Method and system for generating traditional Chinese medicine prescription solution

Abstract

The embodiment of the invention provides a traditional Chinese medicine prescription solution generation method and system, and relates to the technical field of intelligent traditional Chinese medicine. The method comprises the following steps: acquiring corresponding medicinal material information according to traditional Chinese medicine prescription information, performing deep analysis on the traditional Chinese medicine prescription information and the medicinal material information by using a deep learning model, and predicting to obtain medicinal material interaction and incompatibility. According to traditional Chinese medicine prescription information, medicinal material information, medicinal material interaction and incompatibility, an initial prescription solution is obtained, the initial prescription solution is optimized by utilizing a user feedback mechanism, the traditional Chinese medicine prescription solution is automatically generated, a powerful auxiliary tool is provided for traditional Chinese medicine doctors, and the traditional Chinese medicine prescription solution writing efficiency and accuracy are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent traditional Chinese medicine technology, and in particular to a method and system for generating an explanation of a traditional Chinese medicine prescription. Background Art

[0002] In the prior art, the writing of explanations for Chinese medicine prescriptions mainly relies on traditional manual methods, which is time-consuming and easily affected by personal experience, knowledge level and subjective judgment, resulting in low efficiency and uneven accuracy in the writing of explanations for Chinese medicine prescriptions. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a method and system for generating explanations of traditional Chinese medicine prescriptions, which can greatly improve the efficiency and accuracy of writing explanations of traditional Chinese medicine prescriptions.

[0004] In order to achieve the above purpose, the technical solution adopted by the embodiment of the present invention is as follows:

[0005] In a first aspect, the present invention provides a method for generating a Chinese medicine prescription explanation, which is applied to a Chinese medicine prescription explanation generation system, wherein the Chinese medicine prescription explanation generation system comprises an acquisition module, a database, an intelligent analysis module and a user feedback module; the method comprises:

[0006] The acquisition module sends the received Chinese medicine prescription information to the intelligent analysis module; the Chinese medicine prescription information includes the name of the medicinal material;

[0007] The intelligent analysis module queries the database according to the medicinal material name to obtain the medicinal material information corresponding to the medicinal material name;

[0008] The intelligent analysis module generates a prescription solution framework according to the traditional Chinese medicine prescription information and the medicinal material information;

[0009] The intelligent analysis module uses a deep learning model to perform complex relationship analysis based on the prescription solution framework, and generates an initial prescription solution based on the analysis results and the prescription solution framework; the analysis results include medicinal material interactions and incompatibility taboos;

[0010] The user feedback module receives user feedback information from the user and sends the user feedback information to the intelligent analysis module; the user feedback information represents the user's modification suggestions for the initial solution;

[0011] The intelligent analysis module generates a Chinese medicine prescription explanation based on the user feedback information and the initial prescription explanation.

[0012] In an optional embodiment, the prescription explanation framework includes medicinal material names, TCM disease diagnosis information, and TCM syndrome diagnosis information; the intelligent analysis module uses a deep learning model to perform complex relationship analysis based on the prescription explanation framework, and generates an initial prescription explanation based on the analysis results and the prescription explanation framework, including:

[0013] The intelligent analysis module obtains the corresponding medicinal material vector, disease name vector and syndrome vector according to the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information;

[0014] The intelligent analysis module inputs the medicinal material vector, the disease name vector, the syndrome vector and the prescription interpretation framework into the deep learning model to obtain medicinal material interactions and incompatibility taboos, and generates an initial prescription interpretation based on the prescription interpretation framework, the medicinal material interactions and the incompatibility taboos.

[0015] In an optional implementation, the intelligent analysis module obtains the corresponding medicinal material vector, disease name vector and syndrome vector according to the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information, including:

[0016] The intelligent analysis module sends the medicinal material name, the TCM disease diagnosis information and the TCM syndrome diagnosis information to the database;

[0017] The database searches a vocabulary table based on the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information to obtain a medicinal material vector corresponding to the medicinal material name, a disease name vector corresponding to the TCM disease name diagnosis information and a syndrome vector corresponding to the TCM syndrome diagnosis information;

[0018] The database sends the medicinal material vector, the disease name vector and the syndrome vector to the intelligent analysis module.

[0019] In an optional embodiment, the intelligent analysis module inputs the medicinal material vector, the disease name vector, the syndrome vector and the prescription interpretation framework into the deep learning model to obtain medicinal material interactions and incompatibility taboos, including:

[0020] The intelligent analysis module uses the deep learning model to obtain medicinal material information based on the medicinal material vector;

[0021] The intelligent analysis module uses the deep learning model to obtain the medicinal material effects and compatibility relationships based on the medicinal material vector, the disease name vector, and the syndrome vector;

[0022] The intelligent analysis module uses the deep learning model to perform analysis based on the medicinal material information, the medicinal material effects and the compatibility relationship to obtain the medicinal material interactions and the compatibility contraindications.

[0023] In an optional implementation, the intelligent analysis module generates a prescription solution framework according to the traditional Chinese medicine prescription information and the medicinal material information, including:

[0024] The intelligent analysis module obtains a target template according to the medicinal material information of the traditional Chinese medicine prescription information;

[0025] The intelligent analysis module generates the prescription framework according to the target template, the traditional Chinese medicine prescription information and the medicinal material information.

[0026] In a second aspect, the present invention provides a system for generating a Chinese medicine prescription explanation, including an acquisition module, a database, an intelligent analysis module and a user feedback module;

[0027] The acquisition module is used to send the received Chinese medicine prescription information to the intelligent analysis module; the Chinese medicine prescription information includes the name of the medicinal material;

[0028] The intelligent analysis module is used to query the database according to the medicinal material name to obtain the medicinal material information corresponding to the medicinal material name;

[0029] The intelligent analysis module generates a prescription solution framework according to the traditional Chinese medicine prescription information and the medicinal material information;

[0030] The intelligent analysis module is used to perform complex relationship analysis based on the prescription solution framework using a deep learning model, and generate an initial prescription solution based on the analysis results and the prescription solution framework; the analysis results include drug interactions and incompatibility taboos;

[0031] The user feedback module is used to receive user feedback information from the user and send the user feedback information to the intelligent analysis module; the user feedback information represents the user's modification suggestions for the initial solution;

[0032] The intelligent analysis module is used to generate a Chinese medicine prescription explanation based on the user feedback information and the initial prescription explanation.

[0033] In an optional embodiment, the prescription explanation framework includes the name of the medicinal material, TCM disease diagnosis information and TCM syndrome diagnosis information;

[0034] The intelligent analysis module is used to obtain the corresponding medicinal material vector, disease name vector and syndrome vector according to the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information;

[0035] The intelligent analysis module is used to input the medicinal material vector, the disease name vector, the syndrome vector and the prescription interpretation framework into the deep learning model to obtain medicinal material interactions and incompatibility taboos, and generate an initial prescription interpretation based on the prescription interpretation framework, the medicinal material interactions and the incompatibility taboos.

[0036] In an optional embodiment, the intelligent analysis module is used to send the medicinal material name, the TCM disease diagnosis information and the TCM syndrome diagnosis information to the database;

[0037] The database is used to search the vocabulary table based on the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information to obtain the medicinal material vector corresponding to the medicinal material name, the disease name vector corresponding to the TCM disease name diagnosis information and the syndrome vector corresponding to the TCM syndrome diagnosis information;

[0038] The database is used to send the medicinal material vector, the disease name vector and the syndrome vector to the intelligent analysis module.

[0039] In an optional embodiment, the intelligent analysis module is used to obtain medicinal material information based on the medicinal material vector using the deep learning model;

[0040] The intelligent analysis module is used to obtain the medicinal material effects and compatibility relationships based on the medicinal material vector, the disease name vector, and the syndrome vector using the deep learning model;

[0041] The intelligent analysis module is used to use the deep learning model to perform analysis based on the medicinal material information, the medicinal material effects and the compatibility relationship to obtain the medicinal material interactions and the compatibility contraindications.

[0042] In an optional embodiment, the intelligent analysis module is used to obtain a target template according to the traditional Chinese medicine prescription information;

[0043] The intelligent analysis module is used to generate the prescription framework according to the target template, the traditional Chinese medicine prescription information and the medicinal material information.

[0044] Compared with the prior art, the method and system for generating explanations of Chinese medicine prescriptions provided in the embodiments of the present invention obtain corresponding medicinal material information according to Chinese medicine prescription information, use a deep learning model to deeply analyze the Chinese medicine prescription information and medicinal material information, and predict medicinal material interactions and incompatibility taboos. An initial explanation is obtained according to the Chinese medicine prescription information, medicinal material information, medicinal material interactions and incompatibility taboos, and the initial explanation is optimized using a user feedback mechanism, and an explanation of Chinese medicine prescriptions is automatically generated, providing a powerful auxiliary tool for Chinese medicine physicians, greatly improving the efficiency and accuracy of writing Chinese medicine prescription explanations.

[0045] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present invention is shown.

[0048] Figure 2 A schematic flow chart of a method for generating an explanation of a traditional Chinese medicine prescription provided by an embodiment of the present invention is shown.

[0049] Figure 3 Another schematic flow chart of a method for generating an explanation of a traditional Chinese medicine prescription provided in an embodiment of the present invention is shown.

[0050] Figure 4 Another schematic flow chart of a method for generating an explanation of a traditional Chinese medicine prescription provided in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0051] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0052] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0053] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0054] At present, explanations of Chinese medicine prescriptions are usually written manually, and are mainly generated through four steps: manual review of literature and classics, manual analysis and reasoning, handwritten or electronic document records, and expert review and modification.

[0055] 1) Manually reviewing literature and classics: When Chinese medicine practitioners write prescription explanations, they first need to carefully review Chinese medicine classics, modern pharmacology research literature, clinical cases and other materials to obtain detailed information such as the nature, flavor, meridians, efficacy and indications of each medicinal material. This process requires a lot of time and energy, and requires a high level of professionalism on the part of the reviewer.

[0056] 2) Manual analysis and reasoning: After obtaining the basic information of the medicinal materials, the TCM physician needs to analyze the medicinal materials one by one according to the patient's specific condition (including disease type, syndrome type, etc.), combined with TCM theory and clinical experience, and infer the role of each medicinal material in the prescription, as well as the treatment principle of the entire prescription and the possible treatment effect. This step is highly dependent on the TCM physician's personal experience and subjective judgment.

[0057] 3) Handwritten or electronic document record: After the analysis is completed, the Chinese medicine practitioner will handwrite or enter the content of the prescription explanation into an electronic document to form the prescription explanation. Since this process is done manually, there may be writing errors, omissions or unclear expressions.

[0058] 4) Expert review and modification: In order to improve the accuracy and authority of the prescription interpretation, some institutions or hospitals will arrange experienced TCM experts to review and modify the prescription interpretation. However, this step is also time-consuming and costly, and the final result is still affected by the personal experience and subjective judgment of the review experts.

[0059] However, the existing technology has many problems in writing explanations of traditional Chinese medicine prescriptions, such as low efficiency, difficulty in ensuring accuracy, and reliance on personal experience.

[0060] In order to solve the above problems, the core improvement of the present invention is to obtain the corresponding medicinal material information according to the Chinese medicine prescription information, use the deep learning model to deeply analyze the Chinese medicine prescription information and medicinal material information, and predict the medicinal material interaction and incompatibility. The initial prescription solution is obtained according to the Chinese medicine prescription information, medicinal material information, medicinal material interaction and incompatibility, and the initial prescription solution is optimized by the user feedback mechanism, and the Chinese medicine prescription solution is automatically generated, which provides a powerful auxiliary tool for Chinese medicine physicians and greatly improves the efficiency and accuracy of writing Chinese medicine prescription solutions.

[0061] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0062] Please refer to Figure 1 , Figure 1A schematic diagram of an application scenario applicable to an embodiment of the present invention is shown. Figure 1 In the invention, the Chinese medicine prescription explanation generation system includes an acquisition module, a database, an intelligent analysis module and a user feedback module. The Chinese medicine prescription explanation generation system runs on the server, and the server is connected to the client in communication. The client is used to respond to the user's request to write a Chinese medicine prescription explanation. The server uses the Chinese medicine prescription explanation generation system to perform steps S10 to S60 and corresponding sub-steps in the following example to achieve the corresponding technical effects.

[0063] It should be noted that the client may be a personal computer (PC), a PDA (Personal Digital Assistant), a laptop, a tablet computer, etc. The server may be a local server, a cloud server, a network server, etc., which is not limited by the present invention.

[0064] Please refer to Figure 2 , Figure 2 A flow chart of a method for generating a Chinese medicine prescription explanation provided by an embodiment of the present invention is shown. The method is applied to a Chinese medicine prescription explanation generation system, which includes an acquisition module, a database, an intelligent analysis module, and a user feedback module. The method includes the following steps:

[0065] Step S10, the acquisition module sends the received traditional Chinese medicine prescription information to the intelligent analysis module.

[0066] Among them, Chinese medicine prescription information includes the name of the medicinal materials.

[0067] In the embodiment of the present invention, the acquisition module is used to receive the Chinese medicine prescription information input by the user, and the Chinese medicine prescription information includes the name of the medicinal material, dosage, decoction method, Chinese medicine disease diagnosis information and Chinese medicine symptom diagnosis information. The acquisition module sends the Chinese medicine prescription information to the intelligent analysis module.

[0068] Step S20, the intelligent analysis module queries the database according to the medicinal material name to obtain the medicinal material information corresponding to the medicinal material name.

[0069] In an embodiment of the present invention, the medicinal material information includes traditional Chinese medicine theory, nature, flavor, meridians and efficacy. The database is used to store and manage information related to Chinese medicine prescriptions, and a relational database can be used. Relational databases are known for their structured storage and powerful query capabilities, and are very suitable for storing and retrieving data related to Chinese medicine prescriptions. The database contains multiple data tables such as a medicinal material table, a prescription table, and a disease table, and each data table is connected by a relationship (such as a foreign key) to form a complete data network.

[0070] Among them, the medicinal material table records the medicinal material data including the name of the medicinal material, nature and flavor, meridians, efficacy and indications, dosage, contraindications, etc. The medicinal material data comes from traditional Chinese medicine classics and modern pharmacological research. The prescription table records the prescription data including the prescription name, constituent medicinal materials, dosage, decoction method, corresponding disease and syndrome, etc. The prescription data comes from classic medical books, modern clinical research or expert experience. The disease and syndrome table records the disease and syndrome data including the characteristics, etiology and pathogenesis, syndrome differentiation and typing of various TCM diseases and syndromes. The disease and syndrome data is crucial for understanding diseases and syndromes, selecting medicinal materials and compatibility.

[0071] Considering the complexity and diversity of Chinese medicine, the database contains data on tens of thousands of medicinal materials, thousands of prescriptions, and multiple disease data. The amount of data in the database depends on the coverage and detail of the database. A comprehensive database will contain as much information and data on Chinese medicine as possible.

[0072] Users can search for relevant information in the database based on key search terms such as medicinal material names and disease names, and quickly find the required medicinal materials, prescriptions, and disease data. The database can also improve advanced query functions, allowing users to search based on complex conditions (such as medicinal material efficacy, disease classification, etc.).

[0073] The database can further construct a Chinese medicine knowledge map to display data such as medicinal materials, prescriptions, and disease symptoms in a graphical manner, helping users to more intuitively understand the complexity and diversity of Chinese medicine through visualization, and improving the efficiency of learning and studying Chinese medicine. The specific form of the database can be configured according to the actual application scenario, and the present invention is not limited to this.

[0074] Step S30: the intelligent analysis module generates a prescription explanation framework based on the traditional Chinese medicine prescription information and medicinal material information.

[0075] Step S40: The intelligent analysis module uses a deep learning model to perform complex relationship analysis based on the square solution framework, and generates an initial square solution based on the analysis results and the square solution framework.

[0076] Among them, the analysis results include drug interactions and incompatibility.

[0077] In an embodiment of the present invention, the prescription explanation framework may include but is not limited to the basic prescription principle, the role of each medicinal material in the Chinese medicine prescription, and the expected efficacy of the Chinese medicine prescription. The intelligent analysis module inputs the prescription explanation framework into the deep learning model, performs complex relationship analysis, and gives prompts or suggestions in the prescription explanation framework according to the analysis results to obtain an initial prescription explanation. The intelligent analysis module sends the initial prescription explanation to the user end so that the user end displays the initial prescription explanation to the user through the display unit.

[0078] When the user needs to adjust the initial solution, the user uses the operation unit of the client to edit, modify or add personal insights to the initial solution to obtain user feedback information, and the client sends the user feedback information to the user feedback module.

[0079] Step S50: the user feedback module receives user feedback information from the user and sends the user feedback information to the intelligent analysis module.

[0080] The user feedback information represents the user's modification suggestions for the initial solution.

[0081] Step S60: the intelligent analysis module generates a Chinese medicine prescription explanation based on the user feedback information and the initial prescription explanation.

[0082] In the embodiment of the present invention, the intelligent analysis module updates the user feedback information from the user feedback module to the initial solution to obtain the solution of the Chinese medicine prescription. The intelligent analysis module saves the solution of the Chinese medicine prescription into a database and sends the solution of the Chinese medicine prescription to the user end so that the user end displays the solution of the Chinese medicine prescription to the user through the display unit.

[0083] In summary, the method for generating a Chinese medicine prescription explanation provided by the embodiment of the present invention obtains corresponding medicinal material information according to the Chinese medicine prescription information, uses a deep learning model to perform in-depth analysis on the Chinese medicine prescription information and medicinal material information, and predicts medicinal material interactions and incompatibility taboos. An initial explanation is obtained according to the Chinese medicine prescription information, medicinal material information, medicinal material interactions and incompatibility taboos, and the initial explanation is optimized using a user feedback mechanism, and a Chinese medicine prescription explanation is automatically generated, providing a powerful auxiliary tool for Chinese medicine physicians, greatly improving the efficiency and accuracy of writing Chinese medicine prescription explanations.

[0084] Optionally, the prescription explanation framework also includes the name of the medicinal material, TCM disease diagnosis information and TCM syndrome diagnosis information. The following provides a possible implementation method for how the intelligent analysis module uses the prescription explanation framework to generate an initial prescription explanation. Figure 2 On the basis of Figure 3 Another flow chart of the method for generating a Chinese medicine prescription explanation provided by the embodiment of the present invention. Figure 3 , step S40 comprises:

[0085] Step S401, the intelligent analysis module obtains the corresponding medicinal material vector, disease name vector and syndrome vector according to the medicinal material name, TCM disease name diagnosis information and TCM syndrome diagnosis information.

[0086] In the embodiment of the present invention, since the same Chinese herbal medicine may have multiple different names, in order to uniformly manage the names of the herbal medicines, the same Chinese herbal medicines with different names are mapped into the same herbal medicine vector, i.e., the herbal medicine vector. Similarly, the TCM disease name diagnosis information and TCM syndrome diagnosis information are mapped into disease name vectors and syndrome vectors accordingly.

[0087] Step S402: The intelligent analysis module inputs the medicinal material vector, disease name vector, syndrome vector and prescription explanation framework into the deep learning model to obtain medicinal material interactions and incompatibility taboos, and generates an initial prescription explanation based on the prescription explanation framework, medicinal material interactions and incompatibility taboos.

[0088] In the embodiment of the present invention, the deep learning model is obtained by training the neural network using the medicinal material data, prescription data and disease data. The neural network can be a graph neural network, a recurrent neural network and its variants, an attention mechanism model, etc., to capture the interactions and incompatibility between medicinal materials. The specific training method of the deep learning model is:

[0089] Obtain historical data, which may include but are not limited to medicinal material data, prescription data, and disease data. Prescription data may include but are not limited to successful cases and failed cases with adverse reactions due to drug interactions or incompatibility, and extract information on drug interactions and incompatibility from traditional Chinese medicine classics and modern pharmacology research literature.

[0090] The historical data is preprocessed, including but not limited to cleaning, standardization, labeling and constructing feature vectors. Among them, cleaning is to clean the collected historical data, remove erroneous, redundant and inconsistent data, and obtain the data to be processed; standardization is to standardize the names of medicinal materials and disease names in the data to be processed to obtain standard data. Labeling is to check whether there are interactions or incompatibility contraindications in each prescription or drug combination marker, and obtain the label corresponding to each standard data. Constructing feature vectors is to use word embedding technology to convert the names of medicinal materials, TCM disease diagnosis information and TCM syndrome diagnosis information in the standard data into numerical vectors to obtain embedded vectors.

[0091] The feature importance assessment technique is used to obtain key features from various properties of medicinal materials; key features refer to features that affect the prediction results, including but not limited to nature, flavor, meridian, efficacy, and dosage. The feature importance assessment technique can score the feature importance of random forests.

[0092] Create combined features based on key characteristics, such as the mutual dosage ratio between medicinal materials, the similarity of nature, taste and meridians, etc., to capture more complex interaction patterns.

[0093] The embedding vectors, combined features and labels are divided into training sets and test sets, and the training set is input into the neural network to obtain the interactions and incompatibility of medicinal materials. The loss function is used to calculate the loss information based on the labels, interactions and incompatibility of medicinal materials, and the hyperparameters of the neural network are iteratively updated according to the loss information to obtain the deep learning model to be verified. Among them, the loss function can be classified cross entropy, weighted cross entropy loss, Focal Loss, etc. Weighted cross entropy loss and Focal Loss are used to balance the situation where there are unbalanced categories in the data (for example, the number of interaction cases is far less than the number of non-interaction cases).

[0094] During the hyperparameter update process, the optimal hyperparameter combination, including learning rate, batch size, network level, number of nodes, etc., can be found through grid search, random search, Bayesian optimization, etc.

[0095] The test set is input into the deep learning model to be verified, and the model architecture, feature engineering and hyperparameters of the deep learning model to be verified are continuously adjusted according to the test results. The generalization ability of the deep learning model to be verified is evaluated using poor validation (such as K-fold cross validation). The performance of the deep learning model to be verified is optimized using an independent test set to obtain a deep learning model to improve the prediction accuracy and provide strong support for the automatic generation of solutions to Chinese medicine prescriptions.

[0096] Assuming that a graph neural network (such as graph convolutional network, graph attention network, etc.) is used to train a deep learning model, the medicinal materials can be used as nodes, and the interactions or compatibility relationships between medicinal materials can be used as edges to construct a graph structure. Each node (herb) is initialized as an embedding vector, and the embedding vector is updated through the graph neural network to capture the information of neighboring nodes. Using the updated embedding vector, a fully connected layer or classifier is used to predict whether there are interactions or incompatibility taboos between nodes.

[0097] Assuming that a recurrent neural network and its variants are used to train a deep learning model, the Chinese medicinal materials in the prescription can be arranged into a sequence in a certain order, and the sequence can be encoded using a recurrent neural network and its variants. The embedding vector of a medicinal material is processed at each time step. At the end or a specific position of the sequence, a fully connected layer or classifier is used to predict whether there is an interaction or incompatibility based on the encoding of the entire sequence. The deep learning model can be obtained by selecting a neural network training according to the actual application scenario, and the present invention is not limited to this.

[0098] Optionally, a possible implementation method for obtaining a numerical vector is provided below. Figure 4 , Figure 4 Another flowchart diagram of a method for generating an explanation of a traditional Chinese medicine prescription provided in an embodiment of the present invention. Figure 3 Step S401 includes:

[0099] Step S4011, the intelligent analysis module sends the medicinal material name, TCM disease diagnosis information and TCM syndrome diagnosis information to the database.

[0100] Step S4012, the database searches the vocabulary table based on the medicinal material name, TCM disease diagnosis information and TCM syndrome diagnosis information to obtain the medicinal material vector corresponding to the medicinal material name, the disease name vector corresponding to the TCM disease diagnosis information and the syndrome vector corresponding to the TCM syndrome diagnosis information.

[0101] Step S4013, the database sends the medicinal material vector, disease name vector and syndrome vector to the intelligent analysis module.

[0102] In the embodiment of the present invention, before generating the solution of the Chinese medicine prescription, it is necessary to obtain the names of various medicinal materials and disease names from the database, and the disease names include TCM disease name diagnosis information and TCM syndrome diagnosis information. The medicinal material names, TCM disease name diagnosis information and TCM syndrome diagnosis information are respectively input into the pre-trained word embedding model, and the medicinal material names, TCM disease name diagnosis information and TCM syndrome diagnosis information are mapped into corresponding high-dimensional numerical vectors, namely, medicinal material vectors, disease name vectors and syndrome vectors.

[0103] These numerical vectors can usually capture the semantic relationship and similarity between names. A vocabulary is generated based on all the names of medicinal materials, disease names and corresponding numerical vectors. The word embedding model can be a bidirectional encoder from Transformer (Bidirectional Encoder Representations from Transformers, referred to as BERT).

[0104] Optionally, a possible implementation method is provided below for obtaining drug interactions and incompatibility taboos. Figure 4 , Figure 4 Another flowchart diagram of a method for generating an explanation of a traditional Chinese medicine prescription provided in an embodiment of the present invention. Figure 3 Step S402 includes:

[0105] Step S4021: The intelligent analysis module uses a deep learning model to obtain medicinal material information based on the medicinal material vector.

[0106] In an embodiment of the present invention, the intelligent analysis module uses a deep learning model to obtain medicinal material information corresponding to the medicinal material vector from a database.

[0107] Step S4022: The intelligent analysis module uses a deep learning model to obtain the effects and compatibility of medicinal materials based on the medicinal material vector, disease name vector, and syndrome vector.

[0108] In the embodiment of the present invention, the intelligent analysis module uses the deep learning model to use the medicinal material vector, disease name vector, and syndrome vector as query conditions, and queries the medicinal material effects and compatibility relationships that meet the query conditions from the database. The medicinal material effects and compatibility relationships stored in the database are obtained based on historical prescription data and symptom data.

[0109] Step S4023, the intelligent analysis module uses a deep learning model to analyze based on medicinal material information, medicinal material effects and compatibility relationships to obtain medicinal material interactions and compatibility contraindications.

[0110] In the embodiment of the present invention, the intelligent analysis module uses a deep learning model to analyze the medicinal material information, medicinal material effects and compatibility relationships to capture the spatial relationship and pattern between vectors, thereby inferring potential medicinal material interactions and incompatibility taboos. The intelligent analysis module uses a deep learning model to generate an initial prescription solution based on medicinal material interactions, incompatibility taboos and prescription solution framework.

[0111] Optionally, a possible implementation method for generating a square solution framework is provided below. Figure 2 On the basis of Figure 3 Another flow chart of the method for generating a Chinese medicine prescription explanation provided by the embodiment of the present invention. Figure 3 , step S30 comprises:

[0112] Step S301, the intelligent analysis module obtains a target template according to the Chinese medicine prescription information and medicinal material information.

[0113] Step S302, the intelligent analysis module generates a prescription framework according to the target template, the Chinese medicine prescription information and the medicinal material information.

[0114] In an embodiment of the present invention, in order to generate a more standard Chinese medicine prescription explanation, a prescription explanation sentence template can be pre-set. The prescription explanation sentence template includes but is not limited to a prescription establishment purpose template, a single medicine efficacy template, an efficacy matching template, a mutual requirement template, a mutual use template, a mutual fear template, a mutual hatred template, a mutual killing template, a monarch medicine template, a minister medicine template, an adjuvant medicine template, a messenger medicine template, a nature and flavor meridian and efficacy interpretation template, a disease syndrome and pathogenesis analysis template, a modern pharmacology research combination template, an alternative medicine suggestion template, a clinical application and precautions template, a citation and reference template, and a prescription explanation summary template. Examples of the prescription explanation sentence template are shown in Table 1. The prescription explanation sentence template can be preset according to the application scenario, and the present invention is not limited to this.

[0115] Table 1

[0116]

[0117]

[0118]

[0119]

[0120]

[0121] As a possible implementation method, a matching target template is determined based on the TCM syndrome diagnosis information and the name of the medicinal material in the TCM prescription information, such as the prescription establishment purpose template, the single-flavor medicine efficacy template, the nature and flavor meridian and efficacy interpretation template, the disease syndrome and pathogenesis analysis template, the clinical application and precautions template, and the prescription explanation summary template as the target template. A matching target template is determined based on the medicinal material information, such as the modern pharmacology research combination template, the alternative drug recommendation template, and the citation and reference template as the target template. The TCM prescription information and medicinal material information are updated to the target template to obtain the prescription explanation framework.

[0122] It should be noted that when generating the initial prescription solution, the matching target template is determined according to the analysis results. For example, the prescription solution sentence template that meets the conditions in the efficacy matching template, the mutual need template, the mutual use template, the mutual fear template, the mutual hatred template, the mutual killing template, the main drug template, the minister drug template, the adjuvant drug template, and the messenger drug template is selected as the matching target template, the analysis results are updated to the target template, and integrated with the prescription solution framework to obtain the initial prescription solution.

[0123] In order to more clearly illustrate the method for generating a Chinese medicine prescription solution provided by an embodiment of the present invention, an exemplary description is given in combination with specific Chinese medicine prescription information. Assume that the Chinese medicine prescription information input by the user is:

[0124] Names of medicinal materials: Angelica sinensis, Chuanxiong, White Peony Root, Rehmannia Glutinosa, Lycium barbarum, and Chrysanthemum.

[0125] Dosage: 10 grams, 9 grams, 12 grams, 10 grams, 15 grams, and 12 grams respectively.

[0126] Method of decoction: Decoction in water, one dose per day, divided into two doses.

[0127] Traditional Chinese Medicine disease diagnosis information: Headache.

[0128] TCM syndrome diagnosis information: Headache due to blood deficiency and liver and kidney deficiency.

[0129] The intelligent analysis module queries the database based on the names of six medicinal materials, namely, Angelica sinensis, Chuanxiong, White Peony Root, Rehmannia Glutinosa, Fructus Lycii and Chrysanthemum, to obtain the medicinal material information corresponding to each medicinal material, and generates a prescription framework based on the Chinese medicine prescription information and medicinal material information. The intelligent analysis module obtains the corresponding medicinal material vector, disease name vector and syndrome vector based on the medicinal material name, TCM disease name diagnosis information and TCM syndrome diagnosis information. The intelligent analysis module inputs the medicinal material vector, disease name vector, syndrome vector and prescription framework into the deep learning model, uses the deep learning model to obtain medicinal material information, medicinal material effects and compatibility relationships, performs complex relationship analysis based on medicinal material information, medicinal material effects and compatibility relationships, obtains medicinal material interactions and compatibility contraindications, and generates an initial prescription framework based on the Chinese medicine prescription information, medicinal material interactions and compatibility contraindications in the prescription framework.

[0130] When a Chinese medicine has multiple effects, we will combine the specific TCM disease name diagnosis information and TCM syndrome diagnosis information to select a suitable effect to form a TCM prescription explanation, while following the TCM principle of "differentiation and treatment", and using a deep learning model to combine clinical experience in the database and modern pharmacological research results for comprehensive analysis. The following are the steps to select the efficacy of medicinal materials in TCM prescription information by combining TCM disease name diagnosis information and TCM syndrome diagnosis information:

[0131] 1) In-depth analysis of TCM disease name diagnosis information and TCM syndrome diagnosis information: clarify the main pathological changes of TCM disease name diagnosis information, such as headache is mainly caused by blood deficiency and inability to nourish the brain. In-depth understanding of the specific manifestations of TCM syndrome diagnosis information, such as liver and kidney deficiency may manifest as soreness of waist and knees, dizziness and tinnitus, etc.

[0132] 2) Identify important multiple functions: Understand the full range of functions and indications of each Chinese herbal medicine, and analyze the indications and contraindications of each function in TCM theory.

[0133] 3) Matching the efficacy of Chinese medicine, TCM disease diagnosis information and TCM syndrome diagnosis information: According to the main pathological changes and clinical manifestations of TCM disease diagnosis information and TCM syndrome diagnosis information, the most suitable TCM efficacy is screened out. Considering factors such as the meridians, nature and taste of TCM, select TCM that can directly reach the diseased area and harmonize the internal organs.

[0134] 4) Compatibility of medicinal materials: According to the principle of "monarch, minister, assistant and envoy" in traditional Chinese medicine, determine the compatibility relationship between different Chinese medicines. Choose a combination of Chinese medicines that can enhance each other, reduce side effects or harmonize the medicinal properties.

[0135] 5) Combine clinical essentials with modern research: Refer to the medication experience of doctors of all dynasties and the results of modern pharmacological research. Understand the important mechanisms of action and active ingredients in modern research to more accurately select the efficacy of traditional Chinese medicine.

[0136] 6) Generate initial prescription explanation: The intelligent analysis module uses a deep learning model to determine the role and efficacy of each medicinal material in the traditional Chinese medicine prescription, as well as the interaction and incompatibility of medicinal materials based on the above analysis. When compiling the initial prescription explanation, the selection basis, efficacy and compatibility of each traditional Chinese medicine in the traditional Chinese medicine prescription are explained.

[0137] Among them, the selection basis is obtained through comprehensive analysis of basic theories of traditional Chinese medicine, pathological changes of diseases and syndromes, compatibility of Chinese medicines, clinical experience and modern research.

[0138] First, the basic theory of traditional Chinese medicine: This is the most basic and core basis for selecting the efficacy of traditional Chinese medicine. The basic theory of traditional Chinese medicine includes the nature and flavor of the medicine, its meridians, efficacy and indications, etc. Each traditional Chinese medicine has its specific nature and flavor (such as cold, hot, warm, cool, sour, bitter, sweet, pungent, and salty) and meridians (such as the liver meridian, heart meridian, lung meridian, kidney meridian, and bladder meridian), which determine the basic direction and scope of the medicine. For example, angelica sinensis is sweet and warm in nature and enters the liver, heart, and spleen meridians. It has the effects of nourishing blood, activating blood circulation, regulating menstruation and relieving pain. These effects are based on the basic theory of traditional Chinese medicine.

[0139] Second, the pathological changes of the disease and syndrome: select Chinese medicine according to the specific pathological changes of the disease (such as headache) and syndrome (such as blood deficiency headache and liver and kidney deficiency). For blood deficiency headache, the main pathology is that blood deficiency cannot nourish the brain, leading to headache, so it is reasonable to choose angelica as the main medicine with blood-tonifying effect.

[0140] Third, the compatibility of Chinese medicine: Chinese medicine pays attention to the compatibility of medicines, that is, the principle of "monarch, minister, assistant and envoy". When compatibility is used, it is necessary to consider the interaction between drugs, including synergistic enhancement, reduction of side effects, and coordination of medicinal properties. For example, in the example, Chuanxiong, as a minister, is combined with Angelica sinensis to enhance the effect of nourishing blood and activating blood circulation. This compatibility relationship is based on long-term clinical practice and Chinese medicine theory.

[0141] Fourth, clinical experience and modern research: The experience of doctors in the past dynasties in using medicines has provided a rich practical basis for the selection of Chinese medicines. At the same time, modern pharmacological research has also revealed the effective components and mechanisms of Chinese medicines, providing a scientific basis for the selection of Chinese medicines. For example, modern research has found that angelica contains a variety of active ingredients, which have multiple pharmacological effects such as promoting hematopoiesis, anti-thrombosis, and anti-oxidation. These research results further confirm the efficacy of angelica in replenishing blood and promoting blood circulation.

[0142] Take the Chinese angelica as an example. Chinese angelica has many functions such as nourishing blood and activating blood circulation, regulating menstruation and relieving pain, and moistening the intestines and relieving constipation. If the TCM disease name diagnosis information is headache, and the TCM syndrome diagnosis information is blood deficiency headache and liver and kidney deficiency, then the "nourishing blood and activating blood circulation" function of Chinese angelica is selected. The "nourishing blood and activating blood circulation" function of Chinese angelica can directly treat the pathogenesis of blood deficiency headache, replenish blood deficiency, promote blood circulation, and thus relieve headache.

[0143] The reason for choosing Angelica sinensis is explained in the initial explanation of the prescription. The reason for choosing Angelica sinensis is explained in the explanation of the prescription because its effect of nourishing blood and activating blood circulation is consistent with the pathogenesis of headache caused by blood deficiency. At the same time, it can form a good compatibility relationship with other medicinal materials such as Chuanxiong and Rehmannia glutinosa, and jointly play the role of nourishing blood and activating blood circulation, and harmonizing qi and blood. This ensures that the efficacy of the traditional Chinese medicine selected in the traditional Chinese medicine prescription matches the disease type and syndrome type, forming a scientific and reasonable explanation of the traditional Chinese medicine prescription.

[0144] The intelligent analysis module generates a Chinese medicine prescription solution based on user feedback information and the initial solution, as follows:

[0145] This prescription is designed for headache due to blood deficiency and liver and kidney deficiency. It aims to replenish blood and activate blood circulation, harmonize qi and blood, and nourish the liver and kidney at the same time to relieve headache and improve systemic symptoms. Angelica sinensis, which replenishes blood and activates blood circulation, is the main medicine, aiming to replenish blood deficiency. Chuanxiong, which promotes qi and activates blood circulation, is the ministerial medicine, and works with Angelica sinensis to play the role of replenishing blood and activating blood circulation. White peony root, which nourishes blood and softens the liver, is one of the adjuvants, which can not only enhance the effect of replenishing blood, but also harmonize liver qi and prevent headaches from being aggravated by liver qi stagnation. Rehmannia root, which replenishes blood and nourishes yin, is the second adjuvant. It is used together with Angelica sinensis and white peony root to enhance the power of replenishing blood, nourish the liver and kidney, and improve the symptoms of liver and kidney deficiency. Lycium barbarum, which nourishes the liver and kidney, is the third adjuvant, which can replenish the essence of the liver and kidney, improve the body's immunity, and has a good effect on various symptoms caused by liver and kidney deficiency. Chrysanthemum can dispel wind-heat, soothe the liver and improve eyesight. As a guiding drug, it works together with other herbs in the prescription to clear the head and relieve headaches, and has a certain effect on relieving eye fatigue.

[0146] Based on the same inventive concept, the basic principles and technical effects of the Chinese medicine prescription interpretation generation system provided by the embodiment of the present invention are the same as those of the above embodiment. For the sake of brief description, for parts not mentioned in this embodiment, reference can be made to the corresponding contents in the above embodiment.

[0147] Please continue to refer to Figure 1 The Chinese medicine prescription solution generation system includes an acquisition module, a database, an intelligent analysis module and a user feedback module. The acquisition module is used to send the received Chinese medicine prescription information to the intelligent analysis module; the Chinese medicine prescription information includes the name of the medicinal material;

[0148] The intelligent analysis module is used to query the database according to the name of the medicinal material to obtain the medicinal material information corresponding to the medicinal material name;

[0149] The intelligent analysis module generates a prescription interpretation framework based on the TCM prescription information and medicinal material information;

[0150] The intelligent analysis module is used to use a deep learning model to perform complex relationship analysis based on the prescription interpretation framework, and to generate an initial prescription interpretation based on the analysis results and the prescription interpretation framework; the analysis results include drug interactions and incompatibility taboos;

[0151] The user feedback module is used to receive user feedback information from users and send the user feedback information to the intelligent analysis module; the user feedback information represents the user's modification suggestions for the initial solution;

[0152] The intelligent analysis module is used to generate explanations for Chinese medicine prescriptions based on user feedback information and initial explanations.

[0153] In summary, the Chinese medicine prescription explanation generation system provided by the embodiment of the present invention obtains the corresponding medicinal material information according to the Chinese medicine prescription information, uses the deep learning model to perform in-depth analysis on the Chinese medicine prescription information and the medicinal material information, and predicts the medicinal material interaction and incompatibility. The initial prescription explanation is obtained according to the Chinese medicine prescription information, the medicinal material information, the medicinal material interaction and the incompatibility, and the user feedback mechanism is used to optimize the initial prescription explanation, and the Chinese medicine prescription explanation is automatically generated, which provides a powerful auxiliary tool for Chinese medicine physicians and greatly improves the efficiency and accuracy of writing Chinese medicine prescription explanations.

[0154] Optionally, the prescription explanation framework includes medicinal material names, TCM disease name diagnosis information and TCM syndrome diagnosis information; the intelligent analysis module is used to obtain corresponding medicinal material vectors, disease name vectors and syndrome vectors according to the medicinal material names, TCM disease name diagnosis information and TCM syndrome diagnosis information; the intelligent analysis module is used to input the medicinal material vectors, disease name vectors, syndrome vectors and prescription explanation framework into the deep learning model to obtain medicinal material interactions and incompatibilities, and generate an initial prescription explanation based on the prescription explanation framework, medicinal material interactions and incompatibilities.

[0155] Optionally, the intelligent analysis module is used to send the medicinal material name, TCM disease name diagnosis information and TCM syndrome diagnosis information to the database; the database is used to search the vocabulary based on the medicinal material name, TCM disease name diagnosis information and TCM syndrome diagnosis information to obtain the medicinal material vector corresponding to the medicinal material name, the disease name vector corresponding to the TCM disease name diagnosis information and the syndrome vector corresponding to the TCM syndrome diagnosis information; the database is used to send the medicinal material vector, disease name vector and syndrome vector to the intelligent analysis module.

[0156] Optionally, the intelligent analysis module is used to obtain medicinal material information based on medicinal material vectors using a deep learning model; the intelligent analysis module is used to obtain medicinal material effects and compatibility relationships based on medicinal material vectors, disease name vectors, and syndrome vectors using a deep learning model; the intelligent analysis module is used to use a deep learning model to analyze based on medicinal material information, medicinal material effects, and compatibility relationships to obtain medicinal material interactions and incompatibility contraindications.

[0157] Optionally, the intelligent analysis module is used to obtain a target template based on the traditional Chinese medicine prescription information and medicinal material information; the intelligent analysis module is used to generate a prescription solution framework based on the target template, the traditional Chinese medicine prescription information and medicinal material information.

[0158] In several embodiments provided by the present invention, it should be understood that the disclosed system and method can also be implemented in other ways. The system embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0160] If the function is implemented in the form of a software function module and sold or used as an independent product, it 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. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0161] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating an explanation of a Chinese medicine prescription, characterized in that: Applied to a Chinese medicine prescription interpretation generation system, the Chinese medicine prescription interpretation generation system includes an acquisition module, a database, an intelligent analysis module and a user feedback module; the method includes: The acquisition module sends the received Chinese medicine prescription information to the intelligent analysis module; the Chinese medicine prescription information includes the name of the medicinal material; The intelligent analysis module queries the database according to the medicinal material name to obtain the medicinal material information corresponding to the medicinal material name; The intelligent analysis module generates a prescription solution framework according to the traditional Chinese medicine prescription information and the medicinal material information; The intelligent analysis module uses a deep learning model to perform complex relationship analysis based on the prescription interpretation framework, and generates an initial prescription interpretation based on the analysis results and the prescription interpretation framework; the analysis results include medicinal material interactions and incompatibility taboos; The user feedback module receives user feedback information from the user and sends the user feedback information to the intelligent analysis module; the user feedback information represents the user's modification suggestions for the initial solution; The intelligent analysis module generates a Chinese medicine prescription explanation based on the user feedback information and the initial prescription explanation.

2. The method according to claim 1, characterized in that The prescription explanation framework includes the name of the medicinal material, TCM disease diagnosis information and TCM syndrome diagnosis information; the intelligent analysis module uses a deep learning model to perform complex relationship analysis based on the prescription explanation framework, and generates an initial prescription explanation based on the analysis results and the prescription explanation framework, including: The intelligent analysis module obtains the corresponding medicinal material vector, disease name vector and syndrome vector according to the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information; The intelligent analysis module inputs the medicinal material vector, the disease name vector, the syndrome vector and the prescription interpretation framework into the deep learning model to obtain medicinal material interactions and incompatibility taboos, and generates an initial prescription interpretation based on the prescription interpretation framework, the medicinal material interactions and the incompatibility taboos.

3. The method according to claim 2, characterized in that The intelligent analysis module obtains the corresponding medicinal material vector, disease name vector and syndrome vector according to the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information, including: The intelligent analysis module sends the medicinal material name, the TCM disease diagnosis information and the TCM syndrome diagnosis information to the database; The database searches a vocabulary table based on the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information to obtain a medicinal material vector corresponding to the medicinal material name, a disease name vector corresponding to the TCM disease name diagnosis information and a syndrome vector corresponding to the TCM syndrome diagnosis information; The database sends the medicinal material vector, the disease name vector and the syndrome vector to the intelligent analysis module.

4. The method according to claim 2, characterized in that: The intelligent analysis module inputs the medicinal material vector, the disease name vector, the syndrome vector and the prescription interpretation framework into the deep learning model to obtain medicinal material interactions and incompatibility taboos, including: The intelligent analysis module uses the deep learning model to obtain medicinal material information based on the medicinal material vector; The intelligent analysis module uses the deep learning model to obtain the medicinal material effects and compatibility relationships based on the medicinal material vector, the disease name vector, and the syndrome vector; The intelligent analysis module uses the deep learning model to perform analysis based on the medicinal material information, the medicinal material effects and the compatibility relationship to obtain the medicinal material interactions and the compatibility contraindications.

5. The method according to claim 1, characterized in that The intelligent analysis module generates a prescription solution framework according to the traditional Chinese medicine prescription information and the medicinal material information, including: The intelligent analysis module obtains a target template according to the Chinese medicine prescription information and the medicinal material information; The intelligent analysis module generates the prescription framework according to the target template, the traditional Chinese medicine prescription information and the medicinal material information.

6. A system for generating explanations of traditional Chinese medicine prescriptions, characterized in that: Includes acquisition module, database, intelligent analysis module and user feedback module; The acquisition module is used to send the received Chinese medicine prescription information to the intelligent analysis module; the Chinese medicine prescription information includes the name of the medicinal material; The intelligent analysis module is used to query the database according to the medicinal material name to obtain the medicinal material information corresponding to the medicinal material name; The intelligent analysis module generates a prescription solution framework according to the traditional Chinese medicine prescription information and the medicinal material information; The intelligent analysis module is used to perform complex relationship analysis based on the prescription solution framework using a deep learning model, and generate an initial prescription solution based on the analysis results and the prescription solution framework; the analysis results include drug interactions and incompatibility taboos; The user feedback module is used to receive user feedback information from users and send the user feedback information to the intelligent analysis module; The user feedback information represents the user's modification suggestions for the initial solution; The intelligent analysis module is used to generate a Chinese medicine prescription explanation based on the user feedback information and the initial prescription explanation.

7. The system according to claim 6, characterized in that The prescription explanation framework includes the name of the medicinal material, TCM disease diagnosis information and TCM syndrome diagnosis information; The intelligent analysis module is used to obtain the corresponding medicinal material vector, disease name vector and syndrome vector according to the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information; The intelligent analysis module is used to input the medicinal material vector, the disease name vector, the syndrome vector and the prescription interpretation framework into the deep learning model to obtain medicinal material interactions and incompatibility taboos, and generate an initial prescription interpretation based on the prescription interpretation framework, the medicinal material interactions and the incompatibility taboos.

8. The system according to claim 7, characterized in that The intelligent analysis module is used to send the medicinal material name, the TCM disease diagnosis information and the TCM syndrome diagnosis information to the database; The database is used to search the vocabulary table based on the medicinal material name, the TCM disease name diagnosis information and the TCM syndrome diagnosis information to obtain the medicinal material vector corresponding to the medicinal material name, the disease name vector corresponding to the TCM disease name diagnosis information and the syndrome vector corresponding to the TCM syndrome diagnosis information; The database is used to send the medicinal material vector, the disease name vector and the syndrome vector to the intelligent analysis module.

9. The system according to claim 7, characterized in that The intelligent analysis module is used to obtain medicinal material information based on the medicinal material vector using the deep learning model; The intelligent analysis module is used to obtain the medicinal material effects and compatibility relationships based on the medicinal material vector, the disease name vector, and the syndrome vector using the deep learning model; The intelligent analysis module is used to use the deep learning model to perform analysis based on the medicinal material information, the medicinal material effects and the compatibility relationship to obtain the medicinal material interactions and the compatibility contraindications.

10. The system according to claim 6, characterized in that The intelligent analysis module is used to obtain a target template according to the traditional Chinese medicine prescription information; The intelligent analysis module is used to generate the prescription framework according to the target template, the traditional Chinese medicine prescription information and the medicinal material information.

Images