Traditional Chinese medicine syndrome type association model training method and device, computing equipment and storage medium

Abstract

The invention provides a traditional Chinese medicine symptom type association model training method and device, computing equipment and a storage medium, and the method comprises the steps: determining traditional Chinese medicine symptom type score data through traditional Chinese medicine business original data, obtaining traditional Chinese medicine symptom type coefficient data in combination with preset symptom type total score data, and then obtaining a traditional Chinese medicine symptom type association model according to the stage number of a target symptom; clustering the traditional Chinese medicine symptom type coefficient data, converting the traditional Chinese medicine symptom type coefficient data according to a clustering result to obtain traditional Chinese medicine symptom type stage data, taking the traditional Chinese medicine symptom type stage data as input of an initial traditional Chinese medicine symptom type correlation model, and outputting support degree and confidence degree between any symptom types; and training the initial traditional Chinese medicine syndrome type association model by taking a preset minimum support degree and a minimum confidence coefficient as training conditions to obtain a target traditional Chinese medicine syndrome type association model. The target traditional Chinese medicine symptom type association model can find out the association relationship among traditional Chinese medicine symptoms and the regularity among multiple symptoms, so that pathogenesis analysis and disease development prediction are performed, and effective reference can be provided for clinical diagnosis and treatment.

Description

Technical Field

[0001] The present application relates to the field of smart medical technology, and in particular to a method, device, computing equipment and storage medium for training a TCM syndrome association model. Background Art

[0002] Traditional Chinese medicine has a wide range of indications and unique advantages. Starting from the overall perspective, adjust the balance of qi and blood, yin and yang, and viscera functions of the body, and conduct syndrome differentiation and treatment according to different clinical symptoms. Determine the direction of "treating symptoms first": that is, before the subsequent symptoms appear, which subsequent symptoms that worsen the condition need to be cut off. Discover the correlation between TCM symptoms and the regularity between many symptoms, and analyze the cause of the disease based on the rules, predict the development of the disease, and provide effective reference for future clinical diagnosis and treatment.

[0003] Although TCM syndrome differentiation is extremely flexible and can handle patients' complex and changeable clinical symptoms, showing its therapeutic advantages, the existing TCM syndrome differentiation classification is relatively scattered and is more based on personal experience to divide syndrome types, lacking a unified and standardized standard. In addition, due to the complexity of the disease and differences in physical constitution, most patients have multiple syndromes. Clinical physicians may be misled by their own experience and treat symptoms alone, which violates the principle of TCM syndrome differentiation and treatment. In addition, there are often different opinions on the syndrome differentiation of the same disease. It is difficult for beginners to judge patients with atypical clinical symptoms. Summary of the invention

[0004] In view of this, the embodiment of the present application provides a TCM syndrome type association model training method to solve the technical defects existing in the prior art. The embodiment of the present application also provides a TCM syndrome type association model training device, a computing device, and a computer-readable storage medium.

[0005] According to a first aspect of an embodiment of the present application, a method for training a TCM syndrome association model is provided, comprising: Obtaining original TCM business data, and determining TCM syndrome type score data corresponding to the target disease based on the original TCM business data; According to the preset total syndrome score data, the TCM syndrome score data is processed to obtain TCM syndrome coefficient data; Clustering the TCM syndrome coefficient data based on the stage number of the target disease to obtain a clustered data set; The TCM syndrome coefficient data is converted according to the clustering data set to obtain TCM syndrome stage data, and the TCM syndrome stage data and the corresponding stage of the target disease are used as inputs of an initial TCM syndrome association model to output support and confidence between any syndromes; Taking the preset minimum support and minimum confidence as training conditions, the initial TCM syndrome association model is adjusted until the support and the confidence meet the training conditions, thereby obtaining the target TCM syndrome association model.

[0006] Optionally, determining TCM syndrome type score data corresponding to the target disease based on the original TCM business data includes: Based on preset attribute definition rules, the raw TCM business data is converted into a patient data set; Based on preset standard definition rules, the patient data set is cleaned, and sample data is determined according to the data cleaning result; Based on the preset syndrome symptom definition rules, the sample data is attribute-reduced to obtain TCM syndrome score data.

[0007] Optionally, the converting the original TCM business data into a patient data set based on a preset attribute definition rule includes: Querying the correspondence between the original TCM business data and the attribute definition rules, and converting the original TCM business data into corresponding attribute values ​​according to the query result; The patient data set is constructed according to the attribute values.

[0008] Optionally, the step of performing data cleaning on the patient data set based on a preset standard definition rule, and determining sample data according to the data cleaning result includes: Based on the inclusion criteria in the standard definition rules, the patient data set is screened for the first time, and based on the exclusion criteria in the standard definition rules, the first screening result is screened for the second time to obtain a candidate sample data set; Determine data in the original TCM business data that is associated with the candidate sample data set to obtain the sample data.

[0009] Optionally, the attribute reduction of the sample data based on the preset syndrome symptom definition rules to obtain TCM syndrome score data includes: Performing semantic extraction on the sample data to obtain sample semantics; The sample semantics is matched with the syndrome symptom definition rules for similarity to obtain the TCM syndrome score data.

[0010] Optionally, clustering the TCM syndrome coefficient data based on the stage number of the target disease to obtain a clustered data set includes: Discretizing the TCM syndrome coefficient data using a preset decision tree algorithm to determine the dividing points; The TCM syndrome type coefficient data are clustered according to the division points to obtain the cluster data set.

[0011] Optionally, the TCM syndrome stage data and the corresponding stage of the target disease are used as inputs of an initial TCM syndrome association model, and the support and confidence between any syndromes are output, including: The TCM syndrome stage data and the corresponding stage of the target disease are used as inputs of the initial TCM syndrome association model, and the support representing the frequency of simultaneous occurrence between any syndromes and the confidence representing the probability of the occurrence of any syndrome when the other syndrome also occurs are output.

[0012] According to a second aspect of an embodiment of the present application, a TCM syndrome association model training device is provided, comprising: An acquisition module is configured to acquire original TCM business data and determine TCM syndrome type score data corresponding to the target disease based on the original TCM business data; A processing module is configured to process the TCM syndrome type score data according to preset syndrome type total score data to obtain TCM syndrome type coefficient data; A clustering module is configured to cluster the TCM syndrome coefficient data based on the stage number of the target disease to obtain a clustering data set; A model processing module is configured to convert the TCM syndrome coefficient data according to the clustering data set to obtain TCM syndrome stage data, and use the TCM syndrome stage data and the corresponding stage of the target disease as inputs of an initial TCM syndrome association model, and output support and confidence between any syndromes; The model training module is configured to adjust the parameters of the initial TCM syndrome association model with preset minimum support and minimum confidence as training conditions until the support and confidence meet the training conditions, thereby obtaining the target TCM syndrome association model.

[0013] According to a third aspect of an embodiment of the present application, a computing device is provided, including: Memory and processor; The memory is used to store computer-executable instructions, and the processor implements the steps of the TCM syndrome type association model training method when executing the computer-executable instructions.

[0014] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the TCM syndrome type association model training method are implemented.

[0015] According to a fifth aspect of an embodiment of the present application, a chip is provided, which stores a computer program, and when the computer program is executed by the chip, the steps of the TCM syndrome type association model training method are implemented.

[0016] The training method of the TCM syndrome type association model provided in the present application obtains the original data of TCM business, and determines the TCM syndrome type score data corresponding to the target disease according to the original data of TCM business; processes the TCM syndrome type score data according to the preset syndrome type total score data to obtain TCM syndrome type coefficient data; clusters the TCM syndrome type coefficient data based on the stage number of the target disease to obtain a clustering data set; converts the TCM syndrome type coefficient data according to the clustering data set to obtain TCM syndrome type stage data, and uses the TCM syndrome type stage data and the corresponding stage of the target disease as the input of the initial TCM syndrome type association model, and outputs the support and confidence between any syndrome types; uses the preset minimum support and minimum confidence as training conditions, adjusts the parameters of the initial TCM syndrome type association model until the support and confidence meet the training conditions, and obtains the target TCM syndrome type association model. The target TCM syndrome type association model can find the correlation between TCM symptoms and the regularity between many symptoms, and analyze the cause of the disease, predict the development of the disease, and provide effective reference for future clinical diagnosis and treatment based on the rules. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of a method for training a TCM syndrome association model provided in one embodiment of the present application; Figure 2 It is a structural schematic diagram of a TCM syndrome association model training device provided in one embodiment of the present application; Figure 3 is a structural block diagram of a computing device provided by an embodiment of the present application; Among them, 202-acquisition module, 204-processing module, 206-clustering module, 208-model processing module, 210-model training module, 300-computing device, 310-memory, 320-processor, 330-bus, 340 access device, 350-database, 360-network. DETAILED DESCRIPTION

[0019] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0020] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms of "a", "said" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and includes any or all possible combinations of one or more associated listed items.

[0021] It should be understood that, although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present application, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0022] In the present application, a method for training a TCM syndrome type association model is provided. The present application also relates to a TCM syndrome type association model training device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0023] Figure 1 A flowchart of a TCM syndrome association model training method provided according to an embodiment of the present application is shown, which specifically includes the following steps: Step S102: obtaining original TCM business data, and determining TCM syndrome type score data corresponding to the target disease based on the original TCM business data; Step S104: processing the TCM syndrome score data according to the preset syndrome total score data to obtain TCM syndrome coefficient data; Step S106: clustering the TCM syndrome coefficient data based on the stage number of the target disease to obtain a clustered data set; Step S108: converting the TCM syndrome coefficient data according to the clustering data set to obtain TCM syndrome stage data, and using the TCM syndrome stage data and the corresponding stage of the target disease as inputs of the initial TCM syndrome association model, and outputting the support and confidence between any syndromes; Step S110: Using the preset minimum support and minimum confidence as training conditions, the initial TCM syndrome association model is adjusted until the support and the confidence meet the training conditions, thereby obtaining the target TCM syndrome association model.

[0024] Among them, the original data of TCM business includes the test results of medical tests and doctor consultations of patients, including basic information, age of onset, chief complaint, medical history, physical examination results, diagnosis records and treatment plans; for a certain symptom of the patient, a fixed syndrome type can be summarized, and the TCM syndrome type score data can be understood as the degree of correspondence to the fixed syndrome type, which is displayed in a digitized manner; the total syndrome type score data can be understood as the highest performance score of the above fixed syndrome types, because different symptoms have different degrees of prominence of the corresponding syndrome types. For example, the syndrome type "yin deficiency and toxic heat" corresponding to lung cancer is higher than the syndrome type "phlegm and blood stasis" when the patient is ill. In this case, the total syndrome type score data corresponding to "yin deficiency and toxic heat" is higher than that of "phlegm and blood stasis".

[0025] Based on this, in the process of syndrome correlation analysis for a certain disease, that is, the target disease, the original TCM business data of the patient is obtained, and then the TCM syndrome score data of the fixed syndrome of the target disease corresponding to the original TCM business data is determined. The specific determination method can be carried out through a pre-trained semantic model, that is, the semantic vector of the original TCM business data is extracted, and the semantic similarity is calculated with the semantic vector of the fixed syndrome of the target disease, and the TCM syndrome score data is obtained according to the semantic similarity. Then, the disputed syndrome score data is standardized through the preset syndrome total score data to obtain the TCM syndrome coefficient data. Since the target disease often has different stages, taking lung cancer as an example, the stage number can be determined through the tumor TNM staging standard of lung cancer, and then the TCM syndrome coefficient data is clustered by the stage number, and the TCM syndrome coefficient data is segmented according to the clustering result to obtain the TCM syndrome stage data.

[0026] Afterwards, the TCM syndrome stage data and the stage corresponding to the target disease are used as the input of the initial TCM syndrome association model, which will output the support representing the frequency of simultaneous occurrence of any two syndromes, and the confidence representing the probability of the occurrence of any two syndromes when one syndrome appears and the other syndrome also appears. The preset minimum support and minimum confidence are used as training conditions. When the output of the initial TCM syndrome association model is consistent with the minimum support and minimum confidence, the initial TCM syndrome association model is adjusted, and the output of support and confidence is repeated until the output support and confidence meet the requirements of minimum support and minimum confidence, and the target TCM syndrome association model is obtained.

[0027] Furthermore, in step S102, the process of determining the TCM syndrome score data corresponding to the target disease according to the original TCM business data is specifically implemented as follows in this embodiment: Based on the preset attribute definition rules, the original TCM business data is converted into a patient data set; based on the preset standard definition rules, the patient data set is cleaned, and sample data is determined according to the data cleaning results; based on the preset syndrome symptom definition rules, the sample data is attribute-reduced to obtain TCM syndrome score data.

[0028] Furthermore, for the above process of converting the original TCM business data into the patient data set based on the preset attribute definition rules, in this embodiment, the specific implementation method is as follows: The correspondence between the original TCM business data and the attribute definition rules is queried, and according to the query result, the original TCM business data is converted into corresponding attribute values; according to the attribute values, the patient data set is constructed.

[0029] Furthermore, for the above process of performing data cleaning on the patient data set based on the preset standard definition rules and determining the sample data according to the data cleaning results, in this embodiment, the specific implementation method is as follows: Based on the inclusion criteria in the standard definition rules, the patient data set is screened for the first time, and based on the exclusion criteria in the standard definition rules, the first screening results are screened for the second time to obtain a candidate sample data set; and data associated with the candidate sample data set in the original data of traditional Chinese medicine business is determined to obtain the sample data.

[0030] Furthermore, for the above process of performing attribute reduction on sample data based on the preset syndrome symptom definition rules to obtain TCM syndrome score data, in this embodiment, the specific implementation method is as follows: Semantic extraction is performed on the sample data to obtain sample semantics; similarity matching is performed between the sample semantics and the syndrome symptom definition rules to obtain the TCM syndrome score data.

[0031] The attribute definition rule includes an attribute name and an attribute description. The attribute name represents the element classification included, and the attribute description specifies the numerical conversion relationship of the corresponding element classification. Specifically, taking lung cancer as an example, the preset attribute definition rule can be expressed as an attribute definition table in a tabular form, and the attribute definition table is as follows in Table 1: Table 1 - Attribute definition table

[0032] According to Table 1 above, the original data of TCM business is converted into a patient data set. Specifically, the correspondence between the original data of TCM business and the attribute definition table is queried, the original data of TCM business is associated with the attribute name in the attribute definition table, and according to the corresponding attribute description, the original data of TCM business is converted into a numerical representation to obtain a patient data set, wherein the patient data set can be expressed in a tabular patient data table, and the patient data table is as shown in Table 2 below: Table 2 - Patient data table

[0033] After obtaining the patient data set, the patient data set is cleaned according to the standard definition rules. The cleaning process is to filter the data in the patient data set according to the inclusion criteria and exclusion criteria in the standard definition rules, and then query the data corresponding to the screening results in the original data of traditional Chinese medicine business to obtain sample data. Specifically, the standard definition rules can be expressed in a tabular standard definition table, which is as shown in Table 3: Table 3- Standard Definition Table

[0034] According to the inclusion and exclusion criteria of the standard definition rules, the data is screened to obtain sample data that can be used to study the syndrome relationship of the target disease. Then, according to the syndrome symptom definition rules, the sample data is attributed and reduced to obtain the TCM syndrome score data. Specifically, the TCM syndrome score data is determined by semantic extraction and semantic similarity matching. Taking lung cancer as an example, the fixed syndromes corresponding to lung cancer are qi deficiency and phlegm dampness, yin deficiency and toxic heat, qi and yin deficiency, qi stagnation and blood stasis, raging heat and toxicity, and phlegm and blood stasis. The syndrome symptom definition rules can be expressed in the form of a syndrome symptom definition table in tabular form, and the syndrome symptom definition table is as shown in Table 4: Table 4-Syndrome Symptom Definition Table

[0035] The TCM syndrome score data obtained after attribute reduction is shown in Table 5: Table 5- TCM Syndrome Type Scoring Data

[0036] Afterwards, in step S104, the TCM syndrome type score data needs to be processed based on the syndrome type total score data, so as to obtain TCM syndrome type coefficient data. Specifically, taking lung cancer as an example, the syndrome type total score data is as shown in Table 6 below: Table 6-Syndrome type total score data

[0037] The calculation method for TCM syndrome coefficient data is: TCM syndrome coefficient data = TCM syndrome score data / syndrome total score data * 100. It should be noted that for any patient's TCM syndrome coefficient data, it is necessary to calculate through the TCM syndrome score data and the corresponding syndrome total score data. For example, for patient No. 1 in Table 5 with Qi deficiency and phlegm dampness, the TCM syndrome score data of Qi deficiency and phlegm dampness is the second row and second column of Table 5, and the corresponding syndrome total score data is the first row of Table 6. The TCM syndrome coefficient data of each patient is calculated in turn, and all TCM syndrome coefficient data are obtained as shown in Table 7: Table 7- TCM Syndrome Coefficient Data

[0038] Furthermore, in step S106, based on the stage number of the target disease, the TCM syndrome coefficient data is clustered to obtain a cluster data set. In this embodiment, the specific implementation method is as follows: The TCM syndrome type coefficient data are discretized by a preset decision tree algorithm to determine the division points; the TCM syndrome type coefficient data are clustered according to the division points to obtain the cluster data set.

[0039] Among them, the preset decision tree algorithm can discretize the data of each TCM syndrome coefficient, so that each attribute is clustered into a cluster data set corresponding to the stage number of the target disease. Specifically, taking lung cancer as an example above, the decision tree algorithm C4.5 is used to discretize each syndrome coefficient and cluster each attribute into 6 categories of data.

[0040] Based on this, a clustering algorithm is used to discretize the syndrome coefficients and map the finite individuals in the infinite space to the finite space, so as to improve the time and space efficiency of the algorithm. In other words, discretization is to reduce the data accordingly without changing the relative size of the data. The discretization method based on the decision tree divides the data according to the optimal segmentation point, that is, the decision tree algorithm is used to find the optimal segmentation point.

[0041] In addition, the discretization method based on the decision tree can divide the data more accurately and is suitable for complex data distribution situations. It converts continuous data into discrete data, making data processing more convenient and efficient. However, different discretization methods are suitable for different data distribution situations, and it is necessary to select appropriate decision tree algorithms and parameters. Therefore, the specific clustering algorithm selection is determined by the actual usage scenario, and this embodiment does not limit it.

[0042] Afterwards, in step S108, the TCM syndrome coefficient data is converted according to the clustering data set to obtain the TCM syndrome stage data. Taking lung cancer as an example, the TCM syndrome coefficient data is converted according to the data clustering set, and the TCM syndrome stage data and the corresponding stage of the target disease are obtained as shown in Table 8 below: Table 8 - TCM syndrome stage data and corresponding stages of target diseases

[0043] Furthermore, in step S108, the TCM syndrome stage data and the corresponding stage of the target disease are used as inputs of the initial TCM syndrome association model to output the support and confidence between any syndromes. In this embodiment, the specific implementation method is as follows: The TCM syndrome stage data and the corresponding stage of the target disease are used as inputs of the initial TCM syndrome association model, and the support representing the frequency of simultaneous occurrence between any syndromes and the confidence representing the probability of the occurrence of any syndrome when the other syndrome also occurs are output.

[0044] Specifically, taking lung cancer as an example, Table 8 is used as the input of the initial TCM syndrome association model. The initial TCM syndrome association model can use the FP-Growth algorithm. The initial TCM syndrome association model will output support and confidence, where the support represents the frequency of simultaneous occurrence between any syndromes, and the confidence represents the probability that when one of the syndromes appears, the other syndrome also appears.

[0045] Among them, the calculation formula for support is: , in, Indicates the number of records with a specific TNM category and a specific TCM syndrome combination. Indicates the total number of records.

[0046] The calculation formula for the confidence of the rule TNM category X → TCM syndrome type Y is: , in, Indicates the support of the number of records with both a specific TNM category X and a specific TCM syndrome type Y. The support represents the number of records with a specific TNM category X.

[0047] Corresponding to the above method embodiment, the present application also provides a TCM syndrome association model training device embodiment, Figure 2 FIG. 1 is a schematic diagram showing the structure of a TCM syndrome association model training device provided by an embodiment of the present application. Figure 2As shown, the device comprises: The acquisition module 202 is configured to acquire the original TCM business data, and determine the TCM syndrome type score data corresponding to the target disease according to the original TCM business data; The processing module 204 is configured to process the TCM syndrome type score data according to the preset syndrome type total score data to obtain TCM syndrome type coefficient data; A clustering module 206 is configured to cluster the TCM syndrome coefficient data based on the stage number of the target disease to obtain a clustering data set; The model processing module 208 is configured to convert the TCM syndrome coefficient data according to the clustering data set to obtain TCM syndrome stage data, and use the TCM syndrome stage data and the corresponding stage of the target disease as inputs of the initial TCM syndrome association model, and output the support and confidence between any syndromes; The model training module 210 is configured to adjust the parameters of the initial TCM syndrome association model with preset minimum support and minimum confidence as training conditions until the support and the confidence meet the training conditions, thereby obtaining the target TCM syndrome association model.

[0048] In an optional embodiment, the acquisition module 202 is further configured to: Based on the preset attribute definition rules, the original TCM business data is converted into a patient data set; based on the preset standard definition rules, the patient data set is cleaned, and sample data is determined according to the data cleaning results; based on the preset syndrome symptom definition rules, the sample data is attribute-reduced to obtain TCM syndrome score data.

[0049] In an optional embodiment, the acquisition module 202 is further configured to: The correspondence between the original TCM business data and the attribute definition rules is queried, and according to the query result, the original TCM business data is converted into corresponding attribute values; according to the attribute values, the patient data set is constructed.

[0050] In an optional embodiment, the acquisition module 202 is further configured to: Based on the inclusion criteria in the standard definition rules, the patient data set is screened for the first time, and based on the exclusion criteria in the standard definition rules, the first screening results are screened for the second time to obtain a candidate sample data set; and data associated with the candidate sample data set in the original data of traditional Chinese medicine business is determined to obtain the sample data.

[0051] In an optional embodiment, the acquisition module 202 is further configured to: Semantic extraction is performed on the sample data to obtain sample semantics; similarity matching is performed between the sample semantics and the syndrome symptom definition rules to obtain the TCM syndrome score data.

[0052] In an optional embodiment, the clustering module 206 is further configured to: The TCM syndrome type coefficient data are discretized by a preset decision tree algorithm to determine the division points; the TCM syndrome type coefficient data are clustered according to the division points to obtain the cluster data set.

[0053] In an optional embodiment, the model processing module 208 is further configured to: The TCM syndrome stage data and the corresponding stage of the target disease are used as inputs of the initial TCM syndrome association model, and the support representing the frequency of simultaneous occurrence between any syndromes and the confidence representing the probability of the occurrence of any syndrome when the other syndrome also occurs are output.

[0054] The TCM syndrome type association model training device provided in the present application obtains the original TCM business data, and determines the TCM syndrome type score data corresponding to the target disease according to the original TCM business data; processes the TCM syndrome type score data according to the preset syndrome type total score data to obtain TCM syndrome type coefficient data; clusters the TCM syndrome type coefficient data based on the stage number of the target disease to obtain a cluster data set; converts the TCM syndrome type coefficient data according to the cluster data set to obtain TCM syndrome type stage data, and uses the TCM syndrome type stage data and the corresponding stage of the target disease as the input of the initial TCM syndrome type association model, and outputs the support and confidence between any syndrome types; uses the preset minimum support and minimum confidence as training conditions, adjusts the parameters of the initial TCM syndrome type association model until the support and confidence meet the training conditions, and obtains the target TCM syndrome type association model. The target TCM syndrome type association model can find the correlation between TCM symptoms and the regularity between many symptoms, and analyze the cause of the disease, predict the development of the disease, and provide effective reference for future clinical diagnosis and treatment based on the rules.

[0055] The above is a schematic scheme of a TCM syndrome type association model training device of the present embodiment. It should be noted that the technical scheme of the TCM syndrome type association model training device and the technical scheme of the TCM syndrome type association model training method mentioned above belong to the same concept. For the details not described in detail in the technical scheme of the TCM syndrome type association model training device, please refer to the description of the technical scheme of the TCM syndrome type association model training method mentioned above. In addition, each component in the device embodiment should be understood as a functional module that must be established to implement each step of the program flow or each step of the method, and each functional module is not an actual functional division or separation definition. The device claim defined by such a group of functional modules should be understood as a functional module architecture that mainly implements the solution through the computer program recorded in the specification, and should not be understood as a physical device that mainly implements the solution through hardware.

[0056] Figure 3 The block diagram of a computing device 300 provided according to an embodiment of the present application is shown. The components of the computing device 300 include but are not limited to a memory 310 and a processor 320. The processor 320 is connected to the memory 310 via a bus 330, and the database 350 is used to store data.

[0057] The computing device 300 also includes an access device 340 that enables the computing device 300 to communicate via one or more networks 360. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 340 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0058] In one embodiment of the present application, the above components of the computing device 300 and Figure 3 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 3 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.

[0059] The computing device 300 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 300 may also be a mobile or stationary server.

[0060] The processor 320 is used to execute computer executable instructions for each step of the TCM syndrome type association model training method.

[0061] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned TCM syndrome type association model training method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned TCM syndrome type association model training method.

[0062] An embodiment of the present application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, are used to execute each step of the TCM syndrome type association model training method.

[0063] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned TCM syndrome type association model training method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned TCM syndrome type association model training method.

[0064] An embodiment of the present application further provides a chip storing a computer program, which implements the steps of the TCM syndrome type association model training method when executed by the chip.

[0065] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0067] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0068] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0069] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the present application. The present application selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can understand and use the present application well. The present application is only limited by the claims and their full scope and equivalents.

Claims

1. A method for training a TCM syndrome association model, characterized in that: include: Obtaining original TCM business data, and determining TCM syndrome type score data corresponding to the target disease based on the original TCM business data; According to the preset total syndrome score data, the TCM syndrome score data is processed to obtain TCM syndrome coefficient data; Clustering the TCM syndrome coefficient data based on the stage number of the target disease to obtain a clustered data set; The TCM syndrome coefficient data is converted according to the clustering data set to obtain TCM syndrome stage data, and the TCM syndrome stage data and the corresponding stage of the target disease are used as inputs of an initial TCM syndrome association model to output support and confidence between any syndromes; Taking the preset minimum support and minimum confidence as training conditions, the initial TCM syndrome association model is adjusted until the support and the confidence meet the training conditions, thereby obtaining the target TCM syndrome association model.

2. The method according to claim 1, characterized in that Determining TCM syndrome type score data corresponding to the target disease based on the original TCM business data includes: Based on preset attribute definition rules, the raw TCM business data is converted into a patient data set; Based on preset standard definition rules, the patient data set is cleaned, and sample data is determined according to the data cleaning result; Based on the preset syndrome symptom definition rules, the sample data is attribute-reduced to obtain TCM syndrome score data.

3. The method according to claim 2, characterized in that The method of converting the original TCM business data into a patient data set based on a preset attribute definition rule includes: Querying the correspondence between the original TCM business data and the attribute definition rules, and converting the original TCM business data into corresponding attribute values ​​according to the query result; The patient data set is constructed according to the attribute values.

4. The method according to claim 2, characterized in that: The step of performing data cleaning on the patient data set based on preset standard definition rules and determining sample data according to the data cleaning results includes: Based on the inclusion criteria in the standard definition rules, the patient data set is screened for the first time, and based on the exclusion criteria in the standard definition rules, the first screening result is screened for the second time to obtain a candidate sample data set; Determine data in the original TCM business data that is associated with the candidate sample data set to obtain the sample data.

5. The method according to claim 2, characterized in that: Based on the preset syndrome symptom definition rules, the sample data is attribute-reduced to obtain TCM syndrome score data, including: Performing semantic extraction on the sample data to obtain sample semantics; The sample semantics is matched with the syndrome symptom definition rules for similarity to obtain the TCM syndrome score data.

6. The method according to claim 1, characterized in that The step of clustering the TCM syndrome coefficient data based on the stage number of the target disease to obtain a cluster data set includes: Discretizing the TCM syndrome coefficient data using a preset decision tree algorithm to determine the dividing points; The TCM syndrome type coefficient data are clustered according to the division points to obtain the cluster data set.

7. The method according to claim 1, characterized in that The TCM syndrome stage data and the corresponding stage of the target disease are used as inputs of the initial TCM syndrome association model, and the support and confidence between any syndromes are output, including: The TCM syndrome stage data and the corresponding stage of the target disease are used as inputs of the initial TCM syndrome association model, and the support representing the frequency of simultaneous occurrence between any syndromes and the confidence representing the probability of the occurrence of any syndrome when the other syndrome also occurs are output.

8. A TCM syndrome association model training device, characterized in that: include: An acquisition module is configured to acquire original TCM business data and determine TCM syndrome type score data corresponding to the target disease based on the original TCM business data; A processing module is configured to process the TCM syndrome type score data according to preset syndrome type total score data to obtain TCM syndrome type coefficient data; A clustering module is configured to cluster the TCM syndrome coefficient data based on the stage number of the target disease to obtain a clustering data set; A model processing module is configured to convert the TCM syndrome coefficient data according to the clustering data set to obtain TCM syndrome stage data, and use the TCM syndrome stage data and the corresponding stage of the target disease as inputs of an initial TCM syndrome association model, and output support and confidence between any syndromes; The model training module is configured to adjust the parameters of the initial TCM syndrome association model with preset minimum support and minimum confidence as training conditions until the support and confidence meet the training conditions, thereby obtaining the target TCM syndrome association model.

9. A computing device, characterized in that include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the steps of the TCM syndrome type association model training method described in any one of claims 1 to 7.

10. A computer-readable storage medium storing computer instructions, characterized in that: When the instruction is executed by the processor, the steps of the TCM syndrome type association model training method described in any one of claims 1 to 7 are implemented.

Images