Palm temperature monitor for traditional Chinese medicine diagnosis

Abstract

The invention provides a palm temperature monitor for traditional Chinese medicine diagnosis. The palm temperature monitor comprises an infrared sensor array for collecting palm discrete temperature data; the temperature field reconstruction module generates continuous temperature field distribution; the traditional Chinese medicine partitioning module divides viscera associated regions according to the meridian atlas; the dynamic coupling analysis module calculates thermodynamic coupling parameters among the regions; the abnormity diagnosis module generates grading pathological indexes according to the coupling parameters; the environment compensation module corrects discrete temperature data; the symptom type mapping module matches the pathological indexes with a traditional Chinese medicine symptom type database; and the output module integrates the temperature field distribution and the syndrome type matching result to generate a diagnosis report. The internal organ function state can be accurately reflected, an objective and quantitative basis is provided for traditional Chinese medicine diagnosis, and the diagnosis efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traditional Chinese medicine diagnosis, and more specifically, to a palm temperature monitoring instrument for traditional Chinese medicine diagnosis. Background Art

[0002] In the field of TCM diagnosis, traditional diagnostic methods mainly rely on the subjective experience of physicians, such as observation, smell, questioning, and palpation, lacking objective and quantitative detection indicators and equipment support. In recent years, with the development of modern science and technology, some TCM diagnostic equipment based on biomedical engineering technology has begun to appear, such as equipment that assists diagnosis by measuring the temperature distribution on the human body surface. These devices usually use infrared thermal imaging technology to obtain local or overall temperature information of the human body, trying to reflect the physiological or pathological state of the human body through temperature changes. However, the application of existing temperature monitoring equipment in TCM diagnosis still has limitations. On the one hand, traditional equipment mostly uses single-point or local temperature measurement, which is difficult to fully reflect the subtle changes in the palm temperature field; on the other hand, it lacks partition analysis and dynamic coupling calculation combined with TCM meridian theory, and cannot accurately locate the functional state of the internal organs. In addition, the existing equipment does not compensate for environmental factors sufficiently, which easily leads to measurement errors and affects the accuracy and reliability of the diagnostic results.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: first, the existing equipment is unable to organically combine the palm temperature data with the theory of TCM meridians, making it difficult to achieve standardization and quantification of TCM diagnosis; second, the existing equipment lacks analysis of the dynamic characteristics of the temperature field and is unable to reflect the interaction relationship between the internal organs; finally, the existing equipment does not adequately compensate for environmental factors, resulting in the measurement results being greatly affected by the environment, making it difficult to meet the accuracy requirements of TCM diagnosis. Summary of the invention

[0004] The present invention provides a palm temperature monitoring instrument for traditional Chinese medicine diagnosis, comprising: (1) an infrared sensor array module configured to collect discrete temperature data of a palm surface; (2) a temperature field reconstruction module, receiving the discrete temperature data and generating a continuous temperature field distribution; (3) a TCM partitioning module, which divides the continuous temperature field distribution into viscera-related areas based on a preset meridian map; (4) a dynamic coupling analysis module, receiving the continuous temperature field distribution and partition results, and calculating the thermodynamic coupling parameters between regions; (5) an abnormality diagnosis module, generating a graded pathological index according to the thermodynamic coupling parameter; (6) an environmental compensation module, which corrects the discrete temperature data according to real-time environmental parameters; (7) a syndrome mapping module, which matches the pathological indicators with the TCM syndrome database to obtain a syndrome matching result; (8) An output module, integrating the continuous temperature field distribution and the syndrome matching result to generate a diagnosis report.

[0005] Furthermore, the temperature field reconstruction module includes: (2.1) A data interpolation unit receives the discrete temperature data ,implement: ①Construct interpolation function:

[0006] in, is the weight coefficient of the i-th sensor, is a cubic radial basis function and , is the Euclidean distance between the point to be inserted and the i-th sensor; is the linear compensation term coefficient; ② Solve the coefficients through the constraint equations: } (2.2) The boundary compensation unit receives the interpolated temperature field and executes: ① Extract the temperature gradient modulus to meet The boundary point set of is the spatial temperature gradient; ②Use cubic spline interpolation method to fit the boundary curve ,in is the boundary arc length parameter; ③Calculate curvature , and correct the temperature value:

[0007] (2.3) The noise suppression unit performs the following operations on the compensated temperature field: ① Calculate the difference of temperature field at adjacent moments ,in is the current temperature value, is the temperature value at the previous moment; ②Set the number of variational mode decomposition levels ,in is the floor function.

[0008] Further, the noise suppression unit performs: (3.1) The temperature field is decomposed into IMF ,in ; (3.2) Eliminate the highest frequency component ; (3.3) Reconstruct the noise-reduced temperature field:

[0009] The weight factor Used to suppress high frequency noise.

[0010] Furthermore, the dynamic coupling analysis module performs: (4.1) Space-time tensor construction: Based on the continuous temperature field distribution and time series data, the space-time tensor is constructed:

[0011] in is the time derivative, is the spatial gradient; (4.2) Calculation of inter-regional coupling parameters: Based on the space-time tensor and TCM partition results, the coupling coefficients of adjacent regions are calculated:

[0012] in, is the geometric range of adjacent regions m and n, is the temperature difference between regions; is the shortest distance from the region boundary to the measurement point, is the area of ​​the region; (4.3) Solution of dynamic equations: Based on the space-time tensor and coupling coefficient , solve the dynamic evolution equation:

[0013] in , is the initial temperature field.

[0014] Furthermore, the abnormality diagnosis module performs: (5.1) Obtain the maximum temperature gradient of each region from the dynamic coupling analysis module:

[0015] (5.2) Calculate the temperature difference threshold between adjacent areas:

[0016] in is the current average palm temperature; (5.3) When there exists a region satisfying The temperature difference between adjacent areas When the error occurs, a third-level abnormality indicator is generated.

[0017] Furthermore, the three-level abnormal indicators include: (6.1) Level 1 anomaly: A single area continues to meet Up to 120 seconds; (6.2) Secondary anomaly: temperature difference between two adjacent areas Lasts 60 seconds. (6.3) Level 3 anomaly: Both level 1 and level 2 anomaly conditions are met.

[0018] Furthermore, the certificate type mapping module performs: (7.1) Construct feature vector:

[0019] (7.2) Calculate the syndrome matching degree:

[0020] in is the historical statistical parameter of the kth syndrome type; (7.3) When When the pulse wave data is called, the correction matching degree is calculated .

[0021] Furthermore, the coefficient Replace with:

[0022] Furthermore, when When executing: (9.1) Calculate the temperature difference between three adjacent frames:

[0023] in is the temperature field of the first two frames; (9.2) If , it is judged as instantaneous interference and the original temperature field is restored.

[0024] Furthermore, the environmental compensation module performs: (10.1) Real-time collection of ambient temperature and humidity ; (10.2) Calculate the temperature compensation:

[0025] (10.3) When When , correct the sensor data:

[0026] in is the original temperature value, To compensate for the duration.

[0027] The above-mentioned embodiments according to the present invention have at least the following beneficial effects: the palm temperature monitor for TCM diagnosis of the present invention can realize the automated processing from discrete palm temperature data collection to TCM syndrome diagnosis. Through the infrared sensor array module and the temperature field reconstruction module, the continuous temperature field distribution on the palm surface can be accurately obtained, and the temperature field can be partitioned and analyzed based on the TCM meridian theory, thereby providing an objective basis for the evaluation of the functional status of the internal organs. The dynamic coupling analysis module can calculate the thermodynamic coupling parameters between regions, further reflect the interaction relationship between the internal organs, and provide more comprehensive pathological information for TCM diagnosis. The abnormal diagnosis module can generate graded pathological indicators based on the coupling parameters, which helps to quickly identify potential health problems.

[0028] In addition, the environmental compensation module can correct discrete temperature data in real time, effectively reducing the impact of environmental factors on measurement results and improving the accuracy and reliability of diagnosis. The syndrome mapping module matches pathological indicators with the TCM syndrome database, and can provide patients with personalized TCM syndrome diagnosis results. Overall, the monitor can provide an objective, quantitative and efficient technical means for TCM diagnosis, promoting the modernization and standardization of TCM diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which: Figure 1 A schematic diagram of the structure of a palm temperature monitor for traditional Chinese medicine diagnosis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0031] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0032] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0033] Reference below Figure 1 , Figure 1 This is a schematic diagram of the structure of a palm temperature monitor for TCM diagnosis provided by an embodiment of the present invention. Figure 1 As shown, a palm temperature monitoring instrument for traditional Chinese medicine diagnosis comprises: (1) an infrared sensor array module configured to collect discrete temperature data of a palm surface; (2) a temperature field reconstruction module, receiving the discrete temperature data and generating a continuous temperature field distribution; (3) a TCM partitioning module, which divides the continuous temperature field distribution into viscera-related areas based on a preset meridian map; (4) a dynamic coupling analysis module, receiving the continuous temperature field distribution and partition results, and calculating the thermodynamic coupling parameters between regions; (5) an abnormality diagnosis module, generating a graded pathological index according to the thermodynamic coupling parameter; (6) an environmental compensation module, which corrects the discrete temperature data according to real-time environmental parameters; (7) a syndrome mapping module, which matches the pathological indicators with the TCM syndrome database to obtain a syndrome matching result; (8) An output module, integrating the continuous temperature field distribution and the syndrome matching result to generate a diagnosis report.

[0034] It should be noted that the core of the palm temperature monitor for TCM diagnosis is to realize the collection and analysis of palm temperature through the collaborative work of a series of modules, and finally generate a diagnostic report. Among them, the infrared sensor array module is used to collect discrete temperature data on the palm surface. The discrete temperature data here refers to the temperature values ​​measured by multiple sensors at different positions on the palm. The function of the temperature field reconstruction module is to convert these discrete temperature data into continuous temperature field distribution, so as to more intuitively reflect the temperature changes on the palm surface. The TCM partition module divides the continuous temperature field into regions related to the internal organs based on the preset meridian map. The meridian map here refers to the human meridian distribution map drawn according to TCM theory, which is used to guide the partition. The dynamic coupling analysis module is used to calculate the thermodynamic coupling parameters between the regions, which can reflect the temperature correlation between the regions. The abnormal diagnosis module generates graded pathological indicators based on the coupling parameters to evaluate whether the palm temperature distribution is normal. The environmental compensation module takes into account the influence of environmental factors on the measurement results and improves the measurement accuracy by correcting the discrete temperature data. The syndrome mapping module matches the pathological indicators with the TCM syndrome database to obtain the syndrome matching results. The TCM syndrome database here is a database containing a variety of TCM syndromes and their corresponding pathological characteristics. Finally, the output module integrates the continuous temperature field distribution with the syndrome matching results to generate a diagnosis report to provide a reference for TCM diagnosis.

[0035] Specifically, the infrared sensor array module is composed of multiple high-precision infrared sensors, which are evenly distributed on the palm contact surface and are used to collect temperature data at different positions on the palm surface in real time. The temperature field reconstruction module realizes the conversion of discrete temperature data to continuous temperature field by constructing an interpolation function. The construction of the interpolation function involves the setting of parameters such as weight coefficient and cubic radial basis function. Among them, the weight coefficient is used to adjust the importance of each sensor data in the interpolation process. The cubic radial basis function is a mathematical function used to smoothly connect each discrete data point. The function of the boundary compensation unit is to deal with the boundary effect of the temperature field. By extracting the boundary point set and fitting the boundary curve, the temperature value is further corrected. The noise suppression unit identifies noise by calculating the difference of the temperature field at adjacent moments, and uses the variational mode decomposition technology to reduce the noise of the temperature field. The construction of the space-time tensor in the dynamic coupling analysis module is based on the continuous temperature field distribution and time series data, and reflects the dynamic changes of the temperature field by calculating the time derivative and spatial gradient. The calculation of the inter-regional coupling parameter takes into account the geometric range, temperature difference and regional area of ​​adjacent regions, which is used to quantify the thermodynamic correlation between regions. The abnormal diagnosis module calculates the maximum temperature gradient of each area based on the output of the dynamic coupling analysis module, and combines the temperature difference threshold of adjacent areas to determine whether there is an abnormality. The syndrome mapping module matches the pathological indicators with the syndromes in the TCM syndrome database by constructing feature vectors and calculating the syndrome matching degree, thereby obtaining the closest syndrome result.

[0036] Preferably, the interpolation function in the temperature field reconstruction module can be optimized using a variety of mathematical methods, such as adjusting the distribution method of weight coefficients to improve the interpolation accuracy. In the boundary compensation unit, a more complex curve fitting algorithm can be introduced to improve the accuracy of boundary processing. In the noise suppression unit, the number of layers of variational mode decomposition can be adjusted according to the actual application scenario to better adapt to temperature field data with different noise levels. In the dynamic coupling analysis module, the construction of the space-time tensor can consider introducing more space-time dimension information to more comprehensively reflect the dynamic characteristics of the temperature field. In the abnormal diagnosis module, the calculation of the temperature difference threshold can be personalized according to the physiological characteristics of different populations to improve the accuracy of diagnosis.

[0037] In some embodiments, the temperature field reconstruction module includes: (2.1) A data interpolation unit receives the discrete temperature data ,implement: ①Construct interpolation function:

[0038] in, is the weight coefficient of the i-th sensor, is a cubic radial basis function and , is the Euclidean distance between the point to be inserted and the i-th sensor; is the linear compensation term coefficient; ② Solve the coefficients through the constraint equations: } (2.2) The boundary compensation unit receives the interpolated temperature field and executes: ① Extract the temperature gradient modulus to meet The boundary point set of is the spatial temperature gradient; ②Use cubic spline interpolation method to fit the boundary curve ,in is the boundary arc length parameter; ③Calculate curvature , and correct the temperature value:

[0039] (2.3) The noise suppression unit performs the following operations on the compensated temperature field: ① Calculate the difference of temperature field at adjacent moments ,in is the current temperature value, is the temperature value at the previous moment; ②Set the number of variational mode decomposition levels ,in is the floor function.

[0040] It should be noted that the temperature field reconstruction module is one of the core components of the monitor. Its main function is to generate a continuous temperature field distribution by interpolating and compensating discrete temperature data. The module includes a data interpolation unit, a boundary compensation unit and a noise suppression unit. The data interpolation unit connects discrete temperature data points by constructing an interpolation function to form a continuous temperature field. Among them, the interpolation function combines the weight coefficient, the cubic radial basis function and the linear compensation term coefficient to smoothly transition the temperature data. The boundary compensation unit processes the boundary area of ​​the temperature field, extracts the boundary point set and fits the boundary curve, and corrects the temperature value at the boundary to reduce the error caused by the boundary effect. The noise suppression unit analyzes the difference in temperature fields at adjacent moments, identifies and suppresses noise, thereby improving the quality of temperature field data. The synergy of these units ensures the accuracy and reliability of temperature field reconstruction.

[0041] Specifically, the interpolation function in the data interpolation unit is constructed by mathematical methods, and its core is the cubic radial basis function, which can assign weights according to the distance of the sensor measurement point to generate a smooth temperature distribution. The weight coefficient is used to adjust the contribution of each sensor data in the interpolation process, and the linear compensation term coefficient is used to correct the linear trend of the overall temperature field. The boundary compensation unit identifies the boundary point by calculating the temperature gradient modulus. When the gradient modulus exceeds the set threshold (such as 1.2), the point is considered to be in the boundary area. The boundary curve is fitted using cubic spline interpolation, which is a commonly used curve fitting method that can generate a smooth boundary curve based on the distribution of boundary points. The correction of the boundary temperature value is completed by calculating the curvature and combining it with the correction formula. The curvature reflects the degree of curvature of the boundary shape, and the correction formula adjusts the temperature value according to the curvature to reduce the impact of the boundary effect. The noise suppression unit identifies noise by calculating the difference between the temperature fields at adjacent moments. The greater the difference, the higher the possibility of noise. The setting of the number of variational mode decomposition layers is adjusted according to the dynamic change frequency of the temperature field. By decomposing the temperature field into multiple intrinsic mode functions, high-frequency noise components are eliminated, thereby achieving noise reduction.

[0042] Preferably, the interpolation function in the data interpolation unit can be further optimized, for example, by adjusting the distribution method of the weight coefficients to make it more consistent with the actual characteristics of the palm temperature distribution. In the boundary compensation unit, a more complex curve fitting algorithm, such as high-order polynomial fitting or Bezier curve fitting, can be introduced to improve the accuracy and adaptability of boundary processing. In the noise suppression unit, the number of layers of variational mode decomposition can be dynamically adjusted according to the actual application scenario, such as increasing the number of decomposition layers in an environment with more high-frequency noise to better suppress noise. In addition, adaptive filtering technology can also be introduced to dynamically adjust the filtering parameters according to the real-time changes of the temperature field to further improve the noise reduction effect.

[0043] In some embodiments, the noise suppression unit performs: (3.1) The temperature field is decomposed into IMF ,in ; (3.2) Eliminate the highest frequency component ; (3.3) Reconstruct the noise-reduced temperature field:

[0044] The weight factor Used to suppress high frequency noise.

[0045] It should be noted that the noise suppression unit is an important component of the temperature field reconstruction module. Its main function is to reduce the noise of the compensated temperature field to improve the quality and reliability of the temperature field data. The unit decomposes the temperature field into multiple intrinsic mode functions (IMFs), removes the high-frequency noise components, and reconstructs the temperature field after noise reduction. The intrinsic mode function here refers to the component obtained by variational mode decomposition (VMD) technology that can reflect the different frequency characteristics of the temperature field. In this way, the high-frequency noise in the temperature field can be effectively removed while retaining the effective low-frequency signal, thereby providing a more accurate data basis for subsequent diagnostic analysis.

[0046] Specifically, the operation steps of the noise suppression unit include three main links. First, the temperature field is decomposed into multiple intrinsic mode functions by variational mode decomposition technology. Variational mode decomposition is an adaptive signal decomposition method that can decompose the signal into several components with different frequency characteristics according to its characteristics. In the present invention, the number of decomposition layers is set according to the dynamic change frequency of the temperature field, specifically 3 plus half of the temperature field change frequency (rounded down). Secondly, the highest frequency component is removed because the high-frequency component usually contains more noise information. Finally, the denoised temperature field is generated by weighted reconstruction, where the weight factor is used to further suppress the influence of high-frequency noise. This denoising method can effectively balance the noise reduction effect and signal fidelity, and ensure the accuracy and reliability of the temperature field data.

[0047] Preferably, the operation steps of the noise suppression unit can be further optimized. For example, in the setting of the number of decomposition layers, it can be dynamically adjusted according to the specific application scenario and noise level of the temperature field. For environments with more high-frequency noise, the number of decomposition layers can be appropriately increased to remove noise more thoroughly; for environments with lower noise levels, the number of decomposition layers can be reduced to improve calculation efficiency. In addition, the setting of weight factors can also be adjusted according to actual needs. For example, weights can be dynamically assigned according to the frequency characteristics of the intrinsic mode function, so that the weight of the high-frequency component is smaller, thereby further suppressing high-frequency noise. As an alternative, other noise reduction algorithms, such as wavelet transform or adaptive filtering technology, can also be introduced and combined with variational mode decomposition to improve the noise reduction effect.

[0048] In some embodiments, the dynamic coupling analysis module performs: (4.1) Space-time tensor construction: Based on the continuous temperature field distribution and time series data, the space-time tensor is constructed:

[0049] in is the time derivative, is the spatial gradient; (4.2) Calculation of inter-regional coupling parameters: Based on the space-time tensor and TCM partition results, the coupling coefficients of adjacent regions are calculated:

[0050] in, is the geometric range of adjacent regions m and n, is the temperature difference between regions; is the shortest distance from the region boundary to the measurement point, is the area of ​​the region; (4.3) Solution of dynamic equations: Based on the space-time tensor and coupling coefficient , solve the dynamic evolution equation:

[0051] in , is the initial temperature field.

[0052] It should be noted that the dynamic coupling analysis module is a key part of the monitor for analyzing the dynamic characteristics of the palm temperature field and the relationship between regions. Its core function is to quantitatively analyze the thermodynamic connection between different regions of the palm by constructing a space-time tensor and calculating the coupling parameters between regions. The space-time tensor is a multidimensional array that describes the changing characteristics of the temperature field in time and space, while the coupling parameters reflect the intensity of the temperature correlation between adjacent regions. Through these analyses, dynamic information about the functional status of the internal organs and their interactions can be provided for TCM diagnosis, thereby more accurately identifying potential pathological changes.

[0053] Specifically, the operation of the dynamic coupling analysis module includes three main steps. First, the construction of the space-time tensor is based on the continuous temperature field distribution and its time series data. Among them, the time derivative is used to describe the rate of change of temperature over time, and the spatial gradient reflects the trend of temperature change in space. These two parameters together constitute the basic framework of the space-time tensor, which can fully capture the dynamic characteristics of the temperature field. Secondly, the calculation of the inter-regional coupling parameters is based on the results of traditional Chinese medicine zoning. By quantifying the temperature difference, geometric range and boundary distance of adjacent regions, the coupling coefficient is calculated. The size of the coupling coefficient directly reflects the degree of thermodynamic correlation between the two regions. The larger the temperature difference or the smaller the regional area, the higher the coupling coefficient is usually. Finally, the solution of the dynamic evolution equation further simulates the dynamic change process of the temperature field. By introducing the coupling coefficient and the initial temperature field, the future change trend of the temperature field can be predicted, providing richer dynamic information for diagnosis.

[0054] Preferably, the operation of the dynamic coupling analysis module can be further refined and optimized. For example, in the construction of the space-time tensor, higher-order time derivatives or spatial gradients can be introduced to more finely capture the dynamic changes of the temperature field. For the calculation of the coupling parameters, more weight factors can be introduced to consider the physiological characteristics of different regions or the strength of the internal organs in traditional Chinese medicine theory, so as to more accurately reflect the actual coupling relationship between regions. In addition, the solution of the dynamic evolution equation can adopt more advanced numerical methods, such as finite element analysis or adaptive time step algorithm, to improve the solution accuracy and efficiency. As an alternative, a machine learning algorithm can also be introduced to automatically optimize the calculation model of the coupling parameters by learning a large amount of temperature field data, so as to further improve the accuracy and reliability of the diagnosis.

[0055] In some embodiments, the abnormality diagnosis module performs: (5.1) Obtain the maximum temperature gradient of each region from the dynamic coupling analysis module:

[0056] (5.2) Calculate the temperature difference threshold between adjacent areas:

[0057] in is the current average palm temperature; (5.3) When there exists a region satisfying The temperature difference between adjacent areas When the error occurs, a third-level abnormality indicator is generated.

[0058] It should be noted that the abnormal diagnosis module is a key part of the monitor for identifying and evaluating abnormal conditions in the palm temperature field. Its core function is to generate graded pathological indicators by analyzing the coupling parameters output by the dynamic coupling analysis module, combined with the maximum temperature gradient of the palm temperature field and the temperature difference of adjacent areas. These indicators are used to quantify the degree of abnormality and help the TCM diagnosis system to more accurately identify potential pathological conditions. Among them, the maximum temperature gradient refers to the maximum rate of temperature change in a certain area in the temperature field, and the temperature difference threshold is a reference value dynamically calculated based on the current average palm temperature, which is used to determine whether the temperature difference between regions exceeds the normal range.

[0059] Specifically, the operation process of the abnormal diagnosis module includes three main steps. First, the maximum temperature gradient of each area is obtained from the dynamic coupling analysis module. This parameter reflects the area with the most drastic temperature change in the temperature field. Secondly, the temperature difference threshold of the adjacent area is calculated based on the current average temperature of the palm. The threshold is determined by a linear equation with a base value of 2.0 and a slope of 0.3, reflecting the linear relationship between the average palm temperature and the temperature difference threshold. Finally, when the maximum temperature gradient of a certain area exceeds 3.5 and the temperature difference of the adjacent area exceeds the calculated threshold, the system generates a three-level abnormality indicator. This hierarchical diagnosis method can classify according to the severity of the abnormality, providing more detailed reference information for TCM diagnosis.

[0060] Preferably, the operation of the abnormal diagnosis module can be further refined and optimized. For example, in the calculation of the maximum temperature gradient, the time dimension can be introduced to analyze the changing trend of the temperature gradient over a period of time to more accurately judge the persistence and stability of the abnormality. For the calculation of the temperature difference threshold, personalized adjustments can be made according to the physiological characteristics of different populations (such as age, gender, physique, etc.) to improve the accuracy and adaptability of the diagnosis. In addition, a machine learning algorithm can be introduced to automatically optimize the threshold and grading standards of abnormal diagnosis by learning from a large amount of sample data, further improving the intelligent level of diagnosis.

[0061] In some embodiments, the three-level abnormality indicators include: (6.1) Level 1 anomaly: A single area continues to meet Up to 120 seconds; (6.2) Secondary anomaly: temperature difference between two adjacent areas Lasts 60 seconds. (6.3) Level 3 anomaly: Both level 1 and level 2 anomaly conditions are met.

[0062] It should be noted that the three-level abnormality index is a further refinement and classification of the output results of the abnormal diagnosis module, aiming to more accurately describe the abnormal situation of the palm temperature field. Among them, the first-level abnormality means that the maximum temperature gradient of a single area exceeds the threshold and lasts for a certain period of time, reflecting the significant temperature change in the local area; the second-level abnormality focuses on the temperature difference between adjacent areas exceeding the threshold and lasting for a certain period of time, reflecting the temperature imbalance between regions; the third-level abnormality is the most serious situation that meets the first-level and second-level abnormal conditions at the same time, indicating that there are significant local abnormalities and incoordination between regions in the palm temperature field. This grading method can provide more detailed abnormality information for TCM diagnosis and help doctors more accurately judge the pathological state.

[0063] Specifically, the criterion for the first-level abnormality is that the maximum temperature gradient of a single area exceeds 3.5 and lasts for 120 seconds. This parameter setting is based on the range of changes in the palm temperature gradient under normal physiological conditions. When the temperature gradient of a certain area significantly exceeds the normal range and lasts for a long time, it can be considered that the area may be abnormal. The criterion for the second-level abnormality is that the temperature difference between adjacent areas exceeds the dynamically calculated temperature difference threshold and lasts for 60 seconds. The calculation of the temperature difference threshold takes into account the current average temperature of the palm and reflects the relativity of temperature changes. When the temperature difference between adjacent areas exceeds the normal range, it may indicate an incoordination between the functions of the internal organs. The third-level abnormality satisfies both the first-level and second-level abnormality conditions, indicating that there are serious local abnormalities and regional imbalances in the palm temperature field, which is the most serious situation in abnormal diagnosis.

[0064] Preferably, the parameter settings for abnormal diagnosis can be optimized according to the actual application scenario. For example, for the first-level abnormality, the duration can be adjusted according to the physiological characteristics of different populations. For example, the duration threshold for the elderly can be appropriately extended to adapt to their slower physiological changes. For the second-level abnormality, the calculation formula for the temperature difference threshold can be dynamically adjusted according to the changes in seasons or ambient temperature to more accurately reflect the normal temperature difference range under different conditions. In addition, more physiological parameters (such as heart rate, blood pressure, etc.) can be introduced as auxiliary judgment basis to further improve the accuracy and reliability of abnormal diagnosis.

[0065] In some embodiments, the certificate type mapping module performs: (7.1) Construct feature vector:

[0066] (7.2) Calculate the syndrome matching degree:

[0067] in is the historical statistical parameter of the kth syndrome type; (7.3) When When the pulse wave data is called, the correction matching degree is calculated .

[0068] It should be noted that the syndrome mapping module is the key link in the monitor for matching pathological indicators with TCM syndromes. Its core function is to compare the pathological indicators output by the dynamic coupling analysis module with the standard syndromes in the TCM syndrome database by constructing feature vectors and calculating the syndrome matching degree, so as to obtain the closest syndrome matching result. Among them, the feature vector is a mathematical tool used to integrate multiple dimensions of pathological indicators into a quantifiable vector form; the syndrome matching degree is obtained by calculating the similarity between the feature vector and the syndrome parameters in the database, which is used to evaluate the matching degree between the pathological indicators and a certain TCM syndrome.

[0069] Specifically, the operation of the syndrome mapping module includes three main steps. First, when constructing the feature vector, the pathological indicators such as the maximum temperature gradient of each area, the temperature difference between adjacent areas, and the coupling parameters between regions are integrated into a vector form for subsequent matching calculations. Secondly, when calculating the syndrome matching degree, the similarity between the feature vector and the historical statistical parameters of each syndrome in the TCM syndrome database is quantified using a mathematical formula. The calculation formula for the syndrome matching degree includes the normalization of the square sum of the differences in each dimension to ensure that the calculation of the matching degree is comparable. Finally, when the matching degree is lower than the set threshold (such as 0.6), the system will call the pulse wave data as supplementary information to further correct the matching degree, thereby improving the accuracy and reliability of the diagnosis.

[0070] Preferably, the operation of the syndrome mapping module can be further refined and optimized. For example, when constructing the feature vector, different weights can be assigned to different pathological indicators based on traditional Chinese medicine theory and clinical experience to highlight the importance of certain key indicators. For the calculation of syndrome matching, a more complex similarity calculation method can be introduced, such as a similarity metric based on machine learning, to improve the accuracy and adaptability of the matching. In addition, when calling the pulse wave data for correction, the correction strategy can be dynamically adjusted according to the characteristics of the pulse wave (such as the strength and rhythm of the pulse), and the matching results can be further optimized. As an alternative, multimodal data (such as tongue image, complexion, etc.) can also be introduced as supplementary information, combined with pathological indicators, to further improve the accuracy and comprehensiveness of syndrome matching.

[0071] In some embodiments, the coefficient Replace with:

[0072] It should be noted that the coefficient adjustment in the dynamic equation is dynamically changed according to the size of the coupling coefficient to more accurately reflect the dynamic change characteristics of the temperature field. The coupling coefficient here refers to the quantitative parameter of the temperature correlation strength between adjacent regions, and its size directly affects the simulation accuracy of temperature changes in the dynamic equation. By introducing piecewise functions to adjust the coefficients, the evolution process of the temperature field can be more flexibly controlled under different coupling strengths, thereby improving the adaptability of the diagnostic model to different pathological conditions.

[0073] Specifically, the coefficient adjustment of the dynamic equation is based on the size of the coupling coefficient, which is divided into three intervals: when the coupling coefficient is greater than 0.7, the coefficient is 0.15; when the coupling coefficient is between 0.4 and 0.7, the coefficient is 0.1; when the coupling coefficient is less than 0.4, the coefficient is 0.05. The purpose of this segmented setting is to adjust the sensitivity of the dynamic equation according to the temperature change characteristics under different coupling strengths. For example, when the coupling coefficient is large, the temperature field may change more dramatically, so a higher coefficient is required to enhance the dynamic response; when the coupling coefficient is small, the temperature change is relatively gentle, and a lower coefficient helps to avoid excessive amplification of noise. In this way, the dynamic equation can more accurately simulate the dynamic evolution process of the temperature field and provide a more reliable basis for TCM diagnosis.

[0074] Preferably, the adjustment of the dynamic equation coefficients can be further optimized according to the actual application scenario. For example, more interval divisions of the coupling coefficients can be introduced to achieve more refined dynamic adjustment. In addition, the value of the coefficient can also be dynamically calibrated according to clinical data to adapt to the temperature change characteristics of different populations or under different pathological conditions. As an alternative, it is possible to consider introducing an adaptive algorithm to dynamically adjust the coefficient value according to the real-time monitored coupling coefficient, thereby further improving the adaptability and accuracy of the dynamic equation.

[0075] In some embodiments, when When executing: (9.1) Calculate the temperature difference between three adjacent frames:

[0076] in is the temperature field of the first two frames; (9.2) If , it is judged as instantaneous interference and the original temperature field is restored.

[0077] It should be noted that the noise suppression unit introduces the calculation of the temperature difference between three adjacent frames when processing high-frequency noise to further distinguish instantaneous interference from actual temperature changes. The temperature difference between three adjacent frames here refers to the degree of difference between the temperature field of the current frame and the temperature field of the previous two frames. By calculating the temperature difference, it can be determined whether the temperature change is an instantaneous interference. When the temperature difference is less than the set threshold, the system considers the change to be an instantaneous interference and restores the original temperature field to avoid misjudgment caused by noise. This method can effectively suppress high-frequency noise during dynamic monitoring and improve the accuracy and stability of temperature field data.

[0078] Specifically, the noise suppression unit identifies instantaneous interference by calculating the temperature difference between three adjacent frames. In actual operation, the system records the temperature field of the current frame and the temperature field data of the previous two frames in real time, and then calculates the absolute value of the temperature difference between the current frame and the previous two frames. If the temperature difference is less than the set threshold (such as 2°C), it is judged as instantaneous interference. At this time, the system will restore the original temperature field, that is, ignore the instantaneous change to maintain the continuity and stability of the temperature field data. The core of this method is to utilize the redundancy of time series data and identify noise by comparing multiple frames of data, thereby improving the accuracy and reliability of noise suppression. In addition, the threshold setting can be adjusted according to the actual application scenario and noise level to adapt to different monitoring environments.

[0079] Preferably, the operation of the noise suppression unit can be further refined. For example, an adaptive threshold adjustment mechanism can be introduced to dynamically adjust the temperature difference threshold according to the noise level monitored in real time, so as to more flexibly cope with noise interference in different environments. In addition, other noise detection methods (such as noise detection based on wavelet transform) can be combined with the temperature difference method of three adjacent frames to improve the accuracy and robustness of noise identification. As an alternative, it is possible to consider introducing a deep learning algorithm to automatically identify and suppress noise through a training model to further improve the intelligence level of the system.

[0080] In some embodiments, the environmental compensation module performs: (10.1) Real-time collection of ambient temperature and humidity ; (10.2) Calculate the temperature compensation:

[0081] (10.3) When When , correct the sensor data:

[0082] in is the original temperature value, To compensate for the duration.

[0083] It should be noted that the core function of the environmental compensation module is to collect the ambient temperature and humidity in real time and dynamically adjust the temperature value measured by the sensor according to these parameters to compensate for the impact of environmental factors on the measurement results. Environmental compensation here means that during the measurement process, the impact of environmental factors (such as temperature and humidity) on the measurement data is quantified and corrected to improve the measurement accuracy. The compensation amount is calculated based on the difference between the environmental parameters and the standard conditions (such as 25°C, 50% humidity). The temperature value measured by the sensor is adjusted through a specific compensation logic to ensure the accuracy and reliability of the measurement results.

[0084] Specifically, the operation of the environmental compensation module includes three main steps. First, real-time acquisition of ambient temperature ( ) and humidity ( ), these parameters reflect the actual environmental conditions during measurement. Secondly, the temperature compensation is calculated based on the difference between the environmental parameters and the standard conditions. The calculation logic of the compensation is to multiply the difference between the ambient temperature and the standard temperature (25°C) by 0.5, and add the difference between the ambient humidity and the standard humidity (50%) by 0.2. This calculation method reflects the degree of influence of changes in ambient temperature and humidity on the measurement results. Finally, when the absolute value of the compensation is greater than 1°C, the original sensor data is corrected. The correction process is implemented through an exponential decay function to ensure a smooth transition of the compensation process and avoid measurement errors caused by excessive compensation amplitude.

[0085] Preferably, the operation of the environmental compensation module can be further refined and optimized. For example, the compensation coefficients (0.5 and 0.2) can be adjusted according to the actual application scenario to adapt to the measurement requirements under different environmental conditions. For the compensation duration, it can be dynamically adjusted according to the stability of the actual measurement environment. For example, in a scenario where the environment changes rapidly, the compensation time can be shortened to quickly respond to environmental changes. In addition, a more complex environmental model can be introduced to consider the impact of other environmental factors (such as air flow velocity, light intensity, etc.) on the measurement results, and the compensation accuracy can be further improved through multi-parameter compensation logic.

[0086] The above-mentioned embodiments of the present invention have the following beneficial effects: the palm temperature monitor for TCM diagnosis of the present invention can realize the automated process from palm temperature data collection to TCM syndrome diagnosis through the collaborative work of multiple modules. The infrared sensor array module can accurately collect discrete temperature data on the palm surface, providing reliable basic information for subsequent analysis. The temperature field reconstruction module can generate a continuous temperature field distribution by using interpolation functions and boundary compensation technology, making up for the deficiency that traditional equipment can only obtain discrete data. The TCM partition module divides the viscera-related areas based on the preset meridian map, which can combine the temperature field with TCM theory to provide a basis for the evaluation of the functional state of the viscera. The dynamic coupling analysis module can calculate the thermodynamic coupling parameters between regions, further reflect the interaction relationship between the viscera, and help to comprehensively analyze the pathological state. The abnormal diagnosis module generates graded pathological indicators according to the coupling parameters, which can quickly identify potential health problems and conduct graded warnings. The syndrome mapping module matches the pathological indicators with the TCM syndrome database, which can provide patients with personalized TCM syndrome diagnosis results and improve the pertinence and accuracy of the diagnosis.

[0087] In addition, the environmental compensation module can collect ambient temperature and humidity in real time and correct discrete temperature data, effectively reducing the impact of environmental factors on measurement results and improving the reliability and stability of diagnosis. The noise suppression unit removes high-frequency noise through variational mode decomposition technology, which can further optimize the quality of temperature field data and ensure the accuracy of analysis results. The dynamic equation solving module can solve the dynamic evolution equation based on the space-time tensor and coupling coefficient, providing theoretical support for the dynamic monitoring of the functional status of internal organs. When the environmental compensation module detects that the environment changes significantly, it can automatically adjust the compensation strategy to further enhance the adaptability and stability of the equipment.

[0088] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0089] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A palm temperature monitor for traditional Chinese medicine diagnosis, characterized in that: Includes the following modules connected in sequence: an infrared sensor array module configured to collect discrete temperature data of a palm surface; A temperature field reconstruction module receives the discrete temperature data and generates a continuous temperature field distribution; A traditional Chinese medicine partitioning module divides the continuous temperature field distribution into viscera-related areas based on a preset meridian map; A dynamic coupling analysis module receives the continuous temperature field distribution and partition results and calculates the thermodynamic coupling parameters between regions; an abnormality diagnosis module, generating a graded pathology index according to the thermodynamic coupling parameter; An environmental compensation module, which corrects the discrete temperature data according to real-time environmental parameters; A syndrome type mapping module matches the pathological index with the TCM syndrome type database to obtain a syndrome type matching result; The output module integrates the continuous temperature field distribution and the syndrome matching result to generate a diagnosis report.

2. The monitoring device according to claim 1, characterized in that: The temperature field reconstruction module includes: A data interpolation unit receives the discrete temperature data ,implement: Construct an interpolation function, the interpolation function is: in, is the weight coefficient of the i-th sensor, is a cubic radial basis function and , is the Euclidean distance between the point to be inserted and the i-th sensor; is the linear compensation term coefficient; The coefficients are solved by the constraint equations; the constraint equations are: } The boundary compensation unit is used to receive the interpolated temperature field and execute: Extract the temperature gradient modulus to meet The boundary point set of is the spatial temperature gradient; Fitting boundary curves using cubic spline interpolation ,in is the boundary arc length parameter; Compute the curvature and correct for the temperature: in, is the curvature of the boundary curve; The noise suppression unit performs the following steps on the compensated temperature field: Calculate the temperature field difference at adjacent moments ,in is the current temperature value, is the temperature value at the previous moment; Set the number of variational mode decomposition levels ,in is the floor function.

3. The monitoring device according to claim 2, characterized in that: The noise suppression unit performs the following steps: The temperature field is decomposed into IMF ,in ; Remove the highest frequency components ; Reconstruct the denoised temperature field: Among them, the weight factor Used to suppress high frequency noise.

4. The monitoring device according to claim 1, characterized in that: The dynamic coupling analysis module performs the following steps: A space-time tensor is constructed based on the continuous temperature field distribution and time series data. The space-time tensor is: in, is the time derivative, is the spatial gradient; Based on the space-time tensor and TCM partition results, the coupling coefficient of adjacent regions is calculated: in, is the geometric range of adjacent regions m and n, is the temperature difference between regions; is the shortest distance from the region boundary to the measurement point, is the area of ​​the region; Based on the space-time tensor and coupling coefficient , solve the dynamic evolution equation: in, , is the initial temperature field.

5. The monitoring instrument according to claim 1, characterized in that: The abnormality diagnosis module performs the following steps: Obtain the maximum temperature gradient of each region from the dynamic coupling analysis module: Calculate the temperature difference threshold of adjacent areas: in, is the current average palm temperature; When there is a region satisfying The temperature difference between adjacent areas When the error occurs, a third-level abnormality indicator is generated.

6. The monitoring device according to claim 5, characterized in that: The three-level abnormal indicators include: Level 1 anomaly: A single area continues to meet Up to 120 seconds; Secondary anomaly: temperature difference between two adjacent areas Lasts 60 seconds. Level 3 anomaly: Both level 1 and level 2 anomaly conditions are met.

7. The monitoring instrument according to claim 1, characterized in that: The certificate type mapping module performs the following steps: Construct the feature vector: Calculate the matching degree of the syndrome: in, is the historical statistical parameter of the kth syndrome type; is the feature vector The i-th component of ; when When the pulse wave data is called, the correction matching degree is calculated .

8. The monitoring device according to claim 4, characterized in that: The coefficients in the dynamic evolution equation are Replace with: 。 9. The monitoring instrument according to claim 2, characterized in that: when When the noise suppression unit further performs the following steps: Calculate the temperature difference between three adjacent frames: in, is the temperature field of the first two frames; like , it is judged as instantaneous interference and the original temperature field is restored.

10. The monitoring instrument according to claim 1, characterized in that: The environmental compensation module performs the following steps: Real-time collection of ambient temperature and humidity ; Calculate the temperature compensation: when When , correct the sensor data: in, is the original temperature value, To compensate for the duration.

Images