Traditional Chinese medicine data value evaluation method and device, electronic equipment and storage medium

Abstract

The application belongs to the technical field of traditional Chinese medicine data value evaluation, and discloses a traditional Chinese medicine data value evaluation method and device, an electronic device and a storage medium. The method comprises the following steps: acquiring medical feature data of a target object, extracting time sequence feature data in the medical feature data, and calculating a coincidence degree score of each traditional Chinese medicine school in a time frequency domain by using a time similarity function; calculating a contribution weight of each traditional Chinese medicine standard term in each traditional Chinese medicine school according to the sum of the occurrence times of all western medicine standard terms in the medical feature data, in combination with a traditional Chinese medicine keyword weight matrix and the coincidence degree score; determining a traditional Chinese medicine school diagnosis result based on a school mutual exclusion logical matrix and in combination with the contribution weight; and calculating a traditional Chinese medicine data evaluation value of the medical feature data based on the traditional Chinese medicine school diagnosis result, in combination with a traditional Chinese medicine four-examination information integrity score criterion and a school scarcity coefficient matrix. Through the above method, the accuracy and reliability of traditional Chinese medicine data value evaluation are improved.

Description

Technical Field

[0001] This application relates to the technical field of traditional Chinese medicine data value assessment, and more specifically, to a method, apparatus, electronic device, and storage medium for assessing the value of traditional Chinese medicine data. Background Technology

[0002] With the advancement of the modernization of Traditional Chinese Medicine (TCM), clinical diagnostic and treatment data is accumulating, providing abundant resources for TCM big data research. However, existing technologies face numerous challenges in assessing the value of this TCM data. On the one hand, the complexity of the TCM theoretical system leads to semantic ambiguity and confusion among different schools of thought. For example, certain TCM terms may have different meanings in different schools of thought, which traditional probability-based deep learning models struggle to accurately identify and distinguish, easily leading to errors in school identification due to keyword overlap, thus affecting the accurate assessment of data value. On the other hand, modern clinical medical records often contain integrated TCM and Western medicine data, with a large number of Western medicine terms (such as blood pressure, CT scans, inflammation, etc.) acting as "noise" interference, affecting the feature extraction of traditional TCM syndromes (such as Wei Qi Ying Xue). This interference makes it difficult for existing models to effectively distinguish core TCM information from non-TCM information, thereby reducing the accuracy of TCM data value assessment.

[0003] Furthermore, existing technologies lack a comprehensive system for evaluating high-quality data. Especially for scarce long-tail school data (such as medical records from the Fu Yang school), value assessment often relies on subjective judgment, lacking automated and objective evaluation standards based on data scarcity and logical consistency. This makes the identification and utilization of high-quality TCM data difficult, limiting the further application of TCM big data in clinical practice and research. Therefore, existing technologies urgently need a comprehensive processing system capable of adaptively handling the mixture of TCM and Western medical terminology, possessing logical disambiguation capabilities, and objectively quantifying the value contribution of data, in order to achieve accurate value assessment of TCM data.

[0004] To address the aforementioned issues, existing technologies urgently need improvement. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, electronic device, and storage medium for evaluating the value of traditional Chinese medicine (TCM) data. This method uses a preset scoring criterion for the completeness of TCM four diagnostic methods and a preset school scarcity coefficient matrix. It combines this with TCM school diagnostic results determined by a weighted keyword matching method, a preset school mutual exclusion logic matrix, and the contribution weight of each TCM standard term in the medical feature data to each TCM school. The resulting TCM data evaluation value is calculated. This addresses the shortcomings of existing technologies in evaluating the value of TCM data, such as semantic ambiguity, school confusion, interference from mixed TCM and Western medical terminology, and a lack of objective evaluation standards, which make it difficult to accurately assess the value of TCM data. This method can adaptively handle the mixing of TCM and Western medical terminology, possess logical disambiguation capabilities, and objectively quantify the data contribution value, thus improving the accuracy and reliability of TCM data value evaluation.

[0006] Firstly, this application provides a method for evaluating the value of traditional Chinese medicine data, including: Obtain medical characteristic data of the target object; Extract the temporal feature data from the medical feature data, and use it to calculate the time-frequency domain fit score of each TCM school in the medical feature data through a preset time similarity function. Based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, combined with the preset TCM keyword weight matrix and the fit score, the contribution weight of each TCM standard term in the medical feature data to each TCM school is calculated. Based on a preset mutual exclusion logic matrix of different schools of thought, and combined with the contribution weight, the TCM school of thought diagnosis result of the medical feature data is determined. Based on the diagnostic results of the aforementioned TCM school of thought, and combined with the preset TCM four diagnostic information integrity scoring criteria and the preset school scarcity coefficient matrix, the TCM data evaluation value of the medical feature data is calculated.

[0007] The TCM data value assessment method provided in this application can evaluate the value of TCM data. It uses a pre-set TCM four diagnostic methods completeness scoring criterion and a pre-set school scarcity coefficient matrix, combined with a weighted keyword matching method, a pre-set school mutual exclusion logic matrix, and the contribution weight of each TCM standard term in the medical feature data to each TCM school, to determine the TCM school diagnostic results. This method calculates the TCM data evaluation value of the medical feature data, addressing the shortcomings of existing technologies in TCM data value assessment, such as semantic ambiguity, school confusion, interference from mixed TCM and Western medical terminology, and a lack of objective evaluation standards, which make accurate TCM data value assessment difficult. It can adaptively handle the mixture of TCM and Western medical terminology, possess logical disambiguation capabilities, and objectively quantify the data contribution value, thus improving the accuracy and reliability of TCM data value assessment.

[0008] Optionally, temporal feature data is extracted from the medical feature data to calculate the time-frequency domain fit score of each TCM school in the medical feature data using a preset time similarity function, including: Time-related data are extracted from the medical feature data to obtain time-series feature data; The time series feature data is converted into standardized time values ​​to obtain the converted time series feature data; The transformed time-series feature data is input into a preset time similarity function to calculate the fit score of each TCM school in the time frequency domain in the medical feature data.

[0009] Optionally, based on the sum of the occurrences of all Western medicine standard terms in the medical feature data, combined with a preset TCM keyword weight matrix and the fit score, the contribution weight of each TCM standard term in the medical feature data to each TCM school is calculated, including: Based on a pre-defined medical standard terminology glossary, the sum of the occurrence counts of all Western medicine standard terms in the medical feature data is identified; Determine whether the sum of the occurrence counts is greater than a preset attenuation weight threshold; if so, determine the corresponding attenuation coefficient based on the sum of the occurrence counts to adjust the initial contribution weight in the preset TCM keyword weight matrix, and obtain the intermediate contribution weight of each TCM standard term in the medical feature data in each TCM school; if not, determine the intermediate contribution weight of each TCM standard term in the medical feature data in each TCM school based on the initial contribution weight in the preset TCM keyword weight matrix. Based on the fit score, the intermediate contribution weight is adjusted to obtain the contribution weight of each TCM standard term in the medical feature data in each TCM school.

[0010] Optionally, based on a preset mutual exclusion logic matrix of schools of thought and combined with the contribution weights, the TCM school of thought diagnosis result obtained from the medical feature data is determined, including: The frequency of occurrence of each TCM standard term in the medical feature data and the contribution weight are input into a preset initial score calculation formula to calculate the initial score of each TCM school in the medical feature data. Based on a preset mutually exclusive logic matrix of schools of thought, the initial scores are corrected to obtain the final scores of each of the traditional Chinese medicine schools of thought. The maximum value is extracted from the final score of each of the aforementioned TCM schools, and the TCM school corresponding to the maximum value is determined as the TCM school diagnosis result of the medical feature data.

[0011] The TCM data value assessment method provided in this application can realize the value assessment of TCM data. By introducing a mutually exclusive logic matrix of schools of thought to correct the initial score, it effectively solves the problem of incorrect school of thought identification caused by keyword overlap and improves the accuracy and reliability of TCM school of thought diagnosis.

[0012] Optionally, based on a preset mutual exclusion logic matrix for different schools of thought, the initial scores are corrected to obtain the final scores for each of the aforementioned schools of traditional Chinese medicine, including: Based on the non-zero values ​​in the initial scores, the TCM schools involved in the medical feature data are determined, and the initial category information of the TCM schools in the medical feature data is obtained. Based on a preset mutual exclusion logic matrix of schools of thought, it is determined whether there are mutually exclusive keywords in the medical feature data that logically contradict the initial category information of the TCM schools of thought. If so, then based on the preset mutual exclusion logic matrix of schools of thought, the schools of thought of traditional Chinese medicine that have logical contradictions with the mutual exclusion keywords of schools of thought are determined from the initial category information of the schools of thought of traditional Chinese medicine, so as to use the corresponding penalty factor to correct the corresponding initial score and obtain the final score of each school of thought of traditional Chinese medicine. If not, then there is no need to modify the initial score, and the initial score is determined as the final score of the corresponding TCM school.

[0013] Optionally, based on the diagnostic results of the TCM school of thought, combined with a preset TCM four diagnostic methods information completeness scoring criterion and a preset school scarcity coefficient matrix, the TCM data evaluation value of the medical feature data is calculated, including: According to the preset scoring criteria for the integrity of TCM four diagnostic methods, the existence of TCM four diagnostic methods information in the medical feature data is evaluated, and the integrity score of TCM four diagnostic methods information in the medical feature data is calculated. Based on a preset school scarcity coefficient matrix, the probability of the diagnosis results of the TCM school appearing in the TCM medical knowledge database is determined. The completeness score of the four diagnostic methods of traditional Chinese medicine and the probability of occurrence of the school of thought are input into a preset formula for calculating the value of traditional Chinese medicine data, and the evaluation value of the medical feature data in traditional Chinese medicine is calculated.

[0014] The TCM data value assessment method provided in this application can realize the value assessment of TCM data. By comprehensively considering the completeness of TCM four diagnostic information and the scarcity of schools of thought, it solves the problem of lack of objective basis for the value assessment of scarce long-tail school data, and provides an objective and quantitative standard for TCM data value assessment.

[0015] Optionally, based on a preset scoring criterion for the completeness of TCM four diagnostic methods, an existence assessment of the TCM four diagnostic methods information in the medical feature data is performed to calculate the completeness score of the TCM four diagnostic methods information in the medical feature data, including: Based on the preset scoring criteria for the completeness of TCM four diagnostic methods information, specific fields with preset TCM four diagnostic method information keywords are identified in the medical feature data. Based on the keywords of the four diagnostic methods of traditional Chinese medicine appearing in the specific field, the TCM four diagnostic methods information category recognition result of the specific field is determined; The TCM four diagnostic information category recognition results are input into the preset TCM four diagnostic information integrity score calculation formula to calculate the TCM four diagnostic information integrity score of the medical feature data.

[0016] Secondly, this application provides a device for evaluating the value of traditional Chinese medicine data, comprising: The acquisition module is used to acquire medical characteristic data of the target object; The first calculation module is used to extract the temporal feature data from the medical feature data, and to calculate the fit score of each TCM school in the medical feature data in the time frequency domain through a preset time similarity function. The second calculation module is used to calculate the contribution weight of each TCM standard term in each TCM school based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, combined with the preset TCM keyword weight matrix and the fit score. The determination module is used to determine the TCM school diagnosis result of the obtained medical feature data based on a preset school mutual exclusion logic matrix and the contribution weight. The evaluation module is used to calculate the TCM data evaluation value of the medical feature data based on the diagnostic results of the TCM school, combined with the preset TCM four diagnostic information integrity scoring criteria and the preset school scarcity coefficient matrix.

[0017] This TCM data value assessment device uses a preset scoring criterion for the completeness of TCM four diagnostic methods and a preset school scarcity coefficient matrix. Combined with TCM school diagnosis results determined by a weighted keyword matching method, a preset school mutual exclusion logic matrix, and the contribution weight of each TCM standard term in the medical feature data to each TCM school, it calculates the TCM data evaluation value of the medical feature data. This addresses the shortcomings of existing technologies in TCM data value assessment, such as semantic ambiguity, school confusion, interference from mixed TCM and Western medical terminology, and lack of objective evaluation standards, which make it difficult to accurately assess the value of TCM data. It can adaptively handle the mixture of TCM and Western medical terminology, has logical disambiguation capabilities, and can objectively quantify the data contribution value, thus improving the accuracy and reliability of TCM data value assessment.

[0018] Thirdly, this application provides an electronic device, including a processor and a memory, wherein the memory stores a computer program executable by the processor, and when the processor executes the computer program, it performs the steps in the traditional Chinese medicine data value assessment method described above.

[0019] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps in the traditional Chinese medicine data value assessment method described above.

[0020] Beneficial Effects: The TCM data value assessment method, device, electronic device, and storage medium provided in this application calculate the TCM data evaluation value of medical feature data by using a preset TCM four diagnostic information integrity scoring criterion and a preset school scarcity coefficient matrix, combined with the TCM school diagnosis results determined by a weighted keyword matching method, a preset school mutual exclusion logic matrix, and the contribution weight of each TCM standard term in the medical feature data to each TCM school. This solves the problems of semantic ambiguity, school confusion, interference from mixed TCM and Western medicine terminology, and lack of objective evaluation standards in the existing technology for TCM data value assessment, which make it difficult to accurately assess the value of TCM data. It can adaptively handle the mixture of TCM and Western medicine terminology, has logical disambiguation capabilities, and can objectively quantify the data contribution value, thus improving the accuracy and reliability of TCM data value assessment. Attached Figure Description

[0021] Figure 1 A flowchart of a method for assessing the value of traditional Chinese medicine data provided in an embodiment of this application.

[0022] Figure 2 This is a schematic diagram of the structure of the TCM data value assessment device provided in the embodiments of this application.

[0023] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0024] Labeling Explanation: 1. Acquisition Module; 2. First Calculation Module; 3. Second Calculation Module; 4. Determination Module; 5. Evaluation Module; 301. Processor; 302. Memory; 303. Communication Bus. Detailed Implementation

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0026] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0027] Please refer to Figure 1 , Figure 1 This application provides a method for evaluating the value of traditional Chinese medicine (TCM) data, as described in some embodiments. The method includes the following steps: Step S101: Obtain medical characteristic data of the target object; Step S102: Extract time-series feature data from the medical feature data, and use it to calculate the time-frequency domain fit score of each TCM school in the medical feature data through a preset time similarity function. Step S103: Based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, combined with the preset TCM keyword weight matrix and fit score, calculate the contribution weight of each TCM standard term in the medical feature data to each TCM school. Step S104: Based on the preset mutual exclusion logic matrix of schools of thought and combined with the contribution weight, determine the diagnosis result of the traditional Chinese medicine school of thought obtained from the medical feature data. Step S105: Based on the diagnostic results of TCM schools of thought, combined with the preset TCM four diagnostic information integrity scoring criteria and the preset school scarcity coefficient matrix, the TCM data evaluation value of medical feature data is calculated.

[0028] This method for evaluating the value of TCM data uses a pre-defined scoring criterion for the completeness of TCM four diagnostic methods and a pre-defined school scarcity coefficient matrix. It combines this with a weighted keyword matching method, a pre-defined school mutual exclusion logic matrix, and the contribution weights of standard TCM terms in medical feature data within each TCM school to determine the diagnostic results of the TCM school. This method calculates the TCM data evaluation value of the medical feature data, addressing the shortcomings of existing technologies in evaluating the value of TCM data, such as semantic ambiguity, school confusion, interference from mixed TCM and Western medical terminology, and a lack of objective evaluation standards. This method adaptively handles the mixing of TCM and Western medical terminology, possesses logical disambiguation capabilities, and can objectively quantify the data's contribution value, thus improving the accuracy and reliability of TCM data value evaluation.

[0029] Specifically, in step S101, medical characteristic data of the target object is acquired. Medical characteristic data refers to textual data containing information about the target object's physiology, pathology, and symptoms; this data may include descriptions from both Traditional Chinese Medicine and Western medicine. Medical characteristic data can be acquired in various ways. For example, the target object's medical records can be directly imported from an electronic medical record system; these records are typically in structured or unstructured text format. Another method is to extract relevant information from handwritten medical records, consultation forms, or the target object's self-report using natural language processing technology. Furthermore, integration with medical devices can automatically collect patients' physiological parameters, imaging reports, and other data, and convert them into textual medical characteristic data.

[0030] Specifically, in step S102, temporal feature data is extracted from the medical feature data to calculate the time-frequency domain fit score of each TCM school in the medical feature data using a preset time similarity function, including: Time-related data are extracted from medical feature data to obtain time-series feature data; The time series feature data is converted into standardized time values ​​to obtain the converted time series feature data; The transformed time-series feature data is input into a preset time similarity function to calculate the fit score of each TCM school in the time frequency domain in the medical feature data.

[0031] In step S102, natural language processing (NLP) technology is used to identify and extract all information related to the time dimension through keyword matching (such as keywords such as "admission time", "onset date", "treatment cycle", "follow-up visit interval", "day", "hour", "minute" etc.) to obtain time-series feature data.

[0032] The extracted time-series feature data is uniformly converted into a standardized time representation, such as converting it to a daily unit, resulting in converted time-series feature data. This makes the originally discrete and heterogeneous time information quantifiable and comparable. This processing method enables a more accurate reflection of the inherent patterns and differences between different schools of thought in the time-frequency domain when calculating the fit score of TCM schools.

[0033] The transformed time-series feature data is input into a preset time similarity function to calculate the fit score of each TCM school in the time frequency domain in the medical feature data. The fit score can provide a key adjustment factor for the subsequent calculation of the contribution weight of each TCM standard term in each TCM school.

[0034] The preset time similarity function can be set to a Gaussian kernel function, a Laplace kernel function, a log-normal distribution probability density function, a Weiber distribution probability density function, or a normalized cross-correlation function. This function is used to calculate the similarity between the transformed time-series feature data and the intrinsic time scales of various TCM schools, thus obtaining a fit score. The intrinsic time scale represents the most typical and suitable disease course time range for a particular TCM school. It can be calculated based on historical data, typically using the mode, median, or mean of the historical case course distribution for the corresponding TCM school as a representative value. For example, the Shanghan school has a shorter time cycle, and the intrinsic time scale corresponding to the Shanghan school, calculated from historical data, is generally 33 days; the Huitong school has a longer time cycle, and the intrinsic time scale corresponding to the Huitong school, calculated from historical data, is generally 278 days.

[0035] For example, using the Gaussian kernel function as the preset time similarity function, we get: ; in, Score the compatibility. This represents the x-th transformed time-series feature data; The intrinsic time scale of the TCM school s (the s-th TCM school) can be determined by calculating the difference between the transformed time series feature data and the intrinsic time scale of each TCM school, and the intrinsic time scale of the TCM school corresponding to the minimum value of the difference can be determined. The standard deviation of the time distribution of the TCM school of thought s can be calculated based on historical data.

[0036] Specifically, in step S103, based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, and combined with a preset TCM keyword weight matrix, the contribution weight of each TCM standard term in the medical feature data to each TCM school is calculated, including: Based on a pre-defined medical standard terminology glossary, the sum of the occurrences of all Western medical standard terms in the medical feature data is identified; Determine whether the sum of the occurrences is greater than the preset attenuation weight threshold; if so, determine the corresponding attenuation coefficient based on the sum of the occurrences to adjust the initial contribution weight in the preset TCM keyword weight matrix, and obtain the intermediate contribution weight of each TCM standard term in each TCM school in the medical feature data; if not, determine the intermediate contribution weight of each TCM standard term in each TCM school in the medical feature data based on the initial contribution weight in the preset TCM keyword weight matrix. Based on the fit score, the intermediate contribution weights are adjusted to obtain the contribution weights of each TCM standard term in the medical feature data to each TCM school.

[0037] It should be noted that the pre-set medical standard terminology glossary is a pre-defined collection containing various standard terms of traditional Chinese medicine and Western medicine, along with their corresponding codes or identifiers. Its purpose is to standardize the identification and extraction of Western medicine and traditional Chinese medicine information from medical feature data. For example, terms such as "hypertension" and "diabetes" belong to standard Western medicine terms, while terms such as "red tongue" and "deep and thready pulse" belong to standard traditional Chinese medicine terms.

[0038] The preset TCM keyword weight matrix represents the initial contribution weights of each standard TCM term in each TCM school of thought. This weighting can be adjusted based on medical knowledge and the advice of TCM experts. For example, taking "red tongue" in the preset TCM keyword weight matrix as an example, the initial contribution weight for the Fuyang school corresponding to "red tongue" is 0.4; for the Shanghan school, it is 0.3; for the Wenbing school, it is 0.8; and for the Huitong school, it is 0.3.

[0039] In step S103, based on a preset medical standard terminology glossary, keywords related to Western medicine, i.e., Western medicine standard terms, are identified from the medical feature data, so as to obtain the sum of the occurrence times of all Western medicine standard terms in the medical feature data.

[0040] The method determines whether the sum of occurrences exceeds a preset attenuation weight threshold to assess the impact of the frequency of Western medicine standard terms on contribution weight evaluation. When the sum of occurrences exceeds the preset attenuation weight threshold, it indicates that Western medicine standard terms have a high frequency of occurrence in the medical feature data. In this case, by determining a corresponding attenuation coefficient and using this attenuation coefficient to adjust the initial contribution weight in the preset TCM keyword weight matrix (i.e., multiplying the attenuation coefficient by the initial contribution weight), the excessive influence of high-frequency Western medicine standard terms on the contribution weight of TCM schools can be appropriately reduced, thus obtaining the intermediate contribution weight of each TCM standard term in each TCM school in the medical feature data. Conversely, when the sum of occurrences does not exceed the preset attenuation weight threshold, it indicates that Western medicine standard terms have a relatively low frequency of occurrence in the medical feature data. It is determined that the impact of Western medicine standard terms on the contribution weight of TCM schools is not significant at this time. Based on the initial contribution weight in the preset TCM keyword weight matrix, the intermediate contribution weight of each TCM standard term in each TCM school in the medical feature data is determined.

[0041] The preset attenuation weight threshold is a pre-defined value used to determine whether the frequency of occurrence of Western medical standard terms reaches a level requiring weight adjustment. It can be set according to actual needs. When the sum of occurrences exceeds this threshold, it indicates that the frequency of occurrence of Western medical standard terms is high, which will affect the contribution weight of each TCM standard term in each TCM school. In this case, an attenuation coefficient needs to be set to appropriately reduce the influence of Western medical standard terms.

[0042] The attenuation coefficient is a dynamically determined coefficient based on the sum of occurrences. Its function is to adjust the initial contribution weight in the preset TCM keyword weight matrix. For example, the attenuation coefficient can be a value between 0 and 1. The larger the sum of occurrences, the smaller the attenuation coefficient, thereby appropriately reducing the influence of Western medical standard terms on the contribution weight of TCM schools of thought.

[0043] Based on the fit scores of each TCM school in the time-frequency domain, the corresponding intermediate contribution weights are adjusted, that is, the intermediate contribution weights are multiplied by the fit scores to obtain the contribution weights of each TCM standard term in each TCM school in the medical feature data.

[0044] Therefore, by introducing attenuation weight threshold and attenuation coefficient, the problem of weight imbalance that may be caused by the excessive frequency of Western medicine standard terms when calculating the contribution weight of TCM standard terms to various TCM schools can be effectively solved.

[0045] Specifically, in step S104, based on a preset mutual exclusion logic matrix of different schools of thought and combined with contribution weights, the diagnostic results of the traditional Chinese medicine school of thought obtained from the medical feature data are determined, including: The frequency of occurrence and contribution weight of each TCM standard term in the medical feature data are input into the preset initial score calculation formula to calculate the initial score of each TCM school in the medical feature data. Based on a pre-defined mutually exclusive logic matrix of schools of thought, the initial scores are corrected to obtain the final scores of each school of traditional Chinese medicine. The maximum value is extracted from the final score of each TCM school, and the TCM school corresponding to the maximum value is determined as the TCM school diagnosis result of the medical feature data.

[0046] In step S104, by using a preset medical standard terminology glossary, all standard terms related to traditional Chinese medicine (i.e., TCM standard terms) can be accurately identified from the medical feature data, and the frequency of each TCM standard term in the medical feature data can be counted to obtain the number of times each TCM standard term appears.

[0047] The frequency of occurrence and contribution weight of each TCM standard term are input into a preset initial score calculation formula to calculate the initial score for each TCM school in the medical feature data.

[0048] The preset initial score calculation formula is as follows: ; in, The initial score for school of thought s in Traditional Chinese Medicine; This represents the number of occurrences of the standard TCM term k (the kth standard TCM term); The contribution weight of standard TCM terminology k to TCM schools of thought s; These are the standard TCM terms from the pre-set medical standard terminology glossary.

[0049] Specifically, in step S104, based on a preset mutual exclusion logic matrix of schools of thought, the initial scores are corrected to obtain the final scores for each of the aforementioned schools of traditional Chinese medicine, including: Based on the non-zero values ​​in the initial scores, the TCM schools involved in the medical feature data are determined, and the initial category information of the TCM schools in the medical feature data is obtained. Based on a preset mutually exclusive logic matrix of schools of thought, determine whether there are mutually exclusive keywords in the medical feature data that logically contradict the initial category information of Chinese medicine schools of thought. If so, then based on the preset mutual exclusion logic matrix of schools of thought, the schools of thought of traditional Chinese medicine that have logical contradictions with the mutual exclusion keywords of schools of thought are identified from the initial category information of schools of thought of traditional Chinese medicine. The corresponding initial scores are then corrected using the corresponding penalty factors to obtain the final scores of each school of thought of traditional Chinese medicine. If not, then there is no need to revise the initial score; the initial score will be determined as the final score for the corresponding school of traditional Chinese medicine.

[0050] It should be noted that the mutual exclusion logic matrix of schools of thought is a pre-constructed relation matrix, which defines the possible mutual exclusion relationships between different schools of Chinese medicine and the keywords that lead to these mutual exclusion relationships, as well as the penalty factor when a mutual exclusion relationship occurs. The penalty factor is used to correct the initial score when the corresponding mutual exclusion relationship occurs.

[0051] In step S104, to improve the accuracy and rationality of the diagnostic results, the initial scores need to be corrected. After obtaining the initial scores for each TCM school, the initial category information of the TCM school for obtaining the medical feature data needs to be determined based on the non-zero scores among these initial scores. That is, the TCM school corresponding to the non-zero initial scores is determined as the initial category information of the TCM school.

[0052] Based on a pre-defined mutually exclusive logic matrix of TCM schools, the medical feature data is analyzed to determine whether there are mutually exclusive keywords that logically contradict the initial category information of the identified TCM schools. For example, if one school emphasizes "cold syndrome" while another emphasizes "heat syndrome," and the medical feature data contains strong keywords for both "cold" and "heat," then there may be a logical contradiction between the "heat syndrome" school and "cold," and between the "cold syndrome" school and "heat."

[0053] If the judgment result is "yes," meaning there are logically contradictory mutually exclusive keywords, then based on a pre-defined mutually exclusive logic matrix, it is necessary to identify the TCM schools that logically contradict the mutually exclusive keywords from the initial category information of TCM schools. The corresponding penalty factor is then used to correct the initial score; that is, the initial score is subtracted from the penalty factor to obtain the final score for each TCM school. This method can eliminate or weaken the influence of unreasonable schools, making the final score more accurately reflect the true school tendency of the medical feature data. The penalty factor can be adjusted according to the number of mutually exclusive keywords. For example, the more mutually exclusive keywords a TCM school involves, the larger the penalty factor; the fewer mutually exclusive keywords a TCM school involves, the smaller the penalty factor.

[0054] Conversely, if the judgment result is "no," meaning that no mutually exclusive keywords for a school of traditional Chinese medicine (TCM) appear in the medical feature data that logically contradict the initial category information, it indicates that the initial score is relatively reasonable and no additional correction is needed. In this case, the initial score of each TCM school will be directly determined as the final score for that corresponding TCM school.

[0055] In some optional embodiments, a preset final score calculation formula can be determined through a preset logic gating penalty mechanism to calculate the final score of each TCM school. Specifically, the preset final score calculation formula is as follows: ; in, The final score for school of thought in Traditional Chinese Medicine (TCM); The penalty factor can be obtained from the preset mutual exclusion logic matrix of different schools of thought; For indicator functions, Let be an indicator function for a school of thought in Traditional Chinese Medicine (TCM), and let be an indicator function for a school of thought in TCM that contains a mutually exclusive keyword that contradicts TCM school of thought s. The value is 1, indicating that there are no mutually exclusive keywords related to the TCM school of thought 's' that logically contradict each other. The value is 0. This logic gating penalty mechanism is used for semantic disambiguation, such as distinguishing between "Si Ni Tang" (Fu Yang school) and "Dang Gui Si Ni Tang" (Shang Han school).

[0056] In step S104, after obtaining the final scores of each TCM school, the maximum value among these final scores is extracted, and the corresponding TCM school is determined as the TCM school diagnosis result of the medical feature data, thereby achieving accurate identification of the TCM school to which the medical feature data belongs.

[0057] In some optional embodiments, a neural network model with two layers can be established. One layer is an initial scoring layer, which includes a time similarity function, a medical standard terminology vocabulary, and an initial score calculation formula. Using the medical standard terminology vocabulary and the time similarity function, the initial scoring layer can identify traditional Chinese medicine (TCM) and Western medicine standard terms in the medical feature data and calculate the fit score for each TCM school of thought to determine the contribution weight of each TCM standard term within each TCM school. Thus, the initial score for each TCM school is calculated using the initial score calculation formula. The other layer is a final scoring layer, which includes a school-specific mutual exclusion logic matrix and a final score calculation formula. Using the school-specific mutual exclusion logic matrix, the final scoring layer can identify mutually exclusive keywords that logically contradict each TCM school, determine the corresponding penalty factors, and thus calculate the final score for each TCM school using the final score calculation formula. Finally, the neural network model extracts the maximum value from these final scores and identifies the corresponding TCM school as the TCM school diagnosis result of the medical feature data. This enables the neural network model to identify schools of thought in traditional Chinese medicine. By inputting medical feature data, it can accurately identify the school of thought to which the medical feature data belongs. Thus, steps S102, S103, and S104 are modified to: inputting medical feature data into a preset neural network model to identify the diagnostic result of the school of thought in traditional Chinese medicine based on the medical feature data.

[0058] Specifically, in step S105, based on the diagnostic results of TCM schools of thought, combined with the preset TCM four diagnostic information integrity scoring criteria and the preset school scarcity coefficient matrix, the TCM data evaluation value of the medical feature data is calculated, including: Based on the preset scoring criteria for the completeness of TCM four diagnostic methods information, the existence of TCM four diagnostic methods information in medical feature data is evaluated, and the completeness score of TCM four diagnostic methods information in medical feature data is calculated. Based on the preset school scarcity coefficient matrix, the probability of the obtained TCM school diagnosis results appearing in the TCM medical knowledge database is determined. The completeness score of the four diagnostic methods of traditional Chinese medicine and the probability of the appearance of different schools of thought are input into a preset formula for calculating the value of traditional Chinese medicine data, and the evaluation value of the medical feature data in traditional Chinese medicine is calculated.

[0059] Specifically, in step S105, according to the preset TCM four diagnostic methods information integrity scoring criteria, the existence of TCM four diagnostic methods information in the medical feature data is evaluated, and the TCM four diagnostic methods information integrity score of the medical feature data is calculated, including: Based on the preset scoring criteria for the completeness of TCM four diagnostic methods information, specific fields with preset TCM four diagnostic method information keywords are identified in the medical feature data. Based on the keywords of the four diagnostic methods of traditional Chinese medicine appearing in specific fields, the TCM four diagnostic methods information category recognition results of specific fields are determined; The results of TCM four diagnostic information category recognition are input into the preset TCM four diagnostic information integrity score calculation formula to calculate the TCM four diagnostic information integrity score of medical feature data.

[0060] It should be noted that the preset scoring criteria for the completeness of TCM four diagnostic methods information is a set of pre-set rules or standards used to measure the completeness of TCM four diagnostic methods (inspection, auscultation, inquiry, and palpation) information contained in a medical feature data.

[0061] In step S105, natural language processing technology or keyword matching algorithms are used to parse the medical feature data provided by the target object to identify keywords related to the four diagnostic methods of traditional Chinese medicine (TCM), thus obtaining specific fields with preset TCM four diagnostic information keywords. These TCM four diagnostic information keywords are a predefined set of terms related to the four diagnostic methods of TCM: observation, auscultation, inquiry, and palpation, such as "facial complexion," "tongue coating," "pulse," "inquiry," "auscultation," and "palpation."

[0062] After identifying specific fields containing keywords from the four diagnostic methods (inspection, auscultation, and olfaction), these keywords are further analyzed to determine which category of TCM diagnostic information the field belongs to. For example, if a specific field contains keywords such as "complexion," "tongue coating," or "eye expression," it may be identified as "inspection" information; if it contains keywords such as "pulse" or "abdominal palpation," it may be identified as "palpation" information; if it contains keywords such as "chief complaint" or "medical history," it may be identified as "inquiry" information; and if it contains keywords such as "voice" or "breathing," it may be identified as "auscultation" information. In this way, different types of diagnostic information can be accurately classified, providing a structured data foundation for subsequent integrity assessment.

[0063] The results of the TCM four diagnostic methods information category recognition are input into a preset TCM four diagnostic methods information integrity score calculation formula to calculate the TCM four diagnostic methods information integrity score of the medical feature data. The preset TCM four diagnostic methods information integrity score calculation formula is as follows: ; in, The completeness score of the four diagnostic methods in Traditional Chinese Medicine (TCM) is given; F represents the Fth category of the four diagnostic methods in TCM (Category F of the four diagnostic methods in TCM is any one of the four categories of observation, auscultation, inquiry, and palpation). The weights of information category F in Traditional Chinese Medicine's four diagnostic methods. ; This is an indicator function for the TCM four diagnostic information category recognition results. When the TCM four diagnostic information category recognition results identify a TCM four diagnostic information category F (i.e., any TCM four diagnostic information keyword in any specific field belongs to TCM four diagnostic information category F), the value is 1. When the TCM four diagnostic information category recognition results do not identify a TCM four diagnostic information category F (i.e., all TCM four diagnostic information keywords in all specific fields do not belong to TCM four diagnostic information category F), the value is 0.

[0064] In step S104, a school scarcity coefficient matrix is ​​pre-determined from the TCM medical knowledge database to determine the probability of a TCM school's diagnostic results appearing in the TCM medical knowledge database. The school scarcity coefficient matrix is ​​a pre-defined table or dataset that records the frequency of different TCM schools appearing in the existing database or knowledge base (calculated by the proportion of the occurrences of a single TCM school to the total occurrences of all TCM schools), i.e., the probability of a school's appearance, which can also be called its relative scarcity. The smaller the probability of a school's appearance, the scarcer and more valuable the corresponding TCM data.

[0065] The completeness score of the four diagnostic methods in Traditional Chinese Medicine (TCM) and the probability of occurrence of different schools of thought are input into a preset TCM data value calculation formula to calculate the TCM data evaluation value of the medical feature data. The preset TCM data value calculation formula is as follows: ; in, To evaluate the value of TCM data; This represents the probability of a particular school of thought appearing.

[0066] As shown above, this method for evaluating the value of TCM data involves acquiring the medical characteristic data of the target object, extracting the temporal characteristic data from the medical characteristic data, and using a preset time similarity function to calculate the time-frequency domain fit score of each TCM school in the medical characteristic data. Based on the sum of the occurrence frequencies of all Western medicine standard terms in the medical characteristic data, combined with a preset TCM keyword weight matrix and fit score, the contribution weight of each TCM standard term in the medical characteristic data to each TCM school is calculated. Based on a preset school mutual exclusion logic matrix, combined with the contribution weight, the TCM school diagnostic result of the medical characteristic data is determined. Based on the TCM school diagnostic result, combined with a preset TCM four diagnostic information integrity scoring criterion and a preset school scarcity coefficient matrix, the medical characteristic data is calculated. The evaluation value of TCM data is determined by using a pre-set TCM four diagnostic information integrity scoring criterion and a pre-set school scarcity coefficient matrix, combined with TCM school diagnosis results obtained from a weighted keyword matching method, a pre-set school mutual exclusion logic matrix, and the contribution weight of each TCM standard term in the medical feature data to each TCM school. This method calculates the TCM data evaluation value of the medical feature data, solving the problems of semantic ambiguity, school confusion, interference from mixed TCM and Western medicine terminology, and lack of objective evaluation standards in the value assessment of TCM data. It can adaptively handle the mixture of TCM and Western medicine terminology, has logical disambiguation capabilities, and can objectively quantify the data contribution value, thus improving the accuracy and reliability of TCM data value assessment.

[0067] refer to Figure 2 This application provides a device for evaluating the value of traditional Chinese medicine data, used to evaluate the value of traditional Chinese medicine data, including: Module 1 is used to acquire medical feature data of the target object; The first calculation module 2 is used to extract time-series feature data from medical feature data, and to calculate the fit score of each TCM school in the time frequency domain through a preset time similarity function. The second calculation module 3 is used to calculate the contribution weight of each TCM standard term in each TCM school based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, combined with the preset TCM keyword weight matrix and fit score. Module 4 is used to determine the TCM school diagnosis results based on the preset school mutual exclusion logic matrix and the contribution weights obtained from the medical feature data. Evaluation module 5 is used to calculate the TCM data evaluation value of medical feature data based on the diagnostic results of TCM schools, combined with the preset TCM four diagnostic information integrity scoring criteria and the preset school scarcity coefficient matrix.

[0068] This TCM data value assessment device uses a preset scoring criterion for the completeness of TCM four diagnostic methods and a preset school scarcity coefficient matrix. Combined with TCM school diagnosis results determined by a weighted keyword matching method, a preset school mutual exclusion logic matrix, and the contribution weight of each TCM standard term in the medical feature data to each TCM school, it calculates the TCM data evaluation value of the medical feature data. This addresses the shortcomings of existing technologies in TCM data value assessment, such as semantic ambiguity, school confusion, interference from mixed TCM and Western medical terminology, and lack of objective evaluation standards, which make it difficult to accurately assess the value of TCM data. It can adaptively handle the mixture of TCM and Western medical terminology, has logical disambiguation capabilities, and can objectively quantify the data contribution value, thus improving the accuracy and reliability of TCM data value assessment.

[0069] Specifically, during execution, module 1 acquires the medical characteristic data of the target object. Medical characteristic data refers to textual data containing information about the target object's physiology, pathology, and symptoms; this data may include descriptions from both Traditional Chinese Medicine and Western medicine. Medical characteristic data can be acquired in various ways. For example, it can be directly imported from an electronic medical record system; these records are typically in structured or unstructured text format. Another method is to extract relevant information from handwritten medical records, consultation forms, or the target object's self-report using natural language processing technology. Furthermore, it can be integrated with medical devices to automatically collect patients' physiological parameters, imaging reports, and other data, and convert them into textual medical characteristic data.

[0070] Specifically, when the first calculation module 2 extracts the temporal feature data from the medical feature data and uses it to calculate the time-frequency domain fit score of each TCM school in the medical feature data through a preset time similarity function, it executes: Time-related data are extracted from medical feature data to obtain time-series feature data; The time series feature data is converted into standardized time values ​​to obtain the converted time series feature data; The transformed time-series feature data is input into a preset time similarity function to calculate the fit score of each TCM school in the time frequency domain in the medical feature data.

[0071] When the first calculation module 2 is executed, it uses natural language processing (NLP) technology to identify and extract all information related to the time dimension through keyword matching (such as keywords such as "admission time", "onset date", "treatment cycle", "follow-up visit interval", "day", "hour", "minute" etc.) to obtain time-series feature data.

[0072] The extracted time-series feature data is uniformly converted into a standardized time representation, such as converting it to a daily unit, resulting in converted time-series feature data. This makes the originally discrete and heterogeneous time information quantifiable and comparable. This processing method enables a more accurate reflection of the inherent patterns and differences between different schools of thought in the time-frequency domain when calculating the fit score of TCM schools.

[0073] The transformed time-series feature data is input into a preset time similarity function to calculate the fit score of each TCM school in the time frequency domain in the medical feature data. The fit score can provide a key adjustment factor for the subsequent calculation of the contribution weight of each TCM standard term in each TCM school.

[0074] The preset time similarity function can be set to a Gaussian kernel function, a Laplace kernel function, a log-normal distribution probability density function, a Weiber distribution probability density function, or a normalized cross-correlation function. This function is used to calculate the similarity between the transformed time-series feature data and the intrinsic time scales of various TCM schools, thus obtaining a fit score. The intrinsic time scale represents the most typical and suitable disease course time range for a particular TCM school. It can be calculated based on historical data, typically using the mode, median, or mean of the historical case course distribution for the corresponding TCM school as a representative value. For example, the Shanghan school has a shorter time cycle, and the intrinsic time scale corresponding to the Shanghan school, calculated from historical data, is generally 33 days; the Huitong school has a longer time cycle, and the intrinsic time scale corresponding to the Huitong school, calculated from historical data, is generally 278 days.

[0075] For example, using the Gaussian kernel function as the preset time similarity function, we get: ; in, Score the compatibility. This represents the x-th transformed time-series feature data; The intrinsic time scale of the TCM school s (the s-th TCM school) can be determined by calculating the difference between the transformed time series feature data and the intrinsic time scale of each TCM school, and the intrinsic time scale of the TCM school corresponding to the minimum value of the difference can be determined. The standard deviation of the time distribution of the TCM school of thought s can be calculated based on historical data.

[0076] Specifically, when the second calculation module 3 calculates the contribution weight of each TCM standard term in the medical feature data to each TCM school of thought based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data and in combination with the preset TCM keyword weight matrix, it executes the following: Based on a pre-defined medical standard terminology glossary, the sum of the occurrences of all Western medical standard terms in the medical feature data is identified; Determine whether the sum of the occurrences is greater than the preset attenuation weight threshold; if so, determine the corresponding attenuation coefficient based on the sum of the occurrences to adjust the initial contribution weight in the preset TCM keyword weight matrix, and obtain the intermediate contribution weight of each TCM standard term in each TCM school in the medical feature data; if not, determine the intermediate contribution weight of each TCM standard term in each TCM school in the medical feature data based on the initial contribution weight in the preset TCM keyword weight matrix. Based on the fit score, the intermediate contribution weights are adjusted to obtain the contribution weights of each TCM standard term in the medical feature data to each TCM school.

[0077] It should be noted that the pre-set medical standard terminology glossary is a pre-defined collection containing various standard terms of traditional Chinese medicine and Western medicine, along with their corresponding codes or identifiers. Its purpose is to standardize the identification and extraction of Western medicine and traditional Chinese medicine information from medical feature data. For example, terms such as "hypertension" and "diabetes" belong to standard Western medicine terms, while terms such as "red tongue" and "deep and thready pulse" belong to standard traditional Chinese medicine terms.

[0078] The preset TCM keyword weight matrix represents the initial contribution weights of each standard TCM term in each TCM school of thought. This weighting can be adjusted based on medical knowledge and the advice of TCM experts. For example, taking "red tongue" in the preset TCM keyword weight matrix as an example, the initial contribution weight for the Fuyang school corresponding to "red tongue" is 0.4; for the Shanghan school, it is 0.3; for the Wenbing school, it is 0.8; and for the Huitong school, it is 0.3.

[0079] When the second calculation module 3 is executed, it identifies keywords related to Western medicine from the medical feature data, i.e., Western medicine standard terms, according to the preset medical standard terminology list, so as to obtain the sum of the occurrence times of all Western medicine standard terms in the medical feature data.

[0080] The method determines whether the sum of occurrences exceeds a preset attenuation weight threshold to assess the impact of the frequency of Western medicine standard terms on contribution weight evaluation. When the sum of occurrences exceeds the preset attenuation weight threshold, it indicates that Western medicine standard terms have a high frequency of occurrence in the medical feature data. In this case, by determining a corresponding attenuation coefficient and using this attenuation coefficient to adjust the initial contribution weight in the preset TCM keyword weight matrix (i.e., multiplying the attenuation coefficient by the initial contribution weight), the excessive influence of high-frequency Western medicine standard terms on the contribution weight of TCM schools can be appropriately reduced, thus obtaining the intermediate contribution weight of each TCM standard term in each TCM school in the medical feature data. Conversely, when the sum of occurrences does not exceed the preset attenuation weight threshold, it indicates that Western medicine standard terms have a relatively low frequency of occurrence in the medical feature data. It is determined that the impact of Western medicine standard terms on the contribution weight of TCM schools is not significant at this time. Based on the initial contribution weight in the preset TCM keyword weight matrix, the intermediate contribution weight of each TCM standard term in each TCM school in the medical feature data is determined.

[0081] The preset attenuation weight threshold is a pre-defined value used to determine whether the frequency of occurrence of Western medical standard terms reaches a level requiring weight adjustment. It can be set according to actual needs. When the sum of occurrences exceeds this threshold, it indicates that the frequency of occurrence of Western medical standard terms is high, which will affect the contribution weight of each TCM standard term in each TCM school. In this case, an attenuation coefficient needs to be set to appropriately reduce the influence of Western medical standard terms.

[0082] The attenuation coefficient is a dynamically determined coefficient based on the sum of occurrences. Its function is to adjust the initial contribution weight in the preset TCM keyword weight matrix. For example, the attenuation coefficient can be a value between 0 and 1. The larger the sum of occurrences, the smaller the attenuation coefficient, thereby appropriately reducing the influence of Western medical standard terms on the contribution weight of TCM schools of thought.

[0083] Based on the fit scores of each TCM school in the time-frequency domain, the corresponding intermediate contribution weights are adjusted, that is, the intermediate contribution weights are multiplied by the fit scores to obtain the contribution weights of each TCM standard term in each TCM school in the medical feature data.

[0084] Therefore, by introducing attenuation weight threshold and attenuation coefficient, the problem of weight imbalance that may be caused by the excessive frequency of Western medicine standard terms when calculating the contribution weight of TCM standard terms to various TCM schools can be effectively solved.

[0085] Specifically, when determining the TCM school diagnosis result based on the preset school-specific mutual exclusion logic matrix and contribution weights, module 4 executes the following: The frequency of occurrence and contribution weight of each TCM standard term in the medical feature data are input into the preset initial score calculation formula to calculate the initial score of each TCM school in the medical feature data. Based on a pre-defined mutually exclusive logic matrix of schools of thought, the initial scores are corrected to obtain the final scores of each school of traditional Chinese medicine. The maximum value is extracted from the final score of each TCM school, and the TCM school corresponding to the maximum value is determined as the TCM school diagnosis result of the medical feature data.

[0086] When module 4 is executed, it can accurately identify all standard terms related to traditional Chinese medicine (i.e., TCM standard terms) from medical feature data through a preset medical standard terminology glossary, and count the frequency of each TCM standard term in the medical feature data to obtain the number of times each TCM standard term appears.

[0087] The frequency of occurrence and contribution weight of each TCM standard term are input into a preset initial score calculation formula to calculate the initial score for each TCM school in the medical feature data.

[0088] The preset initial score calculation formula is as follows: ; in, The initial score for school of thought s in Traditional Chinese Medicine; This represents the number of occurrences of the standard TCM term k (the kth standard TCM term); The contribution weight of standard TCM terminology k to TCM schools of thought s; These are the standard TCM terms from the pre-set medical standard terminology glossary.

[0089] Specifically, when determining the final score of each TCM school by correcting the initial score based on a preset mutual exclusion logic matrix of schools of thought, module 4 executes the following: Based on the non-zero values ​​in the initial scores, the TCM schools involved in the medical feature data are determined, and the initial category information of the TCM schools in the medical feature data is obtained. Based on a preset mutually exclusive logic matrix of schools of thought, determine whether there are mutually exclusive keywords in the medical feature data that logically contradict the initial category information of Chinese medicine schools of thought. If so, then based on the preset mutual exclusion logic matrix of schools of thought, the schools of thought of traditional Chinese medicine that have logical contradictions with the mutual exclusion keywords of schools of thought are identified from the initial category information of schools of thought of traditional Chinese medicine. The corresponding initial scores are then corrected using the corresponding penalty factors to obtain the final scores of each school of thought of traditional Chinese medicine. If not, then there is no need to revise the initial score; the initial score will be determined as the final score for the corresponding school of traditional Chinese medicine.

[0090] It should be noted that the mutual exclusion logic matrix of schools of thought is a pre-constructed relation matrix, which defines the possible mutual exclusion relationships between different schools of Chinese medicine and the keywords that lead to these mutual exclusion relationships, as well as the penalty factor when a mutual exclusion relationship occurs. The penalty factor is used to correct the initial score when the corresponding mutual exclusion relationship occurs.

[0091] To improve the accuracy and reasonableness of the diagnostic results, module 4 needs to correct the initial scores during execution. After obtaining the initial scores for each TCM school, the initial category information of the TCM school for obtaining the medical feature data needs to be determined based on the non-zero scores among these initial scores. That is, the TCM school corresponding to the non-zero initial scores is determined as the initial category information of the TCM school.

[0092] Based on a pre-defined mutually exclusive logic matrix of TCM schools, the medical feature data is analyzed to determine whether there are mutually exclusive keywords that logically contradict the initial category information of the identified TCM schools. For example, if one school emphasizes "cold syndrome" while another emphasizes "heat syndrome," and the medical feature data contains strong keywords for both "cold" and "heat," then there may be a logical contradiction between the "heat syndrome" school and "cold," and between the "cold syndrome" school and "heat."

[0093] If the judgment result is "yes," meaning there are logically contradictory mutually exclusive keywords, then based on a pre-defined mutually exclusive logic matrix, it is necessary to identify the TCM schools that logically contradict the mutually exclusive keywords from the initial category information of TCM schools. The corresponding penalty factor is then used to correct the initial score; that is, the initial score is subtracted from the penalty factor to obtain the final score for each TCM school. This method can eliminate or weaken the influence of unreasonable schools, making the final score more accurately reflect the true school tendency of the medical feature data. The penalty factor can be adjusted according to the number of mutually exclusive keywords. For example, the more mutually exclusive keywords a TCM school involves, the larger the penalty factor; the fewer mutually exclusive keywords a TCM school involves, the smaller the penalty factor.

[0094] Conversely, if the judgment result is "no," meaning that no mutually exclusive keywords for a school of traditional Chinese medicine (TCM) appear in the medical feature data that logically contradict the initial category information, it indicates that the initial score is relatively reasonable and no additional correction is needed. In this case, the initial score of each TCM school will be directly determined as the final score for that corresponding TCM school.

[0095] In some optional embodiments, a preset final score calculation formula can be determined through a preset logic gating penalty mechanism to calculate the final score of each TCM school. Specifically, the preset final score calculation formula is as follows: ; in, The final score for school of thought in Traditional Chinese Medicine (TCM); The penalty factor can be obtained from the preset mutual exclusion logic matrix of different schools of thought; For indicator functions, Let be an indicator function for a school of thought in Traditional Chinese Medicine (TCM), and let be an indicator function for a school of thought in TCM that contains a mutually exclusive keyword that contradicts TCM school of thought s. The value is 1, indicating that there are no mutually exclusive keywords related to the TCM school of thought 's' that logically contradict each other. The value is 0. This logic gating penalty mechanism is used for semantic disambiguation, such as distinguishing between "Si Ni Tang" (Fu Yang school) and "Dang Gui Si Ni Tang" (Shang Han school).

[0096] When module 4 is executed, after obtaining the final scores of each TCM school, it extracts the maximum value among these final scores and determines the corresponding TCM school as the TCM school diagnosis result of the medical feature data, thus achieving accurate identification of the TCM school to which the medical feature data belongs.

[0097] In some optional embodiments, a neural network model with two layers can be established. One layer is an initial scoring layer, which includes a time similarity function, a medical standard terminology vocabulary, and an initial score calculation formula. Using the medical standard terminology vocabulary and the time similarity function, the initial scoring layer can identify traditional Chinese medicine (TCM) and Western medicine standard terms in the medical feature data and calculate the fit score for each TCM school of thought to determine the contribution weight of each TCM standard term within each TCM school. Thus, the initial score for each TCM school is calculated using the initial score calculation formula. The other layer is a final scoring layer, which includes a school-specific mutual exclusion logic matrix and a final score calculation formula. Using the school-specific mutual exclusion logic matrix, the final scoring layer can identify mutually exclusive keywords that logically contradict each TCM school, determine the corresponding penalty factors, and thus calculate the final score for each TCM school using the final score calculation formula. Finally, the neural network model extracts the maximum value from these final scores and identifies the corresponding TCM school as the TCM school diagnosis result of the medical feature data. This enables the neural network model to identify schools of thought in traditional Chinese medicine. By inputting medical feature data, it can accurately identify the school of thought to which the medical feature data belongs. As a result, the steps executed by the first calculation module 2, the second calculation module 3, and the determination module 4 are combined and modified to: inputting medical feature data into the preset neural network model and identifying the diagnosis result of the school of thought in traditional Chinese medicine based on the medical feature data.

[0098] Specifically, when evaluation module 5 calculates the TCM data evaluation value of medical feature data based on the diagnostic results of TCM schools of thought, combined with the preset TCM four diagnostic information integrity scoring criteria and the preset school scarcity coefficient matrix, it performs the following: Based on the preset scoring criteria for the completeness of TCM four diagnostic methods information, the existence of TCM four diagnostic methods information in medical feature data is evaluated, and the completeness score of TCM four diagnostic methods information in medical feature data is calculated. Based on the preset school scarcity coefficient matrix, the probability of the obtained TCM school diagnosis results appearing in the TCM medical knowledge database is determined. The completeness score of the four diagnostic methods of traditional Chinese medicine and the probability of the appearance of different schools of thought are input into a preset formula for calculating the value of traditional Chinese medicine data, and the evaluation value of the medical feature data in traditional Chinese medicine is calculated.

[0099] Specifically, when evaluation module 5 performs an existence assessment of the TCM four diagnostic methods information in the medical feature data according to the preset TCM four diagnostic methods information integrity scoring criteria, and calculates the TCM four diagnostic methods information integrity score of the medical feature data, it executes the following: Based on the preset scoring criteria for the completeness of TCM four diagnostic methods information, specific fields with preset TCM four diagnostic method information keywords are identified in the medical feature data. Based on the keywords of the four diagnostic methods of traditional Chinese medicine appearing in specific fields, the TCM four diagnostic methods information category recognition results of specific fields are determined; The results of TCM four diagnostic information category recognition are input into the preset TCM four diagnostic information integrity score calculation formula to calculate the TCM four diagnostic information integrity score of medical feature data.

[0100] It should be noted that the preset scoring criteria for the completeness of TCM four diagnostic methods information is a set of pre-set rules or standards used to measure the completeness of TCM four diagnostic methods (inspection, auscultation, inquiry, and palpation) information contained in a medical feature data.

[0101] During execution, evaluation module 5 uses natural language processing technology or keyword matching algorithms to parse the medical feature data provided by the target object, thereby identifying keywords related to the four diagnostic methods of Traditional Chinese Medicine (TCM) and obtaining specific fields with preset TCM diagnostic keywords. These TCM diagnostic keywords are a predefined set of terms related to the four diagnostic methods of TCM: observation, auscultation, inquiry, and palpation, such as "facial complexion," "tongue coating," "pulse," "inquiry," "auscultation," and "palpation."

[0102] After identifying specific fields containing keywords from the four diagnostic methods (inspection, auscultation, and olfaction), these keywords are further analyzed to determine which category of TCM diagnostic information the field belongs to. For example, if a specific field contains keywords such as "complexion," "tongue coating," or "eye expression," it may be identified as "inspection" information; if it contains keywords such as "pulse" or "abdominal palpation," it may be identified as "palpation" information; if it contains keywords such as "chief complaint" or "medical history," it may be identified as "inquiry" information; and if it contains keywords such as "voice" or "breathing," it may be identified as "auscultation" information. In this way, different types of diagnostic information can be accurately classified, providing a structured data foundation for subsequent integrity assessment.

[0103] The results of the TCM four diagnostic methods information category recognition are input into a preset TCM four diagnostic methods information integrity score calculation formula to calculate the TCM four diagnostic methods information integrity score of the medical feature data. The preset TCM four diagnostic methods information integrity score calculation formula is as follows: ; in, The completeness score of the four diagnostic methods in Traditional Chinese Medicine (TCM) is given; F represents the Fth category of the four diagnostic methods in TCM (Category F of the four diagnostic methods in TCM is any one of the four categories of observation, auscultation, inquiry, and palpation). The weights of information category F in Traditional Chinese Medicine's four diagnostic methods. ; This is an indicator function for the TCM four diagnostic information category recognition results. When the TCM four diagnostic information category recognition results identify a TCM four diagnostic information category F (i.e., any TCM four diagnostic information keyword in any specific field belongs to TCM four diagnostic information category F), the value is 1. When the TCM four diagnostic information category recognition results do not identify a TCM four diagnostic information category F (i.e., all TCM four diagnostic information keywords in all specific fields do not belong to TCM four diagnostic information category F), the value is 0.

[0104] When evaluation module 5 is executed, it pre-determines a school-of-science scarcity coefficient matrix from the TCM medical knowledge database, thereby determining the probability of a TCM school of thought appearing in the database. The school-of-science scarcity coefficient matrix is ​​a pre-defined table or dataset that records the frequency of different TCM schools of thought in the existing database or knowledge base (calculated by the proportion of the occurrences of a single TCM school of thought to the total occurrences of all TCM schools of thought), i.e., the probability of occurrence of a school of thought, which can also be referred to as relative scarcity. The lower the probability of occurrence of a school of thought, the scarcer and more valuable the corresponding TCM data.

[0105] The completeness score of the four diagnostic methods in Traditional Chinese Medicine (TCM) and the probability of occurrence of different schools of thought are input into a preset TCM data value calculation formula to calculate the TCM data evaluation value of the medical feature data. The preset TCM data value calculation formula is as follows: ; in, To evaluate the value of TCM data; This represents the probability of a particular school of thought appearing.

[0106] As can be seen from the above, this TCM data value assessment device acquires the medical feature data of the target object, extracts the temporal feature data from the medical feature data, and uses a preset time similarity function to calculate the time-frequency domain fit score of each TCM school in the medical feature data. Based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, combined with a preset TCM keyword weight matrix and fit score, the contribution weight of each TCM standard term in the medical feature data to each TCM school is calculated. Based on a preset school mutual exclusion logic matrix, combined with the contribution weight, the TCM school diagnosis result of the medical feature data is determined. Based on the TCM school diagnosis result, combined with the preset TCM four diagnostic information integrity scoring criterion and the preset school scarcity coefficient matrix, the medical feature is calculated. The evaluation value of TCM data is determined by using a pre-set TCM four diagnostic information integrity scoring criterion and a pre-set school scarcity coefficient matrix, combined with TCM school diagnosis results obtained from a weighted keyword matching method, a pre-set school mutual exclusion logic matrix, and the contribution weight of each TCM standard term in the medical feature data to each TCM school. This method calculates the TCM data evaluation value of the medical feature data, solving the problems of semantic ambiguity, school confusion, interference from mixed TCM and Western medicine terminology, and lack of objective evaluation standards in the value assessment of TCM data. It can adaptively handle the mixture of TCM and Western medicine terminology, has logical disambiguation capabilities, and can objectively quantify the data contribution value, thus improving the accuracy and reliability of TCM data value assessment.

[0107] Please refer to Figure 3 , Figure 3This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes a processor 301 and a memory 302. The processor 301 and the memory 302 are interconnected and communicate with each other via a communication bus 303 and / or other forms of connection mechanisms (not shown). The memory 302 stores a computer program executable by the processor 301. When the electronic device is running, the processor 301 executes the computer program to perform the traditional Chinese medicine data value assessment method in any optional implementation of the above embodiments, to achieve the following functions: acquiring medical feature data of the target object, extracting time-series feature data from the medical feature data, and using it for... The time-frequency domain fit score of each TCM school in the medical feature data is calculated by using a preset time similarity function. Based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, combined with the preset TCM keyword weight matrix and fit score, the contribution weight of each TCM standard term in the medical feature data to each TCM school is calculated. Based on the preset school mutual exclusion logic matrix and the contribution weight, the TCM school diagnosis result of the medical feature data is determined. Based on the TCM school diagnosis result, combined with the preset TCM four diagnostic information integrity scoring criterion and the preset school scarcity coefficient matrix, the TCM data evaluation value of the medical feature data is calculated.

[0108] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it executes the TCM data value assessment method in any optional implementation of the above embodiments to achieve the following functions: acquiring medical feature data of a target object; extracting time-series feature data from the medical feature data; calculating the time-frequency domain fit score of each TCM school in the medical feature data using a preset time similarity function; calculating the contribution weight of each TCM standard term in each TCM school based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, combined with a preset TCM keyword weight matrix and fit score; determining the TCM school diagnosis result of the medical feature data based on a preset school mutual exclusion logic matrix and contribution weight; and calculating the TCM data evaluation value of the medical feature data based on the TCM school diagnosis result, combined with a preset TCM four diagnostic information integrity scoring criterion and a preset school scarcity coefficient matrix. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0109] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0110] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0111] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0112] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0113] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for evaluating the value of traditional Chinese medicine (TCM) data, characterized in that, Including the following steps: Obtain medical characteristic data of the target object; Extract the temporal feature data from the medical feature data, and use it to calculate the time-frequency domain fit score of each TCM school in the medical feature data through a preset time similarity function. Based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, combined with the preset TCM keyword weight matrix and the fit score, the contribution weight of each TCM standard term in the medical feature data to each TCM school is calculated. Based on a preset mutual exclusion logic matrix of different schools of thought, and combined with the contribution weight, the TCM school of thought diagnosis result of the medical feature data is determined. Based on the diagnostic results of the aforementioned TCM school of thought, and combined with the preset TCM four diagnostic information integrity scoring criteria and the preset school scarcity coefficient matrix, the TCM data evaluation value of the medical feature data is calculated.

2. The method for evaluating the value of traditional Chinese medicine data according to claim 1, characterized in that, Extracting temporal feature data from the medical feature data, and using it to calculate the time-frequency domain fit score of each TCM school in the medical feature data through a preset time similarity function, including: Time-related data are extracted from the medical feature data to obtain time-series feature data; The time series feature data is converted into standardized time values ​​to obtain the converted time series feature data; The transformed time-series feature data is input into a preset time similarity function to calculate the fit score of each TCM school in the time frequency domain in the medical feature data.

3. The method for evaluating the value of traditional Chinese medicine data according to claim 1, characterized in that, Based on the sum of the occurrences of all Western medicine standard terms in the medical feature data, combined with a preset TCM keyword weight matrix and the fit score, the contribution weight of each TCM standard term in the medical feature data to each TCM school is calculated, including: Based on a pre-defined medical standard terminology glossary, the sum of the occurrence counts of all Western medicine standard terms in the medical feature data is identified; Determine whether the sum of the occurrence counts is greater than a preset attenuation weight threshold; if so, determine the corresponding attenuation coefficient based on the sum of the occurrence counts to adjust the initial contribution weight in the preset TCM keyword weight matrix, and obtain the intermediate contribution weight of each TCM standard term in the medical feature data in each TCM school; if not, determine the intermediate contribution weight of each TCM standard term in the medical feature data in each TCM school based on the initial contribution weight in the preset TCM keyword weight matrix. Based on the fit score, the intermediate contribution weight is adjusted to obtain the contribution weight of each TCM standard term in the medical feature data in each TCM school.

4. The method for evaluating the value of traditional Chinese medicine data according to claim 1, characterized in that, Based on a preset mutual exclusion logic matrix of medical schools, and combined with the contribution weights, the TCM school diagnosis results obtained from the medical feature data are determined, including: The frequency of occurrence of each TCM standard term in the medical feature data and the contribution weight are input into a preset initial score calculation formula to calculate the initial score of each TCM school in the medical feature data. Based on a preset mutually exclusive logic matrix of schools of thought, the initial scores are corrected to obtain the final scores of each of the traditional Chinese medicine schools of thought. The maximum value is extracted from the final score of each of the aforementioned TCM schools, and the TCM school corresponding to the maximum value is determined as the TCM school diagnosis result of the medical feature data.

5. The method for evaluating the value of traditional Chinese medicine data according to claim 4, characterized in that, Based on a preset mutually exclusive logic matrix for different schools of thought, the initial scores are corrected to obtain the final scores for each of the aforementioned schools of traditional Chinese medicine, including: Based on the non-zero values ​​in the initial scores, the TCM schools involved in the medical feature data are determined, and the initial category information of the TCM schools in the medical feature data is obtained. Based on a preset mutual exclusion logic matrix of schools of thought, it is determined whether there are mutually exclusive keywords in the medical feature data that logically contradict the initial category information of the TCM schools of thought. If so, then based on the preset mutual exclusion logic matrix of schools of thought, the schools of thought of traditional Chinese medicine that have logical contradictions with the mutual exclusion keywords of schools of thought are determined from the initial category information of the schools of thought of traditional Chinese medicine, so as to use the corresponding penalty factor to correct the corresponding initial score and obtain the final score of each school of thought of traditional Chinese medicine. If not, then there is no need to modify the initial score, and the initial score is determined as the final score of the corresponding TCM school.

6. The method for evaluating the value of traditional Chinese medicine data according to claim 1, characterized in that, Based on the diagnostic results of the aforementioned TCM school of thought, combined with a preset TCM four diagnostic methods information completeness scoring criterion and a preset school scarcity coefficient matrix, the TCM data evaluation value of the medical feature data is calculated, including: According to the preset scoring criteria for the integrity of TCM four diagnostic methods, the existence of TCM four diagnostic methods information in the medical feature data is evaluated, and the integrity score of TCM four diagnostic methods information in the medical feature data is calculated. Based on a preset school scarcity coefficient matrix, the probability of the diagnosis results of the TCM school appearing in the TCM medical knowledge database is determined. The completeness score of the four diagnostic methods of traditional Chinese medicine and the probability of occurrence of the school of thought are input into a preset formula for calculating the value of traditional Chinese medicine data, and the evaluation value of the medical feature data in traditional Chinese medicine is calculated.

7. The method for evaluating the value of traditional Chinese medicine data according to claim 6, characterized in that, Based on a preset scoring criterion for the completeness of TCM four diagnostic methods information, an existence assessment of the TCM four diagnostic methods information in the medical feature data is performed, and a completeness score for the TCM four diagnostic methods information in the medical feature data is calculated, including: Based on the preset scoring criteria for the completeness of TCM four diagnostic methods information, specific fields with preset TCM four diagnostic method information keywords are identified in the medical feature data. Based on the keywords of the four diagnostic methods of traditional Chinese medicine appearing in the specific field, the TCM four diagnostic methods information category recognition result of the specific field is determined; The TCM four diagnostic information category recognition results are input into the preset TCM four diagnostic information integrity score calculation formula to calculate the TCM four diagnostic information integrity score of the medical feature data.

8. A device for evaluating the value of traditional Chinese medicine data, used to evaluate the value of traditional Chinese medicine data, characterized in that, include: The acquisition module is used to acquire medical characteristic data of the target object; The first calculation module is used to extract the temporal feature data from the medical feature data, and to calculate the fit score of each TCM school in the medical feature data in the time frequency domain through a preset time similarity function. The second calculation module is used to calculate the contribution weight of each TCM standard term in each TCM school based on the sum of the occurrence times of all Western medicine standard terms in the medical feature data, combined with the preset TCM keyword weight matrix and the fit score. The determination module is used to determine the TCM school diagnosis result of the obtained medical feature data based on a preset school mutual exclusion logic matrix and the contribution weight. The evaluation module is used to calculate the TCM data evaluation value of the medical feature data based on the diagnostic results of the TCM school, combined with the preset TCM four diagnostic information integrity scoring criteria and the preset school scarcity coefficient matrix.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a computer program executable by the processor, and when the processor executes the computer program, it performs the steps in the method for evaluating the value of traditional Chinese medicine data as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it performs the steps in the method for evaluating the value of traditional Chinese medicine data as described in any one of claims 1-7.

Images