CN110008326B - Knowledge abstract generation method and system in session system - Google Patents
Knowledge abstract generation method and system in session system Download PDFInfo
- Publication number
- CN110008326B CN110008326B CN201910255435.3A CN201910255435A CN110008326B CN 110008326 B CN110008326 B CN 110008326B CN 201910255435 A CN201910255435 A CN 201910255435A CN 110008326 B CN110008326 B CN 110008326B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- session
- conversation
- points
- knowledge point
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a knowledge abstract generating method and a knowledge abstract generating system in a session system, wherein the method comprises the following steps: pre-constructing a knowledge organization structure, wherein the knowledge organization structure comprises a theme map and a knowledge point map; recording a conversation theme and a plurality of conversation knowledge points related to a user in a conversation process; generating the knowledge summary based at least on the topic and the plurality of conversational knowledge points. According to the invention, the main body map and the knowledge point map are constructed in advance for generating the knowledge abstract, so that the generated abstract form is a structured text, and the generated abstract granularity is knowledge point level, thereby facilitating the use of a user and large-scale automatic analysis.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a knowledge abstract generating method and system in a session system.
Background
Most of the existing abstract generation methods in the prior art or products are based on a text abstract model, that is, user conversations are divided into a plurality of conversation groups, each conversation group comprises a plurality of sentences, and then a text abstract is automatically generated by using a topic model, topic clustering and neural network technologies or important sentences are extracted from texts by using an information extraction technology to be combined into an abstract. Therefore, the traditional technology utilizes a text summarization method, and the generated summarization form is an unstructured text and lacks structural information; the generated abstract granularity is at the chapter, paragraph or sentence level, not the knowledge point level, and is not beneficial to the use of users and large-scale automatic analysis.
Disclosure of Invention
The embodiment of the invention provides a knowledge summary generation method and a knowledge summary generation system in a session system, which are used for solving at least one of the technical problems.
In a first aspect, an embodiment of the present invention provides a method for generating a knowledge summary in a session system, including:
pre-constructing a knowledge organization structure, wherein the knowledge organization structure comprises a theme map and a knowledge point map;
recording a conversation theme and a plurality of conversation knowledge points related to a user in a conversation process;
generating the knowledge summary based at least on the topic and the plurality of conversational knowledge points.
In a second aspect, an embodiment of the present invention provides a knowledge summary generating system in a session system, including:
the map building program module is used for building a knowledge organization structure in advance, and the knowledge organization structure comprises a theme map and a knowledge point map;
the recording program module is used for recording a conversation theme and a plurality of conversation knowledge points related to a user in a conversation process;
a summary generation program module for generating the knowledge summary based at least on the topic and the plurality of session knowledge points.
In a third aspect, an embodiment of the present invention provides a storage medium, where one or more programs including execution instructions are stored, where the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to perform the knowledge summary generation method in any session system of the present invention.
In a fourth aspect, an electronic device is provided, comprising: the system comprises at least one processor and a memory which is connected with the at least one processor in a communication mode, wherein the memory stores instructions which can be executed by the at least one processor, and the instructions are executed by the at least one processor so as to enable the at least one processor to execute the knowledge summary generation method in any conversation system.
In a fifth aspect, an embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program stored on a storage medium, and the computer program includes program instructions, which, when executed by a computer, cause the computer to execute the knowledge summary generation method in any one of the above-mentioned conversation systems.
The embodiment of the invention has the beneficial effects that: according to the invention, the main body map and the knowledge point map are constructed in advance for generating the knowledge abstract, so that the generated abstract form is a structured text, and the generated abstract granularity is at a knowledge point level, thereby facilitating the use of a user and large-scale automatic analysis.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a flow diagram of one embodiment of a knowledge summary generation method in a conversational system of the present invention;
FIG. 2 is a flow chart of another embodiment of a knowledge summary generation method in a conversational system of the present invention;
FIG. 3 is a flow chart of yet another embodiment of a knowledge summary generation method in a conversational system of the present invention;
FIG. 4 is a schematic diagram of a knowledge point path in a session process according to an embodiment of the present invention;
FIG. 5 is a diagram of a knowledge summary visualization graphical form in an embodiment of the invention;
FIG. 6 is a schematic diagram of the organization of topics and knowledge points in an embodiment of the invention;
FIG. 7 is a schematic diagram of relationships between topics in a topic map in an embodiment of the present invention;
FIG. 8 is a schematic diagram of the relationship between nodes of a topic graph and nodes of a knowledge point graph in an embodiment of the invention;
FIG. 9 is a diagram illustrating relationships between knowledge points in a knowledge point map, in accordance with an embodiment of the present invention;
FIG. 10 is a functional block diagram of one embodiment of a knowledge summary generation system in a conversational system of the present invention;
FIG. 11 is a functional block diagram of another embodiment of a knowledge summary generation system in a conversation system in the present invention;
FIG. 12 is a functional block diagram of one embodiment of an extended program module of the present invention;
FIG. 13 is a functional block diagram of another embodiment of a knowledge summary generation system in a conversation system in the present invention;
fig. 14 is a schematic structural diagram of an embodiment of an electronic device according to the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
As used in this disclosure, "module," "device," "system," and the like are intended to refer to a computer-related entity, either hardware, a combination of hardware and software, or software in execution. In particular, for example, an element may be, but is not limited to being, a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. Also, an application or script running on a server, or a server, may be an element. One or more elements may be in a process and/or thread of execution and an element may be localized on one computer and/or distributed between two or more computers and may be operated by various computer-readable media. The elements may also communicate by way of local and/or remote processes in accordance with a signal having one or more data packets, e.g., signals from data interacting with another element in a local system, distributed system, and/or across a network of the internet with other systems by way of the signal.
Finally, it should be further noted that relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The patent hopes to construct a structured, knowledge point granular, extensible knowledge abstract method and device. Firstly, thematic organization and fine granularity are carried out on knowledge points in a session system, and the incidence relation and the incidence strength between themes and the knowledge points are established. And then based on the organization structure of the topics and the knowledge points in the session system, combining the knowledge points mentioned by the user in the session process and the related knowledge points, automatically constructing the knowledge abstract of the user, and visualizing the knowledge abstract, thereby completing more efficient knowledge summarization and arrangement, improving the knowledge obtaining efficiency of the user and improving the satisfaction degree of the user.
As shown in fig. 1, an embodiment of the present invention provides a knowledge summary generation method in a conversation system, including:
s11, pre-constructing a knowledge organization structure, wherein the knowledge organization structure comprises a theme map and a knowledge point map;
s12, recording a conversation theme and a plurality of conversation knowledge points related to the user in the conversation process;
s13, generating the knowledge abstract at least based on the conversation theme and the plurality of conversation knowledge points.
In the embodiment of the invention, the main body map and the knowledge point map are constructed in advance for generating the knowledge abstract, so that the generated abstract form is a structured text, and the generated abstract granularity is at a knowledge point level, thereby facilitating the use of a user and large-scale automatic analysis.
In some embodiments, the knowledge summary generation method in the session system of the present invention further includes: determining a plurality of expanded knowledge points according to the association strength between the knowledge points in the knowledge point map and the plurality of session knowledge points;
the generating the knowledge digest based on at least the conversation topic and the plurality of conversation knowledge points comprises: generating the knowledge digest based on the conversation topic, the plurality of conversation knowledge points, and the plurality of extended knowledge points.
As shown in fig. 2, in some embodiments, said determining a plurality of expanded knowledge points based on strength of association between a knowledge point in said knowledge point graph and said plurality of session knowledge points comprises:
s21, selecting the last n session knowledge points in the jump path formed by the session knowledge points;
s22, calculating the association strength between each knowledge point Ki (0< i < n) in the last n session knowledge points and a neighboring knowledge point set of Ki, where the neighboring knowledge point set takes knowledge points with a distance of 1 from Ki, and the similarity calculation formula is as follows:
Sim(Ki，Kj)＝e-λtS(Ki，Kj)D(Ki，Kj)，i≠j，j∈Set(Ki) (1)
in formula (1), set (Ki) represents a neighboring knowledge point set of a knowledge point Ki having a knowledge point path i, and Sim (Ki, Kj) is the correlation strength between Ki and Kj; e.g. of the type-λtThe time attenuation factor is t-n-i, the last knowledge point i-n on the path, and t-n-i-0; s (Ki, Kj) is the static correlation strength of Ki and Kj, and D (Ki, Kj) is the dynamic correlation strength of Ki and Kj;
and S23, taking the first k knowledge points with high correlation strength as the plurality of expanded knowledge points.
The patent and the prior art have four main differences:
firstly, the method comprises the following steps: the form of the knowledge abstract is structured;
secondly, the method comprises the following steps: the granularity of the knowledge abstract is at the knowledge point level;
thirdly, the method comprises the following steps: the knowledge abstract not only comprises knowledge points in the conversation, but also performs necessary extension and expansion according to the knowledge points;
fourthly: the knowledge abstracts allow for visualization of a hierarchy of topics and knowledge points.
Fig. 3 is a flowchart of another embodiment of a knowledge summary generation method in a session system according to the present invention, which includes the following steps:
step 1, organizing structures and dynamically updating the topics and the knowledge points. The knowledge organization structure in the session system comprises a theme map and a knowledge point map, wherein the nodes of the theme map are themes, and the relationships comprise parent-child relationships, brother relationships and the like; the nodes of the knowledge point graph include, without limitation, triplets or question-answer pairs, as well as other forms of knowledge points, such as < question, action step >, etc. The knowledge organization structure includes relationships and relationship strengths.
And 2, generating an initial knowledge abstract. During the interaction process between the user and the session system, the topics and knowledge points involved in the user session are marked in the topic map and the knowledge point map. After a session is over, the marked knowledge points are used as initial knowledge abstracts.
Illustratively, the paths of the knowledge points mentioned in the conversation process in the topic map and the knowledge point map are initial knowledge abstracts. As shown in fig. 4, the user starts to chat with knowledge point < S1, P1, O1> during the session, then jumps to < Q1, a1>, and finally jumps to < S2, P2, O2 >. Then the initial knowledge digest is [ < S1, P1, O1>, < Q1, a1>, < S2, P2, O2> ].
And 3, expanding the knowledge abstract based on the relevance of the theme and the knowledge points. And performing necessary expansion on the initial knowledge abstract according to the incidence relation between the theme and the knowledge points.
Illustratively, matching of the topic graph and the knowledge point graph simultaneously considers the static association strength, the dynamic association strength and the path position of the knowledge point during the conversation. The last n knowledge points of the path of the knowledge points in the session are selected, wherein n is a hyper-parameter and can be set. For example, if the user has 10 knowledge points involved from the beginning to the end of the session, then n may be 3. Calculating the association strength of each known point Ki (0< i < n) and a neighboring knowledge point set of Ki, wherein the neighboring knowledge point set can take the knowledge point with the distance of 1 from Ki, and the similarity calculation formula is as follows:
Sim(Ki，Kj)＝e-λtS(Ki，Kj)D(Ki，Kj)，i≠j，j∈Set(Ki) (1)
set (Ki) in equation (1) represents a neighbor knowledge point set of a knowledge point Ki having a knowledge point path i, and Sim (Ki, Kj) is the correlation strength between Ki and Kj.
e-λtThe last knowledge point i-n and t-n-i-0 on the path is the time attenuation factor.
S (Ki, Kj) is the static correlation strength of Ki and Kj, and D (Ki, Kj) is the dynamic correlation strength of Ki and Kj.
And taking the first k knowledge points with high correlation strength as abstract extension of the knowledge points, wherein k is also a hyper-parameter and can be preset.
And 4, visualization of the knowledge abstract, namely visualization of the knowledge abstract constructed in the step 3.
In some embodiments, the knowledge summary generation method in the session system of the present invention further includes: and visually displaying the knowledge abstract, wherein the visual display comprises a table form (shown in the following table 1) and/or a graph form (shown in fig. 5).
Table 1 table visualization example
Steps 1-4 in the above examples are further illustrated below, respectively:
for step 1, as shown in fig. 6, it is a schematic diagram of an organization structure of topics and knowledge points in the embodiment of the present invention. The method comprises a theme graph and a knowledge point graph, and is introduced from two aspects of nodes and relations as follows:
node definition:
the nodes of the theme map represent themes, and the relationships comprise parent-child relationships and brother relationships; nodes of the knowledge-point graph spectrum include, but are not limited to, knowledge triples (open nodes) or question-and-answer pairs (solid nodes) or other forms of knowledge points.
The triplets have 2 forms < entity, relationship, entity >, < entity, attribute value >; < entity, relationship, entity > is as < China, capital, Beijing >, wherein "China" and "Beijing" represent the entity respectively, and "capital" represents the relationship. < entity, attribute value > such as < china, coastline length, 1.8 ten thousand meters > where "china" represents an entity, "coastline length" represents an attribute, and "1.8 ten thousand meters" represents an attribute value.
The question-answer pair is in the form of < Q, a >, Q represents a question, a represents an answer, e.g. <' please simply introduce the next chinese? "," the people's republic of China is located in the east Asia, the Pacific coast ">.
Relationship definition:
as shown in fig. 7, which is a schematic diagram of the relationship between topics in the topic map of the present invention, for example, for the topic "artificial intelligence", it includes the sub-topic "deep learning technique".
Fig. 8 is a schematic diagram showing the relationship between the nodes of the topic graph and the nodes of the knowledge point graph in the present invention. Illustratively, the nodes of the topic graph and the nodes of the knowledge point graph have containment relationships that represent which knowledge points a topic includes. For example, the node "geography" in the theme spectrum contains the knowledge point < china, capital, beijing > in the knowledge point map.
Fig. 9 is a schematic diagram showing the relationship between knowledge points in the knowledge point map of the present invention. Illustratively, the association relationship between the triplets and the question-answer pairs, for example, if the triplets include an entity "china", and the question-answer pairs also include an entity "china", then the triplets and the question-answer pairs establish an equivalent association relationship between the entities. Other types of entity relationships are included in addition to equivalence association relationships. The construction method comprises the following steps: and performing entity link on the entities in the question-answer pairs and the triplets to find equivalent association, and constructing the relationship between the entities in the triplets and the entities in the question-answer pairs according to the entity relationship among the triplets.
Association between triplets: the association of entities in triples.
There is also a relationship between question and answer pairs: and (4) association relation of entities in the question-answer pairs.
Relationship strengths are divided into static relationship strengths (as shown in table 2 below) and dynamic relationship strengths (as shown in table 3 below). Dynamic relationship strength refers to adjusting relationship strength depending on the session process. The static relation strength represents the correlation strength of knowledge in the objective world and does not change along with the conversation process.
TABLE 2 static correlation Strength
TABLE 3 dynamic Association Strength
Illustratively, the dynamic association strength will be dynamically updated with the session process, and when jumping from knowledge point a to B, the dynamic association strength from a to B increases; and simultaneously, correspondingly adjusting the theme relationship corresponding to the A and the B. The scene that A jumps to B comprises the step that the user asks the knowledge point B after asking the knowledge point A. After the user asks the knowledge point A, the session system recommends to ask the knowledge point B again, and the knowledge point B is selected by the user.
It should be noted that for simplicity of explanation, the foregoing method embodiments are described as a series of acts or combination of acts, but those skilled in the art will appreciate that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention. In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
As shown in fig. 10, an embodiment of the present invention further provides a knowledge summary generating system 100 in a conversation system, including:
the map building program module 110 is used for building a knowledge organization structure in advance, wherein the knowledge organization structure comprises a theme map and a knowledge point map;
a recording program module 120, configured to record a session topic and a plurality of session knowledge points that are involved in a session process of a user;
a summary generator module 130 configured to generate the knowledge summary based at least on the topic and the plurality of session knowledge points.
According to the invention, the main body map and the knowledge point map are constructed in advance for generating the knowledge abstract, so that the generated abstract form is a structured text, and the generated abstract granularity is knowledge point level, thereby facilitating the use of users and large-scale automatic analysis.
As shown in fig. 11, in some embodiments, the knowledge summary generation system 100 in the conversation system further includes: an extended program module 140 for determining a plurality of extended knowledge points according to the strength of association between knowledge points in the knowledge point graph and the plurality of session knowledge points; the generating the knowledge-summary based at least on the conversation topic and the plurality of conversation knowledge points comprises: generating the knowledge summary based on the session topic, the plurality of session knowledge points, and the plurality of extended knowledge points.
As shown in FIG. 12, in some embodiments, the extension program module 140 includes:
a knowledge point selection program unit 141, configured to select the last n session knowledge points in a jump path formed by the session knowledge points;
a calculating program unit 142, configured to calculate an association strength between each knowledge point Ki (0< i < n) in the last n session knowledge points and a neighboring knowledge point set of Ki, where the neighboring knowledge point set takes a knowledge point with a distance of 1 from Ki, and a similarity calculation formula is as follows:
Sim(Ki，Kj)＝e-λtS(Ki，Kj)D(Ki，Kj)，i≠j，j∈Set(Ki) (1)
wherein set (Ki) represents a neighboring knowledge point set of knowledge points Ki with knowledge point path i, Sim (Ki, Kj) is the correlation strength of Ki and Kj; e.g. of the type-λtThe time attenuation factor is t-n-i, the last knowledge point i-n on the path, and t-n-i-0; s (Ki, Kj) is the static correlation strength of Ki and Kj, and D (Ki, Kj) is the dynamic correlation strength of Ki and Kj;
an extension program unit 143 configured to take the first k knowledge points with high correlation strength as the plurality of extended knowledge points.
As shown in fig. 13, in some embodiments, the knowledge summary generation system 100 in the conversation system further includes: and a visualization program module 150, configured to visually display the knowledge abstract, where the visual display includes a tabular form and/or a graphical form.
In some embodiments, the present invention provides a non-transitory computer readable storage medium, in which one or more programs including executable instructions are stored, where the executable instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to perform the knowledge summary generation method in any session system of the present invention.
In some embodiments, the present invention further provides a computer program product comprising a computer program stored on a non-volatile computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform any one of the above-mentioned methods for knowledge summary generation in a conversational system.
In some embodiments, an embodiment of the present invention further provides an electronic device, which includes: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a knowledge digest generation method in a conversational system.
In some embodiments, the present invention further provides a storage medium on which a computer program is stored, wherein the program is characterized in that the program is executed by a processor to perform a knowledge summary generation method in a conversational system.
The knowledge summary generation system in the session system according to the embodiment of the present invention may be configured to execute the knowledge summary generation method in the session system according to the embodiment of the present invention, and accordingly achieve the technical effect achieved by the knowledge summary generation method in the session system according to the embodiment of the present invention, which is not described herein again. In the embodiment of the present invention, the relevant functional module may be implemented by a hardware processor (hardware processor).
Fig. 14 is a schematic hardware configuration diagram of an electronic device for performing a knowledge summary generation method in a conversation system according to another embodiment of the present application, where, as shown in fig. 14, the device includes:
one or more processors 1410 and memory 1420, with one processor 1410 being illustrated in FIG. 14.
The apparatus for performing the knowledge digest generation method in the conversational system may further include: an input device 1430 and an output device 1440.
The processor 1410, memory 1420, input 1430, and output 1440 may be connected by a bus or otherwise, as illustrated in fig. 14 by a bus.
The memory 1420, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the knowledge summary generation method in the session system in the embodiment of the present application. The processor 1410 executes various functional applications of the server and data processing by running nonvolatile software programs, instructions, and modules stored in the memory 1420, that is, implements the knowledge digest generation method in the conversation system of the above-described method embodiments.
The memory 1420 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the knowledge digest generation apparatus in the conversation system, and the like. Further, memory 1420 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 non-volatile solid-state storage device. In some embodiments, memory 1420 optionally includes memory located remotely from processor 1410, which may be connected to knowledge summary generation apparatus in the conversational system via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 1430 may receive input numeric or character information and generate signals related to user settings and function control of the knowledge digest generation apparatus in the conversation system. The output device 1440 may include a display device such as a display screen.
The one or more modules are stored in the memory 1420 and, when executed by the one or more processors 1410, perform a knowledge summary generation method in a conversational system in any of the method embodiments described above.
The product can execute the method provided by the embodiment of the application, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include PDA, MID, and UMPC devices, such as ipads.
(3) Portable entertainment devices such devices may display and play multimedia content. Such devices include audio and video players (e.g., ipods), handheld game consoles, electronic books, as well as smart toys and portable car navigation devices.
(4) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.
(5) And other electronic devices with data interaction functions.
The above-described embodiments of the apparatus are merely illustrative, and 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a general hardware platform, and may also be implemented by hardware. Based on such understanding, the technical solutions mentioned above may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute the method according to the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit 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 (6)
1. A knowledge abstract generation method in a session system comprises the following steps:
pre-constructing a knowledge organization structure, wherein the knowledge organization structure comprises a theme map and a knowledge point map;
recording a conversation theme and a plurality of conversation knowledge points related to a user in a conversation process;
generating the knowledge summary based on the conversation topic, the plurality of conversation knowledge points, and the plurality of extended knowledge points;
selecting the last n session knowledge points in a jump path formed by the plurality of session knowledge points;
calculating the association strength of each knowledge point Ki (0< i ≦ n) in the last n session knowledge points and a neighboring knowledge point set of Ki, wherein the neighboring knowledge point set takes knowledge points with the distance of 1 from the Ki, and the association strength calculation formula is as follows:
Sim(Ki，Kj)＝e-λt(Ki，Kj)D(Ki，Kj)，i≠j，j∈Set(Ki) (1)
in formula (1), set (Ki) represents a neighboring knowledge point set of a knowledge point Ki having a knowledge point path i, and Sim (Ki, Kj) is the correlation strength between Ki and Kj;
e-λtthe time attenuation factor is t-n-i, the last knowledge point i-n on the path, and t-n-i-0;
s (Ki, Kj) is the static correlation strength of Ki and Kj, and D (Ki, Kj) is the dynamic correlation strength of Ki and Kj; the dynamic association strength is dynamically updated along with the session process, and the static association strength represents the association strength of knowledge in the objective world and does not change along with the session process;
and taking the first k knowledge points with high correlation strength as the plurality of expanded knowledge points.
2. The method of claim 1, further comprising: and visually displaying the knowledge abstract, wherein the visual display comprises a tabular form and/or a graphical form.
3. A knowledge summary generation system in a conversational system, comprising:
the map building program module is used for building a knowledge organization structure in advance, and the knowledge organization structure comprises a theme map and a knowledge point map;
the recording program module is used for recording a conversation theme and a plurality of conversation knowledge points related to a user in a conversation process;
a summary generation program module for generating the knowledge summary based on the conversation topic, the plurality of conversation knowledge points and the plurality of extended knowledge points;
an extended program module comprising:
a knowledge point selection program unit, configured to select the last n session knowledge points in a skip path formed by the session knowledge points;
a calculating program unit, configured to calculate an association strength between each knowledge point Ki (0< i ≦ n) in the last n session knowledge points and a neighboring knowledge point set of Ki, where the neighboring knowledge point set takes a knowledge point whose distance from Ki is 1, and the association strength calculation formula is as follows:
Sim(Ki，Kj)＝e-λtS(Ki，Kj)D(Ki，Kj)，i≠j，j∈Set(Ki) (1)
wherein set (Ki) represents a neighboring knowledge point set of knowledge points Ki with knowledge point path i, Sim (Ki, Kj) is the correlation strength of Ki and Kj; e.g. of the type-λtThe time attenuation factor is t-n-i, the last knowledge point i-n on the path, and t-n-i-0; s (Ki, Kj) is the static correlation strength of Ki and Kj, and D (Ki, Kj) is the dynamic correlation strength of Ki and Kj; the dynamic association strength is dynamically updated along with the session process, and the static association strength represents the association strength of knowledge in the objective world and does not change along with the session process;
and the extension program unit is used for taking the first k knowledge points with high association strength as the plurality of extension knowledge points.
4. The system of claim 3, further comprising:
and the visualization program module is used for visually displaying the knowledge abstract, and the visual display comprises a tabular form and/or a graphic form.
5. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any of claims 1-2.
6. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910255435.3A CN110008326B (en) | 2019-04-01 | 2019-04-01 | Knowledge abstract generation method and system in session system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910255435.3A CN110008326B (en) | 2019-04-01 | 2019-04-01 | Knowledge abstract generation method and system in session system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110008326A CN110008326A (en) | 2019-07-12 |
| CN110008326B true CN110008326B (en) | 2020-11-03 |
Family
ID=67169157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910255435.3A Active CN110008326B (en) | 2019-04-01 | 2019-04-01 | Knowledge abstract generation method and system in session system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110008326B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113051405B (en) * | 2019-04-30 | 2024-06-11 | 五竹科技(北京)有限公司 | Intelligent outbound knowledge graph construction method and device based on dialogue scene |
| CN110928992B (en) * | 2019-11-21 | 2022-06-10 | 邝俊伟 | Text searching method, device, server and storage medium |
| CN112988988A (en) * | 2019-12-18 | 2021-06-18 | 华为技术有限公司 | Question answering method, device and equipment |
| CN111159382B (en) * | 2019-12-27 | 2022-07-12 | 思必驰科技股份有限公司 | Method and device for constructing and using session system knowledge model |
| CN112597285B (en) * | 2020-12-10 | 2021-08-10 | 太极计算机股份有限公司 | Man-machine interaction method and system based on knowledge graph |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447346A (en) * | 2016-08-29 | 2017-02-22 | 北京中电普华信息技术有限公司 | Method and system for construction of intelligent electric power customer service system |
| CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
| CN109284363A (en) * | 2018-12-03 | 2019-01-29 | 北京羽扇智信息科技有限公司 | A kind of answering method, device, electronic equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919674A (en) * | 2017-02-20 | 2017-07-04 | 广东省中医院 | A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks |
| CN107870994A (en) * | 2017-10-31 | 2018-04-03 | 北京光年无限科技有限公司 | Man-machine interaction method and system for intelligent robot |
| CN107845422A (en) * | 2017-11-23 | 2018-03-27 | 郑州大学第附属医院 | A kind of remote medical consultation with specialists session understanding and method of abstracting based on the fusion of multi-modal clue |
| CN108763494B (en) * | 2018-05-30 | 2020-02-21 | 苏州思必驰信息科技有限公司 | Knowledge sharing method between conversation systems, conversation method and device |
| CN108874915A (en) * | 2018-05-30 | 2018-11-23 | 苏州思必驰信息科技有限公司 | Method of Knowledge Organization, system, electronic equipment and storage medium |
-
2019
- 2019-04-01 CN CN201910255435.3A patent/CN110008326B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447346A (en) * | 2016-08-29 | 2017-02-22 | 北京中电普华信息技术有限公司 | Method and system for construction of intelligent electric power customer service system |
| CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
| CN109284363A (en) * | 2018-12-03 | 2019-01-29 | 北京羽扇智信息科技有限公司 | A kind of answering method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110008326A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008326B (en) | Knowledge abstract generation method and system in session system | |
| Wu et al. | Automatic alt-text: Computer-generated image descriptions for blind users on a social network service | |
| CN108763494B (en) | Knowledge sharing method between conversation systems, conversation method and device | |
| Georgiev et al. | Enhancing user creativity: Semantic measures for idea generation | |
| CN109389870B (en) | Data self-adaptive adjusting method and device applied to electronic teaching | |
| CN109119067B (en) | Speech synthesis method and device | |
| CN111159382B (en) | Method and device for constructing and using session system knowledge model | |
| CN110569364A (en) | online teaching method, device, server and storage medium | |
| CN108846030B (en) | method, system, electronic device and storage medium for visiting official website | |
| CN111813889B (en) | Question information ordering method and device, medium and electronic equipment | |
| CN109154948B (en) | Method and apparatus for providing content | |
| CN109948151A (en) | The method for constructing voice assistant | |
| US10318094B2 (en) | Assistive technology (AT) responsive to cognitive states | |
| WO2019228231A1 (en) | Knowledge organization method and apparatus, and electronic device and storage medium | |
| CN110727782A (en) | Question and answer corpus generation method and system | |
| CN112698895A (en) | Display method, device, equipment and medium of electronic equipment | |
| CN112115703B (en) | Article evaluation method and device | |
| US10559298B2 (en) | Discussion model generation system and method | |
| CN110750633B (en) | Method and device for determining answer of question | |
| CN115510203A (en) | Question answer determining method, device, equipment, storage medium and program product | |
| CN114745594A (en) | Method and device for generating live playback video, electronic equipment and storage medium | |
| CN110688464B (en) | Man-machine conversation method and system | |
| CN113680071A (en) | Electronic medal generation method, device, equipment and storage medium | |
| CN113407763A (en) | Hot music mining method, electronic device and computer-readable storage medium | |
| CN106407225A (en) | Pinyin display method and device |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee after: Sipic Technology Co.,Ltd. Address before: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee before: AI SPEECH Ltd. |