CN111309877A - Intelligent question-answering method and system based on knowledge graph - Google Patents
Intelligent question-answering method and system based on knowledge graph Download PDFInfo
- Publication number
- CN111309877A CN111309877A CN201811520770.3A CN201811520770A CN111309877A CN 111309877 A CN111309877 A CN 111309877A CN 201811520770 A CN201811520770 A CN 201811520770A CN 111309877 A CN111309877 A CN 111309877A
- Authority
- CN
- China
- Prior art keywords
- knowledge graph
- natural language
- question
- user
- keywords
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an intelligent question-answering method and system based on a knowledge graph, which comprises the following steps: crawling data sources of all industry fields on the Internet, respectively establishing a knowledge graph aiming at each industry field, and storing the knowledge graph in a database; receiving a natural language question input by a user; performing word segmentation operation on the natural language question by adopting a dictionary matching method or a word frequency statistical method, and extracting one or more keywords in the natural language question; and judging the industry field to which the natural language question belongs, selecting a knowledge graph of the corresponding field from the database, and searching according to the keywords in the knowledge graph to generate a corresponding search result. According to the invention, keywords are extracted through semantic analysis of the natural language question, knowledge maps in related technical fields are firstly locked according to the keywords, and then the keywords are utilized for retrieval, so that the retrieval precision and the answer matching degree can be greatly improved in the secondary retrieval step.
Description
Technical Field
The invention relates to the technical field of knowledge graph and natural semantic recognition, in particular to an intelligent question answering method and system based on a knowledge graph.
Background
With the development of the internet, the question and answer function is pushed out from the customer service column of many portal sites. However, the current question-answering mode mainly adopts a manual question-answering mode, the efficiency of the mode is low, a questioner usually needs to wait for a long time, and the user experience is poor.
In order to solve the above problems, the existing question-answering method provides a chat robot, which can automatically generate a corresponding response according to the chat content input by the user. However, the current chat robot has a poor semantic analysis function, and cannot realize the preparation identification of the natural language input by the user, so that the semantic analysis result is inaccurate, the distance from the answer required by the user is large, and the error rate of the answer is high.
Disclosure of Invention
The object of the present invention is to solve at least one of the technical drawbacks mentioned.
Therefore, the invention aims to provide an intelligent question-answering method and system based on a knowledge graph.
In order to achieve the above object, an embodiment of the present invention provides an intelligent question-answering method based on a knowledge graph, including the following steps:
step S1, crawling data sources of various industry fields on the Internet, respectively establishing a knowledge graph aiming at each industry field, and storing the knowledge graph in a database;
step S2, receiving a natural language question input by a user;
step S3, performing word segmentation operation on the natural language question by adopting a dictionary matching method or a word frequency statistical method, and extracting one or more keywords in the natural language question;
and step S4, judging the industry field to which the natural language question belongs according to the keywords obtained in the step S3, then selecting a knowledge graph of the corresponding field from the database, searching according to the keywords from the knowledge graph, generating a corresponding search result, performing natural semantic processing on the search result, outputting the result as an answer and displaying the answer to the user.
Further, in the step S1, establishing a knowledge graph, including the following steps: the method comprises the steps of extracting the title and the text of each item of data from the data source of each industry field on the Internet, splitting sentences, filtering splitting results according to a preset filtering principle to remove redundant words, reserving key information texts, performing semantic analysis according to the reserved key information texts to obtain the field to which the data source belongs, and marking the field of the data source in the database for subsequent query and use.
Further, in step S2, the natural language question input by the user is in a text form or a speech form, and when the natural language question is in a language form, the speech is subjected to character recognition processing to generate a corresponding text language.
Further, in step S4, the retrieving from the knowledge graph according to the keyword to generate a corresponding retrieving result includes the following steps:
searching in the knowledge graph according to the plurality of key words, and inquiring to obtain a plurality of search results;
and performing relevance sequencing on the multiple search results, performing natural language sorting on the search result with the highest relevance degree with the keyword, and outputting the search result as an answer to a user for viewing.
Further, in the step S4, the answer is output to the user for viewing, and meanwhile, the related domain information of the natural language question is synchronously pushed to the user under the output interface.
The embodiment of the invention also provides an intelligent question-answering system based on the knowledge graph, which comprises: the system comprises a knowledge graph establishing module, a database and a database, wherein the knowledge graph establishing module is used for crawling data sources of all industry fields on the Internet, respectively establishing a knowledge graph aiming at each industry field and storing the knowledge graph in the database; a database for storing the knowledge-graph; the question input module is used for receiving a natural language question input by a user; the word segmentation module is used for performing word segmentation operation on the natural language question by adopting a dictionary matching method or a word frequency statistical method, and extracting one or more keywords in the natural language question; the retrieval module is used for judging the industry field to which the natural language question belongs according to the key words, then selecting a knowledge graph of the corresponding field from the database, retrieving from the knowledge graph according to the key words and generating corresponding retrieval results; the natural semantic processing module is used for carrying out natural semantic processing on the retrieval result; and the answer output and display module is used for outputting and displaying the answer after the natural semantic processing to the user.
Furthermore, the knowledge graph establishing module extracts the title and the text of each data from the crawled data sources of various industry fields on the internet, then performs sentence splitting, filters the splitting result according to a preset filtering principle to remove redundant words and phrases, retains key information texts, performs semantic analysis according to the retained key information texts to obtain the field to which the data source belongs, and marks the field of the data source in the database for subsequent query and use.
Further, the natural language question input by the user is in a text form or a voice form, and when the natural language question is in the language form, the question input module performs character recognition processing on the voice to generate a corresponding text language.
Further, the retrieval module retrieves in the knowledge graph according to a plurality of keywords, and queries to obtain a plurality of retrieval results; and performing relevance sequencing on the multiple search results, performing natural language sorting on the search result with the highest relevance degree with the keyword, and outputting the search result as an answer to a user for viewing.
Furthermore, the answer output and display module outputs the answer to the user for viewing, and synchronously pushes the related field information of the natural language question to the user under an output interface.
According to the intelligent question-answering method and system based on the knowledge graph, the knowledge graph of each field is established, the received keywords in the natural language question of the user are utilized to perform query retrieval in the knowledge graph of the related field, the corresponding retrieval result is obtained through analysis, the retrieval result is subjected to relevance sequencing, and the most relevant result is output to the user as an answer. The invention establishes knowledge maps of various fields by crawling mass data, and has wide resource coverage. And extracting keywords through semantic analysis of the natural language question, firstly locking the knowledge graph of the related technical field according to the keywords, and then searching by using the keywords, wherein the secondary searching step can greatly improve the searching precision and the answer matching degree. In addition, the invention can push the information of the related field to the user while outputting the answer, thereby improving the user experience.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method for intelligent knowledge-graph based question answering according to an embodiment of the present invention;
FIG. 2 is a block diagram of an intelligent problem system based on finger-maps, according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
As shown in fig. 1, the intelligent question answering method based on knowledge graph in the embodiment of the present invention includes the following steps:
and step S1, crawling data sources of various industry fields on the Internet, respectively establishing a knowledge graph aiming at each industry field, and storing the knowledge graph in a database.
Specifically, the crawled data sources of all the industry fields on the internet are subjected to title and text extraction of each item of data, then sentence splitting is carried out, splitting results are filtered according to a preset filtering principle to remove redundant words and phrases, key information texts are reserved, semantic analysis is carried out according to the reserved key information texts to obtain the fields to which the data sources belong, and the fields of the data sources are marked in a database for subsequent query and use.
For example, crawled data sources for various industry domains on the internet include: enterprise official networks, industry portals, papers, technical specifications, etc. It should be noted that the crawled data source is not limited to the above example, and may also be other data sources, which are not described herein again.
In step S2, a natural language question input by the user is received.
In one embodiment of the invention, the natural language question entered by the user is in text form or speech form.
And when the natural language question is in a language form, performing character recognition processing on the voice to generate a corresponding text language.
Therefore, the invention supports the user to input the question sentence in the form of text or voice, so that the user can initiate the question by voice even under the condition that the user is inconvenient to input characters.
It should be noted that the question forms supported by the present application are not limited to the above, and may include pictures and short videos. And judging a question target of the user by identifying the entity characteristics in the picture or the short video, and generating a corresponding text form.
And step S3, performing word segmentation operation on the natural language question by adopting a dictionary matching method or a word frequency statistical method, and extracting one or more keywords in the natural language question.
(1) Dictionary matching method: the dictionary method is that the words in the dictionary are searched one by one in the text, and the search hit is recorded as a word.
(2) Word frequency statistical method: the word frequency method does not depend on a dictionary, but calculates the frequency of simultaneous occurrence of any two words in the text for statistics, and the frequency calculation takes a large amount of natural texts as a corpus, and the probability that the words with high frequency of simultaneous occurrence become words is high. After word segmentation is finished, nonsense words such as auxiliary words, adverbs, connecting words and the like need to be removed, and the word segmentation is finished by depending on the conventional general dictionary. In addition, a self-defined dictionary needs to be established, and words with little meaning in an enterprise search environment are also removed.
The keywords extracted by the two methods are most sufficiently covered by effective information, and the subsequent retrieval precision is improved.
And step S4, judging the industry field to which the natural language question belongs according to the keywords obtained in the step S3, then selecting a knowledge graph of the corresponding field from the database, searching according to the keywords from the knowledge graph, generating a corresponding search result, performing natural semantic processing on the search result, outputting the result as an answer and displaying the answer to the user.
Namely, the invention adopts the secondary retrieval steps: the industry field to which the natural language question belongs is positioned in a database for the first time according to the key words; and searching in the knowledge graph of the located industry field according to the keywords for the second time. The secondary retrieval mode can improve retrieval accuracy and retrieval efficiency.
In the step, retrieval is carried out in the knowledge graph according to a plurality of key words, and a plurality of retrieval results are obtained through query. And performing relevance sorting on the multiple search results, and outputting the search result with the highest relevance degree with the keywords as an answer to a user for viewing after natural language arrangement.
Furthermore, when the answer is output to the user for viewing, the related field information of the natural language question is synchronously pushed to the user under the output interface. The user clicks the interested information in the interface, and the output interface automatically pushes the detailed information related to the clicked content, so that the experience degree of the user can be greatly improved, and the viscosity of the user is increased.
As shown in fig. 2, the intellectual property map based intelligent question answering system of the embodiment of the present invention includes: the system comprises a knowledge graph establishing module 1, a database 2, a question input module 3, a word segmentation module 4, a retrieval module 5, a natural semantic processing module 6 and an answer output and display module 7.
Specifically, the knowledge graph establishing module 1 crawls data sources of all industry fields on the internet, respectively establishes a knowledge graph for each industry field, and stores the knowledge graph in the database 2. The database 2 stores a knowledge map. In one embodiment of the present invention, the database 2 is a SQL database or an Oracle database.
The knowledge graph establishing module 1 extracts the title and the text of each data from the data source of each industry field on the internet, which is obtained by crawling, then performs sentence splitting, filters the splitting result according to a preset filtering principle to remove redundant words, retains key information texts, performs semantic analysis according to the retained key information texts to obtain the field to which the data source belongs, and marks the field of the data source in the database 2 for subsequent query and use.
For example, the data sources of various industry fields on the internet that are obtained by crawling the knowledge-graph building module 1 include: enterprise official networks, industry portals, papers, technical specifications, etc. It should be noted that the crawled data source is not limited to the above example, and may also be other data sources, which are not described herein again.
The question input module 3 receives a natural language question input by a user. Specifically, the natural language question input by the user is in a text form or a speech form, and when the natural language question is in a language form, the question input module 3 performs character recognition processing on the speech to generate a corresponding text language.
Therefore, the invention supports the user to input the question sentence in the form of text or voice, so that the user can initiate the question by voice even under the condition that the user is inconvenient to input characters.
It should be noted that the question forms supported by the present application are not limited to the above, and may include pictures and short videos. And judging a question target of the user by identifying the entity characteristics in the picture or the short video, and generating a corresponding text form.
The word segmentation module 4 performs word segmentation operation on the natural language question by adopting a dictionary matching method or a word frequency statistical method, and extracts one or more keywords in the natural language question.
(1) Dictionary matching method: the dictionary method is that the words in the dictionary are searched one by one in the text, and the search hit is recorded as a word.
(2) Word frequency statistical method: the word frequency method does not depend on a dictionary, but calculates the frequency of simultaneous occurrence of any two words in the text for statistics, and the frequency calculation takes a large amount of natural texts as a corpus, and the probability that the words with high frequency of simultaneous occurrence become words is high. After word segmentation is finished, nonsense words such as auxiliary words, adverbs, connecting words and the like need to be removed, and the word segmentation is finished by depending on the conventional general dictionary. In addition, a self-defined dictionary needs to be established, and words with little meaning in an enterprise search environment are also removed.
The keywords extracted by the two methods are most sufficiently covered by effective information, and the subsequent retrieval precision is improved.
The retrieval module 5 judges the industry field to which the natural language question belongs according to the keywords, then selects the knowledge graph of the corresponding field in the database 2, and retrieves according to the keywords from the knowledge graph to generate a corresponding retrieval result. The retrieval module 5 retrieves in the knowledge graph according to the plurality of keywords and queries to obtain a plurality of retrieval results; and performing relevance sorting on the multiple search results, and outputting the search result with the highest relevance degree with the keywords as an answer to a user for viewing after natural language arrangement.
The invention adopts the following secondary retrieval steps: the industry field to which the natural language question belongs is positioned in the database 2 for the first time according to the keywords; and searching in the knowledge graph of the located industry field according to the keywords for the second time. The secondary retrieval mode can improve retrieval accuracy and retrieval efficiency.
And the natural semantic processing module 6 carries out natural semantic processing on the retrieval result. And the answer output and display module 7 outputs and displays the answer after the natural semantic processing to the user.
In an embodiment of the present invention, the answer output and display module 7 synchronously pushes the related domain information of the natural language question to the user under the output interface while outputting the answer to the user for viewing. The user clicks the interested information in the interface, and the output interface automatically pushes the detailed information related to the clicked content, so that the experience degree of the user can be greatly improved, and the viscosity of the user is increased.
According to the intelligent question-answering method and system based on the knowledge graph, the knowledge graph of each field is established, the received keywords in the natural language question of the user are utilized to perform query retrieval in the knowledge graph of the related field, the corresponding retrieval result is obtained through analysis, the retrieval result is subjected to relevance sequencing, and the most relevant result is output to the user as an answer. The invention establishes knowledge maps of various fields by crawling mass data, and has wide resource coverage. And extracting keywords through semantic analysis of the natural language question, firstly locking the knowledge graph of the related technical field according to the keywords, and then searching by using the keywords, wherein the secondary searching step can greatly improve the searching precision and the answer matching degree. In addition, the invention can push the information of the related field to the user while outputting the answer, thereby improving the user experience.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art without departing from the principle and spirit of the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. An intelligent question-answering method based on a knowledge graph is characterized by comprising the following steps:
step S1, crawling data sources of various industry fields on the Internet, respectively establishing a knowledge graph aiming at each industry field, and storing the knowledge graph in a database;
step S2, receiving a natural language question input by a user;
step S3, performing word segmentation operation on the natural language question by adopting a dictionary matching method or a word frequency statistical method, and extracting one or more keywords in the natural language question;
and step S4, judging the industry field to which the natural language question belongs according to the keywords obtained in the step S3, then selecting a knowledge graph of the corresponding field from the database, searching according to the keywords from the knowledge graph, generating a corresponding search result, performing natural semantic processing on the search result, outputting the result as an answer and displaying the answer to the user.
2. The intellectual question answering method based on the knowledge graph of claim 1, wherein in the step S1, establishing the knowledge graph comprises the following steps: the method comprises the steps of extracting the title and the text of each item of data from the data source of each industry field on the Internet, splitting sentences, filtering splitting results according to a preset filtering principle to remove redundant words, reserving key information texts, performing semantic analysis according to the reserved key information texts to obtain the field to which the data source belongs, and marking the field of the data source in the database for subsequent query and use.
3. The intellectual question answering method based on the knowledge graph of claim 1, wherein in the step S2, the natural language question input by the user is in a text form or a speech form, and when the natural language question is in a language form, the speech is subjected to a word recognition process to generate a corresponding text language.
4. The intellectual question answering method based on knowledge graph according to claim 1 wherein in step S4, the retrieving from the knowledge graph according to the keyword generates the corresponding retrieving result, including the following steps:
searching in the knowledge graph according to the plurality of key words, and inquiring to obtain a plurality of search results;
and performing relevance sequencing on the multiple search results, performing natural language sorting on the search result with the highest relevance degree with the keyword, and outputting the search result as an answer to a user for viewing.
5. The intellectual question answering method based on the knowledge graph according to claim 1 or 4 wherein in the step S4, the relevant domain information of the natural language question sentence is synchronously pushed to the user under the output interface while the answer is output to the user for viewing.
6. An intelligent question-answering system based on knowledge graph, which is characterized in that the system comprises:
the system comprises a knowledge graph establishing module, a database and a database, wherein the knowledge graph establishing module is used for crawling data sources of all industry fields on the Internet, respectively establishing a knowledge graph aiming at each industry field and storing the knowledge graph in the database;
a database for storing the knowledge-graph;
the question input module is used for receiving a natural language question input by a user;
the word segmentation module is used for performing word segmentation operation on the natural language question by adopting a dictionary matching method or a word frequency statistical method, and extracting one or more keywords in the natural language question;
the retrieval module is used for judging the industry field to which the natural language question belongs according to the key words, then selecting a knowledge graph of the corresponding field from the database, retrieving from the knowledge graph according to the key words and generating corresponding retrieval results;
the natural semantic processing module is used for carrying out natural semantic processing on the retrieval result;
and the answer output and display module is used for outputting and displaying the answer after the natural semantic processing to the user.
7. The intellectual question answering system based on the knowledge graph as claimed in claim 6, wherein the knowledge graph establishing module extracts the title and the text of each data from the crawled data sources of various industry fields on the internet, then performs sentence splitting, filters the splitting result according to a preset filtering principle to remove redundant words, retains key information texts, performs semantic analysis according to the retained key information texts to obtain the field to which the data source belongs, and marks the field of the data source in the database for subsequent query.
8. The intellectual question answering system based on the knowledge graph of claim 6, wherein the natural language question input by the user is in a text form or a voice form, and when the natural language question is in a language form, the question sentence input module performs character recognition processing on the voice to generate a corresponding text language.
9. The intellectual question answering system based on knowledge graph as claimed in claim 6, wherein the retrieval module retrieves in the knowledge graph according to a plurality of keywords, and queries to obtain a plurality of retrieval results; and performing relevance sequencing on the multiple search results, performing natural language sorting on the search result with the highest relevance degree with the keyword, and outputting the search result as an answer to a user for viewing.
10. The intellectual question answering system based on the knowledge graph of claim 6 or 9, wherein the answer outputting and displaying module synchronously pushes the relevant domain information of the natural language question to the user under an output interface while outputting the answer to the user for viewing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811520770.3A CN111309877A (en) | 2018-12-12 | 2018-12-12 | Intelligent question-answering method and system based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811520770.3A CN111309877A (en) | 2018-12-12 | 2018-12-12 | Intelligent question-answering method and system based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111309877A true CN111309877A (en) | 2020-06-19 |
Family
ID=71159638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811520770.3A Pending CN111309877A (en) | 2018-12-12 | 2018-12-12 | Intelligent question-answering method and system based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111309877A (en) |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753055A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | Automatic client question and answer prompting method and device |
| CN111800493A (en) * | 2020-06-29 | 2020-10-20 | 百度在线网络技术（北京）有限公司 | Information content pushing method and device, electronic equipment and storage medium |
| CN111813916A (en) * | 2020-07-21 | 2020-10-23 | 润联软件系统(深圳)有限公司 | Intelligent question and answer method, device, computer equipment and medium |
| CN111930911A (en) * | 2020-08-12 | 2020-11-13 | 杭州东方通信软件技术有限公司 | Rapid field question-answering method and device |
| CN111949774A (en) * | 2020-07-08 | 2020-11-17 | 深圳鹏锐信息技术股份有限公司 | Intelligent question answering method and system |
| CN111949855A (en) * | 2020-07-31 | 2020-11-17 | 国网上海市电力公司 | Knowledge map-based engineering technology knowledge retrieval platform and method thereof |
| CN112115234A (en) * | 2020-09-28 | 2020-12-22 | 中国银行股份有限公司 | Question bank analysis method and device |
| CN112231459A (en) * | 2020-10-27 | 2021-01-15 | 恩亿科(北京)数据科技有限公司 | Method and system for realizing intelligent question answering of software test based on knowledge graph |
| CN112328808A (en) * | 2020-11-03 | 2021-02-05 | 四川长虹电器股份有限公司 | Knowledge graph-based question and answer method and device, electronic equipment and storage medium |
| CN112380848A (en) * | 2020-11-19 | 2021-02-19 | 平安科技（深圳）有限公司 | Text generation method, device, equipment and storage medium |
| CN112507105A (en) * | 2021-01-26 | 2021-03-16 | 王三山 | Multi-mode intelligent question-answering system and method based on WeChat public number |
| CN112528041A (en) * | 2020-12-17 | 2021-03-19 | 贵州电网有限责任公司 | Scheduling phrase specification verification method based on knowledge graph |
| CN112597285A (en) * | 2020-12-10 | 2021-04-02 | 太极计算机股份有限公司 | Man-machine interaction method and system based on knowledge graph |
| CN112667773A (en) * | 2020-12-23 | 2021-04-16 | 医渡云（北京）技术有限公司 | Data acquisition method based on knowledge graph and related equipment |
| CN112685545A (en) * | 2020-12-29 | 2021-04-20 | 浙江力石科技股份有限公司 | Intelligent voice interaction method and system based on multi-core word matching |
| CN112836067A (en) * | 2021-03-16 | 2021-05-25 | 上海适享文化传播有限公司 | Intelligent searching method based on knowledge graph |
| CN112991545A (en) * | 2021-04-22 | 2021-06-18 | 苏州科嘉智能科技有限公司 | Visual voice interaction operation and maintenance management platform |
| CN112989029A (en) * | 2021-03-09 | 2021-06-18 | 上海魔橙网络科技有限公司 | Method, system, device and medium for realizing visual quick retrieval of knowledge map |
| CN112989009A (en) * | 2021-04-22 | 2021-06-18 | 苏州科嘉智能科技有限公司 | Intelligent question-answering system based on knowledge graph |
| CN113434645A (en) * | 2021-05-26 | 2021-09-24 | 上海声通信息科技股份有限公司 | Financial product intelligence customer service system |
| CN113486137A (en) * | 2021-06-07 | 2021-10-08 | 广发银行股份有限公司 | Construction method and system of linguistic data of question-answering robot of bank performance system |
| CN113590797A (en) * | 2021-08-05 | 2021-11-02 | 云上贵州大数据产业发展有限公司 | Intelligent operation and maintenance customer service system and implementation method |
| CN113672699A (en) * | 2021-08-12 | 2021-11-19 | 国家电网有限公司大数据中心 | Knowledge graph-based NL2SQL generation method |
| CN113987146A (en) * | 2021-10-22 | 2022-01-28 | 国网江苏省电力有限公司镇江供电分公司 | Dedicated novel intelligence of electric power intranet system of asking for answering |
| CN114490982A (en) * | 2022-01-21 | 2022-05-13 | 青岛文达通科技股份有限公司 | Intelligent community question-answering method and system based on wavelet transformation and knowledge graph reasoning |
| CN114510558A (en) * | 2022-01-26 | 2022-05-17 | 北京博瑞彤芸科技股份有限公司 | Question-answering method and system based on traditional Chinese medicine knowledge graph |
| CN114647718A (en) * | 2020-12-18 | 2022-06-21 | 北京金山数字娱乐科技有限公司 | Question-answering method and device based on knowledge graph |
| CN114764433A (en) * | 2020-12-30 | 2022-07-19 | 北京千里日成科技有限公司 | Information searching method and device, electronic equipment and storage medium |
| CN116455861A (en) * | 2023-04-17 | 2023-07-18 | 江苏鑫翊翔智能化工程有限公司 | Big data-based computer network security monitoring system and method |
| CN117591658A (en) * | 2024-01-17 | 2024-02-23 | 翌东寰球(深圳)数字科技有限公司 | Intelligent question-answering method, device, equipment and storage medium |
| CN117648926A (en) * | 2024-01-30 | 2024-03-05 | 北京数语科技有限公司 | Method and system for automatically creating data model based on natural language |
| CN118116620A (en) * | 2024-04-28 | 2024-05-31 | 支付宝(杭州)信息技术有限公司 | Medical question answering method and device and electronic equipment |
-
2018
- 2018-12-12 CN CN201811520770.3A patent/CN111309877A/en active Pending
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753055A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | Automatic client question and answer prompting method and device |
| CN111753055B (en) * | 2020-06-28 | 2024-01-26 | 中国银行股份有限公司 | Automatic prompt method and device for customer questions and answers |
| CN111800493A (en) * | 2020-06-29 | 2020-10-20 | 百度在线网络技术（北京）有限公司 | Information content pushing method and device, electronic equipment and storage medium |
| CN111800493B (en) * | 2020-06-29 | 2023-07-28 | 百度在线网络技术（北京）有限公司 | Information content pushing method, information content pushing device, electronic equipment and storage medium |
| CN111949774A (en) * | 2020-07-08 | 2020-11-17 | 深圳鹏锐信息技术股份有限公司 | Intelligent question answering method and system |
| CN111813916A (en) * | 2020-07-21 | 2020-10-23 | 润联软件系统(深圳)有限公司 | Intelligent question and answer method, device, computer equipment and medium |
| CN111813916B (en) * | 2020-07-21 | 2024-03-05 | 华润数字科技有限公司 | Intelligent question-answering method, device, computer equipment and medium |
| CN111949855A (en) * | 2020-07-31 | 2020-11-17 | 国网上海市电力公司 | Knowledge map-based engineering technology knowledge retrieval platform and method thereof |
| CN111949855B (en) * | 2020-07-31 | 2024-11-01 | 国网上海市电力公司 | Knowledge graph-based engineering technology warp knowledge retrieval platform and method thereof |
| CN111930911A (en) * | 2020-08-12 | 2020-11-13 | 杭州东方通信软件技术有限公司 | Rapid field question-answering method and device |
| CN111930911B (en) * | 2020-08-12 | 2024-03-29 | 杭州东方通信软件技术有限公司 | Rapid field question-answering method and device thereof |
| CN112115234A (en) * | 2020-09-28 | 2020-12-22 | 中国银行股份有限公司 | Question bank analysis method and device |
| CN112231459A (en) * | 2020-10-27 | 2021-01-15 | 恩亿科(北京)数据科技有限公司 | Method and system for realizing intelligent question answering of software test based on knowledge graph |
| CN112328808A (en) * | 2020-11-03 | 2021-02-05 | 四川长虹电器股份有限公司 | Knowledge graph-based question and answer method and device, electronic equipment and storage medium |
| CN112380848B (en) * | 2020-11-19 | 2022-04-26 | 平安科技（深圳）有限公司 | Text generation method, device, equipment and storage medium |
| CN112380848A (en) * | 2020-11-19 | 2021-02-19 | 平安科技（深圳）有限公司 | Text generation method, device, equipment and storage medium |
| CN112597285B (en) * | 2020-12-10 | 2021-08-10 | 太极计算机股份有限公司 | Man-machine interaction method and system based on knowledge graph |
| CN112597285A (en) * | 2020-12-10 | 2021-04-02 | 太极计算机股份有限公司 | Man-machine interaction method and system based on knowledge graph |
| CN112528041A (en) * | 2020-12-17 | 2021-03-19 | 贵州电网有限责任公司 | Scheduling phrase specification verification method based on knowledge graph |
| CN114647718A (en) * | 2020-12-18 | 2022-06-21 | 北京金山数字娱乐科技有限公司 | Question-answering method and device based on knowledge graph |
| CN112667773A (en) * | 2020-12-23 | 2021-04-16 | 医渡云（北京）技术有限公司 | Data acquisition method based on knowledge graph and related equipment |
| CN112685545A (en) * | 2020-12-29 | 2021-04-20 | 浙江力石科技股份有限公司 | Intelligent voice interaction method and system based on multi-core word matching |
| CN114764433A (en) * | 2020-12-30 | 2022-07-19 | 北京千里日成科技有限公司 | Information searching method and device, electronic equipment and storage medium |
| CN112507105A (en) * | 2021-01-26 | 2021-03-16 | 王三山 | Multi-mode intelligent question-answering system and method based on WeChat public number |
| CN112989029A (en) * | 2021-03-09 | 2021-06-18 | 上海魔橙网络科技有限公司 | Method, system, device and medium for realizing visual quick retrieval of knowledge map |
| CN112836067A (en) * | 2021-03-16 | 2021-05-25 | 上海适享文化传播有限公司 | Intelligent searching method based on knowledge graph |
| CN112836067B (en) * | 2021-03-16 | 2023-12-12 | 上海适享文化传播有限公司 | Intelligent searching method based on knowledge graph |
| CN112989009A (en) * | 2021-04-22 | 2021-06-18 | 苏州科嘉智能科技有限公司 | Intelligent question-answering system based on knowledge graph |
| CN112991545A (en) * | 2021-04-22 | 2021-06-18 | 苏州科嘉智能科技有限公司 | Visual voice interaction operation and maintenance management platform |
| CN113434645A (en) * | 2021-05-26 | 2021-09-24 | 上海声通信息科技股份有限公司 | Financial product intelligence customer service system |
| CN113486137A (en) * | 2021-06-07 | 2021-10-08 | 广发银行股份有限公司 | Construction method and system of linguistic data of question-answering robot of bank performance system |
| CN113590797A (en) * | 2021-08-05 | 2021-11-02 | 云上贵州大数据产业发展有限公司 | Intelligent operation and maintenance customer service system and implementation method |
| CN113672699A (en) * | 2021-08-12 | 2021-11-19 | 国家电网有限公司大数据中心 | Knowledge graph-based NL2SQL generation method |
| CN113987146B (en) * | 2021-10-22 | 2023-01-31 | 国网江苏省电力有限公司镇江供电分公司 | Dedicated intelligent question-answering system of electric power intranet |
| CN113987146A (en) * | 2021-10-22 | 2022-01-28 | 国网江苏省电力有限公司镇江供电分公司 | Dedicated novel intelligence of electric power intranet system of asking for answering |
| CN114490982A (en) * | 2022-01-21 | 2022-05-13 | 青岛文达通科技股份有限公司 | Intelligent community question-answering method and system based on wavelet transformation and knowledge graph reasoning |
| CN114510558A (en) * | 2022-01-26 | 2022-05-17 | 北京博瑞彤芸科技股份有限公司 | Question-answering method and system based on traditional Chinese medicine knowledge graph |
| CN116455861B (en) * | 2023-04-17 | 2023-11-24 | 福建数智闽政科技有限公司 | Big data-based computer network security monitoring system and method |
| CN116455861A (en) * | 2023-04-17 | 2023-07-18 | 江苏鑫翊翔智能化工程有限公司 | Big data-based computer network security monitoring system and method |
| CN117591658A (en) * | 2024-01-17 | 2024-02-23 | 翌东寰球(深圳)数字科技有限公司 | Intelligent question-answering method, device, equipment and storage medium |
| CN117591658B (en) * | 2024-01-17 | 2024-03-29 | 翌东寰球(深圳)数字科技有限公司 | Intelligent question-answering method, device, equipment and storage medium |
| CN117648926A (en) * | 2024-01-30 | 2024-03-05 | 北京数语科技有限公司 | Method and system for automatically creating data model based on natural language |
| CN118116620A (en) * | 2024-04-28 | 2024-05-31 | 支付宝(杭州)信息技术有限公司 | Medical question answering method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111309877A (en) | Intelligent question-answering method and system based on knowledge graph | |
| CN107451153B (en) | Method and device for outputting structured query statement | |
| CN106649778B (en) | Interaction method and device based on deep question answering | |
| CN105955976B (en) | A kind of automatic answering system and method | |
| CN103678576B (en) | The text retrieval system analyzed based on dynamic semantics | |
| US8250074B2 (en) | Document processing system and method thereof | |
| CN110929125B (en) | Search recall method, device, equipment and storage medium thereof | |
| CN106708940B (en) | Method and device for processing pictures | |
| CN110750995B (en) | File management method based on custom map | |
| US9798776B2 (en) | Systems and methods for parsing search queries | |
| KR20080114764A (en) | System and method for identifying related queries for languages with multiple writing systems | |
| CN102968987A (en) | Speech recognition method and system | |
| CN108121715B (en) | Character labeling method and character labeling device | |
| EP4187400A1 (en) | Method for converting natural language query to sql and device thereof | |
| JP2002132812A (en) | Method and system for answering question and recording medium with recorded question answering program | |
| US20150206101A1 (en) | System for determining infringement of copyright based on the text reference point and method thereof | |
| US11487795B2 (en) | Template-based automatic software bug question and answer method | |
| CN106599215A (en) | Question generation method and question generation system based on deep learning | |
| CN111160007B (en) | Search method and device based on BERT language model, computer equipment and storage medium | |
| CN116738065B (en) | Enterprise searching method, device, equipment and storage medium | |
| CN112015907A (en) | Method and device for quickly constructing discipline knowledge graph and storage medium | |
| CN112711716A (en) | Knowledge graph-based marine industry news pushing method and system | |
| CN113177061A (en) | Searching method and device and electronic equipment | |
| CN111966899A (en) | Search ranking method, system and computer readable storage medium | |
| CN108733848B (en) | Knowledge searching method and system |
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 |