CN110580342A - public number question-answer response method and device - Google Patents

public number question-answer response method and device Download PDF

Info

Publication number
CN110580342A
CN110580342A CN201910888915.3A CN201910888915A CN110580342A CN 110580342 A CN110580342 A CN 110580342A CN 201910888915 A CN201910888915 A CN 201910888915A CN 110580342 A CN110580342 A CN 110580342A
Authority
CN
China
Prior art keywords
user
question
public number
article
content
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.)
Pending
Application number
CN201910888915.3A
Other languages
Chinese (zh)
Inventor
许春雯
许建伟
初敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
AI Speech Ltd
Original Assignee
AI Speech Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by AI Speech Ltd filed Critical AI Speech Ltd
Priority to CN201910888915.3A priority Critical patent/CN110580342A/en
Publication of CN110580342A publication Critical patent/CN110580342A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/31Indexing; Data structures therefor; Storage structures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/335Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/338Presentation of query results

Abstract

The invention discloses a method and a device for responding to public number questions and answers, wherein the method for responding to the public number questions and answers is used for a server side and comprises the following steps: automatically synchronizing and updating published article materials of the public number aiming at the public number associated with the server side; identifying the content of the published article materials by utilizing an automatic reading understanding technology; and establishing a material library and an index file at least based on the identified content, wherein the material library comprises the article materials published by the public number, and the index file is an index corresponding to the article materials. Therefore, the scheme of the application can establish a corresponding material library and an index file for the published articles of the public number, so that the articles of the public number can be found more easily, and the exposure rate is improved.

Description

public number question-answer response method and device
Technical Field
the invention belongs to the technical field of voice recognition, and particularly relates to a public number question-answer response method and device.
Background
in the related art, in some schemes, in some wechat public account dialogue services provided by an artificial intelligence dialogue service platform, the content of a public account article can be independently learned and used as a dialogue material. In other schemes, a public operator can configure search functions such as search in a number, and provide a search tool for article contents.
In the scheme of the autonomous learning, when a question is received, the technology can search the content which can be used for answering from the content of the article and extract the content of the article for answering the question. And the user can manually control whether to participate in question answering or not in the management platform by using the article as an alternative answer.
The scheme of searching in numbers is mainly to search for matched contents in a special search page in a keyword retrieval mode. The search-in-number scheme is an application mode of a traditional search engine tool in the vertical field.
The inventor finds that the prior scheme has at least the following defects in the process of implementing the application:
The defects of the autonomous learning scheme are as follows:
1. most of the self-help learning modes only support clear contents in partial fields, such as brief introduction of a certain object, scenic spot operation time and the like, and the contents are clear and definite in structure. This puts high demands on the content of the article itself, and the supported questionable content is also limited by the model training progress.
2. when the conversation relates to article contents, only a part of the article contents are selected to be pushed out as an answer, and the whole article is not recommended. On the one hand, incomplete answers, or lack of contextual information, may result in excerpts; on the other hand, the number of the articles exposed and read is also reduced, which causes traffic loss for the operator.
3. Whether the articles are used as a question and answer material library or not needs to be manually regulated in the platform, although the degree of freedom of operation is improved, the operation cost is increased for the public numbers with a large number of articles and guaranteed article quality or needing to increase or delete the articles frequently.
Defects of search-in-number scheme:
1. the method is suitable for inquiring in a search interface, and users need to have the consciousness of active search and cannot support the direct realization of similar functions in a conversation interface.
2. the keyword search has high requirements on the information literacy of users, and the required content can be found quickly only by mastering a certain keyword extraction skill.
Disclosure of Invention
the embodiment of the invention provides a public number question-answer response method and a public number question-answer response device, which are used for solving at least one technical problem.
in a first aspect, an embodiment of the present invention provides a public account question-answer response method, used in a server, including: automatically synchronizing and updating published article materials of the public number aiming at the public number associated with the server side; identifying the content of the published article materials by utilizing an automatic reading understanding technology; and establishing a material library and an index file at least based on the identified content, wherein the material library comprises the article materials published by the public number, and the index file is an index corresponding to the article materials.
In a second aspect, an embodiment of the present invention provides a public account question-answering response apparatus, which is used for a user terminal, and includes: in response to receiving a question of a user, semantically understanding the question to extract an intent of the question; based on the intention of the question, searching an index file related to the intention from a material library established according to claim 1 to form a candidate set, wherein the candidate set comprises at least one candidate result; ranking the at least one candidate result based on preset indexes, wherein the preset indexes comprise material evaluation indexes and user attribute indexes; and sending at least one candidate result ranked in the front to the user as a recommendation.
in a third aspect, an embodiment of the present invention provides a public account question-answering response apparatus, used for a server, including: the synchronous updating module is configured to automatically synchronize and update the published article materials of the public numbers aiming at the public numbers associated with the server side; an understanding identification module configured to identify the content of the published article material using automated reading understanding techniques; and the index establishing module is configured to establish a material library and an index file at least based on the identified content, wherein the material library comprises the article materials published by the public number, and the index file is an index corresponding to the article materials.
In a fourth aspect, an embodiment of the present invention provides a public account question-answering response apparatus, which is used for a user terminal, and includes: an understanding processing module configured to, in response to receiving a question of a user, semantically understand-process the question to extract an intent of the question; a candidate set forming module configured to search an index file related to the intention from the material library established according to claim 1 based on the intention of the question to form a candidate set, wherein the candidate set comprises at least one candidate result; the sorting module is configured to sort the at least one candidate result based on preset indexes, wherein the preset indexes comprise material evaluation indexes and user attribute indexes; and the pushing module is configured to send at least one candidate result ranked in the front to the user as a recommendation result.
in a fifth aspect, an electronic device is provided, 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 public answer and question response method of any of the embodiments of the present invention.
In a sixth aspect, the present invention further provides a computer program product, where the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is caused to execute the steps of the public answering to questions response method according to any embodiment of the present invention.
According to the scheme provided by the method and the device, the contents of the article materials are identified by automatically reading and understanding the article materials published by the public at the server side, so that a corresponding material library and an index file of the article materials in the material library are established. Therefore, a corresponding material library and an index file are established for the published articles of the public number, so that the articles of the public number can be found more easily, and the exposure rate is improved. And then, semantically understanding the question of the user at the user terminal to extract the intention and/or keywords of the user question, further finding a candidate set with higher association degree from a material library of the server terminal according to the intention, then sequencing at least one candidate result in the candidate set according to the attribute of the article and the attribute information of the user, and recommending the result ranked in the front to the user, so that the result recommended to the user is more in line with the expectation of the user, the recommendation is more accurate, and the user experience is better.
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 flowchart of a response method for a public account question answering according to an embodiment of the present invention;
Fig. 2 is a flowchart of another public address question-answer response method according to an embodiment of the present invention;
Fig. 3 is a flowchart of an embodiment of a response scheme for a public answering questions and answers according to an embodiment of the present invention;
fig. 4 is a block diagram of a public address question answering apparatus according to an embodiment of the present invention;
Fig. 5 is a block diagram of another public address question answering device according to an embodiment of the present invention;
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present 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.
referring to fig. 1, a flowchart of an embodiment of the public number question answering response method according to the present application is shown, and the public number question answering response method according to the present embodiment may be applied to a server corresponding to a terminal with voice recognition and understanding capabilities, such as an intelligent voice television, an intelligent sound box, an intelligent dialogue toy, and other existing servers with semantic recognition and understanding capabilities.
as shown in fig. 1, in step 101, automatically synchronizing and updating published article materials of the public number for the public number associated with the server side;
In step 102, identifying the content of published article materials by using an automatic reading and understanding technology;
In step 103, a material library and an index file are established at least based on the identified content, wherein the material library comprises the article materials published by the public number, and the index file is an index corresponding to the article materials.
In this embodiment, for step 101, the public number may be bound to the server side corresponding to the corresponding device through the operation of the user at the user terminal, so that the server side may have a right to collect article materials published by the public number, and the server side may monitor the public number in real time, so that the article materials are updated to the server side in time after being published by the public number, and the content of the public number may also be updated synchronously at regular time, for example, once a day or twice a day, which is not limited again in this application.
For step 102, after the server collects the article materials of the public number, the server may separately identify the content of the updated article materials by using an automatic reading and understanding technology, and update the material library and the index file only according to the updated article materials. Certainly, the server side may also perform content identification on recent articles in a unified manner according to updated article materials, and rearrange the index files, where the method may be directed to the case where there are fewer public numbers and fewer contents, and if there are more article materials, the load of identifying the server side according to the above method is small, which is not described herein again, and the present application is not limited herein.
For step 103, the server establishes a material library and an index file at least based on the identified content, wherein the material library comprises the article materials listed by the public number, the index file is an index corresponding to the article materials, and the article materials related to the material library can be quickly located by searching the index file, so that the time for searching is reduced, and the response speed is increased. The index file can include, for example, article titles, subtitles in the articles, and association relations between keywords and the articles, and a user can associate the index file with corresponding content by searching for the corresponding content, and can quickly find the corresponding articles through the index file.
the method of the embodiment identifies the content of the article material by automatically reading and understanding the article material published by the public at the server side, thereby establishing a corresponding material library and an index file of the article material in the material library. Therefore, a corresponding material library and an index file are established for the published articles of the public number, so that the articles of the public number can be found more easily, and the exposure rate is improved.
In some optional embodiments, the step 103 further includes: establishing a material library based on published article materials of the public number, and automatically synchronizing and updating the material library based on the operations of adding, modifying and deleting the article materials of the public number; and generating a corresponding index file based on the identified content and the structured information of the published article material. Therefore, when the material is subjected to operations such as addition, modification and deletion, the material can be synchronized and updated in time, and invalid content can be deleted in time. Furthermore, data synchronization can be performed at regular time every day to ensure that newly added and changed contents can be timely recorded by the system and the timeliness is ensured; at the same time, the deleted material can be cleared from the library so that invalid content is not pushed out. The structured information of the article materials may include titles of the articles, abstracts of the articles, search information or keywords, and the like.
referring to fig. 2, which shows a flowchart of another embodiment of the public number question-answering response method of the present application, the public number question-answering response method of the present embodiment may be applied to a user terminal with voice recognition and understanding capabilities, such as an intelligent voice television, an intelligent sound box, an intelligent dialogue toy, and other existing user terminals with semantic recognition and understanding capabilities.
In step 201, in response to receiving a question of a user, performing semantic understanding processing on the question to extract an intention of the question;
In step 202, based on the intention of the question, searching an index file related to the intention from the material library established according to the previous embodiment to form a candidate set, wherein the candidate set comprises at least one candidate result;
In step 203, sorting at least one candidate result based on a preset index;
In step 204, at least one candidate ranked in the front is sent to the user as a recommendation.
in this embodiment, for step 201, in response to receiving a question of a user, the user terminal performs semantic understanding processing on the user question to extract an intention or keyword information of the question, so that subsequent processing can be performed according to the intention or keyword information, where the intention or keyword may be, for example, the latest discount information of a certain clothing brand, the latest policy of a country for a certain region, and the like. Then, for step 202, the user terminal sends a corresponding search request to the server terminal based on the intention of the question, and then the server terminal searches the index file based on the search request, and then finds the associated article materials, forms a candidate set, and feeds the candidate set back to the user terminal, where the candidate set is a set of at least one candidate result.
Then, for step 203, the user terminal performs priority ranking on at least one candidate result in the candidate set according to preset indexes, where the preset indexes include material evaluation indexes and user attribute indexes, the material evaluation indexes may be indexes used for evaluating relevance and real-time performance of materials, and the user attribute indexes may be interests and history records of the user, which is not limited herein. It should be noted that, this step does not necessarily need to be completed at the user terminal, and may also be completed at the server side, and the application is not limited herein.
Finally, for step 204, the user terminal sends at least one candidate result ranked in the front to the user as a recommendation result according to the ranking result. For example, a candidate result ranked first may be recommended directly to the user, or several candidate results may be recommended to the user, which is not limited herein.
According to the method, the intention and/or keywords of the user question are/is extracted by semantically understanding the user question, a candidate set with high relevance is found from a material library of a server side according to the intention, at least one candidate result in the candidate set is ranked according to the attribute of the article and the attribute information of the user, and the result ranked in the candidate set is recommended to the user, so that the result recommended to the user is more in line with the expectation of the user, the recommendation is more accurate, and the user experience is better.
In some optional embodiments, the method further comprises: receiving real-time feedback of a user on a recommendation result; judging whether the recommendation result is the content which is interested by the user or not based on the feedback; and if the recommendation result is the content which is interested by the user, continuously recommending at least one candidate result which is ranked in the front in the rest candidate results to the user. For example, whether the user is interested in the recommendation result can be judged according to whether the user clicks on the recommendation result, whether the recommendation result is read and the duration of reading the recommendation result, and the application is not limited in this respect. On the other hand, if the user is not interested in the recommendation result, the user attribute index may be updated, for example, the weight value of the content may be reduced, and the user may also be asked about which information the user wants to know, so as to further collect more keywords, and further redetermine the content to be recommended to the user according to the new keywords and the new user attribute, which is not limited herein. The method of the embodiment can further recommend more interesting contents to the user, improve the user experience, and well improve the exposure of the articles in the public account.
In some optional embodiments, the material evaluation indicators include a degree of relevance of the article material to the intent, an article material publication time, an article material popularity, and an article material goodness. Therefore, the articles with higher recent popularity and more in line with the intention of the user can be recommended for the user.
In further alternative embodiments, the user attribute metrics include historical behavior of the user, whether the user read the candidate results, and the user's content interest preferences. Further, after the user clicks and/or reads the recommendation result, the user attribute index is updated, so that the subsequent recommendation result can be more accurate.
the following description is provided to enable those skilled in the art to better understand the present disclosure by describing some of the problems encountered by the inventors in implementing the present disclosure and by describing one particular embodiment of the finally identified solution.
the inventor finds in the process of implementing the present application that the defects of the prior art are mainly caused by the following:
The content processing mode is self-learning, and the contents meeting the standard and meeting the question and answer condition are extracted by depending on the learning model to be used as the question and answer material, so that the supportable contents are necessarily limited by the model. The answer reasoning mode and material authority control may be related to the product design concept.
the search-in-number product is limited by the product form and has a general capability of supporting natural language.
The scheme of the application provides a public number question-answering response device.
The scheme integrates the use experience of an AI intelligent conversation user and the personal appeal of a public number operator, combines the intelligent conversation with the article popularization, and is the integration of the AI technology and the operation appeal. The proposal of the solution requires related practitioners to have corresponding intelligent technology and operational thinking at the same time.
full-text content is processed through article content reading understanding technology. When a question request is received, the optimal solution is matched from all processing results, and the article to which the part of content belongs is pushed out as a final answer. Therefore, the problem that the content is not answered comprehensively can be solved, and the problem that part of the content cannot respond accurately due to model limitation is reduced. Meanwhile, repeated exposure of historical articles of public operators is facilitated, and efficiency is improved.
Further referring to fig. 3, it shows an automatic reading understanding of the article content and the application of the question-answer response in the public number provided by an embodiment of the present application.
the method comprises the following steps: article materials are synchronized and updated regularly. And automatically synchronizing published article materials of the micro-information public number which is authorized to be bound. Moreover, data synchronization is performed at regular time every day to ensure that newly added and changed contents can be timely recorded by the system and the timeliness is ensured; at the same time, the deleted material can be cleared from the library so that invalid content is not pushed out.
Step two: and constructing a material library through content analysis and processing. The method comprises the steps of identifying the narration content of an article by utilizing an automatic reading and understanding technology, and establishing a related index file by combining the structural information of the article.
step three: and processing the user questions. In the on-line service process, a question of a front-end user is received, the meaning of the user question is extracted after natural language processing, and an answer candidate set is searched from a material library.
step four: and sorting the candidate sets. On one hand, the results are sorted according to the relevance degree of the articles, the near-future period of publication time, the article popularity and the favorable degree; on the other hand, the order can be adjusted according to whether the questioner reads a certain article (the read weight is reduced and derived) and personalized data such as content interest preference by combining the historical behavior record of the questioner on the platform.
step five: preference updates and associated recommendations. After the article is released to the user, the personal record data can be updated according to the real-time feedback of the user so as to optimize the follow-up recommendation effect. Meanwhile, if the content is the content which the user is interested in, the related content can be continuously recommended to the user, the requirement of the user for extended reading is met, and meanwhile, the exposure opportunity of the article is further increased for the public number operator.
The scheme of the embodiment of the application can realize the following beneficial effects: the scheme provided by the application can solve the problem that the answer of the public number content is incomplete in the prior art and can also reduce the problem that part of the content cannot be accurately responded due to model limitation. Meanwhile, repeated exposure of historical articles of public operators is facilitated, and efficiency is improved.
Referring to fig. 4, a block diagram of a public answering device for a server according to an embodiment of the present invention is shown.
As shown in fig. 4, the public number question answering device 400 includes a synchronization update module 410, an understanding identification module 420 and an index establishing module 430.
The synchronous updating module 410 is configured to automatically synchronize and update the published article materials of the public number aiming at the public number associated with the server side; an understanding identification module 420 configured to identify the content of the published article material using automated reading understanding techniques; and an index establishing module 430 configured to establish a material library and an index file based on at least the identified content, wherein the material library includes the article material published by the public number, and the index file is an index corresponding to the article material.
Referring to fig. 5, a block diagram of a public answering device for a user terminal according to an embodiment of the present invention is shown.
As shown in fig. 5, the public address question-answering device 500 includes an understanding processing module 510, a candidate set forming module 520, a ranking module 530, and a pushing module 540.
Wherein, the understanding processing module 510 is configured to, in response to receiving a question of a user, perform semantic understanding processing on the question to extract an intention of the question; a candidate set forming module 520, configured to search, based on the intention of the question, an index file related to the intention from a material library established by the public answering device 400 to form a candidate set, where the candidate set includes at least one candidate result; a ranking module 530 configured to rank the at least one candidate result based on preset indexes, wherein the preset indexes include a material evaluation index and a user attribute index; and a push module 540 configured to send at least one candidate result ranked in the front to the user as a recommendation.
It should be understood that the modules depicted in fig. 4 and 5 correspond to various steps in the methods described with reference to fig. 1 and 2. Thus, the operations and features described above for the method and the corresponding technical effects are also applicable to the modules in fig. 4 and 5, and are not described again here.
It should be noted that the modules in the embodiments of the present application are not intended to limit the solution of the present application, for example, the pushing module may be described as a module that sends at least one candidate result ranked in the front as the recommendation result to the user. In addition, the related function module may also be implemented by a hardware processor, for example, the push module may also be implemented by a processor, which is not described herein again.
in other embodiments, an embodiment of the present invention further provides a non-volatile computer storage medium, where the computer storage medium stores computer-executable instructions, and the computer-executable instructions may execute the public number question-answer response method in any of the above method embodiments;
as one embodiment, a non-volatile computer storage medium of the present invention stores computer-executable instructions configured to:
automatically synchronizing and updating published article materials of the public number aiming at the public number associated with the server side;
Identifying the content of the published article materials by utilizing an automatic reading understanding technology;
And establishing a material library and an index file at least based on the identified content, wherein the material library comprises the article materials published by the public number, and the index file is an index corresponding to the article materials.
as another embodiment, a non-volatile computer storage medium of the present invention stores computer-executable instructions configured to:
In response to receiving a question of a user, semantically understanding the question to extract an intent of the question;
Based on the intention of the question, searching an index file related to the intention from a material library established according to claim 1 to form a candidate set, wherein the candidate set comprises at least one candidate result;
Ranking the at least one candidate result based on preset indexes, wherein the preset indexes comprise material evaluation indexes and user attribute indexes;
And sending at least one candidate result ranked in the front to the user as a recommendation result.
The non-volatile computer-readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the voice recognition apparatus, and the like. Further, the non-volatile computer-readable storage medium 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, the non-transitory computer readable storage medium optionally includes memory located remotely from the processor, which may be connected to the speech recognition apparatus over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
embodiments of the present invention also provide 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 of the speech recognition methods described above.
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the electronic device includes: one or more processors 610 and a memory 620, with one processor 610 being an example in fig. 6. The apparatus of the voice recognition method may further include: an input device 630 and an output device 640. The processor 610, the memory 620, the input device 630, and the output device 640 may be connected by a bus or other means, such as the bus connection in fig. 6. The memory 620 is a non-volatile computer-readable storage medium as described above. The processor 610 executes various functional applications of the server and data processing by running nonvolatile software programs, instructions and modules stored in the memory 620, that is, implements the voice recognition method of the above-described method embodiment. The input device 630 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the voice recognition device. The output device 640 may include a display device such as a display screen.
the product can execute the method provided by the embodiment of the invention, 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 method provided by the embodiment of the present invention.
As an implementation manner, the electronic device is applied to a public number question answering device, and is used on a server side, and 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 cause the at least one processor to:
Automatically synchronizing and updating published article materials of the public number aiming at the public number associated with the server side;
Identifying the content of the published article materials by utilizing an automatic reading understanding technology;
And establishing a material library and an index file at least based on the identified content, wherein the material library comprises the article materials published by the public number, and the index file is an index corresponding to the article materials.
As another embodiment, the electronic device is applied to a response device for public number question answering, and is used on a server side, and 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 cause the at least one processor to:
In response to receiving a question of a user, semantically understanding the question to extract an intent of the question;
based on the intention of the question, searching an index file related to the intention from a material library established according to claim 1 to form a candidate set, wherein the candidate set comprises at least one candidate result;
Ranking the at least one candidate result based on preset indexes, wherein the preset indexes comprise material evaluation indexes and user attribute indexes;
And sending at least one candidate result ranked in the front to the user as a recommendation result.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) A mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) ultra mobile personal computer device: the 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, etc., such as ipads.
(3) A portable entertainment device: such devices can 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 the 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. One of ordinary skill in the art can understand and implement it without inventive effort.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will 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 of the embodiments of the present invention.

Claims (10)

1. A public number question-answer response method is used for a server side and comprises the following steps:
Automatically synchronizing and updating published article materials of the public number aiming at the public number associated with the server side;
Identifying the content of the published article materials by utilizing an automatic reading understanding technology;
And establishing a material library and an index file at least based on the identified content, wherein the material library comprises the article materials published by the public number, and the index file is an index corresponding to the article materials.
2. the method of claim 1, wherein the creating a stories library and an index file based at least on the identified content comprises:
Establishing a material library based on the published article materials of the public number, and automatically synchronizing and updating the material library based on the operations of adding, modifying and deleting the article materials of the public number;
And generating a corresponding index file based on the identified content and the structural information of the published article material.
3. A public number question-answer response method is used for a user terminal and comprises the following steps:
In response to receiving a question of a user, semantically understanding the question to extract an intent of the question;
based on the intention of the question, searching an index file related to the intention from a material library established according to claim 1 to form a candidate set, wherein the candidate set comprises at least one candidate result;
Ranking the at least one candidate result based on preset indexes, wherein the preset indexes comprise material evaluation indexes and user attribute indexes;
and sending at least one candidate result ranked in the front to the user as a recommendation result.
4. the method of claim 3, wherein the method further comprises:
Receiving real-time feedback of the user on the recommendation result;
Judging whether the recommendation result is the content which is interested by the user or not based on the feedback;
And if the recommendation result is the content which the user is interested in, continuously recommending at least one candidate result ranked in the front in the remaining candidate results to the user.
5. The method of claim 3 or 4, wherein the material evaluation indicators include a degree of relevance of the article material to the intent, an article material publication time, an article material popularity, and an article material goodness.
6. The method of claim 5, wherein the user attribute metrics include historical behavior records of the user, whether the user read the candidate results, and content interest preferences of the user.
7. A public number question-answering response device for a server side, comprising:
The synchronous updating module is configured to automatically synchronize and update the published article materials of the public numbers aiming at the public numbers associated with the server side;
an understanding identification module configured to identify the content of the published article material using automated reading understanding techniques;
and the index establishing module is configured to establish a material library and an index file at least based on the identified content, wherein the material library comprises the article materials published by the public number, and the index file is an index corresponding to the article materials.
8. A public number question-answering response apparatus for a user terminal, comprising:
an understanding processing module configured to, in response to receiving a question of a user, semantically understand-process the question to extract an intent of the question;
A candidate set forming module configured to search an index file related to the intention from the material library established according to claim 1 based on the intention of the question to form a candidate set, wherein the candidate set comprises at least one candidate result;
The sorting module is configured to sort the at least one candidate result based on preset indexes, wherein the preset indexes comprise material evaluation indexes and user attribute indexes;
a push module configured to send at least one candidate result ranked in front to the user as a recommendation.
9. 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 one of claims 1 to 6.
10. a storage medium having stored thereon a computer program, characterized in that the program, when being executed by a processor, is adapted to carry out the steps of the method of any one of claims 1 to 6.
CN201910888915.3A 2019-09-19 2019-09-19 public number question-answer response method and device Pending CN110580342A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910888915.3A CN110580342A (en) 2019-09-19 2019-09-19 public number question-answer response method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910888915.3A CN110580342A (en) 2019-09-19 2019-09-19 public number question-answer response method and device

Publications (1)

Publication Number Publication Date
CN110580342A true CN110580342A (en) 2019-12-17

Family

ID=68813191

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910888915.3A Pending CN110580342A (en) 2019-09-19 2019-09-19 public number question-answer response method and device

Country Status (1)

Country Link
CN (1) CN110580342A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113794623A (en) * 2021-08-31 2021-12-14 北京明略软件系统有限公司 Method and device for generating response message, electronic equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000339314A (en) * 1999-05-25 2000-12-08 Nippon Telegr & Teleph Corp <Ntt> Automatic answering method, dialog analyzing method, answer sentence generating method and their device and medium with their program recorded thereon
CN106789559A (en) * 2016-12-02 2017-05-31 上海智臻智能网络科技股份有限公司 Information processing method, device and system for wechat public platform
CN108446284A (en) * 2017-02-16 2018-08-24 上海颐为网络科技有限公司 The information processing method and system of wechat public platform based on structuring
CN108491434A (en) * 2018-02-09 2018-09-04 深圳前海道己社文化有限公司 Article methods of exhibiting, device and terminal based on wechat public platform

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000339314A (en) * 1999-05-25 2000-12-08 Nippon Telegr & Teleph Corp <Ntt> Automatic answering method, dialog analyzing method, answer sentence generating method and their device and medium with their program recorded thereon
CN106789559A (en) * 2016-12-02 2017-05-31 上海智臻智能网络科技股份有限公司 Information processing method, device and system for wechat public platform
CN108446284A (en) * 2017-02-16 2018-08-24 上海颐为网络科技有限公司 The information processing method and system of wechat public platform based on structuring
CN108491434A (en) * 2018-02-09 2018-09-04 深圳前海道己社文化有限公司 Article methods of exhibiting, device and terminal based on wechat public platform

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113794623A (en) * 2021-08-31 2021-12-14 北京明略软件系统有限公司 Method and device for generating response message, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
US11138388B2 (en) Method and system for facilitating a user-machine conversation
KR101797856B1 (en) Method and system for artificial intelligence learning using messaging service and method and system for relaying answer using artificial intelligence
US8285654B2 (en) Method and system of providing a personalized performance
US10902077B2 (en) Search result aggregation method and apparatus based on artificial intelligence and search engine
CN106126524B (en) Information pushing method and device
CN110209843A (en) Multimedia resource playback method, device, equipment and storage medium
CN107623621B (en) Chat corpus collection method and device
CN114339285B (en) Knowledge point processing method, video processing method, device and electronic equipment
CN109460503B (en) Answer input method, answer input device, storage medium and electronic equipment
CN112131361B (en) Answer content pushing method and device
CN108846030B (en) method, system, electronic device and storage medium for visiting official website
CN114430490A (en) Live question and answer and interface display method and computer storage medium
CN111553138A (en) Auxiliary writing method and device for standardizing content structure document
US20220058562A1 (en) Dynamic and continous onboarding of service providers in an online expert marketplace
CN114491149A (en) Information processing method and apparatus, electronic device, storage medium, and program product
CN111104583A (en) Live broadcast room recommendation method, storage medium, electronic device and system
CN111767386B (en) Dialogue processing method, device, electronic equipment and computer readable storage medium
CN110580342A (en) public number question-answer response method and device
CN112749328B (en) Searching method, searching device and computer equipment
CN111159382B (en) Method and device for constructing and using session system knowledge model
CN111737449B (en) Method and device for determining similar problems, storage medium and electronic device
CN111813915A (en) Message interaction method, device, equipment and computer readable storage medium
CN110215704A (en) Game open method, device, electronic equipment and storage medium
CN113779305B (en) Information retrieval method and device and electronic equipment
TWI806207B (en) Method and system for initiating a location-based topic

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province

Applicant after: Sipic Technology Co.,Ltd.

Address before: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province

Applicant before: AI SPEECH Ltd.