CN116595256B - Method and system for data screening and immersive interaction of digital exhibition - Google Patents
Method and system for data screening and immersive interaction of digital exhibition Download PDFInfo
- Publication number
- CN116595256B CN116595256B CN202310582456.2A CN202310582456A CN116595256B CN 116595256 B CN116595256 B CN 116595256B CN 202310582456 A CN202310582456 A CN 202310582456A CN 116595256 B CN116595256 B CN 116595256B
- Authority
- CN
- China
- Prior art keywords
- information
- science popularization
- target
- index
- search
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012216 screening Methods 0.000 title claims abstract description 36
- 230000003993 interaction Effects 0.000 title claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims description 47
- 230000000737 periodic effect Effects 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 12
- 238000007654 immersion Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000003930 cognitive ability Effects 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 8
- 238000005192 partition Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/904—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical field of data processing, and provides a method and a system for data screening and immersive interaction of a digital exhibition. Information acquisition is carried out according to the science popularization requirements of the user, information screening of acquiring science popularization information is carried out by taking the user requirement characteristics as constraints, virtual reality scene generation is carried out based on the screened information to obtain a target exhibition scene, and the user carries out immersive interaction based on the target exhibition scene. The technical problems that in the prior art, the popular science knowledge provided according to the popular science needs of the user, the cognitive ability of the user and the preference tendency of the knowledge types are not adapted, so that the receiving and understanding ability of the user to the popular science knowledge is poor, the popular science knowledge of the user is browsed and learned and experiences are poor are solved, the popular science knowledge meeting the cognitive ability of the user is guaranteed to be supplied, the browsing and exploration of the popular science knowledge information in a simulated scene are realized, the diversified understanding of the popular science knowledge is deepened, and the receiving efficiency of the user to the required popular science knowledge is improved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a method and a system for data screening and immersive interaction of a digital exhibition.
Background
At present, more and more science popularization information websites and platforms provide rich science popularization knowledge content for vast users, but in practical application, the problem of cognition mismatch exists between the users and the science popularization information websites, so that the receiving and understanding ability of the users on the science popularization knowledge is reduced, and the learning experience is poor.
Specifically, the science popularization information website only provides science popularization knowledge related to the science popularization requirements of the user according to the science popularization requirements of the user, and the fact that the actual content of the science popularization knowledge is not matched with the cognitive ability and knowledge type preference tendency of the user reduces the knowledge seeking of the science popularization knowledge of the user based on the science popularization website, so that the browsing and learning experience of the science popularization knowledge of the user is poor.
In summary, in the prior art, the technical problems of poor receiving and understanding ability of the user on the science popularization knowledge and poor browsing and learning experience of the user science popularization knowledge due to the fact that the science popularization knowledge provided according to the science popularization requirement of the user is not matched with the cognitive ability and the knowledge type preference tendency of the user exist.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method and a system for data screening and immersive interaction of a digital exhibition, which can ensure that popular science according to the cognitive ability of a user is provided, so that the user can search for popular science information through immersive browsing in a simulated scene, thereby deepening diversified understanding of popular science by the user and improving the receiving efficiency of the user for the required popular science.
A method of data screening and immersive interaction for a digital display, the method comprising: acquiring information of a first target user to obtain historical receiving information, wherein the historical receiving information comprises historical active searching information and historical passive recommending information; user demand analysis is carried out based on the historical search information, and target demand characteristics are obtained; obtaining target science popularization requirements of the first target user; acquiring information according to the target science popularization requirement to obtain a first science popularization information set, wherein the first science popularization information set comprises a plurality of science popularization information clusters; information screening of the first science popularization information set is conducted by taking the target demand characteristics as constraints, and second science popularization information is generated; generating a virtual reality scene for the second science popularization information to obtain a target exhibition scene; the first target user performs immersive interaction based on the target display scene.
A system of data screening and immersive interaction for a digital display, the system comprising: the information acquisition execution module is used for acquiring information of a first target user to obtain historical receiving information, wherein the historical receiving information comprises historical active search information and historical passive recommendation information; the demand characteristic analysis module is used for carrying out user demand analysis based on the historical search information to obtain target demand characteristics; the science popularization requirement generation module is used for obtaining the target science popularization requirement of the first target user; the demand information acquisition module is used for acquiring information according to the target science popularization demand to obtain a first science popularization information set, wherein the first science popularization information set comprises a plurality of science popularization information clusters; the information screening execution module is used for carrying out information screening on the first science popularization information set by taking the target demand characteristics as constraints to generate second science popularization information; the virtual scene generation module is used for generating a virtual reality scene for the second science popularization information to obtain a target exhibition scene; and the immersion interaction executing module is used for carrying out immersion interaction on the basis of the target exhibition scene by the first target user.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring information of a first target user to obtain historical receiving information, wherein the historical receiving information comprises historical active searching information and historical passive recommending information;
user demand analysis is carried out based on the historical search information, and target demand characteristics are obtained;
obtaining target science popularization requirements of the first target user;
acquiring information according to the target science popularization requirement to obtain a first science popularization information set, wherein the first science popularization information set comprises a plurality of science popularization information clusters;
information screening of the first science popularization information set is conducted by taking the target demand characteristics as constraints, and second science popularization information is generated;
generating a virtual reality scene for the second science popularization information to obtain a target exhibition scene;
the first target user performs immersive interaction based on the target display scene.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
Acquiring information of a first target user to obtain historical receiving information, wherein the historical receiving information comprises historical active searching information and historical passive recommending information;
user demand analysis is carried out based on the historical search information, and target demand characteristics are obtained;
obtaining target science popularization requirements of the first target user;
acquiring information according to the target science popularization requirement to obtain a first science popularization information set, wherein the first science popularization information set comprises a plurality of science popularization information clusters;
information screening of the first science popularization information set is conducted by taking the target demand characteristics as constraints, and second science popularization information is generated;
generating a virtual reality scene for the second science popularization information to obtain a target exhibition scene;
the first target user performs immersive interaction based on the target display scene.
The method and the system for data screening and immersive interaction of the digital exhibition solve the technical problems that in the prior art, the receiving understanding ability of the user on the science popularization knowledge is poor due to the fact that the science popularization knowledge provided according to the science popularization requirement of the user is not matched with the cognitive ability of the user and the preference tendency of the knowledge type is bad, and the knowledge browsing learning experience of the user is poor.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a flow diagram of a method of data screening and immersive interaction for a digital display in one embodiment;
FIG. 2 is a flow chart of a method for data screening and immersive interaction for a digital display for second science popularization information optimization, according to one embodiment;
FIG. 3 is a block diagram of a system for data screening and immersive interaction for a digital display in one embodiment;
fig. 4 is an internal structural diagram of a computer device in one embodiment.
Reference numerals illustrate: the system comprises an information acquisition and execution module 1, a demand characteristic analysis module 2, a science popularization demand generation module 3, a demand information acquisition module 4, an information screening and execution module 5, a virtual scene generation module 6 and an immersion interaction execution module 7.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
As shown in fig. 1, the present application provides a method for data screening and immersive interaction of a digital display, the method comprising:
s100: acquiring information of a first target user to obtain historical receiving information, wherein the historical receiving information comprises historical active searching information and historical passive recommending information;
specifically, in this embodiment, a plurality of types of science popularization knowledge are recorded in the science popularization information website, and the types of science popularization knowledge in the website include, but are not limited to, a graphic form and a video form. The first target user learns to acquire required science popularization knowledge based on the science popularization information website so as to deepen an unspecified user for understanding a certain knowledge.
After the first target user logs in the science popularization information website, the first target user has authority to inquire the science popularization information and directly passively receives and browses the website pushing information at the science popularization information website. Thus, the embodiment collects the browsing records of the target user, and obtains the historical received information, where the historical received information is the popular science information including but not limited to the text and video browsed by the first target user in a past period of time, such as a past month.
The historical receiving information is subdivided into the historical active searching information and the historical passive recommending information, wherein the historical searching information is science popularization knowledge information which is obtained by clicking and checking the science popularization information in a plurality of science popularization information by a first target user after the first target user inputs a search word in a search field of the science popularization information website, and the science popularization information website outputs a plurality of science popularization information based on the search word. The historical passive recommendation information is science popularization knowledge information clicked and checked by the first target user when the first target user browses the science popularization information network station main page or each science popularization partition page in an unintentional mode.
And any piece of popular science knowledge information in the historical active search information and the historical passive recommendation information is marked with viewing time. According to the method, the historical receiving information is obtained, and reference data are provided for subsequent analysis of the popular science knowledge understanding capability and the popular science interest direction of the first target user.
S200: user demand analysis is carried out based on the historical search information, and target demand characteristics are obtained;
in one embodiment, the method step S200 provided by the present application further includes:
s210, carrying out acquisition period division on the historical search information to obtain multicycle search information;
S220, carrying out information depth analysis on the multicycle search information to obtain an information depth index set;
s230, carrying out information density analysis on the multicycle search information to obtain an information density index set;
s240, carrying out information intensity analysis according to the information depth index set and the information depth index set to generate an information fluctuation index;
s250, carrying out demand prediction according to the information fluctuation index to generate the target demand characteristics, wherein the target demand characteristics comprise information density predicted values and information depth predicted values.
In one embodiment, the information depth analysis is performed on the multicycle search information to obtain an information depth index set, and the method step S220 provided by the present application further includes:
s221, extracting and obtaining first periodic search information based on the multicycle search information;
s222, carrying out multidimensional data analysis on the first periodic search information to obtain a first literature citation index, a first reading difficulty index and a first space paragraph index;
s223, traversing the first document citation index, the first reading difficulty index and the first space paragraph index, and setting a first weight, a second weight and a third weight;
S224, according to the first weight, the second weight and the third weight, the first document citation index, the first reading difficulty index and the first space paragraph index are fused, and a first information depth index is obtained.
Specifically, based on step S100, any piece of popular knowledge information in the history search information in this embodiment identifies the viewing time, so that the information dividing period is preset in this embodiment, for example, 1 hour day is taken as one information dividing period.
Based on a preset information dividing period, carrying out acquisition period division on the historical search information to obtain multicycle search information, wherein each cycle search information in the multicycle search information comprises science popularization knowledge information which is browsed by a first target user in a science popularization information website in an active search or passive pushing mode within 1 hour, and the method comprises but is not limited to image-text forms and video forms.
In order to facilitate the subsequent knowledge density analysis and knowledge depth analysis of science popularization information, AHD Subtitles Maker (subtitle editing software) is adopted in the embodiment to extract subtitle manuscripts of the video-form science popularization information in advance, so that the knowledge depth analysis and the knowledge density analysis are both performed based on text content, and the information processing complexity during analysis is reduced.
In this embodiment, the information depth index is the knowledge depth degree and knowledge understanding difficulty of the quantized popular science knowledge information, and is used to characterize the understanding capability of the first target user on the popular science knowledge information. The embodiment performs information depth analysis on the multicycle search information in pure text form to obtain an information depth index set, wherein the information depth index set comprises a plurality of cycle information depth indexes, and each cycle information depth index represents science popularization knowledge information of which degree of tarnish can be understood by a first target user in a time period.
In this embodiment, an information depth index obtaining method of any one period of the multi-period search information is taken as an example, and an explanation of the information depth index collection method is performed.
And extracting and obtaining first periodic search information based on the multicycle search information, wherein the first periodic search information is periodic search information of a random periodic division result in the multicycle search information. And extracting all text contents in the first periodic search information, and counting reference citation frequencies to obtain a first literature citation index, wherein the higher the first literature citation index is, the higher the rigor degree of the first periodic search information is.
Inputting the extracted first periodic search information into an existing Chinese legibility analyzer for legibility analysis, and generating the first reading difficulty index, wherein the higher the first reading difficulty index is, the higher the understanding difficulty of the popular science knowledge of the first periodic search information is for a person with ordinary learning ability.
According to a plurality of pieces of science popularization knowledge information in the image-text form in the first period search information, the original paragraph format of the science popularization knowledge information in the image-text form is reserved, paragraph counting is carried out after the text format is unified, the paragraph number of each piece of science popularization knowledge information in the image-text form and the line number of each piece of science popularization knowledge information in the first period search information are obtained, the average paragraph number of the plurality of pieces of science popularization knowledge information in the image-text form and the average line number of each piece of science popularization knowledge information are further calculated, dimensionless processing is carried out on the average paragraph number and the average line number, and the first paragraph index is obtained, and reflects the length characteristics of the image-text of the science popularization knowledge information read by a first target user in a time period corresponding to the first period search information.
The method comprises the steps of assigning a first weight to a literature citation index, assigning a second weight to a reading difficulty index, and assigning a third weight to a space paragraph index, wherein assignment results of the first weight, the second weight and the third weight represent the influence degree of the literature citation amount, the reading difficulty and the space paragraph length on the information depth index in information depth index generation.
The weight assignment setting can contact a plurality of experts in the information analysis field by adopting a public channel or letter mode through an expert evaluation method, multiple groups of first subjective weight, second subjective weight and third subjective weight are obtained based on the plurality of groups of experts, mean value calculation is carried out on the multiple groups of first subjective weight, second subjective weight and third subjective weight, subjectivity of the expert weight assignment is eliminated, and the first weight, the second weight and the third weight which can objectively reflect importance of each index in information depth calculation are obtained.
And according to the first weight, the second weight and the third weight, performing weighted calculation on the first document citation index, the first reading difficulty index and the first spread paragraph index to generate the first information depth index. And obtaining a plurality of information depth indexes corresponding to the multicycle search information by adopting the same method for obtaining the first information depth index to form the information depth index set.
In this embodiment, the information density reflects the information amount of the popular science knowledge information, and the higher the information density index is, the larger the information amount of the popular science knowledge information viewed by the first target user is. In this embodiment, information density analysis is performed on the multicycle search information one by one to obtain an information density index set, where the information density index set includes multicycle information density indexes corresponding to the multicycle search information, and a method for obtaining the information density indexes is described in detail in a later description.
It should be understood that in this embodiment, the multi-period search information includes a plurality of period search information having a chronological order, and each period search information has an information depth index and an information density index.
And generating a scatter diagram of the information depth index changing along with the time period based on the information depth index set, and calculating and obtaining a correlation coefficient between the information depth index and the time period based on the scatter diagram to serve as an information depth increase coefficient.
And generating a scatter diagram of the information density index changing along with the time period based on the information density index set, and calculating and obtaining a correlation coefficient between the information density index and the time period based on the scatter diagram to serve as an information density increase coefficient.
The information depth increasing coefficient and the information density increasing coefficient form the information fluctuation index, and the information fluctuation index reflects the situation that the first target user increases along with the total time of referring to the science popularization information website, and the difficulty of browsable and understood science popularization knowledge information and the information quantity increase along with time.
And obtaining a group of information density indexes and information depth indexes corresponding to the period search information of the last period in the multi-period search information, and calculating to obtain the target demand characteristics by combining the information depth increase coefficient and the information density increase coefficient in the information fluctuation indexes, wherein the target demand characteristics comprise information density predicted values and information depth predicted values. The target demand features are information density limit and information depth limit of the predicted popular science knowledge information which can be browsed by the first target user in a barrier-free mode. When the information depth and information density of the science popularization knowledge information exceed the target demand characteristics, the readability of the science popularization knowledge information is reduced for the first target user.
According to the method and the device for obtaining the target demand characteristics, the technical effect of screening and referencing the science popularization knowledge information is provided for providing the science popularization knowledge information which can be browsed and understood by the first target user in a barrier-free mode for the follow-up, and therefore the technical effect of improving the experience of browsing the science popularization knowledge information by the first target user is achieved.
S300, obtaining target science popularization requirements of the first target user;
s400, acquiring information according to the target science popularization requirement to obtain a first science popularization information set, wherein the first science popularization information set comprises a plurality of science popularization information clusters;
specifically, in this embodiment, the target science popularization requirement is a short search term, such as insects, organic chemistry, and warrior history, which is input by the first target user in the science popularization information website search field. And carrying out relevant word divergence based on the target science popularization requirement, expanding a science popularization knowledge information search range, and obtaining a target science popularization word set, wherein for example, the target requirement information is a warrior history, the target science popularization word set comprises a warrior national alignment history, a warrior Chu national history, a warrior economic history, a warrior military war annual history and a warrior swallow national history, and it is understood that words in the target science popularization word set are lower words of the target science popularization requirement.
Traversing the subject names of the science popularization information knowledge in the science popularization information website by the target science popularization word set one by one to obtain a plurality of science popularization information clusters, wherein each science popularization information cluster contains the science popularization knowledge information of the same target science popularization word for a plurality of subject names. The plurality of science popularization information clusters and the plurality of target science popularization words in the target science popularization word set have a one-to-one mapping relation, and the plurality of science popularization information clusters form the first science popularization information set.
S500, carrying out information screening on the first science popularization information set by taking the target demand characteristics as constraints to generate second science popularization information;
specifically, in this embodiment, text content extraction is performed for each period of search information in the multi-period search information, and the format is unified, and on the basis of this, the data amount of each period of search information is further obtained, a plurality of data amounts (unit kb) of the multi-period search information are obtained, and an average data amount is obtained by averaging the plurality of data amounts.
And randomly extracting information from each science popularization information cluster of the first science popularization information set to obtain a text information extraction result meeting the average data quantity.
And (2) obtaining the information density index and the information depth index of the text randomly extracted from each science popularization information cluster in the first science popularization information set by adopting the same information density index and information depth index calculation method in the step (S200).
And traversing the information density indexes and the information depth indexes corresponding to the plurality of science popularization information clusters by taking the information density predicted value and the information depth predicted value of the target demand characteristics as judging references of whether the science popularization information clusters are reserved or not.
And reserving all the contents in the science popularization information clusters meeting the target demand characteristics, and forming second science popularization information based on a plurality of reserved science popularization information clusters, wherein the second science popularization information ensures that the science popularization knowledge information provided for the first target user is within the acceptable range of the first target user.
S600, generating a virtual reality scene of the second science popularization information to obtain a target exhibition scene;
in one embodiment, as shown in fig. 2, the method step S600 provided by the present application further includes:
s610, presetting a scene generation information threshold;
s620, judging whether the second science popularization information meets the scene generation information threshold;
s630, if the second science popularization information does not meet the scene generation information threshold, user interest analysis is conducted based on the historical passive recommendation information, and target interest characteristics are obtained;
S640, analyzing the information association degree of the target interest feature and the second science popularization information to obtain an associated information feature;
and S650, optimizing the second science popularization information according to the associated information characteristics.
In one embodiment, the virtual reality scene generation is performed on the second science popularization information to obtain the target exhibition scene, and the method step S600 provided by the application further includes:
s661, generating an information classification feature set according to the target science popularization requirement, wherein the information classification feature set comprises a plurality of information classification features;
s662, carrying out second science popularization information classification based on the information classification features to obtain a plurality of virtual information clusters, wherein each virtual information cluster is provided with the information classification feature identification;
s663, according to the similarity between the information classification features and the target science popularization requirement information, carrying out relevance ranking on the virtual information clusters;
s664, generating local virtual reality scenes of the plurality of virtual information clusters according to the sorting result to obtain a plurality of local virtual reality scenes;
s665: and constructing the target exhibition scene according to the plurality of local virtual reality scenes.
Specifically, in this embodiment, a scene generation information threshold is preset, where the scene generation information threshold is a data volume requirement (unit MB/GB) that needs to be satisfied by the second science popularization information when the virtual scene is built based on the second science popularization information, and a specific value of the scene generation information threshold may be set according to the data volume accommodated in the virtual reality scene that is planned to be built, and the value of the scene generation information threshold is not limited in this embodiment.
Obtaining a second science popularization information integral data volume (unit MB/GB), judging whether the second science popularization information integral data volume meets the scene generation information threshold, if the second science popularization information does not meet the scene generation information threshold, indicating that the current second science popularization information data volume is insufficient for building a virtual reality scene, and if the virtual reality scene is forcedly built for a first target user to carry out immersed interactive science popularization knowledge browsing, the problem that the first target user experiences poor due to insufficient science popularization knowledge information exists.
Therefore, the embodiment calls the historical passive recommendation information, wherein the historical passive recommendation information is science popularization knowledge information clicked and checked by the first target user when the first target user browses the science popularization information network station main page or each science popularization partition page in an unintentional mode. And obtaining the image-text type information and the video type information duty ratio in the historical passive recommendation information, and generating the target interest feature, wherein the target interest feature reflects the popular science knowledge information browsing type tendency of the first target user.
Further, obtaining a science popularization partition to which the target demand features belong, and obtaining a target science popularization partition. Setting the information association degree of the target interest feature and the second science popularization information, wherein the information association degree is the correlation between the historical passive recommendation information and the target demand feature corresponding to the second science popularization information, and in the embodiment, when any science popularization knowledge information in the historical passive recommendation information is considered to meet the requirement of the target science popularization region and meets the information type requirement of the target interest feature, the arbitrary science popularization knowledge information is considered to meet the information association degree, namely, the association information feature is formed by the target interest feature and the target science popularization region and is used as a screening condition for carrying out the historical passive recommendation information.
And extracting M pieces of recommended science popularization knowledge information falling into the target science popularization partition from the historical passive recommendation information, wherein M is a positive integer greater than 1. K pieces of recommended knowledge information which accords with the target interest feature are further obtained from the M pieces of recommended knowledge information and are used as supplements of the second science popularization information, and optimization of the second science popularization information is completed.
And obtaining the information quantity of the optimized second science popularization information and comparing the information quantity with a scene generation information threshold, if the information quantity does not meet the scene generation information threshold, obtaining the extension knowledge of K pieces of recommended knowledge information, and re-optimizing the optimized second science popularization information again so as to ensure that the information quantity of the second science popularization information meets the scene generation information threshold.
In this embodiment, virtual reality scene generation is performed based on the second science popularization information obtained through optimization, and an information classification feature set is generated according to the target science popularization requirement, wherein the information classification feature set comprises a plurality of information classification features, and the information classification features are mapped to the target science popularization word set.
And classifying the second science popularization information based on the information classification features by taking the main body names of the science popularization knowledge information as classification references to obtain a plurality of virtual information clusters, wherein each virtual information cluster is provided with the information classification feature identification, and the subject names of the science popularization knowledge information in each virtual information cluster also have the same science popularization words.
Because of the upper and lower position relations among all the science popularization words in the target science popularization word set, a plurality of information classification features corresponding to the target science popularization word set also have the characteristic upper and lower position relations, the upper and lower position relations of the science popularization words are used as the similarity relations between the information classification features and the target science popularization demand information, and therefore association degree ranking is carried out on the virtual information clusters, and parallel ranking virtual information clusters with parallel relations corresponding to the target science popularization words in the ranking result are obtained.
And generating local virtual reality scenes of the virtual information clusters according to the sorting result to obtain a plurality of local virtual reality scenes, wherein each local virtual reality scene is a spatial science popularization knowledge information scene, and the local virtual reality scene is an annular picture and text wall which is divided into a plurality of rectangular sections, wherein each section is a science popularization knowledge information theme name, picture and text and short introduction, a first target user enters the local virtual reality scene through VR equipment, the annular picture and text wall surrounds the first target user, and the first target user can grasp any rectangular section at will to browse the video and the picture and text science popularization knowledge in the section in an immersive manner.
And arranging the plurality of partial virtual reality scenes according to the sorting result to complete the construction of the target exhibition scene, wherein the earlier partial virtual reality scenes in the target exhibition scene are sorted more forward in the sorting result, and the first target user can interactively browse the science popularization knowledge information in each partial virtual reality scene in an immersed mode.
And S700, carrying out immersive interaction by the first target user based on the target exhibition scene.
Specifically, in this embodiment, the first target user may enter a local virtual reality scene corresponding to any target science popularization word (information classification feature) to perform immersive interactive browsing based on the target exhibition scene, so as to perform science popularization knowledge information exploration in a simulated scene, continuously deepen diversified understanding of science popularization knowledge, and improve knowledge receiving effect of the first target user on required science popularization knowledge.
In one embodiment, the information density analysis is performed on the multicycle search information to obtain an information density index set, and the method step S230 provided by the present application further includes:
s231, extracting and obtaining first periodic search information based on the multicycle search information;
S232, irrelevant information is removed from the first period search information, and first pure information is obtained;
s233, performing word frequency calculation on the first pure information to obtain a first keyword set, wherein the first keyword set comprises n keywords and n keyword frequencies;
and S234, generating a first information density according to the first keyword set and the first search period total word number.
In one embodiment, the method step S234 further includes:
s234-1, calculating an information density index according to an information density calculation formula, wherein the specific formula is as follows:
wherein Keyword Frequency is keyword frequency, total Words is Total word number, keyword i The i-th keyword, n is the number of related keywords;
s234-2, bringing the first keyword set and the first search period total word number into the information density calculation formula to obtain a first information density.
Specifically, the embodiment is a refinement of step S200, and is also an optimal embodiment of performing information density analysis on the multicycle search information to obtain an information density index set. In this embodiment, taking an information density index of random certain period search information in the multi-period search information as an example, a method for obtaining information density of the period search information is described.
It should be understood that, in order to facilitate knowledge density analysis (i.e., information density analysis) of science popularization knowledge information, AHD Subtitles Maker (subtitle editing software) is adopted in this embodiment in advance to extract subtitle documents of science popularization information in video form, so that the information density analysis is performed based on text content.
Specifically, any periodic search information is randomly extracted based on the multicycle search information and used as the first periodic search information, wherein the first periodic search information is a plurality of science popularization knowledge information texts in a word form.
And after integrating a plurality of science popularization knowledge information, performing irrelevant information rejection, and specifically rejecting punctuation marks, connective words and nonsensical words (such as adjectives) to obtain first pure information. Dividing the first pure information according to words, counting the occurrence frequency of each word, extracting n keywords with the top ranking of the occurrence frequency, and forming a first keyword set, wherein the first keyword set comprises n keywords and n keyword frequencies.
The first search period total word number characterizing the word number in the first search period is obtained based on the original text of the first search period information. And carrying the first keyword set and the first search period total word number into the information density calculation formula to obtain the first information density reflecting the information density condition of the kepu knowledge information in the first search period.
The specific information density calculation formula is as follows:
wherein Keyword Frequency is keyword frequency, total Words is Total word number, keyword i For the ith keyword, n is the number of related keywords.
And calculating to obtain multicycle information density indexes with mapping relation with the multicycle search information by adopting a first information density same method for calculating to obtain first search cycle information, and forming the information density index set. And each index in the information density index set and the information depth set has a one-to-one mapping relation based on multi-period search information.
The information density index calculation method is set, information density conditions which scientifically and objectively reflect popular science knowledge information browsed by the first target user are obtained, and basic data are provided for combining the information depth index to accurately analyze and predict information density limit and information depth limit of popular science knowledge information browsable by the first target user without barriers.
In one embodiment, as shown in FIG. 3, a system for data screening and immersive interaction for a digital display is provided, comprising: the system comprises an information acquisition execution module 1, a demand characteristic analysis module 2, a science popularization demand generation module 3, a demand information acquisition module 4, an information screening execution module 5, a virtual scene generation module 6 and an immersed interaction execution module 7, wherein:
The information acquisition execution module 1 is used for acquiring information of a first target user to obtain historical receiving information, wherein the historical receiving information comprises historical active search information and historical passive recommendation information;
the demand characteristic analysis module 2 is used for carrying out user demand analysis based on the historical search information to obtain target demand characteristics;
a science popularization requirement generation module 3, configured to obtain a target science popularization requirement of the first target user;
the requirement information acquisition module 4 is used for acquiring information according to the target science popularization requirement to obtain a first science popularization information set, wherein the first science popularization information set comprises a plurality of science popularization information clusters;
the information screening execution module 5 is used for carrying out information screening on the first science popularization information set by taking the target demand characteristics as constraints to generate second science popularization information;
the virtual scene generation module 6 is used for generating a virtual reality scene for the second science popularization information to obtain a target exhibition scene;
and the immersion interaction executing module 7 is used for carrying out immersion interaction on the basis of the target exhibition scene by the first target user.
In one embodiment, the system further comprises:
The information threshold setting unit is used for presetting a scene generation information threshold;
an information threshold judging unit for judging whether the second science popularization information meets the scene generation information threshold;
the interest feature generation unit is used for carrying out user interest analysis based on the historical passive recommendation information if the second science popularization information does not meet the scene generation information threshold value, so as to obtain target interest features;
the associated feature generation unit is used for analyzing the information association degree of the target interest feature and the second science popularization information to obtain associated information features;
and the science popularization information optimization unit is used for optimizing the second science popularization information according to the associated information characteristics.
In one embodiment, the system further comprises:
the information dividing and executing unit is used for carrying out acquisition period division on the historical search information to obtain multicycle search information;
the information depth analysis unit is used for carrying out information depth analysis on the multi-period search information to obtain an information depth index set;
the information density analysis unit is used for carrying out information density analysis on the multicycle search information to obtain an information density index set;
The information fluctuation generation unit is used for carrying out information intensity analysis according to the information depth index set and the information depth index set to generate an information fluctuation index;
and the demand characteristic generation unit is used for carrying out demand prediction according to the information fluctuation index to generate the target demand characteristic, wherein the target demand characteristic comprises an information density predicted value and an information depth predicted value.
In one embodiment, the system further comprises:
a search information extraction unit for extracting and obtaining first periodic search information based on the multicycle search information;
the multidimensional data analysis unit is used for multidimensional data analysis of the first periodic search information to obtain a first document quotation index, a first reading difficulty index and a first space paragraph index;
the weight assignment execution unit is used for traversing the first document citation index, the first reading difficulty index and the first space paragraph index and setting a first weight, a second weight and a third weight;
the depth index generation unit is configured to fuse the first document citation index, the first reading difficulty index and the first space paragraph index according to the first weight, the second weight and the third weight, and obtain a first information depth index.
In one embodiment, the system further comprises:
an information extraction execution unit for extracting and obtaining first periodic search information based on the multicycle search information;
the information rejection execution unit is used for rejecting irrelevant information of the first periodic search information to obtain first pure information;
the word frequency calculation execution unit is used for performing word frequency calculation on the first pure information to obtain a first keyword set, wherein the first keyword set comprises n keywords and n keyword frequencies;
and the information density obtaining unit is used for generating a first information density according to the first keyword set and the first search period total word number.
In one embodiment, the system further comprises:
a calculation formula setting unit for calculating an information density index by an information density calculation formula, the specific formula is as follows:
wherein Keyword Frequency is the keyword frequency, total Words is the Total word number, keywords is the ith keyword, and n is the number of related keywords;
and the information density calculation unit is used for bringing the first keyword set and the first search period total word number into the information density calculation formula to obtain a first information density.
In one embodiment, the system further comprises:
the classification feature setting unit is used for generating an information classification feature set according to the target science popularization requirement, wherein the information classification feature set comprises a plurality of information classification features;
the feature identification processing unit is used for carrying out second science popularization information classification based on the information classification features to obtain a plurality of virtual information clusters, wherein each virtual information cluster is provided with the information classification feature identification;
the information cluster ordering unit is used for ordering the association degree of the plurality of virtual information clusters according to the similarity between the plurality of information classification features and the target science popularization requirement information;
the local scene construction unit is used for generating local virtual reality scenes of the plurality of virtual information clusters according to the sequencing result to obtain a plurality of local virtual reality scenes;
and the exhibition scene construction unit is used for constructing the target exhibition scene according to the plurality of local virtual reality scenes.
For a specific embodiment of a system for data screening and immersive interaction for a digital display, reference may be made to the above embodiment of a method for data screening and immersive interaction for a digital display, which is not described herein. The modules in the system for data screening and immersive interaction of a digital display can be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing news data, time attenuation factors and other data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method of data screening and immersive interaction for a digital display.
It will be appreciated by persons skilled in the art that the architecture shown in fig. 4 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer readable storage medium is provided, comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program: acquiring information of a first target user to obtain historical receiving information, wherein the historical receiving information comprises historical active searching information and historical passive recommending information; user demand analysis is carried out based on the historical search information, and target demand characteristics are obtained; obtaining target science popularization requirements of the first target user; acquiring information according to the target science popularization requirement to obtain a first science popularization information set, wherein the first science popularization information set comprises a plurality of science popularization information clusters; information screening of the first science popularization information set is conducted by taking the target demand characteristics as constraints, and second science popularization information is generated; generating a virtual reality scene for the second science popularization information to obtain a target exhibition scene; the first target user performs immersive interaction based on the target display scene.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (6)
1. A method of data screening and immersive interaction for a digital display, the method comprising:
acquiring information of a first target user to obtain historical receiving information, wherein the historical receiving information comprises historical active searching information and historical passive recommending information;
user demand analysis is carried out based on the historical search information, and target demand characteristics are obtained;
obtaining target science popularization requirements of the first target user;
acquiring information according to the target science popularization requirement to obtain a first science popularization information set, wherein the first science popularization information set comprises a plurality of science popularization information clusters;
information screening of the first science popularization information set is conducted by taking the target demand characteristics as constraints, and second science popularization information is generated;
Generating a virtual reality scene for the second science popularization information to obtain a target exhibition scene;
the first target user performs immersive interaction based on the target exhibition scene;
user demand analysis is performed based on the historical search information, and target demand characteristics are obtained, wherein the method further comprises the steps of:
carrying out acquisition period division on the historical search information to obtain multicycle search information;
carrying out information depth analysis on the multicycle search information to obtain an information depth index set;
performing information density analysis on the multicycle search information to obtain an information density index set;
carrying out information intensity analysis according to the information depth index set and the information depth index set to generate an information fluctuation index;
carrying out demand prediction according to the information fluctuation index to generate the target demand characteristics, wherein the target demand characteristics comprise an information density predicted value and an information depth predicted value;
performing information depth analysis on the multicycle search information to obtain an information depth index set, wherein the method further comprises the following steps:
extracting and obtaining first periodic search information based on the multicycle search information;
multidimensional data analysis is carried out on the first periodic search information to obtain a first literature citation index, a first reading difficulty index and a first space paragraph index;
Traversing the first document citation index, the first reading difficulty index and the first space paragraph index, and setting a first weight, a second weight and a third weight;
according to the first weight, the second weight and the third weight, a first document citation index, the first reading difficulty index and the first spread paragraph index are fused, and a first information depth index is obtained;
performing information density analysis on the multicycle search information to obtain an information density index set, wherein the method further comprises:
extracting and obtaining first periodic search information based on the multicycle search information;
removing irrelevant information from the first periodic search information to obtain first pure information;
performing word frequency calculation on the first pure information to obtain a first keyword set, wherein the first keyword set comprises n keywords and n keyword frequencies;
generating a first information density according to the first keyword set and the first search period total word number;
generating a first information density according to the first keyword set and the first search period total word number, wherein the method further comprises:
the information density index is calculated by an information density calculation formula, and the specific formula is as follows:
Wherein, keywordfrequency is the frequency of keywords, total Words is the Total word number, keyword i As the i-th keyword, a keyword is selected,n is the number of related keywords;
and carrying the first keyword set and the first search period total word number into the information density calculation formula to obtain a first information density.
2. The method of claim 1, wherein the second science popularization information is subjected to virtual reality scene generation to obtain a target exhibition scene, and before the method further comprises:
presetting a scene generation information threshold;
judging whether the second science popularization information meets the scene generation information threshold value or not;
if the second science popularization information does not meet the scene generation information threshold, user interest analysis is carried out based on the historical passive recommendation information, and target interest characteristics are obtained;
analyzing the information association degree of the target interest feature and the second science popularization information to obtain an association information feature;
and optimizing the second science popularization information according to the associated information characteristics.
3. The method of claim 1, wherein the second science popularization information is subjected to virtual reality scene generation to obtain a target exhibition scene, the method further comprising:
Generating an information classification feature set according to the target science popularization requirement, wherein the information classification feature set comprises a plurality of information classification features;
performing second science popularization information classification based on the information classification features to obtain a plurality of virtual information clusters, wherein each virtual information cluster is provided with the information classification feature identification;
according to the similarity between the information classification features and the target science popularization demand information, carrying out relevance ranking on the virtual information clusters;
generating local virtual reality scenes of the plurality of virtual information clusters according to the sequencing result to obtain a plurality of local virtual reality scenes;
and constructing the target exhibition scene according to the plurality of local virtual reality scenes.
4. A system for data screening and immersive interaction for a digital display, the system performing the method of any of claims 1-3, the system comprising:
the information acquisition execution module is used for acquiring information of a first target user to obtain historical receiving information, wherein the historical receiving information comprises historical active search information and historical passive recommendation information;
the demand characteristic analysis module is used for carrying out user demand analysis based on the historical search information to obtain target demand characteristics;
The science popularization requirement generation module is used for obtaining the target science popularization requirement of the first target user;
the demand information acquisition module is used for acquiring information according to the target science popularization demand to obtain a first science popularization information set, wherein the first science popularization information set comprises a plurality of science popularization information clusters;
the information screening execution module is used for carrying out information screening on the first science popularization information set by taking the target demand characteristics as constraints to generate second science popularization information;
the virtual scene generation module is used for generating a virtual reality scene for the second science popularization information to obtain a target exhibition scene;
and the immersion interaction executing module is used for carrying out immersion interaction on the basis of the target exhibition scene by the first target user.
5. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 3 when the computer program is executed.
6. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310582456.2A CN116595256B (en) | 2023-05-22 | 2023-05-22 | Method and system for data screening and immersive interaction of digital exhibition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310582456.2A CN116595256B (en) | 2023-05-22 | 2023-05-22 | Method and system for data screening and immersive interaction of digital exhibition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116595256A CN116595256A (en) | 2023-08-15 |
| CN116595256B true CN116595256B (en) | 2023-11-03 |
Family
ID=87595235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310582456.2A Active CN116595256B (en) | 2023-05-22 | 2023-05-22 | Method and system for data screening and immersive interaction of digital exhibition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116595256B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892010B (en) * | 2024-03-14 | 2024-05-24 | 江西省博库信息技术有限公司 | Science popularization knowledge accurate pushing method and system based on big data |
| CN118363594B (en) * | 2024-05-06 | 2024-10-01 | 北京恒歌零一信息科技有限公司 | User interface design method and system based on immersive virtual reality |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280114A (en) * | 2017-07-28 | 2018-07-13 | 淮阴工学院 | A kind of user's literature reading interest analysis method based on deep learning |
| CN108334627A (en) * | 2018-02-12 | 2018-07-27 | 北京百度网讯科技有限公司 | Searching method, device and the computer equipment of new media content |
| WO2019153972A1 (en) * | 2018-02-11 | 2019-08-15 | Oppo广东移动通信有限公司 | Information pushing method and related product |
| WO2020133549A1 (en) * | 2018-12-29 | 2020-07-02 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligent systems and methods for semantic-based search |
| CN114064851A (en) * | 2021-10-19 | 2022-02-18 | 中国人民解放军31511部队 | Multi-machine retrieval method and system for government office documents |
| CN115618949A (en) * | 2022-09-20 | 2023-01-17 | 丁娟 | User interest analysis method and system based on immersive meta universe service |
| CN116108269A (en) * | 2022-12-30 | 2023-05-12 | 北京五八信息技术有限公司 | Search result display method and device, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140365386A1 (en) * | 2013-06-05 | 2014-12-11 | David W. Carstens | Intellectual Property (IP) Analytics System and Method |
| US10803055B2 (en) * | 2017-12-15 | 2020-10-13 | Accenture Global Solutions Limited | Cognitive searches based on deep-learning neural networks |
-
2023
- 2023-05-22 CN CN202310582456.2A patent/CN116595256B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280114A (en) * | 2017-07-28 | 2018-07-13 | 淮阴工学院 | A kind of user's literature reading interest analysis method based on deep learning |
| WO2019153972A1 (en) * | 2018-02-11 | 2019-08-15 | Oppo广东移动通信有限公司 | Information pushing method and related product |
| CN108334627A (en) * | 2018-02-12 | 2018-07-27 | 北京百度网讯科技有限公司 | Searching method, device and the computer equipment of new media content |
| WO2020133549A1 (en) * | 2018-12-29 | 2020-07-02 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligent systems and methods for semantic-based search |
| CN114064851A (en) * | 2021-10-19 | 2022-02-18 | 中国人民解放军31511部队 | Multi-machine retrieval method and system for government office documents |
| CN115618949A (en) * | 2022-09-20 | 2023-01-17 | 丁娟 | User interest analysis method and system based on immersive meta universe service |
| CN116108269A (en) * | 2022-12-30 | 2023-05-12 | 北京五八信息技术有限公司 | Search result display method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116595256A (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116595256B (en) | Method and system for data screening and immersive interaction of digital exhibition | |
| CN109299271B (en) | Training sample generation method, text data method, public opinion event classification method and related equipment | |
| US8805843B2 (en) | Information mining using domain specific conceptual structures | |
| US6751776B1 (en) | Method and apparatus for personalized multimedia summarization based upon user specified theme | |
| CN110390052B (en) | Search recommendation method, training method, device and equipment of CTR (China train redundancy report) estimation model | |
| CN109511015B (en) | Multimedia resource recommendation method, device, storage medium and equipment | |
| Lubis et al. | A framework of utilizing big data of social media to find out the habits of users using keyword | |
| CN110399505B (en) | Semantic tag generation method and device, and computer storage medium | |
| CN111177559A (en) | Text travel service recommendation method and device, electronic equipment and storage medium | |
| Trevisiol et al. | Retrieving geo-location of videos with a divide & conquer hierarchical multimodal approach | |
| US20090327877A1 (en) | System and method for disambiguating text labeling content objects | |
| JP7395377B2 (en) | Content search methods, devices, equipment, and storage media | |
| US8838616B2 (en) | Server device for creating list of general words to be excluded from search result | |
| CN116932906A (en) | Search term pushing method, device, equipment and storage medium | |
| CN117648504A (en) | Method, device, computer equipment and storage medium for generating media resource sequence | |
| Bai et al. | A WeChat official account reading quantity prediction model based on text and image feature extraction | |
| US20220292127A1 (en) | Information management system | |
| CN113204670B (en) | Attention model-based video abstract description generation method and device | |
| CN116450913A (en) | Retrieval method, retrieval device, server and computer readable storage medium | |
| CN112749313B (en) | Label labeling method, label labeling device, computer equipment and storage medium | |
| CN114722313A (en) | Search result sorting method, device, equipment and storage medium | |
| KR20230046041A (en) | Keyword based online advertisement matching system and online advertisement method | |
| CN113656641A (en) | Efficient video retrieval system supporting fuzzy comment mining | |
| CN111666522A (en) | Information processing method, device, equipment and storage medium | |
| CN117648444B (en) | Patent clustering method and system based on graph convolution attribute aggregation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |