may be further determined, assuming that 8 pictures are derivable, i.e., N is 8, each picture has corresponding picture identification information, and each picture has a picture identification. For convenience of description, please refer to table 1, where table 1 is an illustration of an association relationship between pictures and picture identifiers.

TABLE 1

As can be seen from table 1, the picture identification information may be an object type, and the 8 pictures are sorted based on their object type, and the pictures of the same object type may be sorted together in a sorting manner, and then the picture identifications are sequentially output to the terminal device, and the terminal device derives the corresponding pictures according to the picture identifications. For convenience of explanation, please refer to table 2, where table 2 is an illustration of generating a picture ordering result based on the picture identification information shown in table 1.

TABLE 2

Picture ordering results	Picture frame	Picture identification	Picture identification information
				First sheet	Picture A	0000	Transportation means
The second sheet	Picture E	0100	Transportation means
				The third sheet	Picture G	0110	Transportation means
The fourth sheet	Picture B	0001	Plant and method for producing the same
				Fifth sheet of paper	Picture D	0011	Plant and method for producing the same
The sixth sheet	Picture F	0101	Plant and method for producing the same
				The seventh sheet	Picture C	0010	Animal(s) production
Eighth sheet of paper	Picture H	0111	Animal(s) production

Based on this, the terminal device displays N pictures according to the order of the picture identifiers "0000", "0100", "0110", "0001", "0011", "0101", "0010", and "0111", taking fig. 11 as an example, fig. 11 is a schematic diagram of the pictures exported in order by the portable document format file in the embodiment of the present application, and as shown in the figure, the pictures presented on the PDF file are three pictures related to "transportation".

Secondly, in the embodiment of the application, a mode of exporting the pictures in sequence is provided, and through the mode, intelligent aggregation and sequencing can be performed on the pictures according to the picture identification result of each picture in the process of exporting the pictures, and the pictures are reflected to the exported files, namely, the pictures with the same category and higher association degree in the pages are put together, so that a user can conveniently search the corresponding pictures from the files, and the flexibility and the practicability of exporting the pictures are improved.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in the embodiment of the present application, the method further includes the following steps:

if the target atlas identification information meets the picture export condition, the terminal equipment displays N pictures through a picture viewer;

when the operation aiming at the K pictures is detected, the terminal equipment exports the K pictures in the page to be identified as the files corresponding to the target format, wherein the K pictures are contained in the N pictures, and K is an integer which is greater than or equal to 1 and less than or equal to K.

In this embodiment, a manner of manually selecting a plurality of pictures to be exported is introduced. The M pictures on the page to be identified may be displayed on the picture viewer, or only the N pictures allowed to be derived on the page to be identified may be displayed on the picture viewer, and since N is a value less than or equal to M, it may be understood that, when the terminal device displays the N pictures through the picture viewer, the remaining (M-N) pictures may also be displayed, and the remaining (M-N) pictures may be displayed in a grayscale form, may also be displayed in a highlight form in other manners, may also be displayed in a form that is indistinguishable from the N pictures, and is not limited herein.

Specifically, if the target atlas identification information meets the picture export condition, the terminal device displays N pictures through the picture viewer, for convenience of explanation, please refer to fig. 12, where fig. 12 is a schematic diagram of manually selecting an export picture in the embodiment of the present application, as shown in fig. (a), a selection box is indicated by K7, if a user clicks the selection box below a certain picture, it indicates that the picture is selected to be exported, and assuming that the user selects the first picture and the second picture but does not select the third picture, the first picture and the second picture are displayed in the export PDF file, but the third picture is not displayed. That is, even if the third picture itself can be derived, the actual selection by the user is prioritized.

Secondly, in the embodiment of the application, a mode of manually selecting a plurality of pictures to be exported is provided, and through the mode, a user can select K pictures on a picture viewer as exported objects, so that the flexibility and the freedom degree of exporting the pictures are increased, and the requirements of the user on picture export can be better met.

With reference to the above description, the AI-based picture derivation method in the present application will be described below from the perspective of a server, and referring to fig. 13, another embodiment of the AI-based picture derivation method in the present application includes:

201. the method comprises the steps that a server receives a target text identification aiming at a page to be recognized, wherein the target text identification is used for indicating a target text included in the page to be recognized, the page to be recognized comprises M pictures, and M is an integer greater than or equal to 1;

in this embodiment, a page to be identified is displayed on a browser or other client of a terminal device, and specifically, taking a browser installed in the terminal device as an example, a target text and a picture on the page to be identified may be displayed through the browser, where the target text may include a title and a text, the number of pictures is M, and M is an integer greater than or equal to 1. And the target file of the browser is stored in a server by crawling a third-party webpage.

The user can check the picture on the page to be identified, if the user is interested in a certain picture, the user can press the picture for a long time or double click the picture, and the like, so that a picture checking instruction is triggered. The terminal equipment responds to the picture viewing instruction, calls a picture viewer in the client side, and can display M pictures on the page to be recognized on the picture viewer or only display N pictures which are allowed to be exported on the page to be recognized on the picture viewer. The pictures selected by the user can be displayed on the picture viewer in an enlarged mode, and other pictures are displayed in a thumbnail mode.

The terminal equipment can also send the picture viewing instruction to the server after receiving the picture viewing instruction, wherein the picture viewing instruction carries a target text identifier corresponding to a target text, the target text and the target text identifier have a unique corresponding relation, and for the server, the server can analyze the picture viewing instruction after receiving the picture viewing instruction so as to obtain the target text identifier.

202. The server determines target atlas identification information according to the target text identification;

in this embodiment, the server may search for target atlas identification information based on the target text identifier, where the target atlas identification information may be identification information for all pictures on the page to be identified.

203. If the target atlas identification information meets the picture export condition, the server sends an atlas export request to the terminal device, so that the terminal device displays an atlas export interface on a picture viewer according to the atlas export request sent by the server, and when the terminal device detects an operation aiming at the atlas export interface, N pictures in a page to be identified are exported to files corresponding to a target format, wherein the atlas export interface is used for exporting the N pictures in M pictures, and N is an integer which is greater than or equal to 1 and less than or equal to M.

Illustratively, if the target album identification information is "1", that is, the picture derivation condition is satisfied, the server may transmit an album derivation request indicating that N pictures can be derived to the terminal device, where N is M. If the target atlas identification information is "0", that is, the picture derivation condition is not satisfied, the server may send a prompt to the terminal device that the atlas derivation has failed. Illustratively, if it is determined that N pieces of picture identification information therein are "1" based on the target album identification information, i.e., the picture derivation condition is satisfied, the server may send an album derivation request indicating that N pieces of pictures can be derived to the terminal device, at which time N ≦ M. If it is determined that the M picture identification information are all "0", i.e., the picture derivation condition is not satisfied, based on the target album identification information, the server may send a prompt to the terminal device that the album derivation has failed.

If the target atlas identification information meets the atlas exporting condition, the terminal device responds to the operation of the user and exports the N pictures in the page to be identified as the files corresponding to the target format when the user triggers the operation (such as clicking, double clicking or long pressing) on the atlas exporting interface according to the atlas exporting request sent by the server. The target formats include, but are not limited to, picture formats, PDF, excel, word, video formats, and the like.

In the embodiment of the application, an AI-based picture export method is provided, in which a server receives a target text identifier, which is sent by a terminal device and is specific to a page to be recognized, and then determines target atlas identification information according to the target text identifier, if the target atlas identification information meets an atlas export condition, the server sends an atlas export request to the terminal device, so that the terminal device displays an atlas export interface on an atlas viewer according to the atlas export request sent by the server, and when the terminal device detects an operation specific to the atlas export interface, exports N pictures in the page to be recognized as a file corresponding to a target format. By the mode, whether the picture in the page can be derived or not is intelligently decided based on the identification information of the target atlas, so that the reasonability of data derivation is improved. Under the condition that the atlas can be exported, the picture on the page is directly exported to the file corresponding to the target format in a one-key export mode, and a user does not need to save each picture on the page, so that the picture export efficiency is improved.

Optionally, on the basis of the embodiment corresponding to fig. 13, in an optional embodiment provided in the embodiment of the present application, the determining, by the server, the target atlas identification information according to the target text identifier specifically includes the following steps:

and if the target text identifier hits the text identifier library, the server acquires target atlas identification information, wherein the target atlas identification information comprises picture identification information corresponding to each picture in the M pictures, and the text identifier library comprises at least one text identifier and atlas identification information corresponding to each text identifier.

In this embodiment, a manner of obtaining target atlas identification information based on a target text identifier is introduced, that is, a server side maintains a text identifier library, and the text identifier library may store the text identifiers and the atlas identification information corresponding to each text identifier in a key-value (key-value) form. The identified information of the atlas on the page is directly stored in the local server, and the text identification corresponding to the text on the page is used as an index.

Specifically, for ease of description, please refer to table 3, where table 3 is an illustration of storing text labels and atlas identification information based on a text label library.

TABLE 3

As can be seen from table 3, the atlas identification information includes picture identification information of each picture on the page, and table 3 takes the example that the picture identification information may be an object type as an example, and in an actual situation, the picture identification information may further include other information, such as an object name, a keyword, and the like, which is only an illustration here and should not be construed as a limitation to the present application. Wherein the key (key) is a text representation and the value (value) is the atlas identification information.

Based on table 3, assuming that the target text identifier is "3", the text identifier library is hit, and the server may directly obtain target atlas identification information, where the target atlas identification information includes picture identification information corresponding to each of M pictures, where M is 3, and the target atlas identification information includes picture identification information of picture K, picture L, and picture M.

Secondly, in the embodiment of the application, a method for obtaining target atlas identification information based on a target text identification is provided, through the method, a server can preferentially use the target text identification to match with a text identification in a text identification library, if the matching is successful, the atlas identification information corresponding to the text identification can be directly used as the target atlas identification information, the server does not need to detect each picture again, the server can store the atlas identification information to the local, and the text on a page cannot be changed, so that the next user request can be directly returned after one-time processing, thereby improving the processing efficiency and saving the processing resources.

if the target text identification does not hit the text identification library, the server acquires M pictures;

the server identifies the M pictures to obtain target atlas identification information, wherein the target atlas identification information comprises picture identification information corresponding to each picture in the M pictures;

the server stores the target text identification and the target atlas identification information into a text identification library, wherein the text identification library comprises at least one text identification and the atlas identification information corresponding to each text identification.

In this embodiment, a manner of storing the target atlas identification information in the text identification library is introduced, that is, a server side maintains a text identification library, and the text identification library may store the text identifications and the atlas identification information corresponding to each text identification in a key-value form. The identified information of the atlas on the page is directly stored in the local server, and the text identification corresponding to the text on the page is used as an index.

Specifically, taking table 3 as an example, assuming that the target text identifier is "5", the target text identifier does not hit the text identifier library, and therefore the server needs to identify M pictures on the page to be identified, obtain picture identification information corresponding to each picture, use the picture identification information as target atlas identification information, and then add the target atlas identification information and the corresponding target text identifier to the text identifier library. For convenience of introduction, please refer to table 4, where table 4 is an illustration of a text identifier library obtained by adding a target text identifier and target atlas identification information.

TABLE 4

As can be seen from table 4, the atlas identification information includes picture identification information of each picture on the page, and table 4 takes the example that the picture identification information may be an object type, and in an actual situation, the picture identification information may further include other information, such as an object name, a keyword, and the like, which is only an illustration here and should not be construed as a limitation to the present application. Wherein, key is text representation, and value is atlas identification information. As can be seen from table 4, the atlas identification information corresponding to the target text label "5" is already added to the text label library, and if there is an atlas identification result on the page requested by the terminal device, the atlas identification result can be directly obtained without performing secondary identification.

Secondly, in the embodiment of the application, a way of storing the target atlas identification information to the text identification library is provided, and in the way, if the server does not detect the target text identification in the text identification library, the server needs to identify the picture on the page to be identified so as to obtain the target atlas identification information. And then the target atlas identification information and the corresponding target text identification are stored to the local, because the text on the page is unchanged, after one-time processing, the next user request can be directly returned, thereby improving the processing efficiency and saving the processing resources.

Optionally, on the basis of the embodiment corresponding to fig. 13, in an optional embodiment provided in this application, the server identifies M pictures to obtain the target atlas identification information, and specifically includes the following steps:

the server acquires picture identification information corresponding to the picture through the object identification model aiming at each picture in the M pictures, wherein the picture identification information comprises at least one of object categories, object names and keywords;

and the server acquires the identification information of the target atlas according to the picture identification information corresponding to each picture in the M pictures.

In this embodiment, a manner of identifying a picture is introduced, and how to identify and obtain picture identification information of the picture is described below by taking any one of M pictures as an example, it can be understood that other pictures also obtain the picture identification information in a similar manner, and details are not described here.

Specifically, a picture is input to an object recognition model, which is capable of recognizing a class of objects in the picture, such as "plant", "animal", or "vehicle", based on an AI recognition algorithm. If the object recognition model is trained for a certain object class, the object recognition model may also recognize the object name under the object class, and taking the object class as "plant", the recognized object name may be "rose", "tulip", "poplar", "willow", or "wild grass", for example. Taking the object category as "animal" as an example, the identified object name may be "dog", "cat", "pig", "chicken", or "elephant". In addition, if the object recognition model can also be added to recognize the keywords in the training process, so that the keywords of the picture can be reflected. Based on this, the picture identification information includes at least one of an object category, an object name, and a keyword, and more specifically, the picture identification information is represented in the form of a triplet, that is, (object type, object name [ optional ], keyword [ optional ]).

For ease of description, please refer to table 5, where table 5 is an illustration of the target atlas identification information.

TABLE 5

Picture frame	Type of object	Object name	Key word
				Picture W	Transportation means	Bus with a detachable front panel	Coin-freed apparatus
Picture X	Transportation means	Taxi	Payment
				Picture Y	Transportation means	Truck	Gateway
Picture Z	Transportation means	Bus with a detachable front panel	Platform

As can be seen from table 5, taking 4 pictures as an example, the target atlas identification information includes picture identification information corresponding to the 4 pictures respectively, and each picture identification information is represented as a triplet.

It should be noted that the network structure of the object recognition model may be a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a Support Vector Machine (SVM), or the like, and is not limited herein.

In the embodiment of the application, a mode of identifying pictures is provided, and in the above mode, the picture identification information of each picture can be obtained by using an object identification model, and the picture identification information includes at least one of an object type, an object name and a keyword, wherein the object type can intuitively represent the content of the picture, the object name can represent the image-bearing content existing in the picture, and the keyword can represent the picture as an image-bearing concept, so that intelligent processing can be realized based on the picture identification information.

Optionally, on the basis of the embodiment corresponding to fig. 13, in an optional embodiment provided in the embodiment of the present application, the target atlas identification information includes picture identification information corresponding to each picture in the M pictures;

after the server determines the identification information of the target atlas according to the identification of the target text, the method further comprises the following steps:

if the association degree between the picture identification information of the N pictures and the target text meets the picture-text matching condition and the picture identification information of the N pictures meets the information safety condition, the server determines that the target atlas identification information meets the picture derivation condition, wherein the N pictures are contained in the M pictures;

or the like, or, alternatively,

if the association degree between the picture identification information of the N pictures and the target text meets the picture-text matching condition, the server determines that the target atlas identification information meets the picture export condition;

or the like, or, alternatively,

and if the picture identification information of the N pictures meets the information safety condition, the server determines that the target atlas identification information meets the picture export condition.

In this embodiment, a manner of determining whether the target atlas identification information meets the picture derivation condition is introduced, and in an actual situation, the pictures on the page may have situations of picture-text inconsistency or content sensitivity, and the like, so that each picture may be detected before the pictures are derived, the pictures passing the detection may be derived, and the pictures not passing the detection may not be derived. The application provides three ways for judging whether the target atlas identification information meets the picture export condition, and it needs to be noted that the target atlas identification information meets the picture export condition as long as at least one (N) picture can be exported from M pictures included in the page to be identified, and if M pictures cannot be exported, the target atlas identification information does not meet the picture export condition. Based on this, the present application provides three ways to determine whether a picture can be exported.

Judging whether the picture can be exported or not only based on the image-text relevance;

exemplarily, taking a target text and any one of pictures inserted in the target text as an example, the target text may extract corresponding keywords when being put in storage, for example, the keywords may be keywords defined by an author of the target text, keywords obtained by background personnel through labeling, or keywords extracted by using an AI recognition technology, which is not limited herein.

Based on this, the server needs to determine the degree of association between the keywords of the target text and the keywords of the picture. Specifically, the semantic similarity between words can be calculated by using inter-Point Mutual Information (PMI), the basic idea is to count the probability of two words appearing in the text at the same time, assuming that the keyword of the target text is word1, the keyword of the picture is word2, and calculating PMI values of word1 and word2, that is, obtaining PMI (word1& word 2).

PMI (word1& word2) > 0, indicating that two keywords are related, the larger the value, the stronger the correlation.

PMI (word1& word2) is 0, indicating that two keywords are statistically independent, uncorrelated, and not mutually exclusive.

PMI (word1& word2) < 0, indicating that the two keywords are not related and mutually exclusive.

If PMI (word1& word2) is less than a certain threshold, the teletext relevance is considered to be low, i.e. the picture does not satisfy the teletext matching condition. On the contrary, if PMI (word1& word2) is greater than or equal to a certain threshold, it is considered that the teletext relevance is high, that is, it means that the picture satisfies the teletext matching condition.

Judging whether the picture can be exported or not only based on the sensitivity of the picture;

illustratively, taking a target text and any one picture inserted in the target text as an example, after picture identification information of the picture is acquired, whether the content of the picture identification information meets an information security condition is analyzed, and if the picture identification information has a tendency of being pornographic, violent or politically sensitive, the information security condition is not met.

Assuming that the object category included in the picture identification information is "adult movie", the pornographic content may be involved, i.e., the information security condition is not satisfied. Assuming that the object category included in the picture identification information is "horror movie", violent content may be involved, i.e., information security conditions are not satisfied. Assuming that the object category included in the picture identification information is "legislation", politically sensitive content may be involved, i.e., information security conditions are not satisfied.

Assuming that the picture identification information includes an object name of "a certain adult movie male's good", the pornographic content may be involved, that is, the information security condition is not satisfied. Assuming that the picture identification information includes an object name of "machine gun", violent content may be involved, that is, information security conditions are not satisfied. Assuming that the picture identification information includes an object name of "a certain regulation", politically sensitive content may be involved, i.e., information security conditions are not satisfied.

Assuming that the keyword included in the picture identification information is "female optimization", the pornographic content may be involved, that is, the information security condition is not satisfied. Assuming that the keyword included in the picture identification information is "suicide", violent content may be involved, that is, information security conditions are not satisfied. Assuming that the keyword included in the picture identification information is "policy", politically sensitive content may be involved, i.e., information security conditions are not satisfied.

Thirdly, judging whether the picture can be exported or not by considering the relevance of the picture and the sensitivity of the picture;

it can be understood that, please refer to the first method above in terms of the relevance of the pictures, and refer to the second method above in terms of the sensitivity of the pictures, and in case that the matching condition of the pictures and the information security condition are satisfied at the same time, it means that the pictures can be exported.

For convenience of description, in the following, how to determine whether the picture can be derived is described by taking any one of M pictures as an example, it is understood that other pictures also determine whether the picture can be derived in a similar manner, which is not described herein again, please refer to fig. 14, where fig. 14 is a schematic flow chart of determining whether an image set satisfies a picture deriving condition in the embodiment of the present application, and as shown in the figure, specifically:

in step a1, acquiring picture identification information corresponding to a picture, where the picture identification information includes an object type, an object name, and a keyword;

in step a2, entering a security monitoring process, and detecting the picture identification information of each picture by the means of the above second method;

in step a3, the process of detecting includes determining whether the picture identification information relates to sensitive content, such as erotic, violent, or politically sensitive content, and if so, determining that the information security condition is not satisfied. If sensitive content is not involved, determining that an information security condition is satisfied;

in step a4, if the information security condition is satisfied, it indicates that the picture can be exported;

in step a5, keywords of the target text are obtained, and the obtaining manner is not described again;

in step a6, determining the relevance between the keywords of the picture and the keywords of the target text based on the keywords of the picture, if the relevance is larger, determining that the image-text matching condition is satisfied, and if the relevance is smaller, determining that the image-text matching condition is not satisfied;

in step a7, if the matching condition is satisfied, it indicates that the picture can be derived;

in step A8, the server may feed back an atlas derivation request to the terminal device when determining that N of the M pictures satisfy both the image-text matching condition and the information security condition.

Further, in the embodiment of the application, a mode for judging whether the target atlas identification information meets the picture derivation condition is provided, and through the mode, the function of intelligently deriving the picture can be better realized. On the other hand, in view of sensitive content, if the picture is not compliant, the picture is considered not to satisfy the picture derivation condition, so that the propagation of illegal pictures can be effectively controlled, and a good network environment is maintained.

Optionally, on the basis of the embodiment corresponding to fig. 13, in an optional embodiment provided in the embodiments of the present application, N is an integer greater than 1;

if the target image set identification information meets the image derivation condition, the server carries out clustering processing on the N images according to the image identification information corresponding to each image in the N images to obtain N clustered images;

the server determines the association degree between each picture and the target text according to the target text and the picture identification information corresponding to each picture in the N pictures;

the server sorts the N clustered pictures according to the sequence of the relevance degrees from large to small to obtain a picture sorting result;

and the server sends the picture sorting result to the terminal equipment, so that when the terminal equipment detects the operation aiming at the atlas exporting interface, the N sorted pictures are exported to be files corresponding to the picture formats according to the picture sorting result.

In this embodiment, a mode of intelligently sorting pictures to be exported is introduced, which may be firstly clustering based on object categories of pictures, then sorting the clustered results according to the association degree with the target text based on keywords of the target text and keywords of the pictures, the higher the association degree between the pictures and the target text is, the earlier the pictures are arranged, and after finishing the arrangement, the pictures may be aggregated according to object names of the pictures, and finally exported as files in the target format.

Specifically, the exported file may present N exported pictures in a certain order, and in the case that N is equal to 1, that is, it is not necessary to aggregate and sort 1 picture, so this application will be described by taking the case that N is greater than 1 as an example. In the case where the server determines that the target album identification information satisfies the picture derivation condition, N pictures may be sorted. Suppose there are 12 pictures on the page to be identified, i.e. M equals 12. When it is determined that the target atlas identification information meets the picture derivation condition, the number of derivable pictures may be further determined, assuming that 8 pictures are derivable, i.e., N is 8, each picture has corresponding picture identification information, the picture identification information includes an object category, an object name, and a keyword, and each picture has a picture identification. For convenience of illustration, please refer to table 6, where table 6 is an illustration of an association relationship between pictures and picture identifiers.

TABLE 6

Picture frame	Picture identification	Classes of objects	Object name	Degree of association with target text
					Picture A	0000	Transportation means	Bus with a detachable front panel	0.2
Picture B	0001	Plant and method for producing the same	Rose	0.5
					Picture C	0010	Animal(s) production	Sheep (sheep)	0.6
Picture D	0011	Plant and method for producing the same	Tulip	0.1
					Picture E	0100	Transportation means	Truck	0.7
Picture F	0101	Plant and method for producing the same	Tulip	0.4
					Picture G	0110	Transportation means	Taxi	0.3
Picture H	0111	Animal(s) production	Dog	0.9

Based on table 6, the same object class is first clustered to obtain N clustered pictures, for convenience of understanding, please refer to table 7, where table 7 is an illustration of the N clustered pictures.

TABLE 7

Picture frame	Picture identification	Classes of objects	Object name	Degree of association with target text
					Picture A	0000	Transportation means	Bus with a detachable front panel	0.2
Picture E	0100	Transportation means	Truck	0.7
					Picture G	0110	Transportation means	Taxi	0.3
Picture B	0001	Plant and method for producing the same	Rose	0.5
					Picture D	0011	Plant and method for producing the same	Tulip	0.1
Picture F	0101	Plant and method for producing the same	Tulip	0.4
					Picture C	0010	Animal(s) production	Sheep (sheep)	0.6
Picture H	0111	Animal(s) production	Dog	0.9

Based on table 7, the N clustered pictures are sorted in order of decreasing relevance to obtain a picture sorting result, please refer to table 8, where table 8 is an illustration of the picture sorting result obtained after sorting.

TABLE 8

Picture frame	Picture identification	Classes of objects	Object name	Degree of association with target text
					Picture E	0100	Transportation means	Truck	0.7
Picture G	0110	Transportation means	Taxi	0.3
					Picture A	0000	Transportation means	Bus with a detachable front panel	0.2
Picture B	0001	Plant and method for producing the same	Rose	0.5
					Picture F	0101	Plant and method for producing the same	Tulip	0.4
Picture D	0011	Plant and method for producing the same	Tulip	0.1
					Picture H	0111	Animal(s) production	Dog	0.9
Picture C	0010	Animal(s) production	Sheep (sheep)	0.6

At this time, the corresponding pictures can be derived according to the picture sorting result shown in fig. 8, and the terminal device displays N pictures in the order of the picture identifiers "0100", "0110", "0000", "0001", "0101", "0011", "0111", and "0010". Optionally, pictures with the same object name are further clustered, for example, picture F and picture D are both "tulips", so both can be ranked together.

For convenience of illustration, please refer to fig. 15, fig. 15 is a schematic flowchart of the process of sorting the atlas in the embodiment of the present application, as shown in the figure, specifically:

in step B1, first, the picture identification information of each of the N pictures is obtained;

in step B2, clustering the pictures according to the object categories included in the picture identification information, thereby obtaining N clustered pictures;

in step B3, respectively obtaining the association degree between each picture and the target text, and then sorting the N clustered pictures according to the order of the association degrees from large to small to obtain a picture sorting result;

in step B4, the pictures with the same object name may be put together to obtain the final picture sorting result;

in step B5, the server feeds back the result of the image sorting to the terminal device, and when the terminal device detects an operation for the album deriving interface, derives the N sorted images as a file corresponding to the image format according to the result of the image sorting.

Secondly, in the embodiment of the application, a mode for intelligently sequencing the pictures to be exported is provided, and through the mode, intelligent aggregation and sequencing can be performed on the pictures according to the picture identification result of each picture in the process of exporting the pictures, so that the pictures with the same category and higher association degree in the page are put together, a user can conveniently search the corresponding pictures from the files, and the flexibility and the practicability of exporting the pictures are improved.

Referring to fig. 16, fig. 16 is a schematic diagram of an embodiment of a picture deriving device in an embodiment of the present application, and the picture deriving device 30 includes:

the display module 301 is configured to display, when a picture viewing instruction for a to-be-identified page is acquired, M pictures included in the to-be-identified page through a picture viewer, where the picture viewing instruction carries a target text identifier, the target text identifier is used to indicate a target text included in the to-be-identified page, and M is an integer greater than or equal to 1;

a sending module 302, configured to send a target text identifier to a server, so that the server determines target atlas identification information according to the target text identifier;

the display module 301 is further configured to display an album derivation interface on the picture viewer according to an album derivation request sent by the server if the target album identification information meets the picture derivation condition, where the album derivation interface is used to derive N pictures of the M pictures, and N is an integer greater than or equal to 1 and less than or equal to M;

the exporting module 303 is configured to export, when an operation directed to the atlas exporting interface is detected, the N pictures in the page to be identified as a file corresponding to the target format.

In the embodiment of the application, the AI-based picture derivation device is provided, and whether the picture in the page can be derived or not is intelligently decided based on the identification information of the target atlas, so that the rationality of data derivation is increased. Under the condition that the atlas can be exported, the picture on the page is directly exported to the file corresponding to the target format in a one-key export mode, and a user does not need to save each picture on the page, so that the picture export efficiency is improved.

Optionally, on the basis of the embodiment corresponding to fig. 16, in another embodiment of the picture deriving device 30 provided in the embodiment of the present application,

an export module 303, specifically configured to expose the first export interface and the second export interface when an operation directed to the atlas export interface is detected;

Secondly, in the embodiment of the application, a device for exporting pictures into files with different formats is provided, and by adopting the device, a user can select the format of the exported picture according to the actual situation, for example, if the user wants to export an independent picture, the user can select the exported picture as the format of the picture, so that the user can conveniently view and use a single picture subsequently. For another example, if the user wants to view and use the pictures collectively, the user can select the pictures to be exported as PDF, so that the user can call the pictures or view the pictures at one time conveniently, and thus, the flexibility of picture processing is improved.

Optionally, on the basis of the embodiment corresponding to fig. 16, in another embodiment of the picture deriving device 30 provided in the embodiment of the present application, N is an integer greater than 1;

the export module 303 is specifically configured to receive a picture ordering result for the N pictures sent by the server when an operation for the album export interface is detected;

the display module 301 is further configured to display N pictures through a picture viewer if the target atlas identification information meets the picture derivation condition;

the exporting module 303 is further configured to export K pictures in the page to be identified as files corresponding to the target format when detecting an operation for the K pictures, where the K pictures are included in the N pictures, and K is an integer greater than or equal to 1 and less than or equal to K.

Referring to fig. 17, fig. 17 is a schematic diagram of another embodiment of the picture deriving apparatus in the embodiment of the present application, where the picture deriving apparatus 40 includes:

the receiving module 401 is configured to receive a target text identifier, which is sent by a terminal device and is for a page to be recognized, where the target text identifier is used to indicate a target text included in the page to be recognized, the page to be recognized includes M pictures, and M is an integer greater than or equal to 1;

a determining module 402, configured to determine target atlas identification information according to the target text identifier;

a sending module 403, configured to send an atlas derivation request to a terminal device if the target atlas identification information meets the atlas derivation condition, so that the terminal device displays an atlas derivation interface on an atlas viewer according to the atlas derivation request sent by the server, and when the terminal device detects an operation for the atlas derivation interface, derives N pictures in a page to be identified as a file corresponding to the target format, where the atlas derivation interface is used to derive N pictures in M pictures, and N is an integer greater than or equal to 1 and less than or equal to M.

Optionally, on the basis of the embodiment corresponding to fig. 17, in another embodiment of the picture deriving device 40 provided in the embodiment of the present application,

the determining module 402 is specifically configured to, if the target text identifier hits the text identifier library, obtain target atlas identification information, where the target atlas identification information includes picture identification information corresponding to each of the M pictures, and the text identifier library includes at least one text identifier and atlas identification information corresponding to each text identifier.

Secondly, in the embodiment of the application, a device for acquiring target atlas identification information based on a target text identification is provided, by adopting the device, a server can preferentially use the target text identification to match with a text identification in a text identification library, if the matching is successful, the atlas identification information corresponding to the text identification can be directly used as the target atlas identification information, the server does not need to detect each picture again, the server can store the atlas identification information to the local, and because the text on the page cannot change, after one-time processing, the next user request can be directly returned, so that the processing efficiency is improved, and the processing resources are saved.

a determining module 402, configured to obtain M pictures if the target text identifier does not hit the text identifier library;

Secondly, in the embodiment of the application, a device for storing the target atlas identification information to a text identification library is provided, and by adopting the device, if the server does not detect the target text identification in the text identification library, the picture on the page to be identified needs to be identified so as to obtain the target atlas identification information. And then the target atlas identification information and the corresponding target text identification are stored to the local, because the text on the page is unchanged, after one-time processing, the next user request can be directly returned, thereby improving the processing efficiency and saving the processing resources.

a determining module 402, configured to obtain, for each of the M pictures, picture identification information corresponding to the picture through the object identification model, where the picture identification information includes at least one of an object category, an object name, and a keyword;

In the embodiment of the application, a device for identifying pictures is provided, and by adopting the device, picture identification information of each picture can be acquired by adopting an object identification model, and the picture identification information includes at least one of an object type, an object name and a keyword, wherein the object type can intuitively represent the content of the picture, the object name can represent the image-bearing content existing in the picture, and the keyword can represent the picture as an image-bearing concept, so that intelligent processing can be realized based on the picture identification information.

Optionally, on the basis of the embodiment corresponding to fig. 17, in another embodiment of the picture deriving device 40 provided in the embodiment of the present application, the target atlas identification information includes picture identification information corresponding to each of M pictures;

the determining module 402 is further configured to determine that the target atlas identification information meets an image derivation condition if the association degree between the image identification information of the N images and the target text meets the image-text matching condition and the image identification information of the N images meets the information security condition after determining the target atlas identification information according to the target text identifier, where the N images are included in the M images;

or the like, or, alternatively,

Further, in the embodiment of the application, a device for judging whether the target atlas identification information meets the picture derivation condition is provided, by adopting the device, the function of intelligently deriving the picture can be better realized, on one hand, the picture can be considered from the picture-text association degree, if the picture-text seriously does not meet the picture-text association degree, the picture can be considered not to meet the picture derivation condition, and the picture can not be derived, so that the rationality of deriving the picture can be improved. On the other hand, in view of sensitive content, if the picture is not compliant, the picture is considered not to satisfy the picture derivation condition, so that the propagation of illegal pictures can be effectively controlled, and a good network environment is maintained.

Optionally, on the basis of the embodiment corresponding to fig. 17, in another embodiment of the picture deriving device 40 provided in the embodiment of the present application, N is an integer greater than 1;

the picture derivation device 40 further includes a processing module 404;

the processing module 404 is configured to, after determining target atlas identification information according to the target text identifier, perform clustering on the N pictures according to picture identification information corresponding to each picture in the N pictures to obtain N clustered pictures if the target atlas identification information meets a picture derivation condition;

the determining module 402 is further configured to determine, according to the target text and the picture identification information corresponding to each picture in the N pictures, a degree of association between each picture and the target text;

the processing module 404 is further configured to sort the N clustered pictures in an order from a large degree of association to a small degree of association, so as to obtain a picture sorting result;

the sending module 403 is further configured to send the picture sorting result to the terminal device, so that when the terminal device detects an operation for the album exporting interface, the N sorted pictures are exported as a file corresponding to the picture format according to the picture sorting result.

Secondly, in the embodiment of the application, a device for intelligently sequencing pictures to be exported is provided, and by adopting the device, intelligent aggregation and sequencing can be performed on the pictures according to the picture identification result of each picture in the process of exporting the pictures, so that the pictures with the same category and higher association degree in the page are put together, a user can conveniently search the corresponding pictures from the files, and the flexibility and the practicability of exporting the pictures are improved.

As shown in fig. 18, for convenience of description, only the portions related to the embodiments of the present application are shown, and details of the specific technology are not disclosed, please refer to the method portion of the embodiments of the present application. Taking a terminal device as a mobile phone as an example:

fig. 18 is a block diagram illustrating a partial structure of a mobile phone related to a terminal device provided in an embodiment of the present application. Referring to fig. 18, the cellular phone includes: radio Frequency (RF) circuitry 510, memory 520, input unit 530, display unit 540, sensor 550, audio circuitry 560, wireless fidelity (WiFi) module 570, processor 580, and power supply 590. Those skilled in the art will appreciate that the handset configuration shown in fig. 18 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

The following describes each component of the mobile phone in detail with reference to fig. 18:

RF circuit 510 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, for processing downlink information of a base station after receiving the downlink information to processor 580; in addition, the data for designing uplink is transmitted to the base station. In general, RF circuitry 510 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, RF circuit 510 may also communicate with networks and other devices via wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to global system for mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Message Service (SMS), etc.

The memory 520 may be used to store software programs and modules, and the processor 580 executes various functional applications and data processing of the mobile phone by operating the software programs and modules stored in the memory 520. The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 520 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The input unit 530 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the cellular phone. Specifically, the input unit 530 may include a touch panel 531 and other input devices 532. The touch panel 531, also called a touch screen, can collect touch operations of a user on or near the touch panel 531 (for example, operations of the user on or near the touch panel 531 by using any suitable object or accessory such as a finger or a stylus pen), and drive the corresponding connection device according to a preset program. Alternatively, the touch panel 531 may include two parts, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, and sends the touch point coordinates to the processor 580, and can receive and execute commands sent by the processor 580. In addition, the touch panel 531 may be implemented by various types such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. The input unit 530 may include other input devices 532 in addition to the touch panel 531. In particular, other input devices 532 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 540 may be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 540 may include a display panel 541, and optionally, the display panel 541 may be configured in the form of a Liquid Crystal Display (LCD), an organic light-emitting diode (OLED), or the like. Further, the touch panel 531 may cover the display panel 541, and when the touch panel 531 detects a touch operation on or near the touch panel 531, the touch panel is transmitted to the processor 580 to determine the type of the touch event, and then the processor 580 provides a corresponding visual output on the display panel 541 according to the type of the touch event. Although the touch panel 531 and the display panel 541 are shown as two separate components in fig. 18 to implement the input and output functions of the mobile phone, in some embodiments, the touch panel 531 and the display panel 541 may be integrated to implement the input and output functions of the mobile phone.

The handset may also include at least one sensor 550, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 541 according to the brightness of ambient light, and the proximity sensor may turn off the display panel 541 and/or the backlight when the mobile phone is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally, three axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of recognizing the posture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be configured on the mobile phone, further description is omitted here.

Audio circuitry 560, speaker 561, and microphone 562 may provide an audio interface between a user and a cell phone. The audio circuit 560 may transmit the electrical signal converted from the received audio data to the speaker 561, and convert the electrical signal into a sound signal by the speaker 561 for output; on the other hand, the microphone 562 converts the collected sound signals into electrical signals, which are received by the audio circuit 560 and converted into audio data, which are then processed by the audio data output processor 580, and then passed through the RF circuit 510 to be sent to, for example, another cellular phone, or output to the memory 520 for further processing.

WiFi belongs to short distance wireless transmission technology, and the mobile phone can help the user to send and receive e-mail, browse web pages, access streaming media, etc. through the WiFi module 570, which provides wireless broadband internet access for the user. Although fig. 18 shows the WiFi module 570, it is understood that it does not belong to the essential constitution of the handset, and may be omitted entirely as needed within the scope not changing the essence of the invention.

The processor 580 is a control center of the mobile phone, connects various parts of the entire mobile phone by using various interfaces and lines, and performs various functions of the mobile phone and processes data by operating or executing software programs and/or modules stored in the memory 520 and calling data stored in the memory 520, thereby performing overall monitoring of the mobile phone. Alternatively, processor 580 may include one or more processing units; optionally, processor 580 may integrate an application processor, which handles primarily the operating system, user interface, applications, etc., and a modem processor, which handles primarily the wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 580.

The handset also includes a power supply 590 (e.g., a battery) for powering the various components, which may optionally be logically connected to the processor 580 via a power management system, such that the power management system may be used to manage charging, discharging, and power consumption.

Although not shown, the mobile phone may further include a camera, a bluetooth module, etc., which are not described herein.

In the embodiment of the present application, the processor 580 included in the terminal device further has the following functions:

Fig. 19 is a schematic diagram of a server structure provided in an embodiment of the present application, where the server 600 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 622 (e.g., one or more processors) and a memory 632, and one or more storage media 630 (e.g., one or more mass storage devices) for storing applications 642 or data 644. Memory 632 and storage medium 630 may be, among other things, transient or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 622 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the server 600.

The Server 600 may also include one or more power supplies 626, one or more wired or wireless network interfaces 650, one or more input-output interfaces 658, and/or one or more operating systems 641, such as a Windows Server^TM，Mac OS X^TM，Unix^TM,Linux^TM，FreeBSD^TMAnd so on.

The steps performed by the server in the above embodiment may be based on the server configuration shown in fig. 19.

Embodiments of the present application also provide a computer-readable storage medium, in which a computer program is stored, and when the computer program runs on a computer, the computer is caused to execute the method described in the foregoing embodiments.

Embodiments of the present application also provide a computer program product including a program, which, when run on a computer, causes the computer to perform the methods described in the foregoing embodiments.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A method of picture derivation, comprising:

when an image viewing instruction for a page to be identified is obtained, displaying M images contained in the page to be identified through an image viewer, wherein the image viewing instruction carries a target text identifier, the target text identifier is used for indicating a target text included in the page to be identified, and M is an integer greater than or equal to 1;

sending the target text identification to a server so that the server determines target atlas identification information according to the target text identification;

if the target atlas identification information meets the atlas exporting condition, displaying an atlas exporting interface on the picture viewer according to an atlas exporting request sent by a server, wherein the atlas exporting interface is used for exporting N pictures in the M pictures, and N is an integer which is greater than or equal to 1 and less than or equal to M;

2. The picture exporting method according to claim 1, wherein when the operation directed to the atlas exporting interface is detected, exporting the N pictures in the page to be identified as the file corresponding to the target format comprises:

when an operation directed to the atlas export interface is detected, exposing a first export interface and a second export interface;

if the operation aiming at the first export interface is detected, exporting the N pictures in the page to be identified as files corresponding to the picture formats;

and if the operation aiming at the second export interface is detected, exporting the N pictures in the page to be identified as a file corresponding to the portable document format PDF.

3. The picture derivation method according to claim 1, wherein N is an integer greater than 1;

when the operation aiming at the atlas exporting interface is detected, exporting the N pictures in the page to be identified as a file corresponding to a target format, wherein the file comprises:

when the operation aiming at the atlas exporting interface is detected, receiving a picture ordering result sent by the server aiming at the N pictures;

4. The picture derivation method as claimed in claim 1, wherein the method further comprises:

if the target atlas identification information meets the picture export condition, displaying the N pictures through the picture viewer;

when the operation aiming at K pictures is detected, exporting the K pictures in the page to be identified as files corresponding to a target format, wherein the K pictures are contained in the N pictures, and K is an integer which is greater than or equal to 1 and less than or equal to K.

5. A method of picture derivation, comprising:

receiving a target text identifier aiming at a page to be identified, which is sent by a terminal device, wherein the target text identifier is used for indicating a target text included in the page to be identified, the page to be identified contains M pictures, and M is an integer greater than or equal to 1;

if the target atlas identification information meets the atlas exporting condition, sending an atlas exporting request to the terminal equipment so that the terminal equipment displays an atlas exporting interface on an atlas viewer according to the atlas exporting request sent by the server, and exporting the N pictures in the page to be identified as a file corresponding to the target format when the terminal equipment detects an operation aiming at the atlas exporting interface, wherein the atlas exporting interface is used for exporting the N pictures in the M pictures, and N is an integer which is greater than or equal to 1 and less than or equal to M.

6. The picture derivation method as claimed in claim 5, wherein said determining target atlas identification information from the target text identification comprises:

and if the target text identifier hits a text identifier library, acquiring the target atlas identification information, wherein the target atlas identification information comprises picture identification information corresponding to each picture in the M pictures, and the text identifier library comprises at least one text identifier and the atlas identification information corresponding to each text identifier.

7. The picture derivation method as claimed in claim 5, wherein said determining target atlas identification information from the target text identification comprises:

if the target text identification does not hit the text identification library, acquiring the M pictures;

and storing the target text identification and the target atlas identification information into the text identification library, wherein the text identification library comprises at least one text identification and atlas identification information corresponding to each text identification.

8. The picture derivation method according to claim 7, wherein the identifying the M pictures to obtain the target atlas identification information comprises:

for each picture in the M pictures, obtaining picture identification information corresponding to the picture through an object identification model, wherein the picture identification information comprises at least one of an object type, an object name and a keyword;

and acquiring the identification information of the target atlas according to the picture identification information corresponding to each picture in the M pictures.

9. The picture derivation method according to any one of claims 5 to 8, wherein the target atlas identification information includes picture identification information corresponding to each of the M pictures;

after determining the target atlas identification information according to the target text identification, the method further includes:

if the association degree between the picture identification information of the N pictures and the target text meets the picture-text matching condition and the picture identification information of the N pictures meets the information safety condition, determining that the target atlas identification information meets the picture derivation condition, wherein the N pictures are contained in the M pictures;

or the like, or, alternatively,

if the association degree between the picture identification information of the N pictures and the target text meets the picture-text matching condition, determining that the target atlas identification information meets the picture derivation condition;

or the like, or, alternatively,

and if the picture identification information of the N pictures meets the information safety condition, determining that the target atlas identification information meets the picture export condition.

10. The picture derivation method according to claim 5, wherein N is an integer greater than 1;

if the target image set identification information meets the image derivation condition, clustering the N images according to the image identification information corresponding to each image in the N images to obtain N clustered images;

determining the association degree between each picture and the target text according to the target text and the picture identification information corresponding to each picture in the N pictures;

sequencing the N clustered pictures according to the sequence of the relevance from large to small to obtain a picture sequencing result;

and sending the picture sorting result to the terminal equipment so that when the terminal equipment detects the operation aiming at the atlas exporting interface, the N sorted pictures are exported to the file corresponding to the picture format according to the picture sorting result.

11. A picture derivation apparatus, comprising:

the display module is used for displaying M pictures contained in a page to be identified through a picture viewer when a picture viewing instruction for the page to be identified is acquired, wherein the picture viewing instruction carries a target text identifier which is used for indicating a target text contained in the page to be identified, and M is an integer greater than or equal to 1;

the sending module is used for sending the target text identification to a server so that the server determines target atlas identification information according to the target text identification;

the display module is further configured to display an album derivation interface on the picture viewer according to an album derivation request sent by a server if the target album identification information meets an album derivation condition, where the album derivation interface is configured to derive N pictures of the M pictures, where N is an integer greater than or equal to 1 and less than or equal to M;

and the exporting module is used for exporting the N pictures in the page to be identified as a file corresponding to the target format when the operation aiming at the atlas exporting interface is detected.

12. A picture derivation apparatus, comprising:

the device comprises a receiving module, a processing module and a display module, wherein the receiving module is used for receiving a target text identifier which is sent by a terminal device and aims at a page to be recognized, the target text identifier is used for indicating a target text included in the page to be recognized, and M is an integer which is greater than or equal to 1;

a sending module, configured to send an atlas derivation request to the terminal device if the target atlas identification information meets an atlas derivation condition, so that the terminal device displays an atlas derivation interface on an atlas viewer according to the atlas derivation request sent by the server, and when the terminal device detects an operation for the atlas derivation interface, derives the N pictures in the page to be identified as a file corresponding to a target format, where the atlas derivation interface is used to derive N pictures in the M pictures, and N is an integer greater than or equal to 1 and less than or equal to M.

13. A terminal device, comprising: a memory, a transceiver, a processor, and a bus system;

wherein the memory is used for storing programs;

the processor is configured to execute a program in the memory, the processor is configured to perform the picture derivation method of any of claims 1 to 4 according to instructions in the program code;

14. A server, comprising: a memory, a transceiver, a processor, and a bus system;

wherein the memory is used for storing programs;

the processor is configured to execute a program in the memory, the processor is configured to perform the picture derivation method of any of claims 5 to 10 according to instructions in the program code;

15. A computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform the picture derivation method of any of claims 1 to 4, or perform the picture derivation method of any of claims 5 to 10.