Intelligent Virtual Simulation Training System for Clinical Diagnosis in Traditional Chinese Medicine

Abstract

This invention discloses an intelligent virtual simulation training system for TCM clinical diagnosis, belonging to the field of simulation training technology. The system includes a simulation training module, a training labeling module, and a training optimization module. By setting the training labeling module, different diagnostic categories can be classified and labeled, allowing for a direct understanding of the training level for each category. This enables an adaptive increase in the simulation training frequency for lower-standard training categories, ensuring that each category of TCM clinical diagnosis receives appropriate training. The training optimization module can label the simulation training system based on simulation training records, and then judge the optimization status of the simulation training system for the day based on the labeling results. When the simulation training system is labeled as a system requiring optimization, the number of training optimization sessions can be appropriately increased.

Description

Technical Field

[0001] This invention relates to the field of simulation training technology, and more specifically, to an intelligent virtual simulation training system for clinical diagnosis in traditional Chinese medicine. Background Technology

[0002] Traditional Chinese medicine takes Yin-Yang and the Five Elements as its theoretical foundation, viewing the human body as a unified whole of Qi, form, and spirit. Through the four diagnostic methods of "inspection, auscultation, inquiry, and palpation," it explores the cause, nature, and location of the disease, analyzes the pathogenesis and changes in the five internal organs, meridians, joints, Qi, blood, and body fluids, judges the waxing and waning of pathogenic factors and the body's resistance, and thus arrives at the name of the disease.

[0003] Current virtual simulation training systems, when applied to TCM clinical diagnosis, often suffer from uneven distribution of training resources due to the large number of diagnostic categories. This results in some diagnostic categories not receiving adequate simulation training. Furthermore, simulation training systems require continuous optimization to ensure high diagnostic accuracy, but current systems lack the ability to monitor their own optimization progress. Summary of the Invention

[0004] In view of the shortcomings of existing technologies, the purpose of this invention is to provide an intelligent virtual simulation training system for clinical diagnosis in traditional Chinese medicine.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] Based on the intelligent virtual simulation training system for clinical diagnosis in traditional Chinese medicine, it includes a simulation training module, a training labeling module, and a training optimization module;

[0007] The simulation training module is used to collect simulation training records of TCM clinical diagnosis and send the simulation training records to the server for storage;

[0008] The training labeling module is used to classify and label different diagnostic categories, specifically as follows:

[0009] Obtain all simulation training records before the current system time, obtain the diagnostic category of the simulation training records, mark simulation training records with the same diagnostic category as training records of the same type, sort training records of the same type according to the order of training start time and training end time, mark adjacent training records of the same type that are sorted first as previous training records, mark adjacent training records of the same type that are sorted second as subsequent training records, and obtain the training interval Zw of the same type.

[0010] The simulation training duration is obtained by calculating the time difference between the training end time and the training start time of similar training records. Each simulation training duration of similar training records corresponds to a standard training duration. The simulation training duration is compared with the standard training duration. When the simulation training duration is less than the standard training duration, the simulation training duration is marked as the low standard training duration, and the low standard training value Et is obtained. When the simulation training duration is greater than or equal to the standard training duration, the simulation training duration is marked as the high standard training duration, and the high standard training value Db is obtained.

[0011] Using formula Obtain the training label value Fc, where d1 is the high-standard training value coefficient, d2 is the low-standard training value coefficient, and d3 is the training interval coefficient of the same type. Set the low-standard training label value to He and the high-standard training label value to Sm. When the training label value Fc ≥ the high-standard training label value Sm, the diagnosis category is labeled as the high-standard training category. When the low-standard training label value He ≤ the training label value Fc < the high-standard training label value Sm, the diagnosis category is labeled as the standard training category. When the training label value Fc < the low-standard training label value He, the diagnosis category is labeled as the low-standard training category.

[0012] The training optimization module is used to label the simulation training system, specifically as follows:

[0013] All simulation training records of the system for the day are obtained. The diagnostic results of the simulation training records are used as input data for training the evaluation model. The training labels of the output data are obtained and marked as diagnostic accuracy values. The diagnostic accuracy threshold is set to Hp. When the diagnostic accuracy value is greater than or equal to the diagnostic accuracy threshold Hp, the corresponding simulation training record is marked as a reasonable training record and the combined training value Bg is obtained. When the diagnostic accuracy value is less than the diagnostic accuracy threshold Hp, the corresponding simulation training record is marked as an abnormal training record and the abnormal training value Dr is obtained.

[0014] Obtain the training optimization value Tb, and set the training optimization threshold to Lk. When the training optimization value Tb ≥ the training optimization threshold Lk, mark the simulation training system as a system to be optimized. When the training optimization value Tb < the training optimization threshold Lk, do not perform any processing.

[0015] Furthermore, the simulation training record includes the training start time and training end time.

[0016] Furthermore, the training intervals Zw for similar training records are obtained through the following steps: Mark the training end time of the subsequent training record as Sn, the training start time of the subsequent training record as Mt, the training end time of the previous training record as Sd, and the training start time of the previous training record as Mq, using the formula... Obtain the training interval Kd of the same type, where a1 is the training end interval coefficient and a2 is the training start interval coefficient. Sum all the training intervals Kd of the same type and take the average value to obtain the average training interval Zw of the same type.

[0017] Furthermore, the low-standard training value Et is obtained through the following steps: The difference between the standard training duration and the low-standard training duration is calculated to obtain the low-standard training time difference Ei. The low-standard training time difference coefficient is set to Bp, where p = 1, 2, 3, ..., p; B1 < B2 < B3 < ... < Bp. Each low-standard training time difference coefficient corresponds to a range of low-standard training time differences, including (0, E1], (E1, E2], ..., (Ei-1, Ei]. When Ei ∈ (0, E1], the corresponding low-standard training time difference coefficient is B1. Using the formula... Obtain the low-scale time difference value Ck, where i is the number of times the simulation training duration is marked as the low-scale training duration. Obtain the total number of simulation training durations marked as low-scale training durations in the same type of training record and label it as Cw. Obtain the total number of similar training records and label it as Wz. Use the formula... Obtain the low-scale training value Et, where b1 is the low-scale time difference coefficient and b2 is the low-scale training ratio coefficient.

[0018] Furthermore, the high-standard training value Db is obtained through the following steps: The difference between the high-standard training duration and the standard training duration is calculated to obtain the high-standard training time difference Bj. The high-standard training time difference coefficient is set to Fx, where x = 1, 2, 3, ..., x; F1 < F2 < F3 < ... < Fx. Each high-standard training time difference coefficient corresponds to a range of high-standard training time differences, including (0, B1], (B1, B2], ..., (Bj-1, Bj]. When Bj ∈ (0, B1], the corresponding high-standard training time difference coefficient is F1. Using the formula... Obtain the high-standard time difference value Ln, where j is the number of times the simulation training duration is marked as the high-standard training duration. Obtain the total number of simulation training durations marked as high-standard training durations in the same type of training records, and mark it as Gm. Use the formula... Obtain the high-standard training value Db, where c1 is the high-standard time difference coefficient and c2 is the high-standard training ratio coefficient.

[0019] Furthermore, the training evaluation model is obtained through the following steps: the diagnostic results recorded in the simulation training are marked as training data, training labels are assigned to the training data, the training data is divided into training set and validation set according to a set ratio, a neural network model is constructed, the neural network model is iteratively trained through the training set and validation set, when the number of iterations exceeds the iteration threshold, the neural network model is determined to have completed training, and the trained neural network model is marked as the training evaluation model. The larger the value of the training label, the higher the accuracy of the diagnostic results.

[0020] Furthermore, the combined training value Bg is obtained through the following steps: Reasonable training records are sorted sequentially according to their training start times; the time difference between the next adjacent training start time and the previous training start time is calculated to obtain the reasonable training time difference; all reasonable training time differences are summed and averaged to obtain the average combined training time difference, which is denoted as Zk; the total number of reasonable training records is obtained and denoted as Mh; and the formula is used to... The combined training value Bg is obtained, where m1 is the average combined training time difference coefficient and m2 is the reasonable training quantity coefficient.

[0021] Furthermore, the abnormal training value Dr is obtained through the following steps: The abnormal training records are sorted sequentially according to their training start times; the time difference between the next adjacent training start time and the previous training start time is calculated to obtain the abnormal training time difference; all abnormal training time differences are summed and averaged to obtain the average abnormal training time difference, which is denoted as Jn; the total number of abnormal training records is obtained and denoted as Rv; and the formula is used to... Obtain the abnormal training value Dr, where n1 is the average abnormal training time difference coefficient and n2 is the abnormal training quantity coefficient.

[0022] Furthermore, the training optimization value Tb is obtained through the following steps: Tb = Bg × z1 - Dr × z2, where z1 is the coefficient of the combined training value and z2 is the coefficient of the heterogeneous training value.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. A training labeling module can be set up to classify and label different diagnostic categories, thereby allowing for an intuitive understanding of the training level of each diagnostic category. This enables an adaptive increase in the number of simulation training sessions for low-standard training categories, ensuring that each category of TCM clinical diagnosis can receive appropriate training.

[0025] 2. Set up a training optimization module, which can mark the simulation training system according to the simulation training record, and then judge the optimization status of the simulation training system on the day based on the marking results. When the simulation training system is marked as a system to be optimized, the number of training optimization times can be increased appropriately. Attached Figure Description

[0026] Figure 1 This is a block diagram illustrating the principle of the training labeling module of the present invention.

[0027] Figure 2 This is a block diagram illustrating the principle of the training optimization module of the present invention.

[0028] Figure 3 This is a block diagram illustrating the principle of the present invention. Detailed Implementation

[0029] Example 1

[0030] Reference Figure 1 The intelligent virtual simulation training system for clinical diagnosis in traditional Chinese medicine includes a simulation training module and a training labeling module.

[0031] The simulation training module is used to collect simulation training records of TCM clinical diagnosis and send these records to the server for storage. The simulation training records include the training start time and training end time. For example, simulation training record 1 started at 08:05:30 on May 13, 2021, and ended at 08:15:25 on May 13, 2021. Simulation training record 2 started at 08:22:15 on May 13, 2021, and ended at 08:31:02 on May 13, 2021.

[0032] The training labeling module is used to classify and label different diagnostic categories, specifically:

[0033] Step 1: Obtain all simulation training records up to the current system time, and determine the diagnostic category of each record (including but not limited to external diseases, internal diseases, and pediatric diseases). Mark simulation training records with the same diagnostic category as similar training records. Sort these similar training records according to the order of their training start and end times. Mark the preceding similar training record as the previous training record and the following similar training record as the subsequent training record. Obtain the average interval Zw for similar training records. The average interval Zw for similar training records is obtained through the following steps: Mark the end time of the subsequent training record as Sn, the start time as Mt, the end time as Sd, and the start time as Mq, using the formula... Obtain the training interval Kd for the same type, where a1 is the training end interval coefficient and a2 is the training start interval coefficient. The value of a1 is 0.99 and the value of a2 is 0.98. Sum all the training intervals Kd for the same type and take the average value to obtain the average training interval Zw for the same type.

[0034] Step 2: Calculate the time difference between the training end time and training start time of similar training records to obtain the simulated training duration. Set a standard training duration corresponding to the simulated training duration of each similar training record. Compare the simulated training duration with the standard training duration. When the simulated training duration < the standard training duration, mark the simulated training duration as the low-standard training duration and obtain the low-standard training value Et. The low-standard training value Et is obtained through the following steps: Calculate the difference between the standard training duration and the low-standard training duration to obtain the low-standard training time difference Ei. Set the low-standard training time difference coefficient to Bp, p = 1, 2, 3, ..., p; B1 < B2 < B3 < ... < Bp. Set each low-standard training time difference coefficient to correspond to a range of low-standard training time differences, including (0, E1], (E1, E2], ..., (Ei-1, Ei]. When Ei ∈ (0, E1], the corresponding low-standard training time difference coefficient is B1. Use the formula... Obtain the low-scale time difference value Ck, where i is the number of times the simulation training duration is marked as the low-scale training duration. Obtain the total number of simulation training durations marked as low-scale training durations in the same type of training record and label it as Cw. Obtain the total number of similar training records and label it as Wz. Use the formula... Obtain the low-standard training value Et, where b1 is the low-standard time difference coefficient and b2 is the low-standard training ratio coefficient, with b1 taking the value of 0.35 and b2 taking the value of 0.62. When the simulation training duration is greater than or equal to the standard training duration, the simulation training duration is marked as the high-standard training duration, and the high-standard training value Db is obtained. The high-standard training value Db is obtained through the following steps: calculate the difference between the high-standard training duration and the standard training duration to obtain the high-standard training time difference Bj, set the high-standard training time difference coefficient to Fx, x = 1, 2, 3, ..., x; F1 < F2 < F3 < ... < Fx, and set each high-standard training time difference coefficient to correspond to a range of high-standard training time differences, including (0, B1], (B1, B2], ..., (Bj-1, Bj], when Bj∈(0, B1], the corresponding high-standard training time difference coefficient is F1; use the formula Obtain the high-standard time difference value Ln, where j is the number of times the simulation training duration is marked as the high-standard training duration. Obtain the total number of simulation training durations marked as high-standard training durations in the same type of training records, and mark it as Gm. Use the formula... Obtain the high-standard training value Db, where c1 is the high-standard time difference coefficient and c2 is the high-standard training ratio coefficient, with c1 taking the value of 0.34 and c2 taking the value of 0.61.

[0035] Step 3: Using the formula Obtain the training label value Fc, where d1 is the high-standard training value coefficient, d2 is the low-standard training value coefficient, and d3 is the training interval coefficient of the same type. The value of d1 is 0.59, the value of d2 is 0.57, and the value of d3 is 0.74. Set the low-standard training label value to He and the high-standard training label value to Sm. When the training label value Fc ≥ the high-standard training label value Sm, the diagnosis category is labeled as the high-standard training category. When the low-standard training label value He ≤ the training label value Fc < the high-standard training label value Sm, the diagnosis category is labeled as the standard training category. When the training label value Fc < the low-standard training label value He, the diagnosis category is labeled as the low-standard training category. The training label is set with a low value of -2.4 and a high value of 3.6. When the training label value for exogenous diseases is 4.1, it is designated as a high-standard training category. When the training label value for endogenous diseases is 1.3, it is designated as a standard training category. When the training label value for endogenous diseases is -3.1, it is designated as a low-standard training category. This training label module allows for the classification and labeling of different diagnostic categories, providing a clear understanding of the training level for each category. This enables an adaptive increase in the simulation training frequency of the low-standard training category, ensuring that each category of clinical diagnosis receives appropriate training.

[0036] Example 2

[0037] Reference Figures 2-3 Based on Example 1, a training optimization module is also included. This module is used to label the simulation training system, specifically:

[0038] Step 1: Obtain all simulation training records for the day. Use the diagnostic results of the simulation training records as input data for training the evaluation model. Obtain the training labels for the output data. The training evaluation model is obtained through the following steps: Mark the diagnostic results of the simulation training records as training data, assign training labels to the training data, divide the training data into training and validation sets according to a set ratio, construct a neural network model, and iteratively train the neural network model using the training and validation sets. When the number of iterations exceeds the iteration threshold, the neural network model is considered to have completed training. Mark the trained neural network model as the training evaluation model. The larger the value of the training label, the higher the accuracy of the diagnostic results. The training labels of the output data are marked as diagnostic accuracy values. A diagnostic accuracy threshold of Hp is set. When the diagnostic accuracy value is greater than or equal to the threshold Hp, the corresponding simulation training record is marked as a reasonable training record, and the combined training value Bg is obtained. The combined training value Bg is obtained through the following steps: Reasonable training records are sorted sequentially according to their training start times. The time difference between the next adjacent training start time and the previous training start time is calculated to obtain the reasonable training time difference. All reasonable training time differences are summed and averaged to obtain the average combined training time difference, which is marked as Zk. The total number of reasonable training records is obtained and marked as Mh. The formula is then used to calculate the average combined training time difference. The combined training value Bg is obtained, where m1 is the average combined training time difference coefficient, and m2 is the reasonable training quantity coefficient. The value of m1 is 0.87, and the value of m2 is 0.67. When the diagnostic accuracy value is less than the diagnostic accuracy value threshold Hp, the corresponding simulation training record is marked as an abnormal training record, and the abnormal training value Dr is obtained. The abnormal training value Dr is obtained through the following steps: the abnormal training records are sorted in order of training start time; the time difference between the next adjacent training start time and the previous training start time is calculated to obtain the abnormal training time difference; all abnormal training time differences are summed and averaged to obtain the average abnormal training time difference, which is marked as Jn; the total number of abnormal training records is obtained and marked as Rv; and the formula is used to calculate the average abnormal training time difference. Obtain the abnormal training value Dr, where n1 is the average abnormal training time difference coefficient and n2 is the abnormal training quantity coefficient, with n1 taking the value of 0.86 and n2 taking the value of 0.66.

[0039] Step 2: Obtain the training optimization value Tb. The training optimization value Tb is obtained through the following steps: Tb = Bg × z1 - Dr × z2, where z1 is the coefficient of the combined training value and z2 is the coefficient of the dissimilar training value. The value of z1 is 0.39 and the value of z2 is 0.38. Set the training optimization threshold to Lk. When the training optimization value Tb ≥ the training optimization threshold Lk, the simulation training system is marked as a system to be optimized. When the training optimization value Tb < the training optimization threshold Lk, no action is taken. Set the training optimization threshold to 5.5. When the training optimization value is 5.7, the simulation training system is marked as a system to be optimized. Set up a training optimization module. The simulation training system can be marked according to the simulation training records. Then, the optimization status of the simulation training system on that day can be judged according to the marking results. When the simulation training system is marked as a system to be optimized, the number of training optimization times can be appropriately increased.

[0040] Working principle:

[0041] The training labeling module allows for the classification and labeling of different diagnostic categories, providing a clear understanding of the training level for each category. This enables the adaptation of training frequency for low-standard training categories to ensure that each category of TCM clinical diagnosis receives appropriate training. The training optimization module allows for the labeling of the simulation training system based on the simulation training records. The system's optimization status for the day can be assessed based on the labeling results. When a simulation training system is marked as needing optimization, the number of training optimization sessions can be appropriately increased.

[0042] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of this template.

[0043] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. An intelligent virtual simulation training system for clinical diagnosis in Traditional Chinese Medicine, characterized in that, It includes a simulation training module, a training labeling module, and a training optimization module; The simulation training module is used to collect simulation training records of TCM clinical diagnosis and send the simulation training records to the server for storage; The training labeling module is used to classify and label different diagnostic categories, specifically as follows: Obtain all simulation training records before the current system time, obtain the diagnostic category of the simulation training records, mark simulation training records with the same diagnostic category as training records of the same type, sort training records of the same type according to the order of training start time and training end time, mark adjacent training records of the same type that are sorted first as previous training records, mark adjacent training records of the same type that are sorted second as subsequent training records, and obtain the training interval Zw of the same type. The simulation training duration is obtained by calculating the time difference between the training end time and the training start time of similar training records. Each simulation training duration of similar training records corresponds to a standard training duration. The simulation training duration is compared with the standard training duration. When the simulation training duration is less than the standard training duration, the simulation training duration is marked as the low standard training duration, and the low standard training value Et is obtained. When the simulation training duration is greater than or equal to the standard training duration, the simulation training duration is marked as the high standard training duration, and the high standard training value Db is obtained. Using formula Obtain the training label value Fc, where d1 is the high-standard training value coefficient, d2 is the low-standard training value coefficient, and d3 is the training interval coefficient of the same type. Set the low-standard training label value to He and the high-standard training label value to Sm. When the training label value Fc ≥ the high-standard training label value Sm, the diagnosis category is labeled as the high-standard training category. When the low-standard training label value He ≤ the training label value Fc < the high-standard training label value Sm, the diagnosis category is labeled as the standard training category. When the training label value Fc < the low-standard training label value He, the diagnosis category is labeled as the low-standard training category. The training optimization module is used to label the simulation training system, specifically as follows: All simulation training records of the system for the day are obtained. The diagnostic results of the simulation training records are used as input data for training the evaluation model. The training labels of the output data are obtained and marked as diagnostic accuracy values. The diagnostic accuracy threshold is set to Hp. When the diagnostic accuracy value is greater than or equal to the diagnostic accuracy threshold Hp, the corresponding simulation training record is marked as a reasonable training record and the combined training value Bg is obtained. When the diagnostic accuracy value is less than the diagnostic accuracy threshold Hp, the corresponding simulation training record is marked as an abnormal training record and the abnormal training value Dr is obtained. Obtain the training optimization value Tb, and set the training optimization threshold to Lk. When the training optimization value Tb ≥ the training optimization threshold Lk, mark the simulation training system as a system to be optimized. When the training optimization value Tb < the training optimization threshold Lk, do not perform any processing.

2. The intelligent virtual simulation training system for clinical diagnosis based on traditional Chinese medicine as described in claim 1, characterized in that, The simulation training record includes the training start time and training end time.

3. The intelligent virtual simulation training system for clinical diagnosis based on traditional Chinese medicine as described in claim 2, characterized in that, The training interval Zw for similar training records is obtained through the following steps: Mark the training end time of the subsequent training record as Sn, the training start time of the subsequent training record as Mt, the training end time of the previous training record as Sd, and the training start time of the previous training record as Mq, using the formula... Obtain the training interval Kd of the same type, where a1 is the training end interval coefficient and a2 is the training start interval coefficient. Sum all the training intervals Kd of the same type and take the average value to obtain the average training interval Zw of the same type.

4. The intelligent virtual simulation training system for clinical diagnosis based on traditional Chinese medicine according to claim 3, characterized in that, The low-standard training value Et is obtained through the following steps: Calculate the difference between the standard training duration and the low-standard training duration to obtain the low-standard training time difference Ei; set the low-standard training time difference coefficient to Bp; and then use the formula... Obtain the low-scale time difference value Ck, where i is the number of times the simulation training duration is marked as the low-scale training duration. Obtain the total number of simulation training durations marked as low-scale training durations in the same type of training record and label it as Cw. Obtain the total number of similar training records and label it as Wz. Use the formula... Obtain the low-scale training value Et, where b1 is the low-scale time difference coefficient and b2 is the low-scale training ratio coefficient.

5. The intelligent virtual simulation training system for clinical diagnosis based on traditional Chinese medicine according to claim 4, characterized in that, The high-standard training value Db is obtained through the following steps: Calculate the difference between the high-standard training duration and the standard training duration to obtain the high-standard training time difference Bj; set the high-standard training time difference coefficient as Fx; and use the formula... Obtain the high-standard time difference value Ln, where j is the number of times the simulation training duration is marked as the high-standard training duration. Obtain the total number of simulation training durations marked as high-standard training durations in the same type of training records, and mark it as Gm. Use the formula... Obtain the high-standard training value Db, where c1 is the high-standard time difference coefficient and c2 is the high-standard training ratio coefficient.

6. The intelligent virtual simulation training system for clinical diagnosis based on traditional Chinese medicine according to claim 5, characterized in that, The training evaluation model is obtained through the following steps: the diagnostic results recorded in the simulation training are marked as training data, training labels are assigned to the training data, the training data is divided into training set and validation set according to a set ratio, a neural network model is constructed, the neural network model is iteratively trained using the training set and validation set, when the number of iterations exceeds the iteration threshold, the neural network model is determined to have completed training, and the trained neural network model is marked as the training evaluation model. The larger the value of the training label, the higher the accuracy of the diagnostic results.

7. The intelligent virtual simulation training system for clinical diagnosis based on traditional Chinese medicine according to claim 6, characterized in that, The combined training value Bg is obtained through the following steps: Reasonable training records are sorted sequentially according to their training start times. The time difference between the next adjacent training start time and the previous training start time is calculated to obtain the reasonable training time difference. All reasonable training time differences are summed and averaged to obtain the average combined training time difference, which is denoted as Zk. The total number of reasonable training records is obtained and denoted as Mh. The formula is then used to calculate the average combined training time difference. The combined training value Bg is obtained, where m1 is the average combined training time difference coefficient and m2 is the reasonable training quantity coefficient.

8. The intelligent virtual simulation training system for clinical diagnosis based on traditional Chinese medicine according to claim 7, characterized in that, The abnormal training value Dr is obtained through the following steps: The abnormal training records are sorted sequentially according to their training start times. The time difference between the next adjacent training start time and the previous training start time is calculated to obtain the abnormal training time difference. All abnormal training time differences are summed and averaged to obtain the average abnormal training time difference, which is denoted as Jn. The total number of abnormal training records is obtained and denoted as Rv. The value is then calculated using the formula... Obtain the abnormal training value Dr, where n1 is the average abnormal training time difference coefficient and n2 is the abnormal training quantity coefficient.

9. The intelligent virtual simulation training system for clinical diagnosis based on traditional Chinese medicine according to claim 8, characterized in that, The training optimization value Tb is obtained through the following steps: Tb = Bg × z1 - Dr × z2, where z1 is the coefficient of the combined training value and z2 is the coefficient of the dissimilar training value.

Images