CN114547342A - College professional intelligent question-answering system and method based on knowledge graph - Google Patents
College professional intelligent question-answering system and method based on knowledge graph Download PDFInfo
- Publication number
- CN114547342A CN114547342A CN202210188960.XA CN202210188960A CN114547342A CN 114547342 A CN114547342 A CN 114547342A CN 202210188960 A CN202210188960 A CN 202210188960A CN 114547342 A CN114547342 A CN 114547342A
- Authority
- CN
- China
- Prior art keywords
- professional
- question
- colleges
- universities
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000010276 construction Methods 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims description 15
- 230000009193 crawling Effects 0.000 claims description 12
- 238000007635 classification algorithm Methods 0.000 claims description 8
- 238000013500 data storage Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 claims 1
- 238000013467 fragmentation Methods 0.000 abstract 1
- 238000006062 fragmentation reaction Methods 0.000 abstract 1
- 238000007726 management method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
Abstract
The invention relates to a knowledge graph-based professional question-answering system for colleges and universities, which comprises a knowledge graph construction module, a problem classification module, a database query module and a result feedback module. A college professional question-answering method based on a knowledge graph comprises the following steps: s1, collecting professional information of each college and university, and constructing a professional knowledge map of the college and university; s2, acquiring and analyzing a user query text, identifying a keyword and judging a problem type; s3, selecting a structured template corresponding to the problem type, generating a structured statement by combining the keyword, and inquiring to obtain a related result; and S4, integrating the retrieval result, generating a reply sentence, and feeding the reply sentence back to the user. The invention mainly aims at the problems of fragmentation, low efficiency and the like of professional information inquiry of examinees in the process of college entrance examination submission, integrates the professional information of colleges and universities, and effectively improves the accuracy of searching professional knowledge answers of colleges and universities.
Description
Technical Field
The invention belongs to the field of artificial intelligence and machine learning, and particularly relates to a college professional intelligent question-answering system based on a knowledge graph and a method thereof.
Background
Along with the improvement of education level, the number of college entrance examination people is high in innovation frequently, people are more and more applied to the Internet, and professional big data of colleges and universities gradually enter the daily life of people. How to analyze data with large volume and complex structure and obtain information beneficial to examinee examination professions is the key of the practical application of professional big data of colleges and universities. The professional question-answering system in colleges and universities aims to answer the personalized questions of each examinee and help the examinee to acquire the required information. The knowledge map stores and processes data in a map structure form, and can extract useful information from massive data to effectively process massive professional data of colleges and universities. At present, some portal websites cannot provide answers with strong pertinence to personalized questions put forward by users, and the professional question-answering system of colleges and universities can solve the problems.
The existing question-answering system can only inquire according to the key words input by the user, cannot realize the identification and search of the natural language input by the user, has low intelligent degree, one-sided query result, low accuracy rate of matching with the question and no question answering. The invention constructs an intelligent question-answering system in the vertical field based on the knowledge map, fully and reasonably arranges fragmented knowledge in the field together to form a large semantic web, defines query sentences based on the Chinese word segmentation method and technology of HanLP for loading the self-defined dictionary, more quickly and accurately segments personalized problems of users, and improves the accuracy and reliability of word segmentation results.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a college professional intelligent question-answering system and method combining a knowledge map technology and a naive Bayes classification algorithm, helps a user to intelligently ask and answer between the profession and 11 attributes related to the profession through the established artificial intelligent question-answering system, provides a new way for college entrance examination filling, meets the requirements of examinee personalized problems, and improves the user experience.
The purpose of the invention can be realized by the following technical scheme:
a college professional intelligent question-answering system and method based on a knowledge graph comprises a knowledge graph construction module, a problem classification module, a database query module and a result feedback module:
the knowledge map construction module is used for constructing a professional knowledge map of colleges and universities according to data acquired by the vertical website of Chinese education online;
the question classification module is used for acquiring a question text input by a user and identifying a named entity and a question type of a question of the user, wherein the question types are 16 types and are divided by the user according to a questionnaire survey result in advance;
the database query module is used for converting the results of the problem classification and the identified keywords into corresponding graph database query sentences according to the results and the identified keywords, and sending the graph database query sentences into the database to query and obtain results;
and the result feedback module is used for sorting the returned results, assembling the query contents into answers conforming to the natural language and displaying the answers on the front-end dialog box.
Preferably, the knowledge graph building module comprises a professional data crawling unit, a structure adjusting unit and a professional data storage unit;
the professional data crawling unit is used for crawling text data of the webpage-side Chinese education online website and transmitting the text data to the structure adjusting unit;
the structure adjusting unit is used for sorting the text data obtained by the professional data crawling unit, converting the text data according to a format required by the database, and mapping the text data into a subject to which a specialty belongs, a professional name, a professional course, a working direction, a high school related course, six major entities of professional popular colleges and universities and six professional attributes;
the professional data storage unit is used for creating the relationship among the entities, the entity attributes and the entities, storing the json data which are arranged as required according to the < entity, relationship and entity > triple, and generating the professional knowledge map of colleges and universities.
Preferably, the problem classification module comprises a keyword recognition unit and a problem type judgment unit;
the recognition keyword unit is used for recognizing a named entity in the question, and performing word segmentation and part-of-speech tagging on the question by adopting a HanLP tool when analyzing the question of the user;
and the problem type judging unit is used for identifying the problem type input by the user, classifying the problem by using a pre-trained naive Bayes classification algorithm and acquiring the problem label of the problem.
Preferably, the system further comprises a database query module, wherein the database query module is used for receiving the data of the problem classification module, generating a corresponding structured statement according to the problem type and the keyword, converting the structured statement into a corresponding database query language, and querying a result in the professional knowledge map of colleges and universities.
A college professional intelligent question-answering method based on a knowledge graph comprises the following steps:
s1, collecting professional information of each college and university, and constructing a professional knowledge map of the college and university;
s2, acquiring and analyzing a user query text, identifying a keyword and judging a problem type;
s3, selecting a structured template corresponding to the problem type, generating a structured statement by combining the keyword, and inquiring to obtain a related result;
and S4, integrating the retrieval result, generating a reply sentence, and feeding the reply sentence back to the user.
Specifically, the construction of the high school expertise map in step S1 specifically includes the following steps:
s1.1, collecting professional information, sorting and extracting available knowledge units to form structured data, and mainly comprising the following steps: subject to which the specialty belongs, professional name, professional ID, professional age, professional description, work direction, high school related course, male and female proportion, literary proportion, examination related direction, professional course and professional popular college information;
s1.2, mapping professional information of colleges and universities into entities and professional attributes, determining the relationship among the entities, and forming a triple of < entities, relationship, entity >;
s1.3, according to the structured json data, a professional knowledge map of colleges and universities integrating professional related data information of 'new workshops, new medical departments, new agricultural departments and new cultural departments' is constructed.
The process of S2 is:
s2.1, obtaining a user question text, performing word segmentation and word annotation on a user question based on a HanLP tool, and identifying keywords in the question text;
s2.2 the problem is classified using a pre-trained naive Bayes classification algorithm.
The process of S3 is:
s3.1, calling a corresponding structured problem template, matching the extracted keywords with the problem template, and generating a retrieval statement in a knowledge graph library;
and S3.2, acquiring a query result in the professional knowledge map of the colleges and universities.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method utilizes a design technology of integrating massive text collection and lightweight visual crawler, selects a Neo4j graphic database as a storage medium, carries out certain carding and integration on a large amount of complex, disordered and unrelated professional data, constructs a unique college professional knowledge map platform in China, covers all 726 specialties of 'new workshops, new medical departments, new agricultural departments and new cultural departments', and realizes integration and relevance analysis of college professional data resources;
(2) by combining the knowledge graph and the Bayesian classification algorithm, the invention supports question answering of 16 major questions at present, and can quickly and accurately identify the personalized questions of the user;
(3) the invention changes the traditional search input limitation, can support the question asking of any professional related problem, and supports examinee and examinee parents to acquire professional information anytime and anywhere.
Drawings
FIG. 1 is a schematic diagram of the overall structure of the professional question-answering system of colleges and universities according to the present invention.
FIG. 2 is a schematic overall flow chart of the professional question-answering method in colleges and universities according to the present invention.
FIG. 3 is a schematic diagram of an example of a portion of a professional knowledge graph constructed in accordance with the present invention in a college.
FIG. 4 is a schematic diagram of an answer retrieval process of the professional question-answering system of colleges and universities according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, a knowledge-graph-based professional question-answering system for colleges and universities comprises a knowledge-graph construction module, a question classification module, a database query module and a result feedback module;
the knowledge map construction module is used for constructing a professional knowledge map of colleges and universities according to data acquired by the vertical website of Chinese education online;
the question classification module is used for acquiring a question text input by a user and identifying a named entity and a question type of a question of the user, wherein the question type has 16 types, such as what work a certain professional does, what courses a certain professional learns, what specialties exist under a certain subject and the like, and the question classification module is formed by dividing the question text according to questionnaire survey results in advance;
the database query module is used for converting the results of the problem classification and the recognized keywords into corresponding graph database query sentences and sending the graph database query sentences into a database query acquisition result;
and the result feedback module is used for sorting the returned results, assembling the query contents into answers conforming to the natural language and displaying the answers on the front-end dialog box.
Preferably, the knowledge graph building module comprises a professional data crawling unit, a structure adjusting unit and a professional data storage unit;
the professional data crawling unit is used for crawling text data of the webpage-side Chinese education online website and transmitting the text data to the structure adjusting unit;
the structure adjusting unit is used for sorting the text data obtained by the professional data crawling unit, converting the text data according to a format required by the database, and mapping the text data into a subject to which a specialty belongs, a professional name, a professional course, a working direction, a high school related course, six major entities of professional popular colleges and universities and six professional attributes;
the professional data storage unit is used for creating the relationship among the entities, the entity attributes and the entities, storing the json data which are arranged as required according to the < entity, relationship and entity > triple, and generating the professional knowledge map of colleges and universities.
Preferably, the problem classification module comprises a keyword recognition unit and a problem type judgment unit;
the recognition keyword unit is used for recognizing named entities in the question, and when the user question is analyzed, the HanLP tool is used for carrying out word segmentation and part-of-speech tagging on the question, wherein the words in the six entities are respectively provided with parts-of-speech, for example, the part-of-speech of the words in the professional name is 'ma', the part-of-speech of the words in the professional course is 'co', and the like;
the problem type judging unit is used for identifying the type of the problem input by the user, classifying the problem by using a pre-trained naive Bayes classification algorithm, acquiring a problem label of the problem, taking the question text input by the user as an example of managing which courses are scientifically learned, judging the problem as a course under the specialty by the classifier, and setting the label as 2.
Preferably, the system further comprises a database query module, wherein the database query module is used for receiving the data of the problem classification module, generating a corresponding structured statement according to the problem type and the keyword, converting the structured statement into a corresponding database query language, and querying a result in the professional knowledge map of colleges and universities.
As shown in fig. 2, a knowledge graph-based professional question-answering method for colleges and universities includes the following steps:
s1, collecting related professional information (including professional introduction, courses, belonged subject, male and female proportion, literary proportion, working direction, popular colleges and universities and the like) from an online education website, and converting the acquired professional information into structured knowledge through data cleaning and processing to construct a professional knowledge map of colleges and universities for supporting question answer retrieval;
s2, for the question input by the user, performing word segmentation and part-of-speech tagging on the question by using a HanLP word segmentation tool, identifying keywords in the sentence, and classifying the question by using a trained naive Bayes classifier;
s3, according to the classification result of the problem, applying a corresponding structured problem template to generate a structured statement, converting the structured statement into an inquiry statement in a college professional knowledge map library, and acquiring an inquiry result;
and S4, integrating the answers retrieved from the professional knowledge map library of colleges and universities, and feeding back the answers to the user in a text form.
The step S1 specifically includes:
s1.1, crawler operation is carried out on professional information through the vertical website of Chinese education online, data related to all the professions are collected, available knowledge units are sorted and extracted, and json structured data are formed. Finally obtaining 726 major numbers and 12 major attributes, wherein the major numbers respectively comprise subject of major, major name, major ID, major age, major description, working direction, high school related course, male and female proportion, literary proportion, examination related direction, major course and major hot colleges;
s1.2, mapping professional information of colleges and universities into entities and professional attributes, and determining the relationship among the entities. The method comprises the following steps of determining the relationship between a professional name and other five entities by taking a subject to which a profession belongs, the professional name, a professional course, a working direction, a related course in high school and a related college in profession as six entities, taking a professional ID, a professional age, a professional description, a male and female proportion, a literary proportion and a related direction of study as six attributes of the profession, taking the professional name as a link, and respectively defining the relationship between the professional name and other five entities as belong _ to, lean _ court, get _ job, related _ to and hot _ unev;
s1.3, selecting a Neo4j graphic database as a storage medium, and constructing the acquired professional information into a professional knowledge map of colleges and universities. The knowledge graph consists of a plurality of triples < h, r and t >, wherein h is a head entity and is a professional name, t is a tail entity and is a subject to which the profession belongs, a professional course, a working direction, a high school related course and a professional hot university, and r is the relationship between the head entity h and the tail entity t and is the five major relationships defined in the step S1.1. Taking philosophy and logistical specialties as an example, as shown in fig. 3, different colors represent different entities and relationships. The following two major categories belong to philosophy, curriculums to be learned by the logic science comprise set theory, logic philosophy, application logic and the like, the future working direction is deep research or education training, and the popular university comprises Zhongshan university and Beijing university.
As shown in fig. 4, the step S2 specifically includes:
s2.1, natural language question sentences input by a user side are obtained, and word segmentation and part-of-speech tagging are carried out on the question sentences by adopting a HanLP tool. Specifically, in the process of constructing the professional knowledge map in step S1.2, six entity files containing each entity value are generated, for example, 726 professional names in the major text file are generated, and the part of speech of the word in the file is set to ma, and the part of speech of the word is added to the HanLP word segmentation process so as to identify the professional names during word segmentation. Similar part-of-speech settings are also respectively carried out on the words in the other five entities, so that the entities can be identified from the sentences as keywords during word segmentation;
and S2.2, classifying the problems by using a trained naive Bayes classification algorithm to obtain problem labels of the problems, wherein the texts and the labels of a training set of the naive Bayes classifier are artificially determined. We make a questionnaire of 'what questions related to the specialty you would ask if you were a college student and faced with the problem of selecting the specialty at college', and classify and summarize the questionnaire results in detail, and finally obtain that the three questions in front of the number of people asked are the employment of a specialty, the course of learning of a specialty, the brief introduction of a specialty, and then the question of the specialty such as the direction of investigation, the proportion of male and female, the proportion of literature, and the hot colleges. Based on this, we set 16 classes of questions, determine the training set from the question text collected in the questionnaire, and the question labels are represented by 0-15, which are used to train the naive bayes classifier. Taking the example of the user inputting the question text "what is the science of management", the classifier judges it as a professional introduction, and the label is 0.
As shown in fig. 4, the step S3 specifically includes:
and S3.1, matching the extracted keywords with the question template according to the structured question template corresponding to the label, so as to generate a structured statement, and further converting the structured statement into a query statement. For example, the template of the structured question of question 0 (professional introduction) is 'ma introduction', the professional name 'management science' extracted from the text of the user question is replaced by ma in the template to generate the structured sentence 'management science introduction', and then the structured sentence 'management science introduction' is converted into a Neo4j query sentence.
And S3.2, acquiring a query result from the professional knowledge map of the colleges and universities.
The embodiments of the present invention have been described in detail, and various changes and modifications can be made by workers skilled in the art without departing from the scope of the present invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (9)
1. The college professional intelligent question-answering system based on the knowledge graph is characterized by comprising a knowledge graph construction module, a problem classification module, a database query module and a result feedback module:
the knowledge map construction module is used for constructing a professional knowledge map of colleges and universities according to data acquired by the vertical website of Chinese education online;
the question classification module is used for analyzing a user query sentence, performing word segmentation and part-of-speech tagging on the query sentence through a HanLP tool so as to identify a keyword of the sentence, and classifying the sentence by using a pre-trained naive Bayes classification algorithm;
the database query module matches the extracted keywords with the problem template according to the structured problem template corresponding to the label to generate a structured statement, and then converts the structured statement into a corresponding database query statement;
and the result feedback module is used for displaying a front-end chat interface, integrating the retrieval answers, generating a reasonable and natural reply sentence and displaying the sentence to the user.
2. The intellectual question answering system based on knowledge graph in colleges and universities of claim 1 is characterized in that the knowledge graph building module comprises a professional data crawling unit, a structure adjusting unit and a professional data storage unit;
the professional data crawling unit is used for crawling the text data of the vertical website of the Chinese education online and transmitting the text data to the structure adjusting unit;
the structure adjusting unit is used for sorting text data obtained by the professional data crawling unit of colleges and universities, extracting available cells, forming json structured data and storing the json structured data in a database for subsequent analysis;
and the professional data storage unit is used for setting entities and professional attributes, determining the relationship among the entities, storing the sorted data through a Neo4j graphic database, and generating a professional knowledge map of colleges and universities.
3. The intellectual property map based professional intelligent question answering system for colleges and universities as claimed in claim 1 or 2, wherein the question classification module comprises a question recognition keyword unit and a question category judgment unit;
the question keyword recognition unit is used for performing word segmentation and part-of-speech tagging by a HanLP word segmentation tool when analyzing a user sentence, so as to recognize an entity from the sentence as a keyword;
the problem category judging unit is used for identifying problem categories, classifying the problems by using a pre-trained naive Bayes algorithm and obtaining problem labels, for this purpose, the system sets 16 types of problems in total, and the problem labels are represented by 0-15.
4. The intellectual question answering system based on knowledge graph in colleges and universities as claimed in claim 1 or 2, wherein the system further comprises a database query module for converting the data of the question classification module into corresponding database query language.
5. The college professional intelligent question-answering system based on the knowledge graph as claimed in claim 1 or 2, wherein the system further comprises a result feedback module for displaying college professional query results, the front end of the system is a chat room interface, and answers are displayed in a text form.
6. A method for realizing a professional intelligent question-answering system of colleges and universities based on knowledge graphs is characterized by comprising the following steps:
s1, collecting professional information of each college and university, and constructing a professional knowledge map of the college and university;
s2, acquiring and analyzing a user query text, identifying a keyword and judging a problem type;
s3, selecting a structured template corresponding to the problem type, generating a structured statement by combining the keyword, and inquiring to obtain a related result;
and S4, integrating the retrieval result, generating a reply sentence, and feeding the reply sentence back to the user.
7. The method according to claim 6, wherein in the step of S1, the step of constructing the professional knowledge map of colleges and universities is: s1.1, collecting professional information, sorting and extracting available knowledge units to form structured data;
s1.2, mapping professional information of colleges and universities into professional entities and attributes thereof;
s1.3, constructing a professional knowledge map of colleges and universities integrating professional related data information of 'new workshops, new medical departments, new agricultural departments and new cultural departments'.
8. The method of claim 6, wherein the process of S2 is:
s2.1, obtaining a user question text, performing word segmentation and word annotation on a user question based on a HanLP tool, and identifying keywords in the question text;
s2.2 the problem is classified using a pre-trained naive Bayes classification algorithm.
9. The method of claim 6, wherein the process of S3 is:
s3.1, calling a corresponding structured problem template, matching the extracted keywords with the problem template, and generating a retrieval statement in a knowledge graph library;
and S3.2, acquiring a query result in the professional knowledge map of the colleges and universities.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210188960.XA CN114547342A (en) | 2022-02-28 | 2022-02-28 | College professional intelligent question-answering system and method based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210188960.XA CN114547342A (en) | 2022-02-28 | 2022-02-28 | College professional intelligent question-answering system and method based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114547342A true CN114547342A (en) | 2022-05-27 |
Family
ID=81660990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210188960.XA Pending CN114547342A (en) | 2022-02-28 | 2022-02-28 | College professional intelligent question-answering system and method based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114547342A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117271741A (en) * | 2023-10-11 | 2023-12-22 | 北京邮电大学 | College professional information recommendation system and method based on large model driving |
-
2022
- 2022-02-28 CN CN202210188960.XA patent/CN114547342A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117271741A (en) * | 2023-10-11 | 2023-12-22 | 北京邮电大学 | College professional information recommendation system and method based on large model driving |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110765257B (en) | Intelligent consulting system of law of knowledge map driving type | |
| CN110399457B (en) | Intelligent question answering method and system | |
| CN110990590A (en) | Dynamic financial knowledge map construction method based on reinforcement learning and transfer learning | |
| CN111475623A (en) | Case information semantic retrieval method and device based on knowledge graph | |
| CN109947921B (en) | Intelligent question-answering system based on natural language processing | |
| CN112148851A (en) | Construction method of medicine knowledge question-answering system based on knowledge graph | |
| WO2021213314A1 (en) | Data processing method and device, and computer readable storage medium | |
| CN102663129A (en) | Medical field deep question and answer method and medical retrieval system | |
| CN113569023A (en) | Chinese medicine question-answering system and method based on knowledge graph | |
| US7478192B2 (en) | Network of networks of associative memory networks | |
| CN112069327B (en) | Knowledge graph construction method and system for online education classroom teaching resources | |
| CN113673943B (en) | Personnel exemption aided decision making method and system based on historical big data | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| CN115270738A (en) | Method and system for generating newspaper and computer storage medium | |
| CN111524578A (en) | Psychological assessment device, method and system based on electronic psychological sand table | |
| CN112445894A (en) | Business intelligent system based on artificial intelligence and analysis method thereof | |
| CN114036281A (en) | Citrus control question-answering module construction method based on knowledge graph and question-answering system | |
| CN112926325A (en) | Chinese character relation extraction construction method based on BERT neural network | |
| CN115840805A (en) | Method for constructing intelligent question-answering system based on knowledge graph of computer science | |
| CN114547342A (en) | College professional intelligent question-answering system and method based on knowledge graph | |
| CN111125145A (en) | Automatic system for acquiring database information through natural language | |
| CN109766442A (en) | A kind of couple of user takes down notes the method and system classified | |
| CN117216221A (en) | Intelligent question-answering system based on knowledge graph and construction method | |
| CN113392183A (en) | Characterization and calculation method of children domain map knowledge | |
| CN116244277A (en) | NLP (non-linear point) identification and knowledge base construction 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 |