Traditional Chinese medicine implicit efficacy derivation method and device based on knowledge graph

Abstract

The invention relates to the technical field of knowledge maps, in particular to a traditional Chinese medicine implicit efficacy derivation method and device based on a knowledge map. The method comprises the following steps: collecting and sorting traditional Chinese medicine efficacy information recorded in a traditional Chinese medicine book, and constructing a traditional Chinese medicine efficacy basic corpus; on the basis of traditional Chinese medicine basic theoretical knowledge recorded in a traditional Chinese medicine book, and in combination with syndrome differentiation and treatment data of related traditional Chinese medicines, a disease-syndrome-symptom-efficacy knowledge graph is constructed; and combining the traditional Chinese medicine efficacy basic corpus with the disease-syndrome-symptom-efficacy knowledge graph, formulating an implicit efficacy derivation rule, and obtaining the implicit efficacy of the traditional Chinese medicine. Prescription efficacy prediction research is carried out by utilizing the characteristics of the knowledge graph, and the knowledge graph has the advantages that the traditional Chinese medicine knowledge graph systematically integrates various concepts, relationships and attributes in the field of traditional Chinese medicine by constructing a large net knowledge base, can comprehensively cover various efficacies and potential effects of traditional Chinese medicine, and is high in practicability. And a solid foundation is provided for deeply excavating the implicit efficacy of the traditional Chinese medicine.

Description

Technical Field

[0001] The present invention relates to the field of knowledge graph technology, and in particular to a method and device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph. Background Art

[0002] The discovery and acquisition of the hidden efficacy of traditional Chinese medicine is mainly achieved by the following three methods:

[0003] Method 1: Acquisition method based on modern chemical analysis and pharmacological research.

[0004] It uses scientific methods to analyze the chemical components in traditional Chinese medicine and reveal its pharmacological mechanism, thereby expanding and deepening the understanding of the efficacy of traditional Chinese medicine and suggesting the hidden efficacy of traditional Chinese medicine. For example, by extracting, separating and purifying the active ingredients in traditional Chinese medicine, studying its pharmacological effects in vivo and in vitro, such as anti-inflammatory, antibacterial, anti-tumor, etc., it provides a scientific basis for the development of new efficacy and new preparations of traditional Chinese medicine.

[0005] Method 2: Acquisition method based on data mining and association analysis.

[0006] It uses modern information big data collection, mining and analysis techniques to conduct in-depth analysis of the efficacy, safety, and mechanism of action of traditional Chinese medicine, dig out the association between traditional Chinese medicine and diseases, discover new effective ingredients and mechanisms of action, and provide new ideas and methods for the innovative application of traditional Chinese medicine. For example, through algorithms such as Apriori, frequently occurring item sets in the data set are discovered, and association rules are generated to reveal the potential connections between traditional Chinese medicines, between chemical components, and between diseases; classification algorithms are used to classify traditional Chinese medicines and identify categories with similar efficacy or chemical components; clustering algorithms are used to discover natural groupings between traditional Chinese medicines and explore their potential common characteristics.

[0007] Method 3: Acquisition method based on intelligent simulation and artificial intelligence.

[0008] It uses computer simulation technology to simulate the metabolic process and pharmacological effects of traditional Chinese medicine in the body, and predict the efficacy and safety of traditional Chinese medicine. It can conduct simulation experiments in vitro, reduce the use of experimental animals, and improve research efficiency; or use artificial intelligence algorithms to intelligently analyze and process traditional Chinese medicine data to discover the complex relationships and implicit laws between traditional Chinese medicines. It can process large-scale, high-dimensional data and improve analysis efficiency and accuracy.

[0009] Although the above methods have their merits, their shortcomings are also very obvious:

[0010] Method 1: Acquisition method based on modern chemical analysis and pharmacological research. Traditional Chinese medicine is usually a complex system composed of multiple components. The efficacy of traditional Chinese medicine is often not the effect of a single component, but the result of the synergistic effect of multiple components. Modern chemical analysis and pharmacological research often focus on a single component or efficacy of traditional Chinese medicine, ignoring the comprehensive effect of traditional Chinese medicine as a whole. This research method is difficult to fully analyze all the components of traditional Chinese medicine and their interactions, and cannot fully reveal the implicit efficacy of traditional Chinese medicine.

[0011] Method 2: Acquisition method based on data mining and association analysis. This method focuses on the mining of association rules between Chinese medicines, chemical components, and diseases in the study of the efficacy of Chinese medicine. For example, through association analysis, it is found that some Chinese medicines have synergistic effects in the treatment of specific diseases, or the association between certain chemical components and specific efficacy is found. However, there are certain limitations in the mining of the efficacy of a single Chinese medicine, and there is no effective analysis method.

[0012] Method 3: Acquisition method based on intelligent simulation and artificial intelligence. Although the method of acquiring the implicit efficacy of traditional Chinese medicine based on intelligent simulation and artificial intelligence has potential, it also has obvious shortcomings. The main reason is that the model has limited universality and insufficient interpretability, making it difficult to fully capture the complex relationship between traditional Chinese medicine and symptoms. At the same time, technical challenges such as difficulty in multimodal data fusion and algorithm optimization problems limit its application. Summary of the invention

[0013] In order to solve the technical problems that the existing technology cannot fully reveal the implicit efficacy of traditional Chinese medicine and there are certain limitations in the mining and research of the efficacy of a single traditional Chinese medicine, the embodiment of the present invention provides a method and device for deriving the implicit efficacy of traditional Chinese medicine based on a knowledge graph. The technical solution is as follows:

[0014] On the one hand, a method for deducing implicit efficacy of traditional Chinese medicine based on knowledge graph is provided, characterized in that the method comprises:

[0015] S1. Collect and organize the information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books and build a basic corpus of the efficacy of traditional Chinese medicine;

[0016] S2. Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books and combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines, a disease-syndrome-symptom-effect knowledge map is constructed;

[0017] S3. Combine the basic corpus of Chinese medicine efficacy with the disease-syndrome-symptom-efficacy knowledge graph to formulate implicit efficacy derivation rules and obtain the implicit efficacy of Chinese medicine.

[0018] Optionally, in S1, the information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books is collected and sorted to construct a basic corpus of the efficacy of traditional Chinese medicine, including:

[0019] Collect information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books;

[0020] Structuring, normalizing and standardizing the information on the efficacy of traditional Chinese medicines recorded in traditional Chinese medicine books to obtain unified expression of efficacy terms;

[0021] Construct a basic corpus of Chinese medicine efficacy; the information in the basic corpus includes Chinese medicine number, Chinese medicine name and Chinese medicine efficacy.

[0022] Optionally, in S2, based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books and combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines, a disease-syndrome-symptom-effect knowledge graph is constructed, including:

[0023] Acquire basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books;

[0024] Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicine, entity nodes and relationships are used to express traditional Chinese medicine theory and construct a disease-syndrome-symptom-effect knowledge graph;

[0025] The disease-syndrome-symptom-efficacy knowledge graph is modeled and visualized.

[0026] Optionally, entity nodes include: disease, syndrome, symptom nodes and treatment relationship efficacy nodes; entity relationships include: logical relationships of syndrome differentiation and treatment in traditional Chinese medicine theory, and unified expressed relationships between Chinese medicine and its efficacy.

[0027] Optionally, based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines, entity nodes and relationships are used to express traditional Chinese medicine theory to construct a disease-syndrome-symptom-effect knowledge graph, including:

[0028] Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, entity nodes and entity relationships are obtained;

[0029] Express basic TCM theories based on entity nodes and entity relationships;

[0030] Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of related traditional Chinese medicine, a composite node is established;

[0031] When processing efficacy nodes, the efficacy knowledge in the basic corpus of traditional Chinese medicine efficacy is integrated with the efficacy knowledge in the knowledge graph to form a complete and unified knowledge system.

[0032] Optionally, the disease-syndrome-symptom-effect knowledge graph is modeled and visualized, including:

[0033] Establish a knowledge graph in the neo4j graph database to store the processed data in the form of "entity-relationship-entity" triples;

[0034] Use Gephi visualization tool to display the knowledge graph in the form of a point-line graph.

[0035] Optionally, in S3, the basic corpus of TCM efficacy is combined with the disease-syndrome-symptom-efficacy knowledge graph to formulate implicit efficacy derivation rules and obtain the implicit efficacy of TCM, including:

[0036] Construct a basic knowledge network of traditional Chinese medicine based on the basic corpus of traditional Chinese medicine efficacy and the disease-syndrome-symptom-effect knowledge graph;

[0037] Based on the basic knowledge network of traditional Chinese medicine, implicit efficacy derivation rules are formulated; through the formulated rules, the efficacy data of traditional Chinese medicine in the basic corpus of traditional Chinese medicine efficacy are analyzed and derived, and finally the implicit efficacy of traditional Chinese medicine is obtained.

[0038] Optionally, implicit efficacy derivation rules are formulated based on the basic knowledge network of traditional Chinese medicine; through the formulated rules, the efficacy data of traditional Chinese medicine in the basic corpus of traditional Chinese medicine efficacy are analyzed and derived, and finally the implicit efficacy of traditional Chinese medicine is obtained, including:

[0039] According to the importance of the efficacy of traditional Chinese medicine, the efficacy of traditional Chinese medicine is classified into: core efficacy, derived A efficacy, derived B efficacy, derived C efficacy and derived D efficacy;

[0040] Based on the basic corpus of Chinese medicine efficacy, the core efficacy of various Chinese medicines is obtained;

[0041] For the core efficacy, find the corresponding efficacy node in the disease-syndrome-symptom-efficacy knowledge graph;

[0042] Based on the corresponding efficacy nodes, obtain the efficacy of other symptoms manifested by the diseases and syndromes treated in the core efficacy as the derived A efficacy;

[0043] Based on the corresponding efficacy nodes, sub-diseases and sub-syndromes included in the core efficacy diseases and syndromes are obtained as the derivation of B efficacy;

[0044] Based on the corresponding efficacy nodes, obtain the syndrome nodes and disease nodes corresponding to the symptoms in the core efficacy as the derivation of C efficacy;

[0045] Based on the corresponding efficacy nodes, the diseases and syndromes caused by the disease and syndrome nodes in the core efficacy, as well as the corresponding symptoms, are obtained as the derivation of D efficacy;

[0046] Obtain derived A efficacy, derived B efficacy, derived C efficacy and derived D efficacy, remove the core efficacy respectively, and obtain the implicit efficacy of traditional Chinese medicine.

[0047] On the other hand, a device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph is provided, and the device is applied to a method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph, and the device comprises:

[0048] The corpus construction module is used to collect and organize the information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books and build a basic corpus of the efficacy of traditional Chinese medicine;

[0049] The knowledge graph construction module is used to construct a disease-syndrome-symptom-effect knowledge graph based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books and combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines;

[0050] The implicit efficacy derivation module is used to combine the basic corpus of Chinese medicine efficacy and the disease-syndrome-symptom-efficacy knowledge graph, formulate implicit efficacy derivation rules, and obtain the implicit efficacy of Chinese medicine.

[0051] On the other hand, a device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph is provided, and the device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph comprises: a processor; a memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, any one of the methods for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph is implemented.

[0052] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned methods for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph.

[0053] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0054] (1) The present invention conducts research on obtaining the implicit efficacy of traditional Chinese medicine based on the characteristics of traditional Chinese medicine, combines relevant theories of traditional Chinese medicine, and studies the efficacy of traditional Chinese medicine from a holistic perspective, rather than analyzing the efficacy of traditional Chinese medicine from a single component, thereby realizing the analysis and extraction of the overall efficacy of traditional Chinese medicine.

[0055] (2) The present invention uses the characteristics of knowledge graphs to carry out research on the prediction of prescription efficacy. The advantage of knowledge graphs is that the knowledge graph of traditional Chinese medicine systematically integrates various concepts, relationships and attributes in the field of traditional Chinese medicine by constructing a large-scale network knowledge base, which can comprehensively cover the various effects and potential effects of traditional Chinese medicine, and provide a solid foundation for in-depth exploration of the implicit effects of traditional Chinese medicine. Compared with the existing technology, it can systematically integrate the importance and related information of the efficacy of traditional Chinese medicine, making the obtained results of the implicit efficacy of traditional Chinese medicine more accurate and reliable.

[0056] (3) The present invention is based on the known theoretical knowledge of traditional Chinese medicine. Compared with intelligent simulation and artificial intelligence, the knowledge graph of traditional Chinese medicine presents the complex relationship between diseases, syndromes, symptoms and efficacy in a graphical way. It can also display the reasoning path and basis of each step in the reasoning process, so that researchers can browse and query relevant information intuitively and quickly. It not only greatly improves the efficiency of obtaining the implicit efficacy of traditional Chinese medicine, but also improves the interpretability and transparency of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0058] Figure 1 It is a flow chart of a method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph provided by an embodiment of the present invention;

[0059] Figure 2 is a flow chart of deriving A efficacy provided by an embodiment of the present invention;

[0060] Figure 3 is a flow chart of deriving B efficacy provided by an embodiment of the present invention;

[0061] Figure 4 is a flow chart for deriving C efficacy provided by an embodiment of the present invention;

[0062] Figure 5 is a flow chart of deriving D efficacy provided by an embodiment of the present invention;

[0063] Figure 6 It is a block diagram of a device for deriving implicit efficacy of traditional Chinese medicine based on a knowledge graph provided by an embodiment of the present invention;

[0064] Figure 7 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0066] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0067] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0068] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0069] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0070] The embodiment of the present invention provides a method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph, which can be implemented by a device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph, and the device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph can be a terminal or a server. Figure 1 The flowchart of the method for deducing the implicit efficacy of traditional Chinese medicine based on the knowledge graph is shown. The processing flow of the method may include the following steps:

[0071] S1. Collect and organize the information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books and build a basic corpus of traditional Chinese medicine efficacy.

[0072] In a feasible implementation, this step is to collect and organize the information on the efficacy of traditional Chinese medicines clearly recorded in traditional Chinese medicine books, completely reproduce the efficacy in the book, including information such as the name of the traditional Chinese medicine, the efficacy of the traditional Chinese medicine, and construct a relatively accurate and comprehensive basic corpus of the efficacy of traditional Chinese medicines.

[0073] In a feasible implementation, in S1, collecting and collating the information on the efficacy of traditional Chinese medicines recorded in traditional Chinese medicine books to construct a basic corpus of the efficacy of traditional Chinese medicines includes:

[0074] Collect information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books;

[0075] Structuring, normalizing and standardizing the information on the efficacy of traditional Chinese medicines recorded in traditional Chinese medicine books to obtain unified expression of efficacy terms;

[0076] Construct a basic corpus of Chinese medicine efficacy; the information in the basic corpus includes Chinese medicine number, Chinese medicine name and Chinese medicine efficacy.

[0077] In a feasible implementation, data related to the efficacy of traditional Chinese medicine is collected and normalized to construct a relatively accurate and comprehensive basic corpus of the efficacy of traditional Chinese medicine.

[0078] The basic corpus of Chinese medicine efficacy includes Chinese medicine number, Chinese medicine name, and Chinese medicine efficacy, and collects 473 commonly used Chinese medicines.

[0079] At the same time, the collected efficacy data are structured, normalized and standardized to ensure the consistency of the efficacy of each Chinese medicine. For example, when processing the efficacy of "replenishing qi" and "benefiting qi", the unified standard is standardized as "replenishing qi".

[0080] In the embodiment of the present invention, the present invention constructs a basic corpus of Chinese medicine efficacy, which includes a large amount of Chinese medicine and its efficacy information. On the basis of maintaining the original information in the book, it is standardized to ensure the accuracy and consistency of the data, and provide a reliable basis for obtaining the implicit efficacy of Chinese medicine.

[0081] S2. Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books and combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicine, a disease-syndrome-symptom-effect knowledge map is constructed.

[0082] In a feasible implementation method, this step mainly involves collecting and organizing data related to the disease-syndrome-symptom-efficacy knowledge graph. The entity node types in the graph include information such as cause of disease, disease name, syndrome name, symptom name, efficacy and Chinese medicine name. The relationship types in the graph include inclusion relationship, transmission relationship, manifestation relationship and treatment relationship.

[0083] In a feasible implementation, in S2, based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books and combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines, a disease-syndrome-symptom-effect knowledge graph is constructed, including:

[0084] Acquire basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books;

[0085] Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicine, entity nodes and relationships are used to express traditional Chinese medicine theory and construct a disease-syndrome-symptom-effect knowledge graph;

[0086] The disease-syndrome-symptom-efficacy knowledge graph is modeled and visualized.

[0087] In a feasible implementation, the goal of constructing the knowledge graph of the present invention is to use the basic theoretical knowledge of traditional Chinese medicine to deduce the implicit efficacy of traditional Chinese medicine, so its basic data sources are mainly: basic theories of traditional Chinese medicine and traditional Chinese medicine diagnosis.

[0088] In a feasible implementation, entity nodes include: disease, syndrome, symptom nodes and treatment relationship efficacy nodes; entity relationships include: the logical relationship of syndrome differentiation and treatment in traditional Chinese medicine theory, and the unified expression of traditional Chinese medicine and the efficacy relationship of traditional Chinese medicine.

[0089] In a feasible implementation, based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines, entity nodes and relationships are used to express traditional Chinese medicine theory to construct a disease-syndrome-symptom-effect knowledge graph, including:

[0090] Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, entity nodes and entity relationships are obtained;

[0091] Express basic TCM theories based on entity nodes and entity relationships;

[0092] Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicine, a composite node is established;

[0093] When processing efficacy nodes, the efficacy knowledge in the basic corpus of traditional Chinese medicine efficacy is integrated with the efficacy knowledge in the knowledge graph to form a complete and unified knowledge system.

[0094] In a feasible implementation, since the expression of TCM theories from various sources is not consistent, it is necessary to process the data in a unified conceptual level according to the original text records and the understanding of TCM theories, and to structure and standardize the data to form nodes and relationships. Among them, the entity node types are: cause, disease name, syndrome name, symptom name, disease (syndrome), symptom (syndrome), symptom (cause), symptom (disease), efficacy; the relationship types are: inclusion relationship, transmission relationship, manifestation relationship, and treatment relationship.

[0095] In a feasible implementation, in addition to establishing single nodes such as disease names, the present invention also establishes several composite nodes, such as disease (syndrome), symptom (syndrome), etc., in order to better reflect the theory of TCM syndrome differentiation and treatment. Taking "dizziness" as an example, when processing this atlas, in addition to the single entity node of the symptom name "dizziness", it is classified as a "symptom node"; there are also composite nodes such as "dizziness (blood deficiency)" and "dizziness (qi deficiency)", which are classified as "symptom (syndrome) nodes".

[0096] Among them, the compound node is a concept in traditional Chinese medicine. Each compound node represents different meanings. For example, because diseases in traditional Chinese medicine can be divided into various syndromes, the compound node of disease (syndrome) refers to a disease of a certain syndrome. In other words, diseases can be caused by different syndromes, and diseases caused by different syndromes have different treatments. For example, a cold can be caused by different syndromes, which are divided into cold (wind-heat), cold (wind-cold) and cold (summer dampness).

[0097] When processing the efficacy node, the efficacy knowledge in the basic corpus of Chinese medicine efficacy in step (1) is integrated with the efficacy knowledge in the knowledge graph to form a complete and unified knowledge system.

[0098] In a feasible implementation, the disease-syndrome-symptom-effect knowledge graph is modeled and visualized, including:

[0099] Establish a knowledge graph in the neo4j graph database to store the processed data in the form of "entity-relationship-entity" triples;

[0100] Use Gephi visualization tool to display the knowledge graph in the form of a point-line graph.

[0101] In a feasible implementation method, a knowledge graph is established in the neo4j graph database to store the processed data in the form of "entity-relationship-entity" triples, and the Gephi visualization tool is used to display the knowledge graph in the form of a point-line graph. Different point-line relationships are represented by different color properties, and the point-line relationship can be expanded to more than one level, and can have several levels of relationships, and can be edited online.

[0102] In the embodiment of the present invention, by constructing a disease-syndrome-symptom-efficacy knowledge graph, not only a large amount of information related to traditional Chinese medicine is collected and integrated to form a structured traditional Chinese medicine knowledge network, but also the content of syndrome differentiation and treatment on efficacy in traditional Chinese medicine theory can be extracted in the form of nodes and relationships, and the logic of traditional Chinese medicine syndrome differentiation is expressed through graph deduction, inclusion, and expression relationships, and the efficacy data is derived based on this, thereby discovering potential efficacy of traditional Chinese medicine.

[0103] S3. Combine the basic corpus of Chinese medicine efficacy with the disease-syndrome-symptom-efficacy knowledge graph to formulate implicit efficacy derivation rules and obtain the implicit efficacy of Chinese medicine.

[0104] In a feasible implementation, this step is to formulate rules using theoretical knowledge of traditional Chinese medicine, and to deduce the implicit efficacy of traditional Chinese medicine based on the basic knowledge network of traditional Chinese medicine formed by the disease-syndrome-symptom-efficacy knowledge graph according to the originally recorded information of the traditional Chinese medicine efficacy in the basic corpus of traditional Chinese medicine efficacy.

[0105] In a feasible implementation, in S3, the basic corpus of TCM efficacy is combined with the disease-syndrome-symptom-efficacy knowledge graph to formulate implicit efficacy derivation rules to obtain the implicit efficacy of TCM, including:

[0106] Construct a basic knowledge network of traditional Chinese medicine based on the basic corpus of traditional Chinese medicine efficacy and the disease-syndrome-symptom-effect knowledge graph;

[0107] Based on the basic knowledge network of traditional Chinese medicine, implicit efficacy derivation rules are formulated; through the formulated rules, the efficacy data of traditional Chinese medicine in the basic corpus of traditional Chinese medicine efficacy are analyzed and derived, and finally the implicit efficacy of traditional Chinese medicine is obtained.

[0108] In a feasible implementation, implicit efficacy derivation rules are formulated based on the basic knowledge network of traditional Chinese medicine; the efficacy data of traditional Chinese medicine in the basic corpus of traditional Chinese medicine efficacy are analyzed and derived through the formulated rules, and finally the implicit efficacy of traditional Chinese medicine is obtained, including:

[0109] According to the importance of the efficacy of traditional Chinese medicine, the efficacy of traditional Chinese medicine is classified into: core efficacy, derived A efficacy, derived B efficacy, derived C efficacy and derived D efficacy;

[0110] Based on the basic corpus of Chinese medicine efficacy, the core efficacy of various Chinese medicines is obtained;

[0111] For the core efficacy, find the corresponding efficacy node in the disease-syndrome-symptom-efficacy knowledge graph;

[0112] Based on the corresponding efficacy nodes, obtain the efficacy of other symptoms manifested by the diseases and syndromes treated in the core efficacy as the derived A efficacy;

[0113] Based on the corresponding efficacy nodes, sub-diseases and sub-syndromes included in the core efficacy diseases and syndromes are obtained as the derivation of B efficacy;

[0114] Based on the corresponding efficacy nodes, obtain the syndrome nodes and disease nodes corresponding to the symptoms in the core efficacy as the derivation of C efficacy;

[0115] Based on the corresponding efficacy nodes, the diseases and syndromes caused by the disease and syndrome nodes in the core efficacy, as well as the corresponding symptoms, are obtained as the derivation of D efficacy;

[0116] Obtain derived A efficacy, derived B efficacy, derived C efficacy and derived D efficacy, remove the core efficacy respectively, and obtain the implicit efficacy of traditional Chinese medicine.

[0117] In a feasible implementation manner, the present invention divides the efficacy of traditional Chinese medicine into five categories according to the importance of the efficacy from high to low: core efficacy, derived A efficacy, derived B efficacy, derived C efficacy and derived D efficacy.

[0118] Core efficacy: that is, the records of Chinese medicine efficacy obtained from the basic corpus of Chinese medicine efficacy, which fully reflects the efficacy in the book and directly finds the corresponding efficacy node from the disease-syndrome-symptom-efficacy knowledge graph.

[0119] Derived A efficacy: mainly covers the efficacy of other symptoms manifested by the diseases and syndromes treated in the core efficacy. The derivation method is to filter out the lower-level "symptom nodes" of the "manifestation relationship" corresponding to the "disease and syndrome nodes" upstream of the treatment relationship of the core efficacy node from the disease-syndrome-symptom-efficacy knowledge graph, and use the efficacy nodes corresponding to the "treatment relationship" of these "symptom nodes" as the derived A efficacy. Figure 2 shown.

[0120] Derived B efficacy: mainly covers the sub-diseases and sub-syndromes (unlimited in number) contained in the core efficacy diseases and syndromes. The derivation method is to filter out the lower-level "disease and syndrome nodes" in the "inclusion relationship" corresponding to the "disease and syndrome nodes" upstream of the treatment relationship of the core efficacy node from the disease-syndrome-symptom-efficacy knowledge graph, as well as the lower-level "symptom nodes" of the "manifestation relationship" corresponding to them, and filter out the efficacy nodes corresponding to the "treatment relationship" of these "disease, syndrome, symptom nodes" as the derived B efficacy. Figure 3 shown.

[0121] Derived C efficacy: mainly covers the syndrome nodes and disease nodes corresponding to the symptoms (diseases, syndromes) in the core efficacy. The derivation method is to select the upper-level "disease, syndrome nodes" of the "manifestation relationship" of the "symptom (disease, syndrome) nodes" upstream of the treatment relationship of the core efficacy node from the disease-syndrome-symptom-efficacy knowledge graph, and use the efficacy nodes corresponding to the "treatment relationship" of these "disease, syndrome nodes" as the derivation of C efficacy. Figure 4 Shown

[0122] Derived D efficacy: mainly covers the diseases and syndromes caused by the disease and syndrome nodes in the core efficacy, and the corresponding symptoms (only level 1). The derivation method is to use the lower-level "disease and syndrome nodes" in the "derived relationship" corresponding to the "disease and syndrome nodes" upstream of the treatment relationship in the disease-syndrome-symptom-efficacy knowledge graph, and the lower-level "symptom nodes" of the "manifestation relationship" corresponding to the core efficacy nodes, and use the efficacy nodes corresponding to the "treatment relationship" of these "disease, syndrome, symptom nodes" as the derived D efficacy. Figure 5 shown.

[0123] The derived efficacy A, derived efficacy B, derived efficacy C and derived efficacy D obtained through the above rules, and then removing the core efficacy, are the implicit efficacy of traditional Chinese medicine.

[0124] The implicit efficacy obtained in this application is the efficacy of traditional Chinese medicine that is not recorded in the book, and can be derived through the basic theory of traditional Chinese medicine, because the record of the efficacy of traditional Chinese medicine is often highly generalized, and generally only describes the syndrome treated and some of the symptoms involved. For example, Astragalus is recorded to have the effects of replenishing qi and treating fatigue, but it is not recorded that it has the effect of treating laziness. However, according to traditional Chinese medicine theory and clinical experience, qi deficiency may lead to laziness, so Astragalus is likely to have a therapeutic effect on this symptom as well. According to this feature, the present invention uses the logical relationship between the performance relationship of "qi deficiency" (syndrome node) and "laziness" (symptom node) in the constructed atlas to expand the efficacy and reflect the implicit efficacy of traditional Chinese medicine in traditional knowledge.

[0125] In summary, this is to utilize the disease, syndrome, symptom nodes and treatment relationship efficacy nodes of the disease-syndrome-symptom-efficacy knowledge graph, and through the established rules, analyze and deduce the efficacy data of traditional Chinese medicine (i.e. core efficacy) in the basic corpus of traditional Chinese medicine efficacy, and finally obtain the implicit efficacy of traditional Chinese medicine.

[0126] In the embodiments of the present invention, the present invention has formulated special rules according to the logic of TCM theory, and has conducted deductive research on the original knowledge of TCM efficacy, so that the derived implicit efficacy is completely based on the basic theory of TCM, and the knowledge graph content, TCM efficacy data and formulated rules are highly combined, thereby improving the professionalism and accuracy of the obtained implicit efficacy.

[0127] Figure 6 3 is a block diagram of a device 300 for deriving implicit efficacy of traditional Chinese medicine based on a knowledge graph according to an exemplary embodiment. The device is used for a method for deriving implicit efficacy of traditional Chinese medicine based on a knowledge graph. Figure 6 The device includes a corpus construction module 310, a knowledge graph construction module 320 and an implicit efficacy derivation module 330. Among them:

[0128] The corpus construction module 310 is used to collect and organize the information on the efficacy of traditional Chinese medicines recorded in traditional Chinese medicine books and construct a basic corpus of the efficacy of traditional Chinese medicines;

[0129] The knowledge graph construction module 320 is used to construct a disease-syndrome-symptom-effect knowledge graph based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books and combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines;

[0130] The implicit efficacy derivation module 330 is used to combine the basic corpus of Chinese medicine efficacy with the disease-syndrome-symptom-efficacy knowledge graph, formulate implicit efficacy derivation rules, and obtain the implicit efficacy of Chinese medicine.

[0131] Optionally, the corpus construction module 310 is used to collect the efficacy information of traditional Chinese medicine recorded in traditional Chinese medicine books;

[0132] Structuring, normalizing and standardizing the information on the efficacy of traditional Chinese medicines recorded in traditional Chinese medicine books to obtain unified expression of efficacy terms;

[0133] Construct a basic corpus of Chinese medicine efficacy; the information in the basic corpus includes Chinese medicine number, Chinese medicine name and Chinese medicine efficacy.

[0134] Optionally, the knowledge graph construction module 320 is used to obtain basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books;

[0135] Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicine, entity nodes and relationships are used to express traditional Chinese medicine theory and construct a disease-syndrome-symptom-effect knowledge graph;

[0136] The disease-syndrome-symptom-efficacy knowledge graph is modeled and visualized.

[0137] Optionally, entity nodes include: disease, syndrome, symptom nodes and treatment relationship efficacy nodes; entity relationships include: logical relationships of syndrome differentiation and treatment in traditional Chinese medicine theory, and unified expressed relationships between Chinese medicine and its efficacy.

[0138] Optionally, based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines, entity nodes and relationships are used to express traditional Chinese medicine theory to construct a disease-syndrome-symptom-effect knowledge graph, including:

[0139] Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, entity nodes and entity relationships are obtained;

[0140] Express basic TCM theories based on entity nodes and entity relationships;

[0141] Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of related traditional Chinese medicine, a composite node is established;

[0142] When processing efficacy nodes, the efficacy knowledge in the basic corpus of traditional Chinese medicine efficacy is integrated with the efficacy knowledge in the knowledge graph to form a complete and unified knowledge system.

[0143] Optionally, the disease-syndrome-symptom-effect knowledge graph is modeled and visualized, including:

[0144] Establish a knowledge graph in the neo4j graph database to store the processed data in the form of "entity-relationship-entity" triples;

[0145] Use Gephi visualization tool to display the knowledge graph in the form of a point-line graph.

[0146] Optionally, the implicit efficacy derivation module 330 is used to construct a basic knowledge network of traditional Chinese medicine based on the basic corpus of traditional Chinese medicine efficacy and the disease-syndrome-symptom-efficacy knowledge graph;

[0147] Based on the basic knowledge network of traditional Chinese medicine, implicit efficacy derivation rules are formulated; through the formulated rules, the efficacy data of traditional Chinese medicine in the basic corpus of traditional Chinese medicine efficacy are analyzed and derived, and finally the implicit efficacy of traditional Chinese medicine is obtained.

[0148] Optionally, implicit efficacy derivation rules are formulated based on the basic knowledge network of traditional Chinese medicine; through the formulated rules, the efficacy data of traditional Chinese medicine in the basic corpus of traditional Chinese medicine efficacy are analyzed and derived, and finally the implicit efficacy of traditional Chinese medicine is obtained, including:

[0149] According to the importance of the efficacy of traditional Chinese medicine, the efficacy of traditional Chinese medicine is classified into: core efficacy, derived A efficacy, derived B efficacy, derived C efficacy and derived D efficacy;

[0150] Based on the basic corpus of Chinese medicine efficacy, the core efficacy of various Chinese medicines is obtained;

[0151] For the core efficacy, find the corresponding efficacy node in the disease-syndrome-symptom-efficacy knowledge graph;

[0152] Based on the corresponding efficacy nodes, obtain the efficacy of other symptoms manifested by the diseases and syndromes treated in the core efficacy as the derived A efficacy;

[0153] Based on the corresponding efficacy nodes, sub-diseases and sub-syndromes included in the core efficacy diseases and syndromes are obtained as the derivation of B efficacy;

[0154] Based on the corresponding efficacy nodes, obtain the syndrome nodes and disease nodes corresponding to the symptoms in the core efficacy as the derivation of C efficacy;

[0155] Based on the corresponding efficacy nodes, the diseases and syndromes caused by the disease and syndrome nodes in the core efficacy, as well as the corresponding symptoms, are obtained as the derivation of D efficacy;

[0156] Obtain derived A efficacy, derived B efficacy, derived C efficacy and derived D efficacy, remove the core efficacy respectively, and obtain the implicit efficacy of traditional Chinese medicine.

[0157] In the embodiments of the present invention, the present invention is based on known theoretical knowledge of traditional Chinese medicine. Compared with intelligent simulation and artificial intelligence, the knowledge graph of traditional Chinese medicine presents the complex relationship between diseases, syndromes, symptoms and efficacy in a graphical way, and can also display the reasoning path and basis of each step in the reasoning process, so that researchers can browse and query relevant information intuitively and quickly, which not only greatly improves the efficiency of obtaining the implicit efficacy of traditional Chinese medicine, but also improves the interpretability and transparency of the invention.

[0158] Figure 7 is a schematic diagram of the structure of a device for deriving implicit efficacy of traditional Chinese medicine based on a knowledge graph provided by an embodiment of the present invention, such as Figure 7 As shown, the knowledge graph-based Chinese medicine implicit efficacy derivation device may include the above Figure 6 The device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph is shown. Optionally, the device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph 410 may include a first processor 2001 .

[0159] Optionally, the knowledge graph-based traditional Chinese medicine implicit efficacy derivation device 410 may also include a memory 2002 and a transceiver 2003 .

[0160] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0161] Combine the following Figure 7The components of the knowledge graph-based Chinese medicine implicit efficacy derivation device 410 are specifically introduced:

[0162] The first processor 2001 is the control center of the knowledge graph-based Chinese medicine implicit efficacy derivation device 410, which can be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0163] Optionally, the first processor 2001 can perform various functions of the knowledge graph-based traditional Chinese medicine implicit efficacy derivation device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002.

[0164] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 7 CPU0 and CPU1 are shown in FIG.

[0165] In a specific implementation, as an embodiment, the knowledge graph-based Chinese medicine implicit efficacy derivation device 410 may also include multiple processors, such as Figure 7 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0166] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0167] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently, and may be accessed through the interface circuit ( Figure 7 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0168] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0169] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 7 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0170] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently, and may be connected to the first processor 2001 through the interface circuit ( Figure 7 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0171] It should be noted that Figure 7 The structure of the knowledge graph-based TCM implicit efficacy derivation device 410 shown in the figure does not constitute a limitation on the router. The actual knowledge structure identification device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0172] In addition, the technical effects of the device 410 for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph can refer to the technical effects of the method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph described in the above method embodiment, and will not be repeated here.

[0173] It should be understood that the first processor 2001 in the embodiment of the present invention 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), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0174] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0175] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0176] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0177] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0178] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0179] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0180] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0181] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.

[0182] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph, characterized in that: The method comprises: S1. Collect and organize the information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books and build a basic corpus of the efficacy of traditional Chinese medicine; S2. Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books and combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines, a disease-syndrome-symptom-effect knowledge map is constructed; S3. Combine the basic corpus of Chinese medicine efficacy with the disease-syndrome-symptom-efficacy knowledge graph, formulate implicit efficacy derivation rules, and obtain the implicit efficacy of Chinese medicine.

2. The method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph according to claim 1, characterized in that: In S1, the information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books is collected and sorted to construct a basic corpus of the efficacy of traditional Chinese medicine, including: Collect information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books; Structuring, normalizing and standardizing the information on the efficacy of traditional Chinese medicines recorded in the traditional Chinese medicine books to obtain a unified expression of efficacy; A basic corpus of Chinese medicine efficacy is constructed; wherein the information in the basic corpus of Chinese medicine efficacy includes Chinese medicine number, Chinese medicine name and Chinese medicine efficacy.

3. The method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph according to claim 2, characterized in that: In S2, based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books and combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines, a disease-syndrome-symptom-effect knowledge graph is constructed, including: Acquire basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books; Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicine, entity nodes and relationships are used to express traditional Chinese medicine theory and construct a disease-syndrome-symptom-effect knowledge graph; The disease-syndrome-symptom-efficacy knowledge graph is modeled and visualized.

4. The method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph according to claim 3, characterized in that: The entity nodes include: disease, syndrome, symptom nodes and treatment relationship efficacy nodes; the entity relationship includes: the logical relationship of syndrome differentiation and treatment in traditional Chinese medicine theory, and the relationship between traditional Chinese medicine and its efficacy after unified expression.

5. The method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph according to claim 4, characterized in that: The basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books is combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines, and entity nodes and relationships are used to express traditional Chinese medicine theory to construct a disease-syndrome-symptom-effect knowledge graph, including: Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, entity nodes and entity relationships are obtained; Expressing basic TCM theory based on the entity nodes and entity relationships; Based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books, combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicine, a composite node is established; When processing efficacy nodes, the efficacy knowledge in the basic corpus of traditional Chinese medicine efficacy is integrated with the efficacy knowledge in the knowledge graph to form a complete and unified knowledge system.

6. The method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph according to claim 5, characterized in that: The method of performing graph modeling and visualization processing on the disease-syndrome-symptom-effect knowledge graph includes: Establish a knowledge graph in the neo4j graph database and store the processed data in the form of "entity-relationship-entity" triples; Use Gephi visualization tool to display the knowledge graph in the form of a point-line graph.

7. The method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph according to claim 6, characterized in that: In S3, the basic corpus of Chinese medicine efficacy is combined with the disease-syndrome-symptom-efficacy knowledge graph to formulate implicit efficacy derivation rules and obtain the implicit efficacy of Chinese medicine, including: Based on the basic corpus of Chinese medicine efficacy and the disease-syndrome-symptom-efficacy knowledge graph, a basic knowledge network of Chinese medicine is constructed; Based on the basic knowledge network of traditional Chinese medicine, implicit efficacy derivation rules are formulated; through the formulated rules, the efficacy data of traditional Chinese medicine in the basic corpus of traditional Chinese medicine efficacy are analyzed and derived, and finally the implicit efficacy of traditional Chinese medicine is obtained.

8. The method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph according to claim 7, characterized in that: The implicit efficacy derivation rules are formulated based on the basic knowledge network of traditional Chinese medicine; the efficacy data of traditional Chinese medicine in the basic corpus of traditional Chinese medicine efficacy are analyzed and derived through the formulated rules, and the implicit efficacy of traditional Chinese medicine is finally obtained, including: According to the importance of the efficacy of the traditional Chinese medicine, the efficacy of the traditional Chinese medicine is classified into: core efficacy, derived A efficacy, derived B efficacy, derived C efficacy and derived D efficacy; Based on the basic corpus of Chinese medicine efficacy, the core efficacy of various Chinese medicines is obtained; For the core efficacy, find the corresponding efficacy node in the disease-syndrome-symptom-efficacy knowledge graph; Based on the corresponding efficacy nodes, the efficacy of other symptoms manifested by the diseases and syndromes treated in the core efficacy is obtained as the derived A efficacy; Based on the corresponding efficacy node, sub-diseases and sub-syndromes included in the core efficacy disease and syndrome are obtained as the derivation of B efficacy; Based on the corresponding efficacy nodes, obtaining the syndrome nodes and disease nodes corresponding to the symptoms in the core efficacy as the derived C efficacy; Based on the corresponding efficacy nodes, the diseases and syndromes caused by the disease and syndrome nodes in the core efficacy and the corresponding symptoms are obtained as the derived D efficacy; Obtain the derived A efficacy, derived B efficacy, derived C efficacy and derived D efficacy, remove the core efficacy respectively, and obtain the implicit efficacy of the traditional Chinese medicine.

9. A device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph, wherein the device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph is used to implement the method for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph as claimed in any one of claims 1 to 8, characterized in that: The device comprises: The corpus construction module is used to collect and organize the information on the efficacy of traditional Chinese medicine recorded in traditional Chinese medicine books and build a basic corpus of the efficacy of traditional Chinese medicine; The knowledge graph construction module is used to construct a disease-syndrome-symptom-effect knowledge graph based on the basic theoretical knowledge of traditional Chinese medicine recorded in traditional Chinese medicine books and combined with the syndrome differentiation and treatment data of relevant traditional Chinese medicines; The implicit efficacy derivation module is used to combine the basic corpus of Chinese medicine efficacy and the disease-syndrome-symptom-efficacy knowledge graph, formulate implicit efficacy derivation rules, and obtain the implicit efficacy of Chinese medicine.

10. A device for deriving implicit efficacy of traditional Chinese medicine based on knowledge graph, characterized in that: The device for deducing implicit efficacy of traditional Chinese medicine based on knowledge graph includes: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 8 is implemented.

Images