CN110727782A - Question and answer corpus generation method and system - Google Patents
Question and answer corpus generation method and system Download PDFInfo
- Publication number
- CN110727782A CN110727782A CN201911004179.7A CN201911004179A CN110727782A CN 110727782 A CN110727782 A CN 110727782A CN 201911004179 A CN201911004179 A CN 201911004179A CN 110727782 A CN110727782 A CN 110727782A
- Authority
- CN
- China
- Prior art keywords
- question
- entity
- template
- answer
- corpus
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
- G06F16/337—Profile generation, learning or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a question-answer corpus generating method and a question-answer corpus generating system, wherein the method comprises the following steps: acquiring question entity elements; determining at least one target entity card matching the obtained question entity elements from a knowledge graph, the knowledge graph comprising a plurality of entity cards, the entity cards comprising a plurality of entity nodes and edge connections between different entity nodes; and generating question and answer corpus based on the determined content of the connection of the entity nodes and the edges in the target entity card. Therefore, the knowledge graph is used for generating the question and answer corpus in a machine processing mode, and the problems that labor cost is huge and the question and answer corpus cannot be standardized due to a manual input mode can be solved.
Description
Technical Field
The invention belongs to the technical field of internet, and particularly relates to a question and answer corpus generating method and system.
Background
With the continuous development of internet technology, the QA system (question-and-answer system) has made great progress in the fields such as intelligent customer service, robot, etc.
The performance of the QA system has a direct relationship with the corpus sample set of questions and answers adopted by the QA system, and the more complete the corpus sample set of questions and answers is, the stronger the performance of the QA system is. At present, the determination process for the question and answer corpus sample set generally depends on manual operation.
However, the inventor of the present application finds at least the following problems in the related art at present in practicing the present application: if the number of question-answer pairs is large, manual entry consumes large financial resources and easily causes high error rate, so that management is difficult. In addition, if there are multiple kinds of questions for a question, the answer mode may be multiple modes such as pictures, audio and video, which makes manual entry more difficult to accomplish. Further, because of the differentiation of the input personnel, the input operation may be relatively random and spoken, and the standardized question-answer corpus cannot be formed.
Disclosure of Invention
The embodiment of the invention provides a question-answer corpus generating method and a question-answer corpus generating 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 question-answer corpus generating method, including: acquiring question entity elements; determining at least one target entity card matching the obtained question entity elements from a knowledge graph, the knowledge graph comprising a plurality of entity cards, the entity cards comprising a plurality of entity nodes and edge connections between different entity nodes; and generating question and answer corpus based on the determined content of the connection of the entity nodes and the edges in the target entity card.
In a second aspect, an embodiment of the present invention provides a question-answer corpus generating system, including: an entity element acquisition unit configured to acquire question entity elements; a target card determination unit configured to determine at least one target entity card matching the obtained question entity elements from a knowledge graph, the knowledge graph including a plurality of entity cards, the entity cards including a plurality of entity nodes and edge connections between the different entity nodes; and the question and answer corpus generating unit is configured to generate question and answer corpus based on the determined content of the entity node and the edge connection in the target entity card.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the computer-readable medium 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 the steps of the above-described method.
In a fourth aspect, an embodiment of the present invention provides a storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the above method.
The embodiment of the invention has the beneficial effects that: and matching the question entity elements with the knowledge graph to obtain a corresponding target entity card, and generating a question and answer corpus by using content information in the target entity card. Therefore, the question and answer corpus is generated by the knowledge graph through a machine processing mode, and the problems that labor cost is huge and the question and answer corpus cannot be standardized due to a manual input mode are solved.
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 shows a schematic diagram of a knowledge-graph according to an embodiment of the invention;
FIG. 2 is a flowchart showing a corpus generating method according to a first embodiment of the present invention;
FIG. 3 is a flowchart showing a corpus generating method according to a second embodiment of the present invention;
FIG. 4 is a flowchart showing a corpus generating method according to a third embodiment of the present invention;
FIG. 5 is a flowchart showing a corpus generating method according to a fourth embodiment of the present invention;
fig. 6 is a block diagram showing a structure of a corpus generating system 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.
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 herein, a "module," "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 based on a signal having one or more data packets, e.g., from a data packet interacting with another element in a local system, distributed system, and/or across a network in the internet with other systems by way of the signal.
Finally, it should be further noted that the terms "comprises" and "comprising," when used herein, include not only those elements but also other elements not expressly listed or inherent to such processes, methods, articles, or devices. 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.
As shown in fig. 1, a schematic diagram of a knowledge-graph according to an embodiment of the present invention has a plurality of entity cards in the knowledge-graph, for example, entity cards for an entity "liswhite" and an entity "scotch", each entity card being composed of edge connections and entity nodes. As in the example of fig. 1, each square box and each round box represents an entity node (e.g., poet, lipil, etc.) corresponding to an entity card, and a connection line between each entity node is an edge connection, which represents an association attribute (e.g., occupation, dynasty, font size, etc.) existing between entities.
It should be understood that the knowledge graph has a plurality of entity cards and may also include other entity cards not shown in fig. 1, and the types of entities of the respective entity cards should not be limited herein, for example the knowledge graph may also include entity cards for corporate entities. And with the needs and development of services, more entity cards can be supplemented and perfected for the knowledge graph.
As shown in fig. 2, the process of the question-answer corpus generating method according to the first embodiment of the present invention includes:
and S210, obtaining question entity elements.
Here, the question entity element denotes information for describing an entity, such as an entity category (company-class entity or personal-class entity, etc.) or an entity name (XX company, for example), and can be directed to a corresponding entity or entities through the question entity element.
In one example of the present disclosure, the corresponding question entity element is derived directly based on a user input operation. In another example of the present disclosure, a question template is obtained, and question entity elements are extracted from the question template according to template entity element extraction conditions. Assuming that the template entity element extraction condition is "{ }", the question entity element in the question template for "{ company }/CEO/who" is { company }. However, if there is no "}" in the question template, the question template cannot satisfy the template entity element extraction condition (i.e., cannot extract the entity element), and is determined to be an invalid question template.
And S220, determining at least one target entity card matched with the obtained question entity elements from the knowledge graph.
Specifically, the entity cards containing the question entity elements in the knowledge graph can be determined as target entity cards by performing text matching on the question entity elements and the knowledge graph. Referring to the example of fig. 1, when the obtained question entity element is "poem", the entity cards for "scoto slope" and "lilac" should both be determined as the target entity cards.
And S230, generating a question and answer corpus based on the determined content of the entity node and the edge connection in the target entity card.
Illustratively, the content of the entity node and edge connection for the entity card "li-white" is "dynasty" to "down dynasty", then the corresponding question and answer corpus may be "what dynasty is li? -plum white is of the dynasty and what occupation is plum white? -prunus is poem ", etc. Therefore, the question-answer corpus is automatically generated through the knowledge graph. Here, regarding the manner of obtaining the content information in the question-answer corpus except the content of the entity node and the edge connection, on one hand, the method may be implemented by filling the pre-configured template information, on the other hand, the method may be further completed by a semantic model, which is not limited herein.
It should be noted that the corpus types of the question-answer corpus may be diversified, such as text corpus, voice corpus and/or video corpus. For example, when a text corpus is parsed by a map, a corresponding speech corpus or a video corpus may be generated according to the text corpus.
As shown in fig. 3, the process of the question-answer corpus generating method according to the second embodiment of the present invention includes:
s310, at least one candidate question sentence template is obtained.
Here, a plurality of question sentence templates may be input in a batch manner, so as to improve corpus generation efficiency.
S320, aiming at each candidate question template, determining whether the candidate question template meets the template entity element extraction condition.
S330, selecting question templates meeting template entity element extraction conditions from the candidate question templates.
In this way, through the operations of S320 and S330, the invalid question templates can be screened out, and it is ensured that the screened out question templates can be used to extract question entity elements.
And S340, extracting question entity elements from the question template according to the template entity element extraction conditions.
And S350, determining at least one target entity card matched with the obtained question entity elements from the knowledge graph.
And S360, generating a question and answer corpus based on the determined content of the entity node and edge connection in the target entity card.
The operations of S340 to S360 may be combined with the description of the example in fig. 2, and are not repeated here. In the embodiment, the knowledge graph is queried through batched candidate question sentence templates, and the corresponding question and answer corpus is determined, so that the reliability of corpus generation and the operation efficiency are greatly improved.
As shown in fig. 4, the process of the question-answer corpus generating method according to the third embodiment of the present invention includes:
and S410, obtaining a question-answer template pair.
Here, each question-answer template pair includes a question template and an answer template having a slot for the same question entity element, for example, the question entity element is "company", and its corresponding slot is the name of the "company".
And S420, extracting question entity elements from the question template according to the template entity element extraction conditions.
Thus, the corresponding question entity elements can be obtained based on a question-answer template pair.
And S430, determining at least one target entity card matched with the obtained question entity elements from the knowledge graph.
S440, filling slots in the question template based on the determined content of the entity node and the edge connection in the target entity card to generate question sentences aiming at the question entity elements.
S450, filling slots in the answer template based on the determined content of the entity node and edge connection in the target entity card to generate answer sentences aiming at the question entity elements.
And S460, generating a question and answer corpus based on the question sentences and the answer sentences.
Illustratively, the question template may be "(i? That? Is? { # company }? Who is the CEO? "the slot for company in the first physical card corresponds to" Tencent ". Accordingly, the answer template may be "$ { company.name } with the CEO $ { company.ceo.name }", and the slot of { company.ceo.name } in the first entity card corresponds to "martiang".
In some embodiments, there are multiple question-answer template pairs for the same question entity element, e.g., each corresponding to a different question-answer style or question-answer label, respectively. For example, there may be one question-answer template pair for the question-answer entity element "company" for the question-answer bid of "CEO" and another question-answer template pair for the question-answer bid of "registered capital". In addition, the question-answer style can realize diversification of the style of the question-answer corpus for the same question-answer label, for example, the first style is "is li white in down dynasty? -it is, the plum white is in the Tang dynasty, and the second pattern is "which dynasty the plum white lives in — the plum white lives in the Tang dynasty". Therefore, diversified question and answer corpora are realized.
Fig. 5 is a flowchart illustrating a corpus questioning and answering generating method according to a fourth embodiment of the present invention. In the example of the process, KG (Knowledge Graph) is associated with a QA system (i.e., question-answer system), corpora of the QA system are constructed based on the KG system, uniform question-answer pair templates are defined for the same kind of objects, and question-answer pairs are generated in batches for the QA system to use. The QA system can send the question template and the answer template in pairs, or only send the question template, and use the default answer template carried by the knowledge card to form the question-answer corpus.
As shown in FIG. 5, the QA system sends multiple question templates of the same class of things in a batch. Then, whether the problem template is valid is judged to determine whether to perform KG-QA conversion operation. For example, it is determined whether the problem template satisfies the template entity element extraction condition, and the invalid problem template is discarded, and the valid problem template is submitted to the KG system.
The KG system, through Natural Language Processing (NLP) operation, can obtain the object concept corresponding to the question (i.e. question entity element or entity category), the corresponding target attribute (i.e. attribute description between entity nodes indicated by edge connection, such as CEO), and query all entity cards under this question entity element at the same time. The target property in the concept of a thing contains the default answer template (e.g., CEO for xx is xxx). The target attributes in the object concepts are combined with the question template to generate a question text. The target attribute of each entity card is combined with the answer template to generate answer text. Further, the question text and the answer text form a question-answer pair of the entity card. Aiming at a plurality of entity cards, a plurality of question-answer pairs are generated in a one-to-one correspondence mode, all the question-answer pairs can be used as question-answer linguistic data of the QA system, and the performance of the QA system is improved.
By the embodiment of the invention, the information stream is constructed between the KG system and the QA system, and large-batch, high-quality, customizable and standardized question-answer pairs are provided for the QA system. Therefore, the corpus data set of the QA system is enriched through automatic operation, the question answering performance effect and efficiency are improved, and the cost for manually making the corpus is saved.
As shown in fig. 6, the question-answer corpus generating system 600 according to an embodiment of the present invention includes: an entity element acquisition unit 610 configured to acquire question entity elements; a target card determination unit 620 configured to determine at least one target entity card matching the obtained question entity element from a knowledge graph, the knowledge graph including a plurality of entity cards, the entity cards including a plurality of entity nodes and edge connections between different entity nodes; and a corpus generating unit 630 configured to generate a corpus based on the determined contents of the entity node and edge connection in the target entity card.
The system of the embodiment of the present invention may be used to execute the corresponding method embodiment of the present invention, and accordingly achieve the technical effects achieved by the method embodiment of the present invention, which are not described herein again.
In the embodiment of the present invention, the relevant functional module may be implemented by a hardware processor (hardware processor).
In another aspect, an embodiment of the present invention provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the above question-answer corpus generating method.
The product can execute the method provided by the embodiment of the application, and has the 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 client of the embodiment 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) And other electronic devices with data interaction functions.
The above-described system embodiments 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 each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. Based on such understanding, the above technical solutions substantially or contributing to the related art 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, etc.) 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 (10)
1. A question-answer corpus generating method comprises the following steps:
acquiring question entity elements;
determining at least one target entity card matching the obtained question entity elements from a knowledge graph, the knowledge graph comprising a plurality of entity cards, the entity cards comprising a plurality of entity nodes and edge connections between different entity nodes;
and generating question and answer corpus based on the determined content of the connection of the entity nodes and the edges in the target entity card.
2. The method of claim 1, wherein the obtaining a question entity element comprises:
obtaining a question template;
and extracting the question entity elements from the question template according to template entity element extraction conditions.
3. The method of claim 2, wherein the obtaining a question template comprises:
obtaining at least one candidate question template;
determining whether the candidate question template meets the template entity element extraction condition or not aiming at each candidate question template; and
and selecting a question template meeting the template entity element extraction condition from the candidate question templates.
4. The method of claim 2 or 3, further comprising:
obtaining question-answer template pairs, wherein each question-answer template pair comprises a question template and an answer template which have slot positions aiming at the same question entity element;
wherein the generating of the question-answer corpus based on the determined content of the connection of the entity nodes and the edges in the target entity card comprises:
filling slots in the question template based on the determined content of the connection of the entity nodes and the edges in the target entity card to generate question sentences aiming at the question entity elements;
filling slots in the answer template based on the determined content of the entity node and edge connection in the target entity card to generate answer sentences aiming at the question entity elements;
and generating a question-answer corpus based on the question sentences and the answer sentences.
5. The method of claim 4, wherein there are multiple question-answer template pairs for the same question entity element.
6. The method of claim 1, wherein the question entity elements comprise entity categories.
7. The method of claim 1, wherein the question-answer corpus comprises at least one corpus type of: text corpora, voice corpora, and video corpora.
8. A corpus generating system, comprising:
an entity element acquisition unit configured to acquire question entity elements;
a target card determination unit configured to determine at least one target entity card matching the obtained question entity elements from a knowledge graph, the knowledge graph including a plurality of entity cards, the entity cards including a plurality of entity nodes and edge connections between the different entity nodes;
and the question and answer corpus generating unit is configured to generate question and answer corpus based on the determined content of the entity node and the edge connection in the target entity card.
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 1-7.
10. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911004179.7A CN110727782A (en) | 2019-10-22 | 2019-10-22 | Question and answer corpus generation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911004179.7A CN110727782A (en) | 2019-10-22 | 2019-10-22 | Question and answer corpus generation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110727782A true CN110727782A (en) | 2020-01-24 |
Family
ID=69220664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911004179.7A Pending CN110727782A (en) | 2019-10-22 | 2019-10-22 | Question and answer corpus generation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110727782A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488463A (en) * | 2020-04-09 | 2020-08-04 | 中国银行股份有限公司 | Test corpus generation method and device and electronic equipment |
| CN112328876A (en) * | 2020-11-03 | 2021-02-05 | 平安科技（深圳）有限公司 | Electronic card generation and pushing method and device based on knowledge graph |
| CN112347226A (en) * | 2020-11-06 | 2021-02-09 | 平安科技（深圳）有限公司 | Document knowledge extraction method and device, computer equipment and readable storage medium |
| CN112579753A (en) * | 2020-12-17 | 2021-03-30 | 京东数字科技控股股份有限公司 | Information acquisition method, device, equipment, medium and product |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
| CN106919655A (en) * | 2017-01-24 | 2017-07-04 | 网易（杭州）网络有限公司 | A kind of answer provides method and apparatus |
| CN108509519A (en) * | 2018-03-09 | 2018-09-07 | 北京邮电大学 | World knowledge collection of illustrative plates enhancing question and answer interactive system based on deep learning and method |
| CN108959256A (en) * | 2018-06-29 | 2018-12-07 | 北京百度网讯科技有限公司 | Generation method, device, storage medium and the terminal device of short text |
| CN109271459A (en) * | 2018-09-18 | 2019-01-25 | 四川长虹电器股份有限公司 | Chat robots and its implementation based on Lucene and grammer networks |
| CN109918680A (en) * | 2019-03-28 | 2019-06-21 | 腾讯科技（上海）有限公司 | Entity recognition method, device and computer equipment |
| CN109933653A (en) * | 2019-01-24 | 2019-06-25 | 平安科技（深圳）有限公司 | Question and answer querying method, system and the computer equipment of question answering system |
| CN110287209A (en) * | 2019-06-10 | 2019-09-27 | 北京百度网讯科技有限公司 | Question and answer processing method, device, equipment and storage medium |
-
2019
- 2019-10-22 CN CN201911004179.7A patent/CN110727782A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
| CN106919655A (en) * | 2017-01-24 | 2017-07-04 | 网易（杭州）网络有限公司 | A kind of answer provides method and apparatus |
| CN108509519A (en) * | 2018-03-09 | 2018-09-07 | 北京邮电大学 | World knowledge collection of illustrative plates enhancing question and answer interactive system based on deep learning and method |
| CN108959256A (en) * | 2018-06-29 | 2018-12-07 | 北京百度网讯科技有限公司 | Generation method, device, storage medium and the terminal device of short text |
| CN109271459A (en) * | 2018-09-18 | 2019-01-25 | 四川长虹电器股份有限公司 | Chat robots and its implementation based on Lucene and grammer networks |
| CN109933653A (en) * | 2019-01-24 | 2019-06-25 | 平安科技（深圳）有限公司 | Question and answer querying method, system and the computer equipment of question answering system |
| CN109918680A (en) * | 2019-03-28 | 2019-06-21 | 腾讯科技（上海）有限公司 | Entity recognition method, device and computer equipment |
| CN110287209A (en) * | 2019-06-10 | 2019-09-27 | 北京百度网讯科技有限公司 | Question and answer processing method, device, equipment and storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488463A (en) * | 2020-04-09 | 2020-08-04 | 中国银行股份有限公司 | Test corpus generation method and device and electronic equipment |
| CN111488463B (en) * | 2020-04-09 | 2023-08-29 | 中国银行股份有限公司 | Test corpus generation method and device and electronic equipment |
| CN112328876A (en) * | 2020-11-03 | 2021-02-05 | 平安科技（深圳）有限公司 | Electronic card generation and pushing method and device based on knowledge graph |
| CN112328876B (en) * | 2020-11-03 | 2023-08-11 | 平安科技（深圳）有限公司 | Electronic card generation pushing method and device based on knowledge graph |
| CN112347226A (en) * | 2020-11-06 | 2021-02-09 | 平安科技（深圳）有限公司 | Document knowledge extraction method and device, computer equipment and readable storage medium |
| CN112347226B (en) * | 2020-11-06 | 2023-05-26 | 平安科技（深圳）有限公司 | Document knowledge extraction method, device, computer equipment and readable storage medium |
| CN112579753A (en) * | 2020-12-17 | 2021-03-30 | 京东数字科技控股股份有限公司 | Information acquisition method, device, equipment, medium and product |
| CN112579753B (en) * | 2020-12-17 | 2024-04-12 | 京东科技控股股份有限公司 | Information acquisition method, device, equipment, medium and product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110727782A (en) | Question and answer corpus generation method and system | |
| CN110019687B (en) | Multi-intention recognition system, method, equipment and medium based on knowledge graph | |
| CN108877782B (en) | Speech recognition method and device | |
| EP3805954A1 (en) | Method for sharing knowledge between dialog systems, and dialog method and apparatus | |
| CN114461777B (en) | Intelligent question-answering method, device, equipment and storage medium | |
| CN107592255B (en) | Information display method and equipment | |
| CN110046230A (en) | Generate the method for recommending words art set, the method and apparatus for recommending words art | |
| CN109460503B (en) | Answer input method, answer input device, storage medium and electronic equipment | |
| CN111813889B (en) | Question information ordering method and device, medium and electronic equipment | |
| CN117194730B (en) | Intention recognition and question answering method and device, electronic equipment and storage medium | |
| CN109033285A (en) | Information-pushing method and device | |
| CN111506717B (en) | Question answering method, device, equipment and storage medium | |
| CN110750633B (en) | Method and device for determining answer of question | |
| CN111931503B (en) | Information extraction method and device, equipment and computer readable storage medium | |
| CN117172210A (en) | Asynchronous hybrid RLHF labeling method and device, storage medium and electronic device | |
| CN111933133A (en) | Intelligent customer service response method and device, electronic equipment and storage medium | |
| CN117932022A (en) | Intelligent question-answering method and device, electronic equipment and storage medium | |
| CN111178846A (en) | Workflow file generation method, device, equipment and storage medium | |
| CN112328871B (en) | Reply generation method, device, equipment and storage medium based on RPA module | |
| US12045780B2 (en) | Online interview method and system | |
| CN114297380A (en) | Data processing method, device, equipment and storage medium | |
| CN113987335A (en) | Data collection method and device, electronic equipment and storage medium | |
| CN114416931A (en) | Label generation method and device and related equipment | |
| WO2020124444A1 (en) | Information processing method and related apparatus | |
| CN112131484A (en) | Multi-person session establishing method, device, equipment and storage medium |
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 Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200124 |