CN108345690B - Intelligent question and answer method and system - Google Patents
Intelligent question and answer method and system Download PDFInfo
- Publication number
- CN108345690B CN108345690B CN201810199255.3A CN201810199255A CN108345690B CN 108345690 B CN108345690 B CN 108345690B CN 201810199255 A CN201810199255 A CN 201810199255A CN 108345690 B CN108345690 B CN 108345690B
- Authority
- CN
- China
- Prior art keywords
- question
- entities
- search
- determining
- entity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2468—Fuzzy queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/243—Natural language query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- 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
Abstract
The invention discloses an intelligent question answering method, which comprises the following steps: acquiring a keyword of a question when the question input by a user is received; inputting all keywords into a preset matching model to obtain entity information of the problem; the matching model is generated by taking all keywords of each standard text as input and taking entity information of the standard text as output training neural network; the entity information comprises entities and attributes; in the accurate searching mode, searching a pre-constructed knowledge graph by using entity information as a searching condition; when the value of the attribute is searched, determining the value of the attribute as an answer of the question; when the search result is not available, entering a fuzzy search mode; determining a set of associated entities from the entities linked to the entities by the relationship; searching in the associated entity set by taking the entity information as a search condition; and obtaining the answer of the question according to the fuzzy search result. Meanwhile, the invention also provides an intelligent question-answering system. The invention can improve the reliability of intelligent question answering.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an intelligent question answering method and an intelligent question answering system.
Background
At present, a question-answering system can query keywords of question sentences in a knowledge base according to questions provided by a user, so as to position answers.
The inventor finds that the prior art has at least the following disadvantages in the process of implementing the invention:
in the prior art, keyword query is simply carried out, and the relation between concepts is not considered, so that the answer provided by the existing intelligent question-answering method is not high in accuracy and difficult to say.
Disclosure of Invention
The embodiment of the invention provides an intelligent question and answer method and system, which can improve the reliability of intelligent question and answer, reduce the waiting time of customers and improve the quality of customer service.
One aspect of the present invention provides an intelligent question answering method, including:
when a question input by a user is received, acquiring a keyword of the question;
inputting all the obtained keywords into a preset matching model to obtain entity information of the problem; the matching model is generated by taking all keywords of each standard text in a corpus as input and taking entity information of the standard text as output training neural networks; the entity information comprises entities and attributes;
under an accurate searching mode, the entity information is used as a searching condition to search a pre-constructed knowledge graph for the first time;
when the value of the attribute is searched, determining the searched value of the attribute as an answer of the question;
when the search result is not obtained, entering a fuzzy search mode from the precise search mode;
determining the relationship of the entities in a fuzzy search mode, and determining a related entity set according to the entities connected with the entities through the relationship;
searching in the associated entity set by taking the entity information as a search condition to obtain a fuzzy search result;
obtaining answers of the questions according to the fuzzy search results;
when a question input by a user is received, acquiring a keyword of the question, wherein the acquiring comprises the following steps:
when a problem input by a user is received, extracting keywords of the problem based on natural semantic understanding to obtain an extraction result;
acquiring mapping words of the words in the extraction result by adopting a preset mapping template, wherein the mapping words are used as key words of the problem; wherein the mapping template comprises mapping words of a plurality of words.
In an optional embodiment, the method further comprises:
responding to a preset instruction of the matching model, and extracting keywords of each standard text in the corpus;
and training a neural network by taking all keywords of each standard text in the corpus as input and taking entity information of the standard text as output so as to obtain the matching model.
In an optional embodiment, the determining the relationship of the entity and determining the associated entity set according to the entity joined with the entity through the relationship in the fuzzy search mode includes:
determining the searching depth of the relation of the entities according to a preset number in a fuzzy searching mode;
determining entities that are joined by relationships within the search depth to the entities as entities of a set of related entities.
In an optional implementation, the obtaining an answer to the question according to the fuzzy search result includes:
judging whether the search result has the value of the attribute;
when the value of the attribute is judged to be in the search result, determining the value of the attribute in the search result as an answer of the question;
and when judging that the value of the attribute does not exist in the search result, returning search failure information.
The invention also provides an intelligent question-answering system, which comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring the keywords of the questions when the questions input by the user are received;
the matching module is used for inputting all the acquired keywords into a preset matching model so as to obtain entity information of the problem; the matching model is generated by taking all keywords of each standard text in a corpus as input and taking entity information of the standard text as output training neural networks; the entity information comprises entities and attributes;
the accurate searching module is used for searching the pre-constructed knowledge graph for the first time by taking the entity information as a searching condition in an accurate searching mode;
a first determining module, configured to determine, when the value of the attribute is searched, the searched value of the attribute as an answer to the question;
the mode switching module is used for entering a fuzzy search mode from the accurate search mode when a result cannot be searched;
the second determining module is used for determining the relation of the entity in a fuzzy search mode and determining an associated entity set according to the entity connected with the entity through the relation;
the fuzzy search module is used for searching in the associated entity set by taking the entity information as a search condition to obtain a fuzzy search result;
the second acquisition module is used for acquiring answers of the questions according to the fuzzy search results;
wherein the first obtaining module comprises:
the system comprises a first extraction unit, a second extraction unit and a third extraction unit, wherein the first extraction unit is used for extracting keywords of a question based on natural semantic understanding to obtain an extraction result when the question input by a user is received;
a first obtaining unit, configured to obtain a mapping word of a word in the extraction result by using a preset mapping template, where the mapping word is used as a keyword of the problem; wherein the mapping template comprises mapping words of a plurality of words.
In an alternative embodiment, the system further comprises:
the first extraction module is used for responding to a preset instruction of the matching model and extracting keywords of each standard text in the corpus;
and the training module is used for training a neural network by taking all keywords of each standard text in the corpus as input and taking entity information of the standard text as output so as to obtain the matching model.
In an alternative embodiment, the second determining module includes:
the first determining unit is used for determining the searching depth of the relation of the entities according to the preset number in a fuzzy searching mode;
a second determining unit for determining entities linked to the entities by a relationship within the search depth as entities of the set of associated entities.
In an optional implementation, the second obtaining module includes:
a first judgment unit configured to judge whether the search result has a value of the attribute;
a third determination unit configured to determine, when it is determined that the search result has the value of the attribute, the value of the attribute in the search result as an answer to the question;
and the returning unit is used for returning search failure information when judging that the search result does not have the value of the attribute.
Compared with the prior art, the invention has the following outstanding advantages: the invention provides an intelligent question-answering method and an intelligent question-answering system, wherein the method accurately and quickly maps key words to entities, attributes and relations through the approaching capacity and the self-learning capacity of a neural network, so that the waiting time of a user is reduced, when values of the attributes are searched, the searched values of the attributes are determined as answers of the questions, and when results cannot be searched, a fuzzy search mode is entered from an accurate search mode; determining the relation of the entity in a fuzzy search mode, determining an associated entity set according to the entity connected with the entity through the relation, and searching in the associated entity set by taking the entity information as a search condition to obtain a fuzzy search result; and obtaining answers of the questions according to the fuzzy search results, and adopting different search mechanisms under different conditions, so that the questions of the user can be responded efficiently, the accuracy and the objectivity of intelligent questions and answers are improved through the knowledge map, the service quality of the intelligent customer service system is improved, and the user experience is improved.
Drawings
FIG. 1 is a schematic flow chart diagram of a first embodiment of the intelligent question answering method provided by the present invention;
fig. 2 is a schematic structural diagram of a first embodiment of the intelligent question-answering system provided by the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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, which is a schematic flow chart of a first embodiment of the intelligent question answering method provided by the present invention, as shown in fig. 1, the method includes:
step S101, when a problem input by a user is received, obtaining a keyword of the problem;
step S102, inputting all the obtained keywords into a preset matching model to obtain entity information of the problem; the matching model is generated by taking all keywords of each standard text in a corpus as input and taking entity information of the standard text as output training neural networks; the entity information comprises a main body and attributes of an entity;
step S103, under an accurate searching mode, the entity information is used as a searching condition to search a pre-constructed knowledge graph for the first time;
step S104, when the value of the attribute is searched, determining the searched value of the attribute as the answer of the question;
step S105, when the search result is not obtained, entering a fuzzy search mode from the accurate search mode;
step S106, determining the relation of the entity in a fuzzy search mode, and determining an associated entity set according to the entity connected with the entity through the relation;
step S107, searching the associated entity set by taking the entity information as a search condition to obtain a fuzzy search result;
and S108, acquiring answers of the questions according to the fuzzy search results.
For example, the user's problems are: what is the height of the nail? From the question an entity (represented by A) is constructed, here the first entity, the subject of A being the first and the attribute of A being height. The relationship is not considered in a.
And (3) accurate searching:
using the A body and the attribute as a search condition, if the knowledge map has the entity A and the attribute A comprises the height, the answer is obtained.
Fuzzy search:
using A's body and attributes as search criteria, if there are nail entities in the knowledge-graph but there are no height attributes or if there are no nail entities at all in the knowledge-graph, then a search must be conducted by entities in the knowledge-graph that are related to A's body (i.e., nail). For example, in the knowledge graph, the entity B of a subject a (the relationship is a couple) but the entity does not have the height attribute of the old man, the entity related to the subject of the entity B is continuously searched, the entity c (the relationship is a father) is found, the entity B is searched on the condition of the height (the attribute of a), the condition that the attribute of the entity B is the height of the son of the child is 2.2 meters is obtained, and through the derivation of the relationship, the first-couple-second-couple-third-deduces that the parent of the first-third-fourth-third-fourth-third-fourth-third-fourth-.
It should be noted that the knowledge graph is a structured semantic knowledge base, and is a mesh knowledge base formed by linking entities with attributes through the relationship. The entities are mutually connected through the relationship to form a network knowledge structure. And the entity and the attribute corresponding to the standard text are determined according to the manually established standard in the standard text. The corpus includes a large amount of textual data. The keywords may be in the form of word vectors.
The method comprises the steps that a keyword is accurately and quickly mapped to an entity, an attribute and a relation through the approaching capability and the self-learning capability of a neural network, so that the waiting time of a user is reduced, the searched value of the attribute is determined as the answer of the problem when the value of the attribute is searched, and the fuzzy search mode is entered from the accurate search mode when the result is not searched; determining the relation of the entity in a fuzzy search mode, determining an associated entity set according to the entity connected with the entity through the relation, and searching in the associated entity set by taking the entity information as a search condition to obtain a fuzzy search result; and obtaining answers of the questions according to the fuzzy search results, and adopting different search mechanisms under different conditions, so that the questions of the user can be responded efficiently, the accuracy and the objectivity of intelligent questions and answers are improved through the knowledge map, the service quality of the intelligent customer service system is improved, and the user experience is improved.
In an alternative embodiment, the corpus includes a large amount of text data of a target domain; wherein the target domain is the domain to which the problem belongs.
In an alternative embodiment, the text data of the corpus is text data of a target domain.
The invention also provides a second embodiment of the intelligent question answering method, which comprises the steps of S101-S108 in the first embodiment of the intelligent question answering method, and further defines that: when a question input by a user is received, acquiring a keyword of the question, wherein the keyword comprises:
when a problem input by a user is received, extracting keywords of the problem based on natural semantic understanding to obtain an extraction result;
acquiring mapping words of the words in the extraction result by adopting a preset mapping template, wherein the mapping words are used as key words of the problem; wherein the mapping template comprises mapping words of a plurality of words.
It should be noted that Natural semantic Understanding (NLU) is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language.
The method and the system have the advantages that the keywords are extracted from the questions through natural semantic understanding, so that the accuracy of keyword extraction is improved, and the accuracy of intelligent question answering is further improved.
It should be noted that the mapping template can map words into words with characteristics of being difficult to generate ambiguity, being more simplified, and being easier to search; for example,
the user asks questions:
is a 4s department in the sky river on the south road? .
And adopting a mapping template to convert the words: a 4s shop, if, on, the sky river south road:
is not-
In- (Y-O) > is located at
It should be noted that the mapping template is only an example, and the present invention is not limited to this embodiment.
And mapping the words in the user question by using the mapping template to obtain the mapping words of the words, thereby being beneficial to improving the subsequent searching efficiency.
The present invention also provides a third embodiment of the intelligent question answering method, which includes steps S101 to S108 in the first embodiment of the intelligent question answering method, and further defines: the method further comprises the following steps:
responding to a preset instruction of the matching model, and extracting keywords of each standard text in the corpus;
and training a neural network by taking all keywords of each standard text in the corpus as input and taking entity information of the standard text as output so as to obtain the matching model.
The present invention also provides a fourth embodiment of the intelligent question answering method, which includes steps S101 to S108 in the first embodiment of the intelligent question answering method described above, and further defines: determining the relationship of the entity in the fuzzy search mode, and determining an associated entity set according to the entity connected with the entity through the relationship, wherein the method comprises the following steps:
determining the searching depth of the relation of the entities according to a preset number in a fuzzy searching mode;
determining entities that are joined by relationships within the search depth to the entities as entities of a set of related entities.
The search depth is determined through the preset number, so that the relation in the search depth is determined, the phenomenon that the response speed is reduced due to too large search depth is avoided, and the high efficiency of intelligent question answering is further ensured.
The present invention also provides a fifth embodiment of the intelligent question answering method, which includes steps S101 to S108 in the fourth embodiment of the intelligent question answering method described above, and further defines: the obtaining of the answer to the question according to the fuzzy search result includes:
judging whether the search result has the value of the attribute;
when the value of the attribute is judged to be in the search result, determining the value of the attribute in the search result as an answer of the question;
and when judging that the value of the attribute does not exist in the search result, returning search failure information.
Namely, the user experience is improved by feeding back the information of the fuzzy search result.
Referring to fig. 2, which is a schematic structural diagram of a first embodiment of the intelligent question answering system provided by the present invention, as shown in fig. 2, the system includes:
a first obtaining module 201, configured to, when a question input by a user is received, obtain a keyword of the question;
the matching module 202 is configured to input all the obtained keywords into a preset matching model to obtain entity information of the problem; the matching model is generated by taking all keywords of each standard text in a corpus as input and taking entity information of the standard text as output training neural networks; the entity information comprises entities and attributes;
the accurate searching module 203 is used for searching the pre-constructed knowledge graph for the first time by using the entity information as a searching condition in an accurate searching mode;
a first determining module 204, configured to determine, when the value of the attribute is searched, the searched value of the attribute as an answer to the question;
a mode switching module 205, configured to enter a fuzzy search mode from the precise search mode when no result is searched;
a second determining module 206, configured to determine, in a fuzzy search mode, a relationship of the entity, and determine a set of associated entities according to an entity associated with the entity through the relationship;
a fuzzy search module 207, configured to search in the associated entity set by using the entity information as a search condition to obtain a fuzzy search result;
a second obtaining module 208, configured to obtain an answer to the question according to the fuzzy search result.
In an alternative embodiment, the corpus includes a large amount of text data of a target domain; wherein the target domain is the domain to which the problem belongs.
In an alternative embodiment, the text data of the corpus is text data of a target domain.
In an optional implementation, the first obtaining module includes:
the system comprises a first extraction unit, a second extraction unit and a third extraction unit, wherein the first extraction unit is used for extracting keywords of a question based on natural semantic understanding to obtain an extraction result when the question input by a user is received;
a first obtaining unit, configured to obtain a mapping word of a word in the extraction result by using a preset mapping template, where the mapping word is used as a keyword of the problem; wherein the mapping template comprises mapping words of a plurality of words.
In an alternative embodiment, the system further comprises:
the first extraction module is used for responding to a preset instruction of the matching model and extracting keywords of each standard text in the corpus;
and the training module is used for training a neural network by taking all keywords of each standard text in the corpus as input and taking entity information of the standard text as output so as to obtain the matching model.
In an alternative embodiment, the second determining module includes:
the first determining unit is used for determining the series of the relation of the entities according to the preset number in a fuzzy search mode to be used as the search depth;
a second determining unit for determining entities linked to the entities by a relationship within the search depth as entities of the set of associated entities.
In an optional implementation, the second obtaining module includes:
a first judgment unit configured to judge whether the search result has a value of the attribute;
a third determination unit configured to determine, when it is determined that the search result has the value of the attribute, the value of the attribute in the search result as an answer to the question;
and the returning unit is used for returning search failure information when judging that the search result does not have the value of the attribute.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
It should be noted that the above-described embodiments of the apparatus or system are merely schematic, where the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, may be located in one place, or may be distributed on multiple 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. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (8)
1. An intelligent question answering method is characterized by comprising the following steps:
when a question input by a user is received, acquiring a keyword of the question;
inputting all the obtained keywords into a preset matching model to obtain entity information of the problem; the matching model is generated by taking all keywords of each standard text in a corpus as input and taking entity information of the standard text as output training neural networks; the entity information comprises entities and attributes;
under an accurate searching mode, the entity information is used as a searching condition to search a pre-constructed knowledge graph for the first time;
when the value of the attribute is searched, determining the searched value of the attribute as an answer of the question;
when the search result is not obtained, entering a fuzzy search mode from the precise search mode;
determining the relationship of the entities in a fuzzy search mode, and determining a related entity set according to the entities connected with the entities through the relationship;
searching in the associated entity set by taking the entity information as a search condition to obtain a fuzzy search result;
obtaining answers of the questions according to the fuzzy search results;
when a question input by a user is received, acquiring a keyword of the question, wherein the acquiring comprises the following steps:
when a problem input by a user is received, extracting keywords of the problem based on natural semantic understanding to obtain an extraction result;
acquiring mapping words of the words in the extraction result by adopting a preset mapping template, wherein the mapping words are used as key words of the problem; wherein the mapping template comprises mapping words of a plurality of words.
2. The intelligent question-answering method according to claim 1, characterized in that the method further comprises:
responding to a preset instruction of the matching model, and extracting keywords of each standard text in the corpus;
and training a neural network by taking all keywords of each standard text in the corpus as input and taking entity information of the standard text as output so as to obtain the matching model.
3. The intelligent question-answering method according to claim 1, wherein the determining the relationship of the entities and the determining of the associated entity set from the entities linked with the entities through the relationship in the fuzzy search mode comprises:
determining the searching depth of the relation of the entities according to a preset number in a fuzzy searching mode;
determining entities that are joined by relationships within the search depth to the entities as entities of a set of related entities.
4. The intelligent question-answering method according to claim 1 or 3, wherein the obtaining answers to the questions according to the fuzzy search results comprises:
judging whether the search result has the value of the attribute;
when the value of the attribute is judged to be in the search result, determining the value of the attribute in the search result as an answer of the question;
and when judging that the value of the attribute does not exist in the search result, returning search failure information.
5. An intelligent question-answering system, comprising:
the first acquisition module is used for acquiring a keyword of a question when the question input by a user is received;
the matching module is used for inputting all the acquired keywords into a preset matching model so as to obtain entity information of the problem; the matching model is generated by taking all keywords of each standard text in a corpus as input and taking entity information of the standard text as output training neural networks; the entity information comprises entities and attributes;
the accurate searching module is used for searching the pre-constructed knowledge graph for the first time by taking the entity information as a searching condition in an accurate searching mode;
a first determining module, configured to determine, when the value of the attribute is searched, the searched value of the attribute as an answer to the question;
the mode switching module is used for entering a fuzzy search mode from the accurate search mode when a result cannot be searched;
the second determining module is used for determining the relation of the entity in a fuzzy search mode and determining an associated entity set according to the entity connected with the entity through the relation;
the fuzzy search module is used for searching in the associated entity set by taking the entity information as a search condition to obtain a fuzzy search result;
the second acquisition module is used for acquiring answers of the questions according to the fuzzy search results;
wherein the first obtaining module comprises:
the system comprises a first extraction unit, a second extraction unit and a third extraction unit, wherein the first extraction unit is used for extracting keywords of a question based on natural semantic understanding to obtain an extraction result when the question input by a user is received;
a first obtaining unit, configured to obtain a mapping word of a word in the extraction result by using a preset mapping template, where the mapping word is used as a keyword of the problem; wherein the mapping template comprises mapping words of a plurality of words.
6. The intelligent question-answering system according to claim 5, characterized in that the system further comprises:
the first extraction module is used for responding to a preset instruction of the matching model and extracting keywords of each standard text in the corpus;
and the training module is used for training a neural network by taking all keywords of each standard text in the corpus as input and taking entity information of the standard text as output so as to obtain the matching model.
7. The intelligent question-answering system of claim 5, wherein the second determining module comprises:
the first determining unit is used for determining the searching depth of the relation of the entities according to the preset number in a fuzzy searching mode;
a second determining unit for determining entities linked to the entities by a relationship within the search depth as entities of the set of associated entities.
8. The intelligent question-answering system according to claim 5 or 7, characterized in that the second obtaining module comprises:
a first judgment unit configured to judge whether the search result has a value of the attribute;
a third determination unit configured to determine, when it is determined that the search result has the value of the attribute, the value of the attribute in the search result as an answer to the question;
and the returning unit is used for returning search failure information when judging that the search result does not have the value of the attribute.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810199255.3A CN108345690B (en) | 2018-03-09 | 2018-03-09 | Intelligent question and answer method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810199255.3A CN108345690B (en) | 2018-03-09 | 2018-03-09 | Intelligent question and answer method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108345690A CN108345690A (en) | 2018-07-31 |
| CN108345690B true CN108345690B (en) | 2020-11-13 |
Family
ID=62957152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810199255.3A Active CN108345690B (en) | 2018-03-09 | 2018-03-09 | Intelligent question and answer method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108345690B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086438B (en) * | 2018-08-15 | 2021-02-19 | 百度在线网络技术（北京）有限公司 | Method and device for inquiring information |
| CN110866157B (en) * | 2018-08-27 | 2022-07-15 | 北京猎户星空科技有限公司 | Robot response method and device and robot |
| CN109543007A (en) * | 2018-10-16 | 2019-03-29 | 深圳壹账通智能科技有限公司 | Put question to data creation method, device, computer equipment and storage medium |
| CN109408627B (en) * | 2018-11-15 | 2021-03-02 | 众安信息技术服务有限公司 | Question-answering method and system fusing convolutional neural network and cyclic neural network |
| CN109614476A (en) * | 2018-12-11 | 2019-04-12 | 平安科技（深圳）有限公司 | Customer service system answering method, device, computer equipment and storage medium |
| CN109947915B (en) * | 2019-02-25 | 2021-05-04 | 厦门无常师教育科技有限公司 | Knowledge management system-based artificial intelligence expert system and construction method thereof |
| CN112000798A (en) * | 2019-05-27 | 2020-11-27 | 广东小天才科技有限公司 | Chinese question type answer obtaining method and device |
| CN110489755A (en) * | 2019-08-21 | 2019-11-22 | 广州视源电子科技股份有限公司 | Document creation method and device |
| CN110909145B (en) * | 2019-11-29 | 2022-08-09 | 支付宝(杭州)信息技术有限公司 | Training method and device for multi-task model |
| CN111026856A (en) * | 2019-12-09 | 2020-04-17 | 出门问问信息科技有限公司 | Intelligent interaction method and device and computer readable storage medium |
| CN111177345B (en) * | 2019-12-19 | 2023-06-20 | 中国平安财产保险股份有限公司 | Intelligent question-answering method and device based on knowledge graph and computer equipment |
| CN111198971B (en) * | 2020-01-15 | 2023-06-06 | 北京百度网讯科技有限公司 | Searching method, searching device and electronic equipment |
| CN111460116B (en) * | 2020-03-19 | 2023-07-25 | 北京百度网讯科技有限公司 | Question answering method, question answering system, electronic device and storage medium |
| CN111651569B (en) * | 2020-04-24 | 2022-04-08 | 中国电力科学研究院有限公司 | Knowledge base question-answering method and system in electric power field |
| CN111984847A (en) * | 2020-08-21 | 2020-11-24 | 上海风秩科技有限公司 | Information search method, information search device, storage medium and electronic device |
| CN112214607B (en) * | 2020-09-07 | 2021-06-11 | 深圳市镜象科技有限公司 | Interactive method, psychological intervention system, terminal and medium based on artificial intelligence |
| CN112182188A (en) * | 2020-09-30 | 2021-01-05 | 珠海格力电器股份有限公司 | Knowledge graph-based question and answer method and device and storage medium |
| CN113468294A (en) * | 2021-07-20 | 2021-10-01 | 上海明略人工智能(集团)有限公司 | Method and device for question answering of ancient poems, electronic equipment and storage medium |
| CN116089368B (en) * | 2022-08-01 | 2023-12-19 | 荣耀终端有限公司 | File searching method and related device |
| CN116028597B (en) * | 2023-03-27 | 2023-07-21 | 南京燧坤智能科技有限公司 | Object retrieval method, device, nonvolatile storage medium and computer equipment |
| CN116823140A (en) * | 2023-04-21 | 2023-09-29 | 华腾建信科技有限公司 | Project problem information reporting method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372118A (en) * | 2016-08-24 | 2017-02-01 | 武汉烽火普天信息技术有限公司 | Large-scale media text data-oriented online semantic comprehension search system and 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 |
| CN107729319A (en) * | 2017-10-18 | 2018-02-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10832145B2 (en) * | 2015-10-05 | 2020-11-10 | International Business Machines Corporation | Techniques for resolving entities in received questions |
-
2018
- 2018-03-09 CN CN201810199255.3A patent/CN108345690B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372118A (en) * | 2016-08-24 | 2017-02-01 | 武汉烽火普天信息技术有限公司 | Large-scale media text data-oriented online semantic comprehension search system and 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 |
| CN107729319A (en) * | 2017-10-18 | 2018-02-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108345690A (en) | 2018-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108345690B (en) | Intelligent question and answer method and system | |
| CN109284363B (en) | Question answering method and device, electronic equipment and storage medium | |
| US10642938B2 (en) | Artificial intelligence based method and apparatus for constructing comment graph | |
| CN106202476B (en) | A kind of interactive method and device of knowledge based collection of illustrative plates | |
| JP6309644B2 (en) | Method, system, and storage medium for realizing smart question answer | |
| CN105045875B (en) | Personalized search and device | |
| CN106649742A (en) | Database maintenance method and device | |
| CN104050256A (en) | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method | |
| CN112035599B (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| CN113342958B (en) | Question-answer matching method, text matching model training method and related equipment | |
| CN112749266B (en) | Industrial question and answer method, device, system, equipment and storage medium | |
| CN111046147A (en) | Question answering method and device and terminal equipment | |
| CN114691831A (en) | Task-type intelligent automobile fault question-answering system based on knowledge graph | |
| CN112632239A (en) | Brain-like question-answering system based on artificial intelligence technology | |
| CN110442730A (en) | A kind of knowledge mapping construction method based on deepdive | |
| CN112507089A (en) | Intelligent question-answering engine based on knowledge graph and implementation method thereof | |
| CN111625638A (en) | Question processing method, device and equipment and readable storage medium | |
| CN106951470A (en) | A kind of intelligent Answer System retrieved based on professional knowledge figure | |
| CN113610626A (en) | Bank credit risk identification knowledge graph construction method and device, computer equipment and computer readable storage medium | |
| CN113392212A (en) | Service knowledge graph construction method and device, electronic equipment and storage medium | |
| CN116340352A (en) | Data query method and device, storage medium and electronic equipment | |
| CN115757720A (en) | Project information searching method, device, equipment and medium based on knowledge graph | |
| CN116414996A (en) | Knowledge graph-based problem query method and device and electronic equipment | |
| CN114372478A (en) | Knowledge distillation-based question and answer method, terminal equipment and storage medium | |
| CN112905747A (en) | Professional system archive question-answering robot system based on semantic analysis technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |