Association construction method and device for traditional Chinese medicine ancient books, equipment and storage medium

Abstract

The invention provides a traditional Chinese medicine ancient book association construction method and device, equipment and a storage medium, and the method comprises the steps: converting a traditional Chinese medicine ancient book into an editable digital text, obtaining a standardized expression text of the traditional Chinese medicine ancient book, obtaining a semantic relationship and context information of the traditional Chinese medicine ancient book, and determining a relationship between key entities of the traditional Chinese medicine ancient book, constructing a knowledge graph in the traditional Chinese medicine ancient books; the method comprises the following steps: based on a knowledge graph in a traditional Chinese medicine ancient book, obtaining an association relationship of key entities of different traditional Chinese medicine ancient books, completing association construction of different traditional Chinese medicine ancient books, extracting disease and symptom characteristics in modern biomedical data, matching corresponding traditional Chinese medicine ancient book contents, and realizing association construction of the disease and symptom characteristics and the traditional Chinese medicine ancient book contents. According to the application, through association construction among different traditional Chinese medicine ancient books, in-depth analysis of traditional Chinese medicine knowledge is realized, and content in the traditional Chinese medicine ancient books is associated and matched with disease characteristics in modern biomedical data, so that the traditional Chinese medicine ancient books play an important role again.

Description

Technical Field

[0001] The present application relates to the technical field of association construction of ancient Chinese medicine books, and specifically to an association construction method, device, equipment and storage medium for ancient Chinese medicine books. Background Art

[0002] At present, it is common to conduct digital research on ancient Chinese medicine books. Although simple digital storage is convenient for preservation and retrieval, it cannot intuitively show the internal connections and deep logic between ancient books. This limitation makes it particularly difficult to effectively integrate and efficiently utilize ancient knowledge. In addition, ancient books are written in classical Chinese, with complex terminology and have evolved through multiple historical stages. This has led to significant differences in the expression, theoretical framework and drug cognition between different ancient books. This diversity not only increases the difficulty of understanding, but also hinders the coherence of knowledge. The connections between ancient books are often subtle and complex. Manually identifying these connections is not only time-consuming and laborious, but also requires researchers to have deep knowledge of traditional Chinese medicine and rich practical experience, which further exacerbates the difficulty of integrating ancient knowledge. Therefore, how to construct associations for ancient Chinese medicine books has become a key issue that needs to be solved. Summary of the invention

[0003] In order to overcome the above problems existing in the prior art, the present application provides a method, device, equipment and storage medium for building associations of ancient Chinese medicine books, which adopts the following technical solutions:

[0004] In a first aspect, the present application provides a method for building associations of ancient Chinese medicine books, comprising:

[0005] Converting ancient Chinese medicine books into editable digital texts, and obtaining standardized expression texts of the ancient Chinese medicine books based on the editable digital texts;

[0006] Based on the standardized expression text of the ancient Chinese medicine book, the semantic relationship and context information of the ancient Chinese medicine book are obtained, and the relationship between the key entities of the ancient Chinese medicine book is determined;

[0007] Based on the relationship between key entities, a knowledge graph is constructed inside ancient Chinese medicine books;

[0008] Based on the knowledge graph inside the ancient Chinese medicine books, the association relationship between key entities of different ancient Chinese medicine books is obtained, and the association construction of different ancient Chinese medicine books is completed;

[0009] Extract disease and symptom characteristics from modern biomedical data, obtain the related content of ancient Chinese medicine books associated with disease and symptom characteristics, and realize the association construction between disease and symptom characteristics and the content of ancient Chinese medicine books.

[0010] Furthermore, the said conversion of the ancient Chinese medicine books into editable digital texts specifically includes:

[0011] Obtain various ancient Chinese medicine books, including existing ancient Chinese medicine literature materials;

[0012] Scanning the different ancient Chinese medicine books to generate a high-definition electronic image file set;

[0013] Converting the electronic image file set into an editable digital text set based on optical character recognition technology;

[0014] The editable digitized text is formatted to eliminate recognition errors and converted into a unified preset format text.

[0015] Furthermore, based on the editable digital text, the standardized expression text of the ancient Chinese medicine book is obtained, and the specific content includes:

[0016] Build a TCM terminology mapping knowledge base to map terms with different expressions into unified standard terms;

[0017] Standardize the names of medicinal materials and diseases, and establish a standard correspondence between medicinal materials, diseases and prescriptions;

[0018] Identify key entities of Chinese medicinal materials, diseases, and prescriptions in the editable digital text, and perform semantic type annotation on the identified key entities;

[0019] Based on the TCM terminology mapping knowledge base, the identified key entities are replaced with unified standard terms, and the replaced unified standard terms are annotated to generate standardized text expressions.

[0020] Furthermore, based on the standardized expression text of the ancient Chinese medicine book, the semantic relationship and context information of the ancient Chinese medicine book are obtained, and the relationship between the key entities of the ancient Chinese medicine book is determined. Specifically, the content includes:

[0021] Formulate semantic relationship extraction rules based on the language characteristics and professional knowledge of ancient Chinese medicine books;

[0022] Based on regular expressions and semantic relationship extraction rules, the semantic relationship between key entities is obtained by defining regular expression patterns containing relationship keywords and entity types;

[0023] For each key entity, a fixed text window size is set, and in the standardized expression text, the words in the window around the key entity are extracted as context information;

[0024] The acquired semantic relationship information and context information are integrated, and the integrated semantic relationship and context information are stored using a data structure.

[0025] Furthermore, the knowledge graph inside the ancient Chinese medicine books is constructed based on the relationship between key entities, and the specific contents include:

[0026] Analyze the types of key entities and determine the node types in the knowledge graph;

[0027] Define the edge types in the knowledge graph based on the relationships between key entities;

[0028] Based on the operation statements of the graph database or the corresponding API and the determined node types, create nodes in the knowledge graph one by one;

[0029] Based on the determined edge type, edges are created between corresponding nodes to represent the relationship between key entities;

[0030] In the process of creating nodes and edges, their pre-planned attribute values ​​are set at the same time. In addition to directly setting some attributes when creating nodes and edges, the attribute settings of nodes and edges can also be improved through subsequent update operations.

[0031] Furthermore, based on the knowledge graph inside the ancient Chinese medicine book, the association relationship between key entities of different ancient Chinese medicine books is obtained to complete the association construction of different ancient Chinese medicine books, and the specific contents include:

[0032] Identify key entities in the internal knowledge graphs of different ancient Chinese medicine books;

[0033] Obtaining semantic relations between identified key entities;

[0034] Based on the identified key entities and the semantic relationships between key entities, each ancient Chinese medicine book is regarded as a node in the association network, and the key entities in different ancient book knowledge graphs are also regarded as nodes. By adding ancient book source attributes to the key entities, the entities with the same name in different ancient books are distinguished to ensure the uniqueness and identifiability of the nodes in the network; edges are defined according to semantic relationships. When two key entities come from different ancient books and have a semantic relationship, edges are established between the corresponding ancient book nodes and the key entity nodes, so as to construct an association network between different ancient Chinese medicine books.

[0035] Furthermore, the method of obtaining the association relationship between key entities of different ancient Chinese medicine books based on the knowledge graph inside the ancient Chinese medicine books and completing the association construction of different ancient Chinese medicine books also includes:

[0036] Based on the constructed association network and the existing knowledge graph, starting from a key entity node, through depth-first search of other key entity nodes related to the key node, the relationship and path between the key node and other key entity nodes are analyzed to obtain the potential association relationship between the key node and other key entity nodes.

[0037] Furthermore, the extraction of disease symptom characteristics from modern biomedical data, obtaining the content associated with the ancient Chinese medicine books associated with the disease symptom characteristics, and realizing the association between the disease symptom characteristics and the content of the ancient Chinese medicine books are specifically manifested as follows:

[0038] Based on modern biomedical data, collect data related to diseases and symptoms;

[0039] Using the data related to the disease symptoms as input to a preset disease characteristic model to obtain disease symptom characteristics;

[0040] Based on the preset term mapping table, the disease symptom characteristics and related expressions in ancient Chinese medicine books are obtained, and the related expressions are used as search conditions to obtain content nodes of ancient Chinese medicine books related to the disease symptom characteristics;

[0041] Extract relevant information of content nodes of ancient Chinese medicine books as related content of ancient Chinese medicine books associated with disease symptom characteristics;

[0042] The word vector model is used to convert the disease feature description and the content of ancient Chinese medicine books into word vector sequences respectively, and then the cosine similarity semantic similarity index between the two is calculated. According to the set similarity threshold, it is judged whether the semantics match;

[0043] When the disease symptom characteristics and the content of ancient Chinese medicine books meet the semantic match, the symptoms in modern medicine are encoded and processed, and the symptom descriptions in ancient books are converted into word vectors through natural language processing technology. The similarity index between the disease symptom characteristics and the content of ancient Chinese medicine books is calculated to determine the similarity degree of the symptoms.

[0044] When the degree of similarity between the disease symptom characteristics and the symptoms of ancient Chinese medicine books meets the preset threshold, the disease symptom characteristics and the content of ancient Chinese medicine books are associated and constructed at the knowledge graph level to form a cross-domain knowledge network.

[0045] In another aspect, the present application also provides a device for building associations of ancient Chinese medicine books, including:

[0046] A standardized expression text acquisition module is used to convert the ancient Chinese medicine book into an editable digital text, and obtain the standardized expression text of the ancient Chinese medicine book based on the editable digital text;

[0047] A key entity relationship determination module is used to obtain the semantic relationship and context information of the ancient Chinese medicine book based on the standardized expression text of the ancient Chinese medicine book, and determine the relationship between the key entities of the ancient Chinese medicine book;

[0048] The knowledge graph construction module is used to construct the knowledge graph inside the ancient Chinese medicine books based on the relationship between key entities;

[0049] The first association construction module is used to obtain the association relationship between key entities of different ancient Chinese medicine books based on the knowledge graph inside the ancient Chinese medicine books, and complete the association construction of different ancient Chinese medicine books;

[0050] The association construction module is used to extract disease symptom characteristics from modern biomedical data, obtain the related content of ancient Chinese medicine books associated with the disease symptom characteristics, and realize the association construction between disease symptom characteristics and the content of ancient Chinese medicine books.

[0051] In a third aspect, the present application provides an electronic device, including:

[0052] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, cause the device to perform the method as described in the first aspect.

[0053] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method described in the first aspect.

[0054] In a fifth aspect, the present application provides a computer program, which, when executed by a computer, is used to execute the method described in the first aspect.

[0055] In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged together with the processor, or may be stored in whole or in part on a memory not packaged together with the processor.

[0056] This application has the following beneficial effects:

[0057] 1. This application converts ancient Chinese medicine books into editable digital texts, and obtains standardized expression texts of ancient Chinese medicine books based on the editable digital texts. In the process of building associations between different ancient Chinese medicine books, standardized expressions can be used to break down the differences between different ancient Chinese medicine books.

[0058] 2. This application obtains the semantic relationship and context information of ancient Chinese medicine books based on the standardized expression text of ancient Chinese medicine books, determines the relationship between key entities, constructs the knowledge graph inside the ancient Chinese medicine books based on the relationship between key entities, obtains the association relationship between key entities of different ancient Chinese medicine books based on the knowledge graph inside the ancient Chinese medicine books, completes the association construction of different ancient Chinese medicine books, extracts disease symptom characteristics in modern biomedical data, obtains the related content of ancient Chinese medicine books associated with the disease symptom characteristics, and realizes the association construction of disease symptom characteristics and the content of ancient Chinese medicine books; This application obtains semantic relationships and context information from standardized expression texts, can dig out the hidden knowledge in ancient books, establishes association relationships between different ancient Chinese medicine books, can discover the connection between different ancient books in the process of knowledge inheritance and development, associates modern biomedical data with the content of ancient Chinese medicine books, and can dig out the combination of traditional Chinese medicine knowledge and modern medical knowledge; This application realizes in-depth analysis of Chinese medicine knowledge through the association construction between different ancient Chinese medicine books, and associates and matches the content in ancient Chinese medicine books with the symptom characteristics in modern biomedical data, so that ancient Chinese medicine books can play their important role again. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0060] Figure 2 A flow chart of a method for building associations of ancient Chinese medicine books according to an embodiment of the present application;

[0061] Figure 3 A flowchart of obtaining editable digitized text according to an embodiment of the present application;

[0062] Figure 4 A flowchart for obtaining standardized expression text according to an embodiment of the present application;

[0063] Figure 5 A flowchart for determining key entity relationships in ancient Chinese medicine books according to an embodiment of the present application;

[0064] Figure 6 A flowchart for constructing an internal knowledge graph of ancient Chinese medicine books according to an embodiment of the present application;

[0065] Figure 7 A flowchart for associating different ancient Chinese medicine books in the embodiment of the present application;

[0066] Figure 8 A flow chart is constructed for the association between the disease symptom characteristics and the contents of ancient Chinese medicine books in the embodiment of the present application;

[0067] Fig. 9 This is a flow chart of the device according to an embodiment of the present application;

[0068] Fig.10It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0069] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "first", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0070] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0071] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0072] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0073] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0074] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers and desktop computers, etc.

[0075] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0076] It should be noted that the method for building an association between ancient Chinese medicine books provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the device for building an association between ancient Chinese medicine books is generally set in the server / terminal device.

[0077] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0078] Continue to refer Figure 2 , the figure shows a flow chart of a method for building associations of ancient Chinese medicine books of the present application, the method comprising the following steps:

[0079] Step 201, converting the ancient Chinese medicine book into an editable digital text, and obtaining the standardized expression text of the ancient Chinese medicine book based on the editable digital text.

[0080] In a possible implementation, the ancient Chinese medicine book is converted into an editable digital text, please refer to Figure 3 , specifically:

[0081] Step 31, obtaining different ancient Chinese medicine books, including existing ancient Chinese medicine literature materials.

[0082] Step 32, scanning the different ancient Chinese medicine books to generate a high-definition electronic image file set.

[0083] Step 33: Convert the electronic image file set into an editable digital text set based on optical character recognition technology.

[0084] Step 34, formatting the editable digitized text to eliminate recognition errors and converting it into a unified preset format text.

[0085] In a possible implementation manner, based on the editable digital text, obtain the standardized expression text of traditional Chinese medicine ancient books. Please refer to Figure 4 , which is specifically manifested as follows:

[0086] Step 41, construct a mapping knowledge base for traditional Chinese medicine terms, and map terms with different expressions to unified standard terms.

[0087] Step 42, standardize the names of medicinal materials and diseases, and establish the standard corresponding relationship among medicinal materials-diseases-prescriptions.

[0088] Step 43, identify the key entities of medicinal materials, diseases, and prescriptions in the editable digital text, and perform semantic type annotation on the identified key entities.

[0089] Step 44, based on the mapping knowledge base of traditional Chinese medicine terms, replace the identified key entities with unified standard terms, and annotate the replaced unified standard terms to generate a standardized text expression.

[0090] Step 202, based on the standardized expression text of the traditional Chinese medicine ancient books, obtain the semantic relationships and context information of the traditional Chinese medicine ancient books, and determine the relationships among the key entities of the traditional Chinese medicine ancient books.

[0091] In a possible implementation manner, based on the standardized expression text of the traditional Chinese medicine ancient books, obtain the semantic relationships and context information of the traditional Chinese medicine ancient books, and determine the relationships among the key entities of the traditional Chinese medicine ancient books. Please refer to Figure 5 , which is specifically manifested as follows:

[0092] Step 51, formulate semantic relationship extraction rules based on the language characteristics and professional knowledge of traditional Chinese medicine ancient books. For example, for the treatment relationship, if words such as "treat", "cure", "heal", "chiefly treat" appear in the text, and there are a medicinal material name and a disease name before and after respectively, then it can be determined that there is a treatment relationship. For example, for "Ginseng treats qi deficiency", the treatment relationship between ginseng and qi deficiency can be determined.

[0093] Step 52, based on regular expressions and semantic relationship extraction rules, obtain the semantic relationships among key entities by defining a regular expression pattern that includes relationship keywords and entity types. For example, for the inclusion relationship between a prescription and a medicinal material, the regular expression can be set as "prescription name [contains|has|is composed of] medicinal material name".

[0094] Step 53, for each key entity, set a fixed text window size, and in the standardized expression text, extract the words within the window around the key entity as context information. For example, for the key entity "Ginseng", if the text is "Ginseng is sweet in taste, slightly warm in nature, and greatly tonifies primordial qi", taking a certain number of words before and after "Ginseng" as the center, the obtained context information is "sweet in taste, slightly warm in nature, and greatly tonifies primordial qi".

[0095] Step 54, the acquired semantic relationship information and context information are integrated, and the integrated semantic relationship and context information are stored using a data structure. For example, for the therapeutic relationship between two key entities (herbal medicine and disease), the specific situation of the therapeutic relationship can be more accurately understood by combining the context information (such as the nature and taste of the herbal medicine, the symptoms of the disease, etc.).

[0096] The types of relationships between key entities in ancient Chinese medicine books include medicinal material-disease relationship, prescription-symptom relationship, medicinal material-efficacy relationship, disease-treatment relationship, etc.

[0097] Step 203, constructing a knowledge graph inside the ancient Chinese medicine book based on the relationship between key entities.

[0098] In a possible implementation, the knowledge graph of ancient Chinese medicine books is constructed based on the relationship between key entities. Figure 6 , the specific contents include:

[0099] Step 61, analyze the types of key entities and determine the node types in the knowledge graph. In the context of ancient Chinese medicine books, common node types may include: Medicinal material node: represents various Chinese medicinal materials, and its attributes may include information such as medicinal material name, nature and taste, meridian, origin, efficacy, etc. Symptom node: corresponds to various diseases mentioned in ancient books, and its attributes may cover the name of the disease, symptoms, causes, classification, etc. Prescription node: used to represent the prescription recorded in ancient books, and its attributes include prescription name, constituent medicinal materials, usage and dosage, main symptoms, etc. Character node: if the ancient books involve content related to characters such as authors and doctors, character nodes can be set up, and attributes such as name, dynasty, major contributions, etc. Processing method node: for the description of the processing of Chinese medicine, this node is set up, and its attributes include the name of the processing method, operation steps, applicable medicinal materials, etc.

[0100] Step 62, define the type of edge in the knowledge graph according to the relationship determined between the key entities. For example: Treatment relationship edge: connects the medicinal material node and the disease node, indicating that the medicinal material can be used to treat the corresponding disease. Composition relationship edge: exists between the prescription node and the medicinal material node, indicating that the medicinal material is one of the components of this prescription. Writing relationship edge: connects the character node (author) and the ancient book related nodes (such as prescription nodes, disease nodes, etc., if it is the content written by the author), reflecting the creation relationship. Processing relationship edge: associates the medicinal material node and the processing method node, indicating that the medicinal material can be processed using this processing method.

[0101] Step 63, based on the operation statements of the graph database or the corresponding API and the determined node types, create nodes in the knowledge graph one by one.

[0102] Step 64: Based on the determined edge type, edges are created between corresponding nodes to represent the relationship between key entities, for example, a treatment relationship edge is created to represent that ginseng can treat qi deficiency.

[0103] In a possible implementation, in the process of creating nodes and edges, pre-planned attribute values ​​of nodes and edges are set at the same time. In addition to directly setting some attributes when creating nodes and edges, the attribute settings of nodes and edges can also be improved through subsequent update operations.

[0104] For example, for the treatment relationship edge, you can set attributes such as "treatment basis" to record the specific sentences or paragraphs that mention the treatment relationship in ancient books. The "composition of medicinal materials" attribute of the prescription node can be further refined, including information such as the amount of each medicinal material in the prescription and the processing requirements. The "main contribution" attribute of the person node can list in detail his specific academic achievements and works in the field of traditional Chinese medicine.

[0105] Step 204, based on the knowledge graph inside the ancient Chinese medicine book, obtain the association relationship between the key entities of different ancient Chinese medicine books, and complete the association construction of different ancient Chinese medicine books.

[0106] In a possible implementation, the association relationship between key entities of different ancient Chinese medicine books is obtained based on the knowledge graph inside the ancient Chinese medicine books, and the association construction of different ancient Chinese medicine books is completed. Please refer to Figure 7 , specifically:

[0107] Step 71, identifying key entities in the internal knowledge graphs of different ancient Chinese medicine books. The identification of key entities in the internal knowledge graphs of different ancient Chinese medicine books can be achieved by formulating identification rules based on the language characteristics and professional vocabulary rules of the ancient Chinese medicine books, or by machine learning or deep learning to identify key entities in the internal knowledge graphs of different ancient Chinese medicine books.

[0108] Step 72, obtaining the semantic relationship between the identified key entities. The semantic relationship between the identified key entities can be obtained by analyzing the language expressions of ancient Chinese medicine books, summarizing the common expression patterns of the relationship between different entities, and formulating corresponding extraction rules. For example, if the sentence "such and such medicine treats such and such disease" appears in the text, it can be determined that there is a "treatment" relationship between the medicinal material and the disease; if there is a statement "such and such prescription is composed of such and such medicine", the "composition" relationship between the prescription and the medicinal material can be extracted. The relationship between entities is extracted by matching these rule patterns in the knowledge graph text.

[0109] Step 73, based on the identified key entities and the semantic relationship between the key entities, each ancient Chinese medicine book is regarded as a node in the association network, and the key entities in the knowledge graphs of different ancient books are also regarded as nodes. By adding ancient book source attributes to the key entities, the entities with the same name in different ancient books are distinguished to ensure the uniqueness and identifiability of the nodes in the network; the edges are defined according to the semantic relationship. When two key entities come from different ancient books and have a semantic relationship, edges are established between the corresponding ancient book nodes and the key entity nodes, so as to construct an association network between different ancient Chinese medicine books.

[0110] In a possible implementation, the obtaining of association relationships between key entities of different ancient Chinese medicine books based on the knowledge graph within the ancient Chinese medicine books, and completing the association construction of different ancient Chinese medicine books, further includes:

[0111] Based on the constructed association network and the existing knowledge graph, starting from a key entity node, through depth-first search of other key entity nodes related to the key node, the relationship and path between the key node and other key entity nodes are analyzed to obtain the potential association relationship between the key node and other key entity nodes.

[0112] Step 205, extracting disease symptom characteristics from modern biomedical data, obtaining the content of ancient Chinese medicine books associated with the disease symptom characteristics, and realizing the association construction between the disease symptom characteristics and the content of ancient Chinese medicine books.

[0113] In a possible implementation, the disease symptom characteristics in modern biomedical data are extracted, and the content of ancient Chinese medicine books associated with the disease symptom characteristics is obtained to realize the association construction between the disease symptom characteristics and the content of ancient Chinese medicine books. Please refer to Figure 8 , specifically:

[0114] Step 81, collecting data related to disease symptoms based on modern biomedical data;

[0115] Step 82, using the data related to the disease symptoms as input to a preset disease characteristic model to obtain disease symptom characteristics;

[0116] Step 83, based on the preset term mapping table, obtain the disease symptom characteristics and the related expressions in the ancient Chinese medicine books, use the related expressions as search conditions, and obtain the ancient Chinese medicine book content nodes related to the disease symptom characteristics. For example, if the disease symptom characteristic node is "cold", through the association relationships such as treatment relationship and similar symptom relationship, search the ancient Chinese medicine book content nodes that may be related to the treatment of "cold" in the knowledge graph.

[0117] Step 84: extract relevant information of the content node of the ancient Chinese medicine book as the ancient Chinese medicine book-related content associated with the disease symptom characteristics. The relevant information includes the corresponding ancient book title, chapter, specific content description, etc., as the ancient Chinese medicine book-related content associated with the disease symptom characteristics.

[0118] Step 85, using a word vector model (such as Word2Vec, Bert, etc.) to convert the disease symptom feature description and the content of the ancient Chinese medicine book into a word vector sequence, and then calculate the cosine similarity semantic similarity index between the two, and judge whether the semantics match according to the set similarity threshold (such as 0.6). For example, the symptom description and treatment method of "cold" in modern medicine are converted into word vectors, and compared with the content word vector of "cold" in the ancient Chinese medicine book. If the cosine similarity is greater than 0.6, it is considered to be more semantically matched.

[0119] Step 86, when the disease symptom characteristics and the content of the ancient Chinese medicine book meet the semantic match, the symptoms in modern medicine are encoded, and the symptom descriptions in the ancient books are converted into word vectors through natural language processing technology. The similarity index between the disease symptom characteristics and the content of the ancient Chinese medicine book is calculated to determine the degree of similarity of the symptoms. For example, the symptoms of "cold" in modern medicine "fever, cough, runny nose" and the symptoms of "cold" described in the ancient book "fever, cough, runny nose" have a high similarity index after processing, and it is considered that they are more matched in terms of symptom characteristics;

[0120] Step 87, when the degree of similarity between the disease symptom characteristics and the symptoms of the ancient Chinese medicine book content meets the preset threshold, the disease symptom characteristics and the ancient Chinese medicine book content are associated and constructed at the knowledge graph level to form a cross-domain knowledge network.

[0121] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0122] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0123] Continue to refer Fig. 9 The association construction device of the ancient Chinese medicine books described in this embodiment includes:

[0124] The standardized expression text acquisition module 901 is used to convert the ancient Chinese medicine book into an editable digital text, and obtain the standardized expression text of the ancient Chinese medicine book based on the editable digital text;

[0125] The key entity relationship determination module 902 is used to obtain the semantic relationship and context information of the ancient Chinese medicine book based on the standardized expression text of the ancient Chinese medicine book, and determine the relationship between the key entities of the ancient Chinese medicine book;

[0126] The knowledge graph construction module 903 is used to construct the knowledge graph inside the ancient Chinese medicine book based on the relationship between key entities;

[0127] The first association construction module 904 is used to obtain the association relationship between key entities of different ancient Chinese medicine books based on the knowledge graph inside the ancient Chinese medicine books, and complete the association construction of different ancient Chinese medicine books;

[0128] The association construction module 905 is used to extract disease symptom characteristics from modern biomedical data, obtain the related content of ancient Chinese medicine books related to the disease symptom characteristics, and realize the association construction between the disease symptom characteristics and the content of ancient Chinese medicine books.

[0129] To solve the above technical problems, the present application also provides a computer device. Figure 6 , Figure 6 This is a basic structural block diagram of the computer device in this embodiment.

[0130] The computer device 6 includes a memory 6a, a processor 6b, and a network interface 6c that are interconnected through a system bus. It should be noted that the figure only shows a computer device 6 with components 6a-6c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0131] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0132] The memory 6a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 6a can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 6a can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 6a can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 6a is usually used to store the operating system and various application software installed on the computer device 6, such as the program code of the association construction method of ancient Chinese medicine books, etc. In addition, the memory 6a can also be used to temporarily store various types of data that have been output or are to be output.

[0133] The processor 6b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 6b is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 6b is used to run the program code or process data stored in the memory 6a, such as running the program code of the association construction method of the ancient Chinese medicine book.

[0134] The network interface 6c may include a wireless network interface or a wired network interface. The network interface 6c is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0135] The present application also provides another implementation, namely, providing a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a program of a method for building an association of ancient Chinese medicine books, and the association building of the ancient Chinese medicine books can be executed by at least one processor, so that the at least one processor executes the steps of the method for building an association of ancient Chinese medicine books as described above.

[0136] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0137] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for building associations of ancient Chinese medicine books, characterized in that: include: Converting ancient Chinese medicine books into editable digital texts, and obtaining standardized expression texts of the ancient Chinese medicine books based on the editable digital texts; Based on the standardized expression text of the ancient Chinese medicine book, the semantic relationship and context information of the ancient Chinese medicine book are obtained, and the relationship between the key entities of the ancient Chinese medicine book is determined; Based on the relationship between key entities, a knowledge graph is constructed inside ancient Chinese medicine books; Based on the knowledge graph inside the ancient Chinese medicine books, the association relationship between key entities of different ancient Chinese medicine books is obtained, and the association construction of different ancient Chinese medicine books is completed; Extract disease and symptom characteristics from modern biomedical data, obtain the related content of ancient Chinese medicine books associated with disease and symptom characteristics, and realize the association construction between disease and symptom characteristics and the content of ancient Chinese medicine books.

2. The method for building associations of ancient Chinese medicine books according to claim 1, characterized in that: The said conversion of ancient Chinese medicine books into editable digital texts specifically includes: Obtain various ancient Chinese medicine books, including existing ancient Chinese medicine literature materials; Scanning the different ancient Chinese medicine books to generate a high-definition electronic image file set; Converting the electronic image file set into an editable digital text set based on optical character recognition technology; The editable digitized text is formatted to eliminate recognition errors and converted into a unified preset format text.

3. The method for building associations of ancient Chinese medicine books according to claim 2, characterized in that: The method of obtaining the standardized expression text of the ancient Chinese medicine book based on the editable digital text includes: Build a TCM terminology mapping knowledge base to map terms with different expressions into unified standard terms; Standardize the names of medicinal materials and diseases, and establish a standard correspondence between medicinal materials, diseases and prescriptions; Identify key entities of Chinese medicinal materials, diseases, and prescriptions in the editable digital text, and perform semantic type annotation on the identified key entities; Based on the TCM terminology mapping knowledge base, the identified key entities are replaced with unified standard terms, and the replaced unified standard terms are annotated to generate standardized text expressions.

4. The method for building associations of ancient Chinese medicine books according to claim 1, characterized in that: The method of obtaining the semantic relationship and context information of the ancient Chinese medicine books based on the standardized expression text of the ancient Chinese medicine books and determining the relationship between the key entities of the ancient Chinese medicine books specifically includes: Formulate semantic relationship extraction rules based on the language characteristics and professional knowledge of ancient Chinese medicine books; Based on regular expressions and semantic relationship extraction rules, the semantic relationship between key entities is obtained by defining regular expression patterns containing relationship keywords and entity types; For each key entity, a fixed text window size is set, and in the standardized expression text, the words in the window around the key entity are extracted as context information; The acquired semantic relationship information and context information are integrated, and the integrated semantic relationship and context information are stored using a data structure.

5. The method for building associations of ancient Chinese medicine books according to claim 1, characterized in that: The knowledge graph of ancient Chinese medicine books is constructed based on the relationship between key entities. The specific contents include: Analyze the types of key entities and determine the node types in the knowledge graph; Define the edge types in the knowledge graph based on the relationships between key entities; Based on the operation statements of the graph database or the corresponding API and the determined node types, create nodes in the knowledge graph one by one; Based on the determined edge type, edges are created between corresponding nodes to represent the relationship between key entities; In the process of creating nodes and edges, their pre-planned attribute values ​​are set at the same time. In addition to directly setting some attributes when creating nodes and edges, the attribute settings of nodes and edges can also be improved through subsequent update operations.

6. The method for building associations of ancient Chinese medicine books according to claim 1, characterized in that: Based on the knowledge graph inside the ancient Chinese medicine book, the association relationship between the key entities of different ancient Chinese medicine books is obtained, and the association construction of different ancient Chinese medicine books is completed. The specific contents include: Identify key entities in the internal knowledge graphs of different ancient Chinese medicine books; Obtaining semantic relations between identified key entities; Based on the identified key entities and the semantic relationships between key entities, each ancient Chinese medicine book is regarded as a node in the association network, and the key entities in different ancient book knowledge graphs are also regarded as nodes. By adding ancient book source attributes to the key entities, the entities with the same name in different ancient books are distinguished to ensure the uniqueness and identifiability of the nodes in the network; edges are defined according to semantic relationships. When two key entities come from different ancient books and have a semantic relationship, edges are established between the corresponding ancient book nodes and the key entity nodes, so as to construct an association network between different ancient Chinese medicine books.

7. The method for building associations of ancient Chinese medicine books according to claim 1, characterized in that: The extraction of disease symptom characteristics from modern biomedical data, obtaining the content associated with the ancient Chinese medicine books associated with the disease symptom characteristics, and realizing the association between the disease symptom characteristics and the content of the ancient Chinese medicine books are specifically manifested as follows: Based on modern biomedical data, collect data related to diseases and symptoms; Using the data related to the disease symptoms as input to a preset disease characteristic model to obtain disease symptom characteristics; Based on the preset term mapping table, the disease symptom characteristics and related expressions in ancient Chinese medicine books are obtained, and the related expressions are used as search conditions to obtain content nodes of ancient Chinese medicine books related to the disease symptom characteristics; Extract relevant information of content nodes of ancient Chinese medicine books as related content of ancient Chinese medicine books associated with disease symptom characteristics; The word vector model is used to convert the disease feature description and the content of ancient Chinese medicine books into word vector sequences respectively, and then the cosine similarity semantic similarity index between the two is calculated. According to the set similarity threshold, it is judged whether the semantics match; When the disease symptom characteristics and the content of ancient Chinese medicine books meet the semantic match, the symptoms in modern medicine are encoded and processed, and the symptom descriptions in ancient books are converted into word vectors through natural language processing technology. The similarity index between the disease symptom characteristics and the content of ancient Chinese medicine books is calculated to determine the similarity degree of the symptoms; When the degree of similarity between the disease symptom characteristics and the symptoms of ancient Chinese medicine books meets the preset threshold, the disease symptom characteristics and the content of ancient Chinese medicine books are associated and constructed at the knowledge graph level to form a cross-domain knowledge network.

8. A device for building associations of ancient Chinese medicine books, used to implement the method for building associations of ancient Chinese medicine books according to claims 1-7, characterized in that: include: A standardized expression text acquisition module is used to convert the ancient Chinese medicine book into an editable digital text, and obtain the standardized expression text of the ancient Chinese medicine book based on the editable digital text; A key entity relationship determination module is used to obtain the semantic relationship and context information of the ancient Chinese medicine book based on the standardized expression text of the ancient Chinese medicine book, and determine the relationship between the key entities of the ancient Chinese medicine book; The knowledge graph construction module is used to construct the knowledge graph inside the ancient Chinese medicine books based on the relationship between key entities; The first association construction module is used to obtain the association relationship between key entities of different ancient Chinese medicine books based on the knowledge graph inside the ancient Chinese medicine books, and complete the association construction of different ancient Chinese medicine books; The association construction module is used to extract disease symptom characteristics from modern biomedical data, obtain the related content of ancient Chinese medicine books associated with the disease symptom characteristics, and realize the association construction between disease symptom characteristics and the content of ancient Chinese medicine books.

9. An electronic device, characterized in that: include: one or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, enable the device to perform the steps of the method for constructing the association of ancient Chinese medicine books as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the steps of the method for building an association of ancient Chinese medicine books as described in any one of claims 1 to 7.

Images