CN-122025165-A - Medicine and food homologous recommendation method, system, equipment, medium and product

CN122025165ACN 122025165 ACN122025165 ACN 122025165ACN-122025165-A

Abstract

The application discloses a medicine and food homology recommending method, a system, equipment, a medium and a product, and relates to the field of medicine and food homology recommending, wherein the method comprises the steps of obtaining medicine and food homology information of different sources; the method comprises the steps of integrating medical and edible information, constructing knowledge bases of different types, forming a knowledge base set of different types, constructing intelligent specialists of different knowledge backgrounds according to the types of the knowledge bases, constructing an expert intelligent complex according to the intelligent specialists of different knowledge backgrounds, splitting user problems, optimizing and recommending strategies based on intelligent thinking chains, distributing split sub-problems to the intelligent specialists of different knowledge backgrounds for thinking chain interpretation, recommending medical and edible information corresponding to the user problems, and accurately recommending the medical and edible information.

Inventors

FAN XIAOHUI
SHAO XIN
DAI YIZHENG
GUO WENBO
WANG ZHENG

Assignees

浙江大学长三角智慧绿洲创新中心

Dates

Publication Date: 20260512
Application Date: 20251231

Claims (10)

1.A method of pharmaceutical and food homology recommendation, comprising: Obtaining medicine and food homology information of different sources, wherein the different sources comprise a literature, a website and an open source database; Integrating the medicinal and edible information, and constructing knowledge bases of different types to form a knowledge base set under different types, wherein the different types comprise formula optimization, cost control, process extraction, toxicity evaluation and efficacy analysis; constructing intelligent agent experts with different knowledge backgrounds according to the category types in the knowledge base set; constructing an expert intelligent agent complex according to intelligent agent experts with different knowledge backgrounds; Based on the expert intelligent complex, splitting the user problem, optimizing a recommendation strategy based on an intelligent thinking chain, distributing the split sub-problem to intelligent experts with different knowledge backgrounds for thinking chain interpretation, and recommending medicine and food homologous information corresponding to the user problem.
2. The method for recommending homology of medicine and food according to claim 1, wherein obtaining the information of homology of medicine and food from different sources specifically comprises: Retrieving the literature based on the keywords, and capturing the medicine and food homology information in the literature, wherein the medicine and food homology information comprises medicine and food homology, nutrition enhancers and new food raw materials; Capturing medicine and food homologous information in the website and storing the captured webpage; And grabbing the basic information of the traditional Chinese medicine in the open source database to obtain the homologous information of the medicine and food in the open source database, wherein the basic information of the traditional Chinese medicine comprises medicine classification, efficacy and main treatment.
3. The method for recommending homology of medicine and food according to claim 1, wherein integrating the information of homology of medicine and food to construct knowledge bases of different types, forming a knowledge base set of different types, specifically comprising: for medicine and food homology information grabbed from the literature and the website, a constructed knowledge base is constructed The method comprises the following steps: Wherein, the Open source model for Qwen 3-32B; in order to classify the prompt word, Is of different category types; KG is medicine and food homology information; for the medicine and food homology information grabbed from the open source database, a constructed knowledge base is constructed The method comprises the following steps: Wherein, the Is a template function; Structured data that is an open source database; According to knowledge base And knowledge base Forming knowledge base sets under different category types The method comprises the following steps: 。
4. a method of homology of medicine and food recommendation as claimed in claim 3 wherein said intelligent agent specialists of different knowledge backgrounds The method comprises the following steps: Wherein, the Is a large language model; Is a sub-problem after splitting; The method is a prompt word template under different category types; The method comprises the steps of providing an intelligent agent assistant, wherein the intelligent agent assistant is used for distributing the split sub-problems to corresponding intelligent agent specialists; To determine whether to end the inquiry or continue the inquiry.
5. The method for recommending homology of medicine and food according to claim 4, the expert intelligent agent complex is characterized in that The method comprises the following steps: Wherein, the To manage the agent; prompting words for managing the intelligent agent; is a user problem.
6. The method for recommending homology of medicine and food according to claim 1, wherein each agent expert shares data through a knowledge graph and adopts a game theory to balance efficacy and safety, and outputs a personalized scheme of homology of medicine and food.
7. A pharmaceutical and food homology recommendation system, comprising: the information acquisition module is used for acquiring medicine and food homologous information of different sources, wherein the different sources comprise a literature, a website and an open source database; The knowledge base construction module is used for integrating the medicine and food homologous information, constructing knowledge bases of different types and forming a knowledge base set under different types, wherein the different types comprise formula optimization, cost control, process extraction, toxicity evaluation and efficacy analysis; the intelligent agent expert construction module is used for constructing intelligent agent experts with different knowledge backgrounds according to the category types in the knowledge base set; the expert intelligent agent complex construction module is used for constructing an expert intelligent agent complex according to intelligent agent experts with different knowledge backgrounds; and the information recommendation module is used for splitting the user problem based on the expert intelligent agent complex, distributing the split sub-problem to intelligent agent experts with different knowledge backgrounds for carrying out thinking chain interpretation based on an intelligent agent thinking chain optimization recommendation strategy, and recommending medicine and food homology information corresponding to the user problem.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method of homology to medicine of any one of claims 1-6.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of homology of medicine recommendation according to any one of claims 1-6.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the method of homology to medicine according to any one of claims 1-6.

Description

Medicine and food homologous recommendation method, system, equipment, medium and product Technical Field The application relates to the field of medicine and food homology recommendation, in particular to a medicine and food homology recommendation method, a system, equipment, a medium and a product. Background The existing medicine and food homologous recommendation technology is mainly based on an expert system or a data driving algorithm, wherein the former relies on Chinese medicine books to construct a rule base, but has insufficient flexibility, and the latter utilizes collaborative filtering or content recommendation to be difficult to adapt to dynamic information. Although the large model technology is applied to the field of traditional Chinese medicines, the existing method still has the problems of insufficient individuation, difficult multi-source data fusion, poor interpretability and the like, and cannot be used for carrying out accurate recommendation by effectively combining the complex problems of users, interactive communication and decision adjustment. Disclosure of Invention The application aims to provide a medicine and food homology recommending method, a system, equipment, a medium and a product, so as to solve the problem that medicine and food homology information cannot be accurately recommended. In order to achieve the above object, the present application provides the following solutions: in a first aspect, the present application provides a method for recommending homology of medicine and food, comprising: Obtaining medicine and food homology information of different sources, wherein the different sources comprise a literature, a website and an open source database; Integrating the medicinal and edible information, and constructing knowledge bases of different types to form a knowledge base set under different types, wherein the different types comprise formula optimization, cost control, process extraction, toxicity evaluation and efficacy analysis; constructing intelligent agent experts with different knowledge backgrounds according to the category types in the knowledge base set; constructing an expert intelligent agent complex according to intelligent agent experts with different knowledge backgrounds; Based on the expert intelligent complex, splitting the user problem, optimizing a recommendation strategy based on an intelligent thinking chain, distributing the split sub-problem to intelligent experts with different knowledge backgrounds for thinking chain interpretation, and recommending medicine and food homologous information corresponding to the user problem. In a second aspect, the present application provides a pharmaceutical and food homologous recommendation system, comprising: the information acquisition module is used for acquiring medicine and food homologous information of different sources, wherein the different sources comprise a literature, a website and an open source database; The knowledge base construction module is used for integrating the medicine and food homologous information, constructing knowledge bases of different types and forming a knowledge base set under different types, wherein the different types comprise formula optimization, cost control, process extraction, toxicity evaluation and efficacy analysis; the intelligent agent expert construction module is used for constructing intelligent agent experts with different knowledge backgrounds according to the category types in the knowledge base set; the expert intelligent agent complex construction module is used for constructing an expert intelligent agent complex according to intelligent agent experts with different knowledge backgrounds; and the information recommendation module is used for splitting the user problem based on the expert intelligent agent complex, distributing the split sub-problem to intelligent agent experts with different knowledge backgrounds for carrying out thinking chain interpretation based on an intelligent agent thinking chain optimization recommendation strategy, and recommending medicine and food homology information corresponding to the user problem. In a third aspect, the application provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the computer program to implement the method of homology of medicine and food recommendation described above. In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described method of homology of medicine and food recommendation. In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the above-described method of homology of medicine and food recommendation. According to the specific embodiment