CN115563977A - Health-care knowledge recommendation method and system based on knowledge graph - Google Patents
Health-care knowledge recommendation method and system based on knowledge graph Download PDFInfo
- Publication number
- CN115563977A CN115563977A CN202211071832.3A CN202211071832A CN115563977A CN 115563977 A CN115563977 A CN 115563977A CN 202211071832 A CN202211071832 A CN 202211071832A CN 115563977 A CN115563977 A CN 115563977A
- Authority
- CN
- China
- Prior art keywords
- health
- data
- knowledge
- care
- health care
- 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
- 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
-
- 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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- 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
- G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
Abstract
The invention discloses a health-care knowledge recommendation method and system based on a knowledge graph; the method comprises the following steps: acquiring health care knowledge data; converting the acquired data into structured data; converting the structured data into new triple relation data, identifying the health care mode type of the new triple relation data, and performing de-duplication and combination on the new triple relation data and the existing triple relation data according to the health care mode type; constructing a health-care knowledge map based on the triple relation data after the duplication removal and combination; the method comprises the steps of obtaining a problem in the health care field, processing the problem to obtain a problem keyword, and obtaining the best answer corresponding to the problem to output based on the problem keyword and a health care knowledge map.
Description
Technical Field
The invention relates to the technical field of knowledge recommendation, in particular to a health care knowledge recommendation method and system based on a knowledge graph.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
With the continuous improvement of people on the understanding of health preserving concept, more and more middle-aged and elderly people begin to pay attention to relevant knowledge of prevention and health care. However, the words "health care" and "health preserving" are first to be associated with cheats and wrong knowledge of health care and health preserving. It can be seen that the health preservation requirement of the current society is continuously increasing, and middle-aged and old people need to learn correct health care and health preservation knowledge in a formal way urgently. Wrong health preserving information is not beneficial to the health preserving of the old, can also cause harm to the body, and the importance of correct health preserving is self-evident.
In the prior art, people generally acquire health care through searching and mutual propagation, the information acquisition method is low in acquisition efficiency, and hidden information cannot be omitted or inquired due to insufficient knowledge storage of users, so that the accuracy of finally acquired information is low.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a health care knowledge recommendation method and system based on a knowledge map; the invention can use the knowledge reasoning function of the knowledge graph to reason the health care knowledge stored in the health care knowledge graph, obtains and learns new knowledge from the known health care knowledge graph and the fact combination, and interacts through the intelligent question-answering and intelligent recommendation modes.
In a first aspect, the invention provides a health care knowledge recommendation method based on a knowledge graph;
a health-care knowledge recommendation method based on a knowledge graph comprises the following steps:
acquiring health care knowledge data;
converting the acquired data into structured data;
converting the structured data into new triple relation data, identifying the health care mode type of the new triple relation data, and performing de-duplication and combination on the new triple relation data and the existing triple relation data according to the health care mode type; constructing a health-care knowledge map based on the triple relation data after the duplication removal and combination;
the method comprises the steps of obtaining problems in the health-care field, processing the problems to obtain problem keywords, and obtaining the best answer output corresponding to the problems based on the problem keywords and a health-care knowledge map.
In a second aspect, the invention provides a health care knowledge recommendation system based on a knowledge graph;
health preserving knowledge recommendation system based on knowledge graph comprises:
an acquisition module configured to: acquiring health care knowledge data;
a data translation module configured to: converting the acquired data into structured data;
a graph building module configured to: converting the structured data into new triple relation data, identifying the health care mode type of the new triple relation data, and performing de-duplication and combination on the new triple relation data and the existing triple relation data according to the health care mode type; constructing a health-care knowledge map based on the triple relation data after the duplication removal and combination;
a knowledge recommendation module configured to: the method comprises the steps of obtaining a problem in the health care field, processing the problem to obtain a problem keyword, and obtaining the best answer corresponding to the problem to output based on the problem keyword and a health care knowledge map.
In a third aspect, the present invention further provides an electronic device, including:
a memory for non-transitory storage of computer readable instructions; and
a processor for executing the computer readable instructions,
wherein the computer readable instructions, when executed by the processor, perform the method of the first aspect.
In a fourth aspect, the present invention also provides a storage medium storing non-transitory computer readable instructions, wherein the non-transitory computer readable instructions, when executed by a computer, perform the instructions of the method of the first aspect.
In a fifth aspect, the invention also provides a computer program product comprising a computer program for implementing the method of the first aspect when run on one or more processors.
Compared with the prior art, the invention has the beneficial effects that:
the health-care knowledge map and the intelligent auxiliary method provided by the invention can meet the requirement of people on acquisition of health-care knowledge, and can quickly and efficiently answer the relevant problems in the health-care field provided by users. The embeddable application program interface API can be embedded into a system of a medical care health service institution, and a health care knowledge community can be further built.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are included to illustrate an exemplary embodiment of the invention and not to limit the invention.
FIG. 1 is a flowchart of a method according to a first embodiment.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and it should be understood that the terms "comprises" and "comprising", and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
All data are obtained according to the embodiment and are legally applied on the data on the basis of compliance with laws and regulations and user consent.
Example one
The embodiment provides a health care knowledge recommendation method based on a knowledge graph;
as shown in fig. 1, the method for recommending health-preserving knowledge based on knowledge graph includes:
s101: acquiring health care knowledge data;
s102: converting the acquired data into structured data;
s103: converting the structured data into new triple relation data, identifying the health care mode type of the new triple relation data, and performing de-duplication and combination on the new triple relation data and the existing triple relation data according to the health care mode type; constructing a health-care knowledge map based on the triple relation data after the duplication removal and combination;
s104: the method comprises the steps of obtaining problems in the health-care field, processing the problems to obtain problem keywords, and obtaining the best answer output corresponding to the problems based on the problem keywords and a health-care knowledge map.
Further, the S101: acquiring health care knowledge data, and acquiring contents related to health care in medical field thesis, an authoritative medical website, a health knowledge website and the like by using a method of combining automatic crawler acquisition and manual acquisition.
Further, the step S101: acquiring health-care knowledge data, which specifically comprises the following steps:
structured collection, semi-structured analysis and unstructured extraction are carried out to obtain three data acquisition modes, and health care knowledge data are obtained.
Further, the health care knowledge data in various databases, data tables and table files are acquired through structured acquisition.
Further, the semi-structured parsing collects the logic implied in the HTML webpage of the hypertext markup language and parses the logic into words of the structured data.
Further, the unstructured extraction collects words which imply health care knowledge data in a hypertext markup language HTML webpage.
Further, the S102: converting the acquired data into structured data, specifically comprising:
the unstructured data is converted into semi-structured data, and the semi-structured data is converted into structured data.
Further, the converting unstructured data into semi-structured data specifically includes:
and performing data cleaning and noise elimination on the unstructured data in the webpage by using an automatic crawler tool, and converting the unstructured data into semi-structured data.
Further, the converting the semi-structured data into the structured data specifically includes:
and extracting key words from the semi-structured data by using a natural language processing method, extracting entity key words and relation key words from the semi-structured data, and converting the entity key words and the relation key words into structured data.
Further, the step S103: and converting the structured data into new triple relation data by converting the structured data into entity-relation-entity triple relation data.
Further, the step S103: identifying the health-care mode type of the new triple relation data, wherein the health-care mode type comprises the following steps: regulating spirit, preserving health by sports, preserving health by food therapy, preserving health by medicine and preserving health by four seasons.
The method for regulating spirit and preserving health comprises the following steps: relationship between environment and spirit, relationship between psychology and spirit, relationship between thought and spirit, relationship between age and spirit;
exercise and health preservation, comprising: the relationship between exercise and efficacy, the relationship between exercise and exercise, and the relationship between weight and exercise;
food therapy health preserving, comprising: relationship between food and efficacy, relationship between food and food, relationship between food and recipe, relationship between food and disease, relationship between recipe and disease, relationship between age and food;
the medicine health preserving comprises: the relationship of drugs to disease, the relationship of drugs to drugs, the relationship of age to drugs;
four seasons for health preserving, which comprises: the relationship between solar terms and sports, and the relationship between solar terms and recipes.
Further, the method for de-registering the new triple relationship data and the existing triple relationship data according to the health care mode category specifically includes:
and comparing the existing triple relational data of the corresponding data category stored in the relational database MYSQL with the new triple relational data, removing the existing relational data, and merging the new triple relational data into the relational database of the corresponding data category.
Further, the construction of the health-care knowledge graph based on the triplet relation data after the de-duplication and combination specifically includes:
for each health care mode type, reading triple relation data in a relation database MYSQL, connecting the triple relation data with a graph database Neo4j, creating nodes representing entities in the triple relation data in the graph database Neo4j corresponding to the health care mode type, marking the types of the nodes and the names of the entities corresponding to the nodes, creating a joint edge representing the relation between the entities in the triple relation data in the graph database Neo4j, and marking the types of the joint edge.
Types of nodes, including: environment, spirit, psychology, age thoughts, exercise, efficacy, food materials, diet, disease, medication, solar terms, age, and weight.
Types of edges, including: fit, contraindicated, eat, promote, inhibit and form.
Illustratively, the de-duplication and merging of the new triple relationship data and the existing triple relationship data according to the health care mode category specifically includes:
reading the triple relation data of the dietary therapy health preserving and health care modes in the MySQL database, and connecting with a graphic database Neo4j for storing a dietary therapy health preserving and health care knowledge map;
creating a node representing an entity in the triple relation data in a graphic database, taking the entity type as a label of the node, taking the entity name as a name attribute of the node, and taking the detailed entity information as an info attribute of the node;
and determining the entity contained in the triple relational data by using a match statement in the Cypher language of Neo4j, creating a joint edge representing the relationship between the entity and the entity in the triple relational data in the graphic database by using a create statement, and taking the type of the joint edge as the label of the joint edge.
Further, the S104: the method comprises the steps of obtaining problems in the health care field, and embedding the problems into small programs, APP and Web pages through an embeddable application program interface API to obtain natural language problems.
The embeddable application program interface API specifically comprises: and (3) establishing an HTTP server by using a Web application program framework flash, setting a URL path of the intelligent auxiliary system, receiving a GET request method, and acquiring the natural language problem in the health-preserving and health-care field in the GET request.
In applets, APPs and Web pages, information provided by a user is acquired through natural language questions through various interaction methods which are not limited to character input, button clicking and category selection.
Further, processing the question to obtain a question keyword, and obtaining the best answer output corresponding to the question based on the question keyword and the health care knowledge graph specifically includes:
performing word segmentation and part-of-speech tagging on natural language problems of health care, and extracting entity keywords and relation keywords in the natural language problems through a Chinese natural language processing tool and a keyword matching algorithm;
and performing similarity calculation on the natural language problem and a preset problem template through a similarity matching algorithm, screening the problem template with the highest similarity, and determining the category of the natural language problem.
And inquiring knowledge containing entity keywords and relation keywords in a health care knowledge map corresponding to the problem category stored in the Neo4j map database, applying corresponding natural language templates to the inquiry result according to the problem category, and returning the final result.
Further, the method further comprises: and sorting the results according to the personal information of the user.
Further, the sorting the results according to the personal information of the user specifically includes:
in the natural language problem, extracting the personal information characteristic identification of the user through a keyword matching algorithm; the user personal information characteristic identification comprises: height, sex, age, weight, hobby;
segmenting the age, the height and the weight of a user through a rule matching algorithm, and inquiring knowledge containing entity keywords and relation keywords in a health care knowledge map corresponding to the problem category stored in a Neo4j map database based on segmented personal information of the user;
the weight of the entities is adjusted using an artificially set threshold, and the results are sorted by preference.
Further, the method further comprises: and visualizing the health care knowledge data.
Further, the visualizing of health care knowledge data specifically includes:
the health care knowledge map is displayed as a visual health care knowledge network map through a graphic drawing method, the network map comprises nodes and joint edges, the bottom layer abstracts entities and relations in the health care knowledge into the nodes and the joint edges, the health care knowledge data are organized into multi-type and multi-dimensional knowledge forms, and the health care knowledge data are analyzed.
Illustratively, based on the structured data, the visualization of the health care knowledge data specifically includes:
uploading the structured health care knowledge data obtained in the health care knowledge data acquisition stage to a cloud server in the form of a text or a table, and deploying the health care knowledge data to a graph database Neo4j on the cloud server;
the link of the graph database Neo4j is placed in an intelligent auxiliary system, the link is remotely accessed through a browser, a user name (Username) and a Password (Password) are input to enter the graph database Neo4j storing the health care knowledge graph, and then the health care knowledge network graph can be checked;
the visual storage and retrieval query of the health care knowledge data can be realized by using Cypher language commands in the graph database Neo4 j.
It should be understood that the intelligent health-care auxiliary method based on the knowledge graph provides an embeddable application program interface API, is embedded into a system of a medical care and health service institution, accurately positions questioning knowledge required by a user, and provides personalized information service for the user through various interaction modes.
The method is developed under the environments of MySQL 5.1.22 and Neo4j-Community-4.2.7 based on a Python 3.7 platform. According to the technical scheme, a user inputs a problem that' do you like to eat sticky rice to invigorate the spleen and what you can eat to invigorate the spleen in a health-care intelligent assistant in a health-care small program? "is an example:
firstly, creating a health care applet through a applet template, establishing a health care intelligent assistant module, providing an interactive dialog box, accessing an embeddable application program interface API provided by a knowledge graph-based health care intelligent assistance method, and inputting a question ' do you like to eat sticky rice to invigorate spleen and what you can eat to invigorate spleen ' to be proposed by a user in a health care intelligent assistant by the user's input of a question which is about to eat sticky rice to invigorate spleen? ", the question is sent to the HTTP server via the GET request method.
After receiving the natural language problem, the intelligent auxiliary system carries out word segmentation and part of speech tagging on the problem, extracts entity keywords and relation keywords 'sticky rice', 'spleen tonifying' and 'eating' in the natural language problem through a Chinese natural language processing tool and a keyword matching algorithm, and determines the entity keywords and the relation keywords 'sticky rice', 'spleen tonifying' and 'eating' as knowledge categories of food therapy and health preservation.
Matching the obtained keywords with a pre-defined problem template by using a matching algorithm, screening out a problem template with the highest similarity, inquiring the relation between spleen tonifying and food materials in a food therapy health maintenance knowledge map stored in a Neo4j graph database by using match sentences in Cypher languages, obtaining food materials with a good eating relation with the spleen tonifying and food materials with a food avoiding relation, reasoning by using the relation between the food materials and the food recipes, obtaining a result of the food recipe capable of tonifying the spleen, further extracting personal information of 25 years old and eating sticky rice from natural language problems by using the keyword matching algorithm, marking the user as youth by using a rule matching algorithm, obtaining the food materials with a good eating relation with the youth and the food materials with the food avoiding relation, reasoning by using the relation between the keyword matching algorithm and the food recipe, improving the preference degree of the food recipe with the good eating relation with the youth, reducing the preference degree of the food recipe with the food diet relation with the youth, sequencing the food materials according to the preference degree of the food therapy health maintenance, and further establishing a small health maintenance diet from the assistant.
According to the invention, health care knowledge is collected and extracted through a data mining technology, the knowledge graph technology is used for describing and visualizing complex and fussy health care knowledge data, and mutual relations among knowledge in a health care knowledge graph are analyzed and mined simultaneously, so that a health care intelligent auxiliary system based on the knowledge graph is constructed, an embeddable application program interface API of the intelligent auxiliary system can be used by a medical care health service organization, so that a small program and an APP of an intelligent assistant for health care service can be quickly, conveniently and stably established, a health care knowledge community using the health care intelligent auxiliary system based on the knowledge graph can be established, and therefore, a user can be helped to efficiently and correctly obtain the health care knowledge, a health care plan is established, and a habit of correct health care is formed.
The invention also provides a method for displaying the knowledge in the health care knowledge data as a visual health care knowledge network diagram, and the structured health care knowledge is displayed in a graphical form closer to human understanding and cognition.
A health-care intelligent auxiliary system based on a knowledge graph is characterized in that a functional architecture developed by the system is divided into a user side and an administrator side, and a technical architecture comprises a back end and an algorithm.
The back end provides a page for development, debugging and management of an administrator, functions of file transmission, database operation, knowledge map visualization, embedded application program interface API calling statistics and the like are provided, and the analysis and debugging of the problems brought forward by the user by the developer and the administrator are facilitated. The back end is developed by using a Python-based Web application program framework flash framework, and the flash is a lightweight customizable framework and has flexibility, portability, safety and expandability. The invention develops the Web webpage of the intelligent health-care assistant by using a flash frame, and simulates a user to ask for knowledge and answer.
In the aspect of algorithm, entity keywords and relation keywords in the natural language problem are extracted through a keyword matching algorithm. The research idea is as follows:
the patent selects a keyword matching algorithm in the natural language processing field to extract entity keywords and relationship keywords in natural language problems, and the algorithm is mainly used for information search, text review and the like and aims to extract entities, relationships and terms in the natural language problems. And establishing a pattern tree according to the keyword dictionary, and performing multi-mode matching on the natural language problem in the pattern tree through an AC automaton algorithm, thereby extracting entity keywords and relation keywords in the natural language problem.
Extracting entity keywords and relationship keywords in the natural language problem through a keyword matching algorithm, and specifically comprising the following steps:
selecting a keyword matching algorithm in the natural language processing field to extract entity keywords and relationship keywords in the natural language problem, establishing a pattern tree according to a keyword dictionary, and performing multi-mode matching on the natural language problem in the pattern tree through an AC automaton algorithm so as to extract the entity keywords and the relationship keywords in the natural language problem.
The invention provides an embeddable application program interface API through a health care knowledge intelligent auxiliary system by taking artificial intelligence, data mining and knowledge map technology as backgrounds, and provides health care related knowledge in various health care modes such as mind adjustment, guide accommodation, four-time regulation, food nourishing, medicine nourishing, desire saving, grain exorcising and the like in the forms of conversation and the like. In addition, various behaviors in health care are kept free from relation, the intelligent auxiliary system can utilize the reasoning function of the knowledge graph to reason the health care knowledge stored in the health care knowledge graph, the known health care knowledge is combined with personal information provided by the user to help the user to establish an applicable health care plan, and the user is guided to correctly conduct health care.
The health care knowledge map is stored in a high-performance NoSQL graphic database Neo4j mode. Neo4j has the advantage of faster query and search speed, and the entity nodes can retain attributes in the graph database, which means that the entity can retain more information and also have all the characteristics of a mature database.
The embeddable application program interface API is provided by an HTTP server established by a Web application program framework flash, and the flash is a lightweight customizable framework written based on Python language and has flexibility, portability, safety and expandability.
Example two
The embodiment provides a health care knowledge recommendation system based on a knowledge graph;
health preserving knowledge recommendation system based on knowledge graph comprises:
an acquisition module configured to: acquiring health care knowledge data;
a data translation module configured to: converting the acquired data into structured data;
a graph building module configured to: converting the structured data into new triple relation data, identifying the health care mode type of the new triple relation data, and performing de-duplication and combination on the new triple relation data and the existing triple relation data according to the health care mode type; constructing a health-care knowledge map based on the triple relation data after the duplication elimination and combination;
a knowledge recommendation module configured to: the method comprises the steps of obtaining a problem in the health care field, processing the problem to obtain a problem keyword, and obtaining the best answer corresponding to the problem to output based on the problem keyword and a health care knowledge map.
It should be noted here that the acquiring module, the data transforming module, the graph constructing module and the knowledge recommending module correspond to steps S101 to S104 in the first embodiment, and the modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the contents disclosed in the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer executable instructions.
In the foregoing embodiments, the descriptions of the embodiments have different emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The proposed system can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules may be combined or integrated into another system, or some features may be omitted, or not executed.
EXAMPLE III
The present embodiment further provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, a processor is connected with the memory, the one or more computer programs are stored in the memory, and when the electronic device runs, the processor executes the one or more computer programs stored in the memory, so as to make the electronic device execute the method according to the first embodiment.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software.
The method in the first embodiment may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, etc. as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and combines hardware thereof to complete the steps of the method. To avoid repetition, it is not described in detail here.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Example four
The present embodiments also provide a computer-readable storage medium for storing computer instructions, which when executed by a processor, perform the method of the first embodiment.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A health-preserving health-care knowledge recommendation method based on a knowledge graph is characterized by comprising the following steps:
acquiring health care knowledge data;
converting the acquired data into structured data;
converting the structured data into new triple relation data, identifying the health care mode type of the new triple relation data, and performing de-duplication and combination on the new triple relation data and the existing triple relation data according to the health care mode type; constructing a health-care knowledge map based on the triple relation data after the duplication elimination and combination;
the method comprises the steps of obtaining a problem in the health care field, processing the problem to obtain a problem keyword, and obtaining the best answer corresponding to the problem to output based on the problem keyword and a health care knowledge map.
2. The knowledge-graph-based health-preserving health-care knowledge recommendation method according to claim 1, wherein the acquiring health-preserving health-care knowledge data specifically comprises:
acquiring health care knowledge data in three data acquisition modes of structured acquisition, semi-structured analysis and unstructured extraction;
the structured collection is to collect health care knowledge data in various databases, data tables and table files;
the semi-structured analysis is to collect the logic hidden in the HTML webpage of the hypertext markup language and analyze the HTML webpage into characters of structured data;
and the unstructured extraction is used for collecting characters which imply health care knowledge data in a hypertext markup language HTML webpage.
3. The method of knowledge graph-based recommendation of health preserving and care knowledge according to claim 1, wherein the transforming of the acquired data into structured data comprises:
converting unstructured data into semi-structured data, and converting the semi-structured data into structured data;
the converting unstructured data into semi-structured data specifically includes:
performing data cleaning and noise elimination on unstructured data in a webpage by using an automatic crawler tool, and converting the unstructured data into semi-structured data;
the converting the semi-structured data into the structured data specifically includes:
and extracting key words from the semi-structured data by using a natural language processing method, extracting entity key words and relation key words from the semi-structured data, and converting the entity key words and the relation key words into structured data.
4. The knowledge-graph-based health-preserving health-care knowledge recommendation method according to claim 1, wherein a health-preserving health-care mode category of the new triple relationship data is identified, wherein the health-preserving health-care mode category comprises: regulating spirit, preserving health by sports, preserving health by food therapy, preserving health by medicine and preserving health for four seasons;
the method for regulating spirit and preserving health comprises the following steps: relationship between environment and spirit, relationship between mind and spirit, relationship between thought and spirit, relationship between age and spirit;
exercise and health preservation, comprising: the relationship between exercise and efficacy, the relationship between exercise and exercise, and the relationship between weight and exercise;
food therapy health preservation, which comprises the following steps: relationship between food and efficacy, relationship between food and food, relationship between food and recipe, relationship between food and disease, relationship between recipe and disease, relationship between age and food;
the medicine health preserving comprises: the relationship of drugs to diseases, the relationship of drugs to drugs, the relationship of age to drugs;
four seasons for health preserving, which comprises: relationship between solar terms and exercise, and relationship between solar terms and recipes.
5. The knowledge-graph-based health-preserving health-care knowledge recommendation method according to claim 1, wherein the construction of the health-preserving health-care knowledge graph based on the triplet relation data after de-duplication combination specifically comprises:
for each health care mode type, reading triple relation data in a relation database MYSQL, connecting the triple relation data with a graph database Neo4j, creating nodes representing entities in the triple relation data in the graph database Neo4j corresponding to the health care mode type, marking the types of the nodes and the names of the entities corresponding to the nodes, creating a joint edge representing the relation between the entities in the triple relation data in the graph database Neo4j, and marking the types of the joint edge.
6. The method as claimed in claim 1, wherein the processing of the question to obtain the question keyword, and the obtaining of the best answer output corresponding to the question based on the question keyword and the health care knowledge map specifically comprises:
performing word segmentation and part-of-speech tagging on natural language problems of health care, and extracting entity keywords and relation keywords in the natural language problems through a Chinese natural language processing tool and a keyword matching algorithm;
similarity calculation is carried out on the natural language problem and a preset problem template through a similarity matching algorithm, the problem template with the highest similarity is screened out, and the category of the natural language problem is determined;
and inquiring knowledge containing entity keywords and relation keywords in a health care knowledge map corresponding to the problem category stored in the Neo4j map database, applying a corresponding natural language template to an inquiry result according to the problem category, and returning a final result.
7. The method of knowledge-graph-based health care knowledge recommendation of claim 1, wherein the method further comprises: visualizing health care knowledge data; the visualization of the health care knowledge data specifically comprises the following steps:
the health-care knowledge map is displayed as a visual health-care knowledge network map by a graphic drawing method, the network map comprises nodes and joint edges, the bottom layer abstracts entities and relations in the health-care knowledge into the nodes and the joint edges, organizes the health-care knowledge data into multi-type and multi-dimensional knowledge forms, and analyzes the health-care knowledge data.
8. Health preserving and care knowledge recommendation system based on knowledge graph is characterized by comprising:
an acquisition module configured to: acquiring health care knowledge data;
a data translation module configured to: converting the acquired data into structured data;
a graph building module configured to: converting the structured data into new triple relation data, identifying the health care mode type of the new triple relation data, and performing de-duplication and combination on the new triple relation data and the existing triple relation data according to the health care mode type; constructing a health-care knowledge map based on the triple relation data after the duplication removal and combination;
a knowledge recommendation module configured to: the method comprises the steps of obtaining a problem in the health care field, processing the problem to obtain a problem keyword, and obtaining the best answer corresponding to the problem to output based on the problem keyword and a health care knowledge map.
9. An electronic device, comprising:
a memory for non-transitory storage of computer readable instructions; and
a processor for executing the computer readable instructions,
wherein the computer readable instructions, when executed by the processor, perform the method of any of claims 1-7.
10. A storage medium storing non-transitory computer-readable instructions, wherein the non-transitory computer-readable instructions, when executed by a computer, perform the instructions of the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211071832.3A CN115563977A (en) | 2022-09-02 | 2022-09-02 | Health-care knowledge recommendation method and system based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211071832.3A CN115563977A (en) | 2022-09-02 | 2022-09-02 | Health-care knowledge recommendation method and system based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115563977A true CN115563977A (en) | 2023-01-03 |
Family
ID=84739622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211071832.3A Pending CN115563977A (en) | 2022-09-02 | 2022-09-02 | Health-care knowledge recommendation method and system based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115563977A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117011004A (en) * | 2023-10-07 | 2023-11-07 | 苏州元澄科技股份有限公司 | Personalized service recommendation method based on knowledge graph |
-
2022
- 2022-09-02 CN CN202211071832.3A patent/CN115563977A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117011004A (en) * | 2023-10-07 | 2023-11-07 | 苏州元澄科技股份有限公司 | Personalized service recommendation method based on knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649768B (en) | Question-answer clarification method and device based on deep question-answer | |
| CN110765257B (en) | Intelligent consulting system of law of knowledge map driving type | |
| CN106503055B (en) | A kind of generation method from structured text to iamge description | |
| CN111401066B (en) | Artificial intelligence-based word classification model training method, word processing method and device | |
| CN112786194A (en) | Medical image diagnosis guide inspection system, method and equipment based on artificial intelligence | |
| CN111708874A (en) | Man-machine interaction question-answering method and system based on intelligent complex intention recognition | |
| CN111785368A (en) | Triage method, device, equipment and storage medium based on medical knowledge map | |
| US20160321244A1 (en) | Phrase pair collecting apparatus and computer program therefor | |
| CN102955848A (en) | Semantic-based three-dimensional model retrieval system and method | |
| CN108875021A (en) | A kind of sentiment analysis method based on region CNN-LSTM | |
| CN113886716B (en) | Emergency disposal recommendation method and system for food safety emergencies | |
| DE102018008268A1 (en) | Automatically generate instructions from tutorials for search and user navigation | |
| CN113569023A (en) | Chinese medicine question-answering system and method based on knowledge graph | |
| CN115563977A (en) | Health-care knowledge recommendation method and system based on knowledge graph | |
| JP6802332B1 (en) | Information processing method and information processing equipment | |
| KR20220042838A (en) | Systems and Methods to Provide AI Answering Service for Legal Questions | |
| KR102126911B1 (en) | Key player detection method in social media using KeyplayerRank | |
| CN116168844A (en) | Medical data processing system based on big data analysis | |
| CN109284364B (en) | Interactive vocabulary updating method and device for voice microphone-connecting interaction | |
| CN111816276B (en) | Method and device for recommending education courses, computer equipment and storage medium | |
| CN114299196A (en) | Poster automatic generation method and system, storage medium and terminal equipment | |
| CN113870998A (en) | Interrogation method, device, electronic equipment and storage medium | |
| JP2023514023A (en) | Question retrieval device, question retrieval method, device, and storage medium | |
| CN106446198A (en) | Recommending method and device of news based on artificial intelligence | |
| Glanville | Text mining for information specialists |
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 |