Traditional Chinese medicine intelligent auxiliary diagnosis and treatment system for chronic prostatitis

Abstract

The invention discloses a chronic prostatitis traditional Chinese medicine intelligent auxiliary diagnosis and treatment system, and relates to the technical field of medical effect evaluation, and the system comprises a medical history and symptom collection module which is used for obtaining the medical history and clinical symptom data of a patient; the traditional Chinese medicine diagnosis model construction module is used for constructing a traditional Chinese medicine diagnosis model based on the medical history and clinical symptom data of the patient; the symptom assessment module is used for performing symptom assessment on the patient by adopting a traditional Chinese medicine diagnosis model and generating a personalized diagnosis and treatment scheme; the curative effect monitoring module is used for regularly performing curative effect monitoring and symptom quantitative analysis based on the evaluation result; the scheme adjusting module is used for adjusting the diagnosis and treatment scheme according to the curative effect monitoring result and optimizing the treatment effect; according to the traditional Chinese medicine intelligent auxiliary diagnosis and treatment system for chronic prostatitis, the problems that an existing curative effect evaluation technology is difficult to overcome the quantization problem caused by fluctuation of symptoms, and the accuracy of evaluation results and the scientificity of clinical decisions are limited are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical effect evaluation, and in particular to a traditional Chinese medicine intelligent auxiliary diagnosis and treatment system for chronic prostatitis. Background Art

[0002] In existing medical technologies, efficacy evaluation is a key means of judging the effectiveness of treatment methods and the progress of patient recovery. However, the symptoms of many diseases are volatile and uncertain, especially in the treatment of chronic diseases, neurological diseases or mental illnesses. Patients' symptoms often change significantly over time or due to environmental factors, making it difficult to quantify the efficacy. Traditional efficacy evaluation methods usually rely on symptom assessments at fixed time points or patient self-reports, but this method often fails to fully capture symptom fluctuations, which in turn affects the objectivity and accuracy of the evaluation.

[0003] At present, some commonly used evaluation methods include symptom rating scales and physiological index monitoring, but these methods are insufficient in dealing with symptom fluctuations. For example, symptom rating scales are usually limited by the time interval of the evaluation and may not be able to reflect the patient's symptom fluctuations in a timely manner. In addition, patients' self-reports are easily affected by subjective emotions, resulting in large fluctuations in the evaluation results and difficulty in objectively quantifying the efficacy. Although physiological index monitoring can provide certain objective data, it is often difficult to correspond one-to-one with complex symptom manifestations, and it is difficult to comprehensively evaluate the overall efficacy. Therefore, the existing efficacy evaluation technology is difficult to overcome the quantification difficulties caused by the fluctuation of symptoms, and lacks effective data collection and analysis methods for the characteristics of symptom fluctuations, which limits the accuracy of the evaluation results and the scientific nature of clinical decision-making. Summary of the invention

[0004] The purpose of the present invention is to provide a TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis to solve the problem that existing efficacy evaluation technology is difficult to overcome the quantification problem caused by the fluctuation of symptoms, lacks effective data collection and analysis methods for the fluctuation characteristics of symptoms, and limits the accuracy of evaluation results and the scientific nature of clinical decision-making.

[0005] To achieve the above object, the present invention provides the following technical solution: a TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis, the system comprising: Medical history and symptom collection module, used to obtain the patient's medical history and clinical symptom data; The TCM diagnosis model building module connected to the medical history and symptom collection module is used to build a TCM diagnosis model based on the patient's medical history and clinical symptom data, including simulating the main symptoms and their secondary manifestations, calculating the degree of correlation between symptoms, and analyzing their primary and secondary relationships. The specific formula is: F=ma, a=GM / r 2 ; Among them, F represents the degree of correlation between different symptoms, m represents the weight of the symptom, a represents the dynamic trend of the symptom correlation as the disease worsens, G represents the constant of symptom correlation, M represents the severity of the main symptom, and r represents the closeness value between the main symptom and the secondary symptom; Construct a symptom association network, identify high-density symptom clusters as core TCM syndromes, and convert them into diagnostic model inputs. The specific formula is: ; Among them, D represents the density of the symptom association network, E represents the number of associations between different symptoms, and N represents the total number of symptoms involved in the diagnostic model; A symptom assessment module connected to the TCM diagnosis model building module is used to use the TCM diagnosis model to assess the patient's symptoms and generate a personalized diagnosis and treatment plan; The efficacy monitoring module connected to the symptom assessment module is used to regularly monitor the efficacy and conduct quantitative analysis of symptoms based on the assessment results, including modeling the complexity of the patient's symptom changes and judging the stability of the efficacy improvement. The specific formula is: ; Among them, D f The fractal dimension representing the fluctuation of patient efficacy, N ( ) indicates that the scale is In the case of , the minimum number of segments that need to be covered in the efficacy monitoring data to cover symptom fluctuations, a segmented scale to represent symptom fluctuations; Evaluate the efficacy monitoring data, predict future efficacy trends, and warn of deterioration risks. The specific formula is: MA=(P1+P2+……P n ) / n; Among them, MA represents the moving average of the patient efficacy monitoring data, P1, P2, ..., P n represents the therapeutic efficacy monitoring data value of the patient in a continuous time period, and n represents the time window length used to calculate the moving average; The scheme adjustment module connected to the efficacy monitoring module is used to adjust the diagnosis and treatment scheme according to the efficacy monitoring results and optimize the treatment effect.

[0006] Preferably, the medical history and symptom collection module acquires the patient's medical history and clinical symptom data including: Perform spectral analysis on the speech data of patients describing their symptoms and extract frequency domain features to identify emotional states or levels of pain. The specific formula is: ; Wherein, X(k) represents the frequency domain signal value, x(q) represents the time domain signal value, k represents the frequency sequence number, q represents the sampling point index in the time series, B represents the total number of sampling points of the speech data, and j represents the imaginary unit; Calculate the hierarchy of the change information of different disease signals in the medical history and optimize the data classification. The specific formula is: R=(Z2-Z1) / (Z2+Z1); Among them, R represents the hierarchical difference of information in the medical history data, Z1 represents the disease signal strength of the previous layer, and Z2 represents the disease signal strength of the next layer.

[0007] Preferably, the symptom assessment module uses a TCM diagnosis model to assess the patient's symptoms and generates a personalized diagnosis and treatment plan including: Analyze the distribution of patient symptoms and evaluate the degree of orderliness of the overall health status. The specific formula is: ΔS=ΔQ / T; Among them, ΔS represents the change in the degree of order of the patient's overall health status, ΔQ represents the amount of external treatment input during the symptom improvement process, and T represents the patient's symptom distribution improvement time.

[0008] Preferably, the scheme adjustment module adjusts the diagnosis and treatment scheme according to the efficacy monitoring results to optimize the treatment effect, including: Evaluate the sensitivity of the treatment regimen to efficacy and side effects. The specific formula is: E=σ / η; Among them, E represents the sensitivity of the treatment parameters, σ represents the effect strength of the treatment regimen, and η represents the side effect strength of the treatment regimen.

[0009] Preferably, the efficacy monitoring module regularly performs efficacy monitoring and symptom quantitative analysis based on the evaluation results, and also includes obtaining the patient's latest clinical symptom data, comparing the latest clinical symptom data with the initial evaluation results, and calculating the symptom relief degree index based on the comparison results.

[0010] Preferably, the calculation of the symptom relief degree index based on the comparison result includes obtaining the initial score S1 and the latest score S2 of each symptom, calculating the symptom change H=S1-S2, and calculating the symptom relief rate L=H / S1×100% based on the symptom change.

[0011] Preferably, the medical history and symptom collection module also includes a denoising unit for removing background noise in the patient's voice data through a filter.

[0012] Preferably, the medical history and symptom collection module acquires the patient's medical history and clinical symptom data and further includes: extracting information from the medical history data by comparing current patient data with previous databases through hierarchical analysis.

[0013] Preferably, the medical history and symptom collection module acquires the patient's medical history and clinical symptom data and further includes: selecting the number of time series sampling points B and dynamically adjusting it according to the duration of the patient's voice data.

[0014] Preferably, the symptom assessment module uses a TCM diagnosis model to assess the patient's symptoms and generates a personalized diagnosis and treatment plan including: Select the combination with the lowest time and cost among multiple potential diagnosis and treatment options. The specific formula is: ; in, Indicates the current symptom status. Indicates the target health status, Indicates that the patient is in a symptomatic state arrive The total weight of the shortest path to the target state, represents the weight on the treatment path, Represents the set of edges in the patient symptom network.

[0015] It can be seen from the above technical solution that the present invention has the following beneficial effects: The TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis obtains the patient's medical history and clinical symptom data through the medical history and symptom collection module. The TCM diagnosis model construction module constructs a TCM diagnosis model based on the patient's medical history and clinical symptom data. The symptom evaluation module uses the TCM diagnosis model to evaluate the patient's symptoms and generate a personalized diagnosis and treatment plan. The efficacy monitoring module regularly monitors the efficacy and conducts quantitative analysis of symptoms based on the evaluation results. The plan adjustment module adjusts the diagnosis and treatment plan according to the efficacy monitoring results to optimize the treatment effect. It can not only capture the fluctuations of symptoms over time or environmental factors in real time, but also evaluate the stability and change trend of symptoms, avoid the limitations of evaluation at fixed time points, achieve a comprehensive and objective evaluation of the efficacy, make up for the shortcomings of traditional single evaluation methods, timely discover abnormal efficacy fluctuations or potential deterioration risks, support more scientific clinical decisions, and improve the pertinence and accuracy of treatment effects, thereby improving the patient's rehabilitation progress and quality of life. It solves the problem that the existing efficacy evaluation technology is difficult to overcome the quantification problem caused by the fluctuation of symptoms, lacks effective data collection and analysis methods for the characteristics of symptom fluctuations, and limits the accuracy of evaluation results and the scientific nature of clinical decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the connection of the system modules of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, the present invention provides a technical solution: a TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis, the system comprising: Medical history and symptom collection module, used to obtain the patient's medical history and clinical symptom data; The TCM diagnosis model building module connected to the medical history and symptom collection module is used to build a TCM diagnosis model based on the patient's medical history and clinical symptom data, including simulating the main symptoms and their secondary manifestations, calculating the degree of correlation between symptoms, and analyzing their primary and secondary relationships. The specific formula is: F=ma, a=GM / r 2 ; Among them, F represents the degree of correlation between different symptoms, m represents the weight of the symptom, a represents the dynamic trend of the symptom correlation as the disease worsens, G represents the constant of symptom correlation, M represents the severity of the main symptom, and r represents the closeness value between the main symptom and the secondary symptom; Construct a symptom association network, identify high-density symptom clusters as core TCM syndromes, and convert them into diagnostic model inputs. The specific formula is: ; Among them, D represents the density of the symptom association network, E represents the number of associations between different symptoms, and N represents the total number of symptoms involved in the diagnostic model; A symptom assessment module connected to the TCM diagnosis model building module is used to use the TCM diagnosis model to assess the patient's symptoms and generate a personalized diagnosis and treatment plan; The efficacy monitoring module connected to the symptom assessment module is used to regularly monitor the efficacy and conduct quantitative analysis of symptoms based on the assessment results, including modeling the complexity of the patient's symptom changes and judging the stability of the efficacy improvement. The specific formula is: ; Among them, D f The fractal dimension representing the fluctuation of patient efficacy, N ( ) indicates that the scale is In the case of , the minimum number of segments that need to be covered in the efficacy monitoring data to cover symptom fluctuations, a segmented scale to represent symptom fluctuations; Evaluate the efficacy monitoring data, predict future efficacy trends, and warn of deterioration risks. The specific formula is: MA=(P1+P2+……P n ) / n; Among them, MA represents the moving average of the patient efficacy monitoring data, P1, P2, ..., P n represents the therapeutic efficacy monitoring data value of the patient in a continuous time period, and n represents the time window length used to calculate the moving average; The scheme adjustment module connected to the efficacy monitoring module is used to adjust the diagnosis and treatment scheme according to the efficacy monitoring results and optimize the treatment effect.

[0019] The system integrates the patient's medical history and symptom data, uses the TCM diagnostic model construction technology, quantifies the degree of correlation between symptoms, and forms a symptom association network. By analyzing the main symptoms and secondary symptoms, the core symptoms are identified, realizing the integration of TCM theory and modern information technology. The system further uses complexity analysis and dynamic monitoring models to track the changing trends of patients' symptoms in real time, predict the efficacy and warn of potential risks, so as to dynamically adjust the diagnosis and treatment plan to improve the treatment effect and patient satisfaction. By calculating the density of the symptom association network and the weight of the main symptoms, personalized and accurate diagnosis is achieved. The efficacy monitoring module uses fractal dimension modeling and moving average analysis to grasp the fluctuations of patients' symptoms in real time and provide stability evaluation and early warning mechanisms. According to the efficacy monitoring results, the diagnosis and treatment plan is dynamically adjusted to effectively avoid treatment blind spots and misdiagnosis. The modular design realizes step-by-step processing, which is convenient for medical staff to quickly get started and operate.

[0020] The medical history and symptom collection module obtains the patient's medical history and clinical symptom data, including spectrum analysis of the patient's voice data describing the symptoms, and extracts frequency domain features to identify the emotional state or degree of pain. The specific formula is: ; Wherein, X(k) represents the frequency domain signal value, x(q) represents the time domain signal value, k represents the frequency sequence number, q represents the sampling point index in the time series, B represents the total number of sampling points of the speech data, and j represents the imaginary unit; Calculate the hierarchy of the change information of different disease signals in the medical history and optimize the data classification. The specific formula is: R = (Z2-Z1) / (Z2+Z1); Among them, R represents the hierarchical difference of information in the medical history data, Z1 represents the disease signal strength of the previous layer, and Z2 represents the disease signal strength of the next layer.

[0021] This implementation method converts the patient's speech data describing symptoms into frequency domain features through spectral analysis of speech signals, and extracts quantitative indicators of the patient's emotional state or degree of pain from them. At the same time, through hierarchical analysis, the change differences of different disease signals in the medical history data are calculated to achieve optimization of data classification. Spectral analysis is centered on Fourier transform, which converts time domain data into frequency domain signals to reveal potential characteristic signals; hierarchical calculation reveals the dynamic distribution of disease signals as they change with levels through intensity comparison. By extracting speech features, the patient's emotional state or degree of pain can be accurately identified, providing an emotional regulation reference for traditional Chinese medicine diagnosis and treatment. Through hierarchical calculation, the classification ability of medical history data is optimized, and the diagnosis and treatment system's ability to accurately interpret medical history change signals is improved. Multidimensional analysis of medical history and symptom data is achieved, effectively supporting the generation of personalized diagnosis and treatment plans.

[0022] The symptom assessment module uses the TCM diagnosis model to assess the patient's symptoms and generate a personalized diagnosis and treatment plan, including analyzing the patient's symptom distribution and assessing the degree of orderliness of the overall health status. The specific formula is: ΔS=ΔQ / T; Among them, ΔS represents the change in the degree of order of the patient's overall health status, ΔQ represents the amount of external treatment input during the symptom improvement process, and T represents the patient's symptom distribution improvement time.

[0023] This implementation method quantitatively evaluates the patient's health status through the analysis of symptom distribution, and uses the entropy change theory to calculate the degree of order of the patient's health status. During the treatment process, by inputting the treatment amount (ΔQ) and observing the time period (T) for the patient's symptom improvement, the contribution of symptom changes to the overall health status is dynamically evaluated, and a personalized diagnosis and treatment plan combined with traditional Chinese medicine theory is generated. The system comprehensively considers the dynamic change rules of symptoms to assist doctors in quickly formulating targeted treatment plans. Through the accurate evaluation of the patient's symptom distribution, a personalized treatment plan is generated to improve the pertinence and effectiveness of the treatment. The formula is used to quantify the effect of symptom improvement on the health status, providing an objective basis for subsequent treatment decisions. Track the changing trend of the patient's overall health status in real time and provide all-round health assessment support.

[0024] The scheme adjustment module adjusts the diagnosis and treatment scheme according to the results of efficacy monitoring. The optimization of treatment effect includes evaluating the sensitivity of the treatment scheme to efficacy and side effects. The specific formula is: E=σ / η; Among them, E represents the sensitivity of the treatment parameters, σ represents the effect strength of the treatment regimen, and η represents the side effect strength of the treatment regimen.

[0025] This implementation method calculates the sensitivity (E) of the treatment plan to the efficacy and side effects through the real-time data collected by the efficacy monitoring module. The effect intensity (σ) reflects the improvement effect of the treatment measures on the patient's symptoms, while the side effect intensity (η) measures the adverse reactions that may be caused by the treatment. Through the formula E=σ / η, the advantages and disadvantages of each treatment plan can be quantified, and the sensitivity comparison analysis of different plans can be performed, thereby providing a quantitative basis for optimizing personalized diagnosis and treatment plans. By calculating the sensitivity E, the balance of treatment effects and side effects is evaluated, and the effectiveness and safety of different treatment plans are quantified. Based on the results of the sensitivity analysis, the treatment parameters are dynamically adjusted, and the diagnosis and treatment plan with the best effect and the least side effects is selected, which significantly improves the treatment effect. Reduce the side effects caused by treatment, improve the comfort and compliance of patients in treatment, and enhance the safety of diagnosis and treatment.

[0026] The efficacy monitoring module regularly monitors efficacy and conducts quantitative symptom analysis based on the evaluation results, and also includes obtaining the patient's latest clinical symptom data, comparing the latest clinical symptom data with the initial evaluation results, and calculating the symptom relief index based on the comparison results.

[0027] This implementation method regularly obtains the latest clinical symptom data of the patient through the continuous operation of the efficacy monitoring module, and compares and analyzes it with the baseline data of the initial assessment. By comparing the difference between the initial symptom intensity and the latest symptom intensity, the symptom relief degree index (such as the percentage change or the absolute change value) is calculated to quantify the patient's treatment progress. The system will also combine historical data to draw a symptom change curve to provide medical personnel with an intuitive reference for the treatment effect and support the optimization and adjustment of subsequent treatment plans. Regularly monitor the patient's latest clinical symptom data to grasp the progress of treatment in real time; by calculating the relief degree index, provide an intuitive quantitative basis for symptom improvement, and assist doctors in accurately judging the efficacy; based on the data comparison and analysis results, support the dynamic adjustment of personalized diagnosis and treatment plans to further optimize the treatment effect; combine the initial symptom data and the latest data to provide a multi-dimensional assessment of the patient's health status and provide a basis for long-term treatment planning.

[0028] Based on the comparison results, the symptom relief index is calculated, including obtaining the initial score S1 and the latest score S2 of each symptom, calculating the symptom change H=S1-S2, and based on the symptom change, calculating the symptom relief rate L=H / S1×100%.

[0029] This implementation method uses a symptom scoring mechanism to collect the initial score (S1) and the latest score (S2), and calculates the score difference (H) to reflect the extent of symptom improvement, which is further standardized as a percentage value in the form of a remission rate (L), making it easy to compare and evaluate the improvement of different symptoms. The system can perform weighted average or priority sorting on the remission rates of multiple symptoms, providing a scientific basis for comprehensive efficacy evaluation, while supporting the dynamic optimization of personalized treatment plans. Through the formulaic remission rate calculation, the degree of symptom improvement is quantified as a percentage value, which is convenient for doctors to intuitively understand and compare; it supports independent analysis of the change amount and remission rate of multiple symptoms, and generates comprehensive remission evaluation results at the same time; according to the remission rate of different symptoms, adjust the treatment focus and resource allocation, optimize the treatment strategy, and improve the efficacy; through regular updates of the latest scores, dynamic tracking of patient symptom changes is achieved, providing data support for long-term health management.

[0030] The medical history and symptom collection module also includes a denoising unit for removing background noise from the patient's voice data through a filter. In this embodiment, the denoising unit is an important component of the medical history and symptom collection module, and is used to improve the collection quality of the patient's voice data. When the patient describes his condition in voice, there may be background noise, such as ambient sound or other interference signals. The denoising unit has a built-in filter that can identify and remove background noise in the voice data through frequency domain analysis and signal separation technology, thereby extracting clear voice information. The filter can be a bandpass filter or a low-pass filter.

[0031] The medical history and symptom collection module obtains the patient's medical history and clinical symptom data and also includes: extracting information from the medical history data by comparing the current patient data with the previous database through hierarchical analysis. In this embodiment, the medical history and symptom collection module uses hierarchical analysis to process the patient's medical history and symptom data. Specifically, the system performs a multi-dimensional comparative analysis on the data input by the current patient and the medical record information in the previous database. Hierarchical analysis divides the medical history data into multiple feature levels, such as the basic health information layer, the disease evolution layer, and the complication record layer, by constructing a disease-related hierarchical structure. The system first standardizes the input data to ensure that it is consistent with the data format in the database; then, through the feature extraction algorithm, it matches the current patient's medical history information and clinical symptom data; finally, combined with historical cases in the database, key information is extracted and a comprehensive analysis result is generated. This result can provide doctors with clear diagnosis and treatment recommendations and assist the traditional Chinese medicine diagnosis model in optimizing treatment plans.

[0032] The medical history and symptom collection module obtains the patient's medical history and clinical symptom data and also includes: the selection of the time series sampling point number B is dynamically adjusted according to the duration of the patient's voice data. In this embodiment, the medical history and symptom collection module dynamically adjusts the time series sampling point number B according to the duration of the patient's voice data. Specifically, the system first performs a duration detection on the input voice data to obtain the total duration of the voice signal; then, according to the preset dynamic adjustment algorithm, the optimal number of sampling points B is calculated to ensure that the collected time series data can completely cover the voice information, while avoiding the waste of resources caused by excessively high sampling rates. For example, for voice data of shorter duration, the system appropriately reduces the number of sampling points B to reduce data redundancy; for voice data of longer duration, the system automatically increases the number of sampling points B to improve the time resolution of the data. The adjusted number of sampling points ensures the integrity of the voice signal and the accurate capture of key features, providing high-quality input data for subsequent analysis.

[0033] The symptom assessment module uses the TCM diagnostic model to assess the patient's symptoms and generate a personalized treatment plan, including selecting the combination with the lowest time and cost among multiple potential treatment plans. The specific formula is: ; in, Indicates the current symptom status. Indicates the target health status, Indicates that the patient is in a symptomatic state arrive The total weight of the shortest path to the target state, represents the weight on the treatment path, Represents the set of edges in the patient symptom network.

[0034] In this embodiment, the symptom assessment module comprehensively evaluates the patient's symptom status based on the TCM diagnosis model, and optimizes the treatment path based on the symptom network diagram. The system first establishes a symptom network diagram, in which nodes represent different symptom states of the patient, edges represent possible transition paths between symptom states, and weights represent the path of the patient's symptom status. The treatment path is set based on factors such as time, cost, and effectiveness. To target health status By taking the shortest path possible, the system can identify the optimal combination of treatments in terms of time and cost.

[0035] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis, characterized in that: The system comprises: Medical history and symptom collection module, used to obtain the patient's medical history and clinical symptom data; The TCM diagnosis model building module connected to the medical history and symptom collection module is used to build a TCM diagnosis model based on the patient's medical history and clinical symptom data, including simulating the main symptoms and their secondary manifestations, calculating the degree of correlation between symptoms, and analyzing their primary and secondary relationships. The specific formula is: F=ma, a=GM / r 2 ; Among them, F represents the degree of correlation between different symptoms, m represents the weight of the symptom, a represents the dynamic trend of the symptom correlation as the disease worsens, G represents the constant of symptom correlation, M represents the severity of the main symptom, and r represents the closeness value between the main symptom and the secondary symptom; Construct a symptom association network, identify high-density symptom clusters as core TCM syndromes, and convert them into diagnostic model inputs. The specific formula is: ; Among them, D represents the density of the symptom association network, E represents the number of associations between different symptoms, and N represents the total number of symptoms involved in the diagnostic model; A symptom assessment module connected to the TCM diagnosis model building module is used to use the TCM diagnosis model to assess the patient's symptoms and generate a personalized diagnosis and treatment plan; The efficacy monitoring module connected to the symptom assessment module is used to regularly monitor the efficacy and conduct quantitative analysis of symptoms based on the assessment results, including modeling the complexity of the patient's symptom changes and judging the stability of the efficacy improvement. The specific formula is: ; Among them, D f The fractal dimension representing the fluctuation of patient efficacy, N ( ) indicates that the scale is In the case of , the minimum number of segments that need to be covered in the efficacy monitoring data to cover symptom fluctuations, a segmented scale to represent symptom fluctuations; Evaluate the efficacy monitoring data, predict future efficacy trends, and warn of deterioration risks. The specific formula is: MA=(P1+P2+……P n ) / n; Among them, MA represents the moving average of the patient efficacy monitoring data, P1, P2, ..., P n represents the therapeutic efficacy monitoring data value of the patient in a continuous time period, and n represents the time window length used to calculate the moving average; The scheme adjustment module connected to the efficacy monitoring module is used to adjust the diagnosis and treatment scheme according to the efficacy monitoring results and optimize the treatment effect.

2. According to claim 1, a TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis is characterized by: The medical history and symptom collection module obtains the patient's medical history and clinical symptom data including: Perform spectral analysis on the speech data of patients describing their symptoms and extract frequency domain features to identify emotional states or levels of pain. The specific formula is: ; Wherein, X(k) represents the frequency domain signal value, x(q) represents the time domain signal value, k represents the frequency sequence number, q represents the sampling point index in the time series, B represents the total number of sampling points of the speech data, and j represents the imaginary unit; Calculate the hierarchy of the change information of different disease signals in the medical history and optimize the data classification. The specific formula is: R=(Z2-Z1) / (Z2+Z1); Among them, R represents the hierarchical difference of information in the medical history data, Z1 represents the disease signal strength of the previous layer, and Z2 represents the disease signal strength of the next layer.

3. According to claim 1, a TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis is characterized by: The symptom assessment module uses the TCM diagnosis model to assess the patient's symptoms and generate a personalized diagnosis and treatment plan including: Analyze the distribution of patient symptoms and evaluate the degree of orderliness of the overall health status. The specific formula is: ΔS=ΔQ / T; Among them, ΔS represents the change in the degree of order of the patient's overall health status, ΔQ represents the amount of external treatment input during the symptom improvement process, and T represents the patient's symptom distribution improvement time.

4. According to claim 1, a TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis is characterized by: The scheme adjustment module adjusts the diagnosis and treatment scheme according to the efficacy monitoring results to optimize the treatment effect, including: Evaluate the sensitivity of the treatment regimen to efficacy and side effects. The specific formula is: E=σ / η; Among them, E represents the sensitivity of the treatment parameters, σ represents the effect strength of the treatment regimen, and η represents the side effect strength of the treatment regimen.

5. According to claim 1, a TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis is characterized by: The efficacy monitoring module regularly performs efficacy monitoring and symptom quantitative analysis based on the evaluation results, and also includes obtaining the patient's latest clinical symptom data, comparing the latest clinical symptom data with the initial evaluation results, and calculating the symptom relief degree index based on the comparison results.

6. The TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis according to claim 5 is characterized by: The calculation of the symptom relief index based on the comparison result includes obtaining the initial score S1 and the latest score S2 of each symptom, calculating the symptom change H=S1-S2, and calculating the symptom relief rate L=H / S1×100% based on the symptom change.

7. The TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis according to claim 2 is characterized by: The medical history and symptom collection module also includes a denoising unit for removing background noise in the patient's speech data through a filter.

8. The TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis according to claim 2 is characterized by: The medical history and symptom collection module acquires the patient's medical history and clinical symptom data and further includes: extracting information from the medical history data by comparing the current patient data with the previous database through hierarchical analysis.

9. The TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis according to claim 2 is characterized by: The medical history and symptom collection module acquires the patient's medical history and clinical symptom data and further includes: selecting the number of time series sampling points B and dynamically adjusting it according to the duration of the patient's voice data.

10. The TCM intelligent auxiliary diagnosis and treatment system for chronic prostatitis according to claim 1 is characterized by: The symptom assessment module uses the TCM diagnosis model to assess the patient's symptoms and generate a personalized diagnosis and treatment plan including: Select the combination with the lowest time and cost among multiple potential diagnosis and treatment options. The specific formula is: ; in, Indicates the current symptom status. Indicates the target health status, Indicates that the patient is in a symptomatic state arrive The total weight of the shortest path to the target state, represents the weight on the treatment path, Represents the set of edges in the patient symptom network.

Images