CN111046272A - Intelligent question-answering system based on medical knowledge map - Google Patents
Intelligent question-answering system based on medical knowledge map Download PDFInfo
- Publication number
- CN111046272A CN111046272A CN201911055172.8A CN201911055172A CN111046272A CN 111046272 A CN111046272 A CN 111046272A CN 201911055172 A CN201911055172 A CN 201911055172A CN 111046272 A CN111046272 A CN 111046272A
- Authority
- CN
- China
- Prior art keywords
- intelligent question
- medicine
- medical knowledge
- knowledge graph
- answering system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Medicinal Chemistry (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides an intelligent question-answering system based on a medical knowledge graph. The system comprises a medicine knowledge map, a medicine knowledge card, a natural language processing unit, a blind area processing unit, a medicine recommendation interface, an input interface and an intelligent question and answer processor; the medicine knowledge graph and the medicine knowledge card are obtained through common medical data extraction, the input interface sends information input by a user to the natural language processing unit to extract key information, the intelligent question and answer processor compares the information input by the user in the medicine knowledge graph and the medicine knowledge card through the key information and determines recommended medicines by combining with data of the blind area processing unit, and the medicine recommendation interface is used for displaying the recommended medicines. The intelligent question-answering system adopts natural language processing, utilizes a network data source to inquire medicines, and adopts a mode of combining a map and a knowledge card, so that the misunderstanding of the semanteme is reduced, and the readability of a diagnosis result is improved.
Description
Technical Field
The invention relates to the field of internet diagnosis and treatment, in particular to an intelligent question-answering system based on a medical knowledge graph.
Background
The internet diagnosis and treatment can make patients diagnose the basic illness state without going out of home and registering, and has high practical value. However, the difficulty of accurate internet diagnosis and treatment is extremely high, and at present, partial online diagnosis and treatment systems on platforms exist. However, the traditional online diagnosis and treatment platform focuses on how to present the information of the database to the user, and the place where the Chinese language is the largest different from other languages has no space between Chinese words to separate the Chinese words, which increases the difficulty of the language processing algorithm in sentence segmentation and semantic understanding. Therefore, the current online diagnosis often has the problem of wrong semantic understanding of diagnosis and treatment. In addition, the existing online diagnosis and treatment platform lacks diagnosis and treatment combining atlas and medicine recommendation, the phenomenon that a user cannot understand a recommendation result often occurs, and the readability of online diagnosis and treatment is reduced.
Disclosure of Invention
In order to solve the defects of the prior art, the invention aims to provide an intelligent question-answering system based on a medical knowledge graph to solve the problems that an online diagnosis and treatment technology is easy to have understanding errors and a diagnosis result is not easy to be understood by a user.
In order to achieve the above object, the present invention provides an intelligent question-answering system based on medical knowledge maps. The system comprises a medicine knowledge map, a medicine knowledge card, a natural language processing unit, a blind area processing unit, a medicine recommendation interface, an input interface and an intelligent question and answer processor; the medicine knowledge graph and the medicine knowledge card are obtained through common medical data extraction, the input interface sends information input by a user to the natural language processing unit to extract key information, the intelligent question and answer processor compares the information input by the user in the medicine knowledge graph and the medicine knowledge card through the key information and determines recommended medicines by combining with data of the blind area processing unit, and the medicine recommendation interface is used for displaying the recommended medicines.
Preferably, the natural language processing unit performs named entity recognition on the input information according to a natural language expression mode, and performs sentence meaning segmentation on the problem of the input interface.
Preferably, the intelligent question and answer processor combines the medical knowledge map with the medical knowledge card, so that a user can read words to obtain detailed explanation and can perceive the correlation between the knowledge bodies through visual graphics.
Preferably, the blind area processing unit sets a corresponding grid proportion partition by using PS software during design, sets a space proportion for the main web page elements, and compares whether the space structure is reasonable or not in combination with the ordering of importance.
Preferably, the medicine recommendation interface is designed according to the theme, style and proportion of the webpage, and analyzes the browsing data of the user to perform a supplementary adjustment scheme of webpage medical knowledge through comprehensive comparison of an H5 page and a Web page.
Preferably, the medicine knowledge card is a keyword card obtained by extracting characters obtained through an input interface, and matching is performed in the medicine knowledge graph through the keyword card.
Preferably, the intelligent question and answer processor determines whether the keywords are correct by analyzing the words and creates a dictionary for the commonly used medical knowledge.
Preferably, when the words input by the user are disease and symptom type words, the system matches the corresponding symptoms with the database and displays the data of the intelligent question and answer processor.
Preferably, after all the questions are completed, the intelligent question-answering system searches the information to be provided for the user in the existing traditional Chinese medicine knowledge base and presents the information in a knowledge card, a visual map and a medication recommendation mode.
Preferably, the construction process of the medical knowledge graph sequentially comprises three steps of pattern diagram definition, knowledge extraction and knowledge fusion.
Compared with the prior art, the invention has the beneficial effects that:
(1) on the basis of natural language processing, the invention can realize accurate interpretation of user semanteme by using abundant data sources to inquire medicine.
(2) The invention combines the knowledge map with the knowledge card, so that the user can read the text to obtain the detailed explanation and can also perceive the correlation between the knowledge bodies through the visual graph.
Drawings
FIG. 1 is a system block diagram of an intelligent question-answering system based on medical knowledge maps in accordance with the present invention;
FIG. 2 is a flow chart of the operation of an intelligent question-answering system based on medical knowledge maps in accordance with the present invention;
fig. 3 is a construction process of the medical knowledge graph of the intelligent question-answering system based on the medical knowledge graph.
Detailed Description
To further understand the structure, characteristics and other objects of the present invention, the following detailed description is given with reference to the accompanying preferred embodiments, which are only used to illustrate the technical solutions of the present invention and are not to limit the present invention.
Fig. 1 is a system structure diagram of an intelligent question-answering system based on medical knowledge maps according to the present invention. The intelligent question-answering system based on the medical knowledge graph comprises a medical knowledge graph, a medical knowledge card, a natural language processing unit, a blind area processing unit, a medicine recommending interface, an input interface and an intelligent question-answering processor; the medicine knowledge graph and the medicine knowledge card are obtained through common medical data extraction, the input interface sends information input by a user to the natural language processing unit to extract key information, the intelligent question and answer processor compares the information input by the user in the medicine knowledge graph and the medicine knowledge card through the key information and determines recommended medicines by combining with data of the blind area processing unit, and the medicine recommendation interface is used for displaying the recommended medicines.
And the natural language processing unit carries out named entity recognition on input information according to a natural language expression mode and carries out sentence meaning segmentation on the problem of the input interface.
The intelligent question-answering processor combines the medical knowledge map with the medical knowledge card, so that a user can read characters to obtain detailed explanation, and can sense the correlation between knowledge bodies through visual graphs. The characters and the figures assist each other, and the readability of the input of the user is improved. The intelligent question-answering system can realize three-dimensional visual effect according to data processing and imaging software, and carries out three-dimensional mapping through color change and shadow.
The blind area processing unit sets corresponding grid proportion partitions by using PS software during design, sets space proportion for main webpage elements, and compares whether the space structure is reasonable or not by combining importance sequencing of link guidance.
Aiming at the design of the theme, style and proportion of the webpage, the browse data of the user is analyzed to carry out a supplementary adjustment scheme of webpage elements through the comprehensive comparison of an H5 webpage and a Web page. Due to the fact that the initial picture space size is wrong, an image proportion blind area is possibly generated, the webpage design tends to be single, and no strong visual effect exists. The text information related to the Web page can be expanded, and the blind area processing unit comprehensively utilizes a plurality of types of graphic structures in the webpage design. The square image is used, so that the information transmitted to the user is strict and regular, and the method is suitable for webpage design of academic research websites or various news websites. The round image conveys mellow and soft information, can bring pleasant emotional experience to users, and is relatively suitable for webpage design of entertainment websites or shopping websites. The triangular line image has sharp edges and corners, represents the individuation and outstanding image characteristics, and is mainly used for the design of most various individualized websites.
The medicine knowledge card is a keyword card obtained by extracting characters obtained through an input interface, and matching is carried out in the medicine knowledge map through the keyword card.
The medical knowledge graph is used to model a knowledge network that may occur throughout the system. The visual knowledge graph is a huge network knowledge system which is built by taking a 'semantic network' as a framework. The method is used for capturing and showing semantic relations among domain concepts, so that fragmented and loose knowledge bodies in various knowledge resources are related to each other. The medical knowledge map must be clearly understood, and therefore, part of the secondary information needs to be filtered, the primary information needs to be extracted, and the results need to be randomly ordered.
The intelligent question and answer processor determines whether the keywords are correct or not through the analysis of the participles and establishes a dictionary for common medical knowledge.
The natural language input by the user must be processed based on the need for acceptance of the user's natural language processing. The processing method adopts a random field algorithm technology to carry out basic segmentation on user input, and integrates each marked single character according to the mark of the single character according to the marked set identified by the basic noun phrase. This is accomplished by calling the corresponding method of the annotation collection. Because random field algorithms have a high recognition rate for strange words, few undesired results are also unavoidable, especially in sentences with ambiguous words. At this time, other word segmenters need to be called to correct.
After word segmentation results are obtained through a random field algorithm, the results need to be sorted and part of speech is labeled. Aiming at the special requirements of the system, special part-of-speech labels of parts-of-speech such as traditional Chinese medicines, diseases, signal words, query words and the like are added, so that the question-answering system can conveniently filter the extraction of keywords and information words through the method.
Since the user often cannot accurately locate the keyword information of the problem to be searched, it is necessary to perform a process of synonym matching and to add words specific to the characteristics of the traditional Chinese medicine to better perform synonym matching.
When the words input by the user are diseases or symptom type words, the system matches the corresponding symptoms with the database and displays the data of the intelligent question and answer processor. Searching out the related Chinese medicine classes, and providing a Chinese medicine list suitable for the symptom or the disease according to the correlation degree as an auxiliary basis for medication.
The system can label Chinese language according to written or spoken language input by a user; the receiver matches sentence pattern templates according to the signal words and generates corresponding query sentences according to a certain matching principle.
After all the questions are completed, the intelligent question-answering system searches the information needed to be provided for the user in the existing traditional Chinese medicine knowledge base and presents the information in a knowledge card, a visual atlas and a medication recommendation mode.
Fig. 2 is a flow chart of the operation of the intelligent question-answering system based on the medical knowledge map. The specific flow chart is as follows:
s1: the intelligent question-answering system orderly arranges the unordered user corpus information;
s2: processing and extracting natural language keyword information through a conditional random field word segmentation technology;
s3: obtaining a final answer fed back to a user based on a basic principle of a knowledge graph;
s4: and the knowledge map and the attribute list are presented simultaneously as auxiliary recommendation information of medication.
Fig. 3 is a construction process of the medical knowledge graph of the intelligent question-answering system based on the medical knowledge graph, which specifically comprises the following steps:
m1: the definition of the pattern graph comprises concepts owned by the knowledge base, the attributes of the concepts and the hierarchical relation among the concepts;
m2: the knowledge extraction mainly comprises the entity, entity type, synonym relation and attribute value relation related to the medicine in the network;
m3: the common traditional Chinese medicine knowledge base mainly comprises upper-layer concepts such as traditional Chinese medicines, traditional Chinese medicine syndromes, traditional Chinese medicine diseases and the like and attributes of the concepts, and a mode diagram is constructed.
The construction process of the medicine knowledge graph sequentially comprises three steps of pattern definition, knowledge extraction and knowledge fusion.
In addition, a medicine knowledge base for constructing the medicine knowledge graph needs to identify medicine related entities from professional traditional Chinese medicine texts, and a labeling model is learned by utilizing large-scale linguistic data so as to label sentences.
It should be noted that the above summary and the detailed description are intended to demonstrate the practical application of the technical solutions provided by the present invention, and should not be construed as limiting the scope of the present invention. Various modifications, equivalent substitutions, or improvements may be made by those skilled in the art within the spirit and principles of the invention. The scope of the invention is to be determined by the appended claims.
Claims (10)
1. An intelligent question-answering system based on a medical knowledge graph is characterized by comprising a medical knowledge graph, a medical knowledge card, a natural language processing unit, a blind area processing unit, a medicine recommendation interface, an input interface and an intelligent question-answering processor; the medicine knowledge graph and the medicine knowledge card are obtained through common medical data extraction, the input interface sends information input by a user to the natural language processing unit to extract key information, the intelligent question and answer processor compares the information input by the user in the medicine knowledge graph and the medicine knowledge card through the key information and determines recommended medicines by combining with data of the blind area processing unit, and the medicine recommendation interface is used for displaying the recommended medicines.
2. The medical knowledge graph-based intelligent question answering system according to claim 1, wherein the natural language processing unit performs named entity recognition on input information according to a natural language expression mode and performs sentence meaning segmentation on questions of the input interface.
3. The system of claim 1, wherein the smart question-answering processor combines the medical knowledge graph with the medical knowledge card to allow a user to read text for detailed explanation and to perceive the correlation between the knowledge bodies through visual graphics.
4. The medical knowledge graph-based intelligent question-answering system according to claim 1, wherein the blind area processing unit uses PS software to set corresponding grid proportion partitions during design, sets space proportions for main webpage elements, and compares whether the space structure is reasonable or not in combination with the ordering of importance.
5. The intelligent question-answering system based on the medical knowledge graph of claim 1, wherein the medicine recommendation interface is designed according to the theme, style and proportion of the webpage, and analyzes the browsing data of the user through comprehensive comparison of an H5 page and a Web page to perform a supplementary adjustment scheme of the webpage medical knowledge.
6. The medical knowledge graph-based intelligent question-answering system according to claim 1, wherein the medical knowledge graph is a keyword graph obtained by extracting characters obtained through an input interface, and matching is performed in the medical knowledge graph through the keyword graph.
7. The medical knowledge graph-based intelligent question-answering system according to claim 1, wherein the intelligent question-answering processor determines whether the keywords are correct through word segmentation analysis and establishes a dictionary for commonly used medical knowledge.
8. The medical knowledge graph-based intelligent question-answering system according to claim 1, wherein when words input by a user are disease and symptom type words, the medication recommendation interface matches corresponding symptoms with a database and displays data of the intelligent question-answering processor.
9. The intelligent question-answering system based on the medical knowledge graph of claim 1, wherein after all questions are completed, the intelligent question-answering system searches information needed to be provided for a user in an existing traditional Chinese medicine knowledge base and presents the information in a knowledge card, a visual graph and a medication recommendation mode.
10. The intelligent question-answering system based on the medical knowledge graph as claimed in claim 1, wherein the construction process of the medical knowledge graph sequentially comprises three steps of pattern diagram definition, knowledge extraction and knowledge fusion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911055172.8A CN111046272A (en) | 2019-10-31 | 2019-10-31 | Intelligent question-answering system based on medical knowledge map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911055172.8A CN111046272A (en) | 2019-10-31 | 2019-10-31 | Intelligent question-answering system based on medical knowledge map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111046272A true CN111046272A (en) | 2020-04-21 |
Family
ID=70231976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911055172.8A Pending CN111046272A (en) | 2019-10-31 | 2019-10-31 | Intelligent question-answering system based on medical knowledge map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111046272A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111599489A (en) * | 2020-05-19 | 2020-08-28 | 万达信息股份有限公司 | Disease information acquisition method, terminal equipment and storage medium |
| CN112148851A (en) * | 2020-09-09 | 2020-12-29 | 常州大学 | Construction method of medicine knowledge question-answering system based on knowledge graph |
| CN112735583A (en) * | 2020-12-25 | 2021-04-30 | 山东众阳健康科技集团有限公司 | Traditional Chinese medicine health preserving robot and method |
| CN112802575A (en) * | 2021-04-10 | 2021-05-14 | 浙江大学 | Medication decision support method, device, equipment and medium based on graphic state machine |
| CN116340544A (en) * | 2023-04-03 | 2023-06-27 | 浙江大学 | Visual analysis method and system for ancient Chinese medicine books based on knowledge graph |
| CN116721779A (en) * | 2023-08-10 | 2023-09-08 | 成都安哲斯生物医药科技有限公司 | Medical data preprocessing method and system |
| CN117076689A (en) * | 2023-08-21 | 2023-11-17 | 浙江大学 | Intelligent design method for traditional Chinese medicine pharmaceutical process route |
-
2019
- 2019-10-31 CN CN201911055172.8A patent/CN111046272A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111599489A (en) * | 2020-05-19 | 2020-08-28 | 万达信息股份有限公司 | Disease information acquisition method, terminal equipment and storage medium |
| CN112148851A (en) * | 2020-09-09 | 2020-12-29 | 常州大学 | Construction method of medicine knowledge question-answering system based on knowledge graph |
| CN112735583A (en) * | 2020-12-25 | 2021-04-30 | 山东众阳健康科技集团有限公司 | Traditional Chinese medicine health preserving robot and method |
| CN112802575A (en) * | 2021-04-10 | 2021-05-14 | 浙江大学 | Medication decision support method, device, equipment and medium based on graphic state machine |
| CN112802575B (en) * | 2021-04-10 | 2021-09-03 | 浙江大学 | Medication decision support method, device, equipment and medium based on graphic state machine |
| CN116340544A (en) * | 2023-04-03 | 2023-06-27 | 浙江大学 | Visual analysis method and system for ancient Chinese medicine books based on knowledge graph |
| CN116340544B (en) * | 2023-04-03 | 2024-02-23 | 浙江大学 | Visual analysis method and system for ancient Chinese medicine books based on knowledge graph |
| CN116721779A (en) * | 2023-08-10 | 2023-09-08 | 成都安哲斯生物医药科技有限公司 | Medical data preprocessing method and system |
| CN116721779B (en) * | 2023-08-10 | 2023-11-24 | 成都安哲斯生物医药科技有限公司 | Medical data preprocessing method and system |
| CN117076689A (en) * | 2023-08-21 | 2023-11-17 | 浙江大学 | Intelligent design method for traditional Chinese medicine pharmaceutical process route |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111046272A (en) | Intelligent question-answering system based on medical knowledge map | |
| CN110502621B (en) | Question answering method, question answering device, computer equipment and storage medium | |
| CN106776711B (en) | Chinese medical knowledge map construction method based on deep learning | |
| US11080295B2 (en) | Collecting, organizing, and searching knowledge about a dataset | |
| US20150081277A1 (en) | System and Method for Automatically Classifying Text using Discourse Analysis | |
| WO2019153685A1 (en) | Text processing method, apparatus, computer device and storage medium | |
| CN115455935A (en) | Intelligent text information processing system | |
| CN102955848A (en) | Semantic-based three-dimensional model retrieval system and method | |
| KR102329242B1 (en) | Method, apparatus, device and computer readable medium for generating vqa training data | |
| CN111190920B (en) | Data interaction query method and system based on natural language | |
| CN112347204B (en) | Method and device for constructing drug research and development knowledge base | |
| CN109522396B (en) | Knowledge processing method and system for national defense science and technology field | |
| CN113569023A (en) | Chinese medicine question-answering system and method based on knowledge graph | |
| KR101333485B1 (en) | Method for constructing named entities using online encyclopedia and apparatus for performing the same | |
| CN114490984A (en) | Question-answer knowledge extraction method, device, equipment and medium based on keyword guidance | |
| Da et al. | Deep learning based dual encoder retrieval model for citation recommendation | |
| US9881004B2 (en) | Gender and name translation from a first to a second language | |
| CN114141384A (en) | Method, apparatus and medium for retrieving medical data | |
| CN107615268A (en) | System and method for carrying out asymmetric formatting to word interval according to the uncertainty between word | |
| RU2595531C2 (en) | Method and system for generating definition of word based on multiple sources | |
| Şenel et al. | Measuring cross-lingual semantic similarity across European languages | |
| CN112800244A (en) | Method for constructing knowledge graph of traditional Chinese medicine and national medicine | |
| CN103164398A (en) | Chinese-Uygur language electronic dictionary and automatic translating Chinese-Uygur language method thereof | |
| CN103164397A (en) | Chinese-Kazakh electronic dictionary and automatic translating Chinese- Kazakh method thereof | |
| Al-Sultany et al. | Enriching tweets for topic modeling via linking to the wikipedia |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |