Traditional Chinese and western medicine rehabilitation factor analysis method and system for osteoporotic pain

Abstract

The invention relates to the technical field of data processing, in particular to a traditional Chinese and western medicine rehabilitation factor analysis method and system for osteoporotic pain, and the method comprises the steps: obtaining reference patient data, obtaining a diseased region based on a reference focus image, obtaining a region monitoring stress set based on a monitoring region and the diseased region, obtaining a scale value by using the influence disease name set and the reference patient data, obtaining an initial historical data set, retrieving a target historical data set from the initial historical data set by using the reference patient data, the regional monitoring stress set and the scale value, obtaining a component index set, and obtaining a component index set; screening the target historical data set by using the component index set to obtain a screened historical data set, obtaining an evaluation value set based on the screened historical data set, obtaining an evaluation data sequence according to the evaluation value set, and realizing analysis of the traditional Chinese and western medicine rehabilitation factors based on the evaluation data sequence. According to the invention, the intelligent degree and accuracy of processing the historical data can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a TCM and Western medicine rehabilitation factor analysis method and system for osteoporosis pain. BACKGROUND

[0002] Osteoporosis is a disease characterized by bone loss and bone microstructure destruction, and its most serious complication is brittle fracture, accompanied by chronic pain. The occurrence of osteoporosis seriously affects people's normal life.

[0003] At present, when treating osteoporosis, it is mostly dependent on the diagnosis experience of doctors.

[0004] The above method can realize the treatment of osteoporosis patients, but when treating osteoporosis patients, it is limited by the diagnosis experience of doctors, and historical data is not considered as a reference, so how to intelligently process historical data has become a problem to be solved. SUMMARY

[0005] The present application provides a TCM and Western medicine rehabilitation factor analysis method and computer readable storage medium for osteoporosis pain, which mainly aims to improve the intelligent degree and accuracy of processing historical data.

[0006] To achieve the above purpose, the present application provides a TCM and Western medicine rehabilitation factor analysis method for osteoporosis pain, which comprises: receiving factor analysis instruction, confirming the analysis patient to be analyzed based on the factor analysis instruction; obtaining reference patient data of the analysis patient, wherein the reference patient data includes patient age, patient gender, pain assessment value, reference disease history and reference lesion image, obtaining the diseased area based on the reference lesion image, and obtaining the regional monitoring stress set based on the preset monitoring area and the diseased area; obtaining the influence disease name set which has an impact on osteoporosis, obtaining the scale value by using the influence disease name set and the reference patient data, obtaining the initial historical data set as a reference, and retrieving the target historical data set in the initial historical data set by using the reference patient data, the regional monitoring stress set and the scale value; obtaining the component index set as a reference, screening the target historical data set by using the component index set to obtain the screened historical data set; evaluating each screened historical data in the screened historical data set to obtain an evaluation value set, obtaining an evaluation data sequence according to the evaluation value set, and analyzing the TCM and Western medicine rehabilitation factors based on the evaluation data sequence.

[0007] Optionally, the obtaining of the diseased area based on the reference lesion image comprises: obtaining an image analysis node set for implementing analysis of the reference lesion image, wherein the image analysis node set comprises a plurality of image analysis nodes, and each image analysis node comprises an image analysis model and a model accuracy; obtaining an analysis image set by using the image analysis node set and the reference lesion image, wherein the analysis image set comprises a plurality of analysis images, and each analysis image corresponds to one image analysis model; mapping the analysis images in the analysis image set to a pre-constructed coordinate system to obtain a mapping image coordinate set, counting the mapping times of the mapping image coordinate points in the mapping image coordinate set to obtain a mapping coordinate quantity set, extracting the model accuracy set from the image analysis node set, and sorting the model accuracy in the model accuracy set in ascending order to obtain a model accuracy sequence; based on a preset initial value, extracting a plurality of initial model accuracies from the model accuracy sequence, wherein the number of the initial model accuracies is the initial value, calculating a comprehensive accuracy by using the plurality of initial model accuracies and a pre-constructed comprehensive accuracy relationship, comparing the comprehensive accuracy with a preset comprehensive accuracy threshold, if the comprehensive accuracy is less than the comprehensive accuracy threshold, performing a plus one operation on the initial value to obtain an updated value, taking the updated value as the initial value, and returning to the step of extracting a plurality of initial model accuracies from the model accuracy sequence based on the preset initial value until the comprehensive accuracy is greater than or equal to the comprehensive accuracy threshold, and taking the initial value as a reference quantity threshold; obtaining the diseased area according to the reference quantity threshold and the mapping coordinate quantity set.

[0008] Optionally, the obtaining of the scale value by using the influence disease name set and the reference patient data comprises: extracting a diseased node sequence from a reference diseased history corresponding to the reference patient data, wherein the diseased node sequence comprises a plurality of diseased nodes, and each diseased node comprises a historical diseased name and a historical diseased time; performing the following operations on each diseased node in the diseased node sequence: searching for the historical diseased name corresponding to the diseased node in the influence disease name set, if a target diseased name is searched for in the influence disease name set based on the historical diseased name, wherein the target diseased name is the same as the historical diseased name, obtaining an absolute difference value between the historical diseased time corresponding to the diseased node and a pre-confirmed current time to obtain a diseased time interval; associating the diseased time interval with the diseased node to obtain an evaluation node, and collecting the evaluation nodes to obtain an evaluation node set; The evaluation node in the evaluation node set is evaluated by using a pre-constructed analytic hierarchy process to obtain an initial scale value set, wherein the initial scale value set includes one or more initial scale values, and the scale value corresponds to the evaluation node one by one, and the maximum initial scale value in the initial scale value set is taken as the scale value.

[0009] Optionally, the target historical data set is retrieved from the initial historical data set by using the reference patient data, the regional monitoring stress set and the scale value, including: The screening age is obtained by calculating the product of the patient age and the preset first range ratio and the preset second range ratio, and the secondary screening historical data set is screened from the primary screening historical data set by using the screening age; The historical disease name corresponding to the scale value is searched in the secondary screening historical data set, if the historical disease name is searched in the initial historical data in the initial historical data set, the initial historical data is taken as the search historical data, the search evaluation value is obtained based on the search historical data, the regional search stress set and the search pain value of the search historical data are obtained; The regional monitoring stresses in the regional monitoring stress set are sorted in descending order to obtain a regional monitoring stress sequence, the regional search stress sequence is obtained based on the regional search stress set, and the number of regional monitoring stresses in the regional monitoring stress sequence and the number of regional search stresses in the regional search stress sequence are counted respectively to obtain the monitoring stress number and the search stress number; The minimum value of the monitoring stress number and the search stress number is taken as the interception number, and the target monitoring stress sequence and the target search stress sequence are intercepted from the regional monitoring stress sequence and the regional search stress sequence respectively by using the interception number; The monitoring parameter is constructed by using the target monitoring stress sequence, the pain evaluation value and the scale value, wherein the monitoring parameter is as follows: wherein, represents the monitoring parameter, represents the pain evaluation value, represents the scale value, respectively represents the first target monitoring stress and the second target monitoring stress in the target monitoring stress sequence, represents the interception number; The search parameter is constructed based on the target search stress sequence, the search pain value and the search evaluation value, and the search parameter set is obtained by summarizing the search parameter. The target historical data set is obtained based on the monitoring parameter and the search parameter set.

[0010] Optionally, the obtaining the target historical data set based on the monitoring parameter and the search parameter set comprises: correlating the monitoring parameter with the diseased area to obtain a monitoring similarity node, and performing the following operations on each search parameter in the search parameter set: obtaining a search area corresponding to the search parameter to obtain a search similarity node, calculating a node similarity based on the monitoring similarity node and the search similarity node, summarizing the node similarity to obtain a node similarity set, sorting the node similarity in the node similarity set in descending order to obtain a node similarity sequence, and confirming a target node similarity sequence in the node similarity sequence by using the preset first screening threshold, wherein the target node similarity in the target node similarity sequence is greater than or equal to the first screening threshold, counting the number of target node similarities in the target node similarity sequence to obtain a similar node number, and comparing the similar node number with a preset basic screening number.

[0011] Optionally, the node similarity is calculated based on the monitoring similarity node and the search similarity node, and the calculation formula is as follows: wherein, the node similarity is represented by, both are preset coefficients, the search pain value is represented by, the search evaluation value is represented by, the first target search stress in the target search stress sequence is represented by, the mean square error of two images is represented by, the diseased area and the search area are represented by, respectively.

[0012] Optionally, the screening historical data set is obtained by using the component index set on the target historical data set, comprising: obtaining a component index weight set by using a pre-constructed principal component analysis method and the component index set, wherein the component index weight set comprises a plurality of component index weights, and each component index weight corresponds to one component index; Confirm a target index weight set in the ingredient index weight set, wherein the target index weight in the target index weight set is greater than or equal to a preset index weight threshold; The following operations are performed on each target historical data in the target historical data set: The target index parameter value is obtained by using the target index weight set and the target historical data, wherein the target index parameter value includes a plurality of target index values, and the target index value corresponds to the target index weight one by one, and the target index parameter value is summarized to obtain a target index parameter value set; An analysis index parameter value of the patient is obtained, and the analysis index parameter value and the target index parameter value set are clustered to obtain a clustering historical data set; The intersection of the clustering historical data set and the target historical data set is obtained to obtain the screening historical data set.

[0013] Optionally, the screening historical data in the screening historical data set is evaluated to obtain an evaluation value set, including: The diagnosis and treatment scheme set is extracted from the screening historical data set, and the diagnosis and treatment scheme in the diagnosis and treatment scheme set is used to summarize the screening historical data in the screening historical data set to obtain a plurality of diagnosis and treatment data sets; The following operations are performed on each diagnosis and treatment data set in the plurality of diagnosis and treatment data sets: A rehabilitation time set is obtained based on the diagnosis and treatment data set, wherein the rehabilitation time set includes a plurality of rehabilitation times and the rehabilitation time corresponds to the diagnosis and treatment data one by one; The similarity between the analysis index parameter value and the target index parameter value corresponding to the diagnosis and treatment data is obtained to obtain an index similarity, and the evaluation value set is obtained based on the index similarity and the rehabilitation time set.

[0014] Optionally, the evaluation value set is obtained based on the index similarity and the rehabilitation time set, including: The following operations are performed on each rehabilitation time in the rehabilitation time set: The comprehensive similarity is calculated by using the index similarity corresponding to the rehabilitation time and the node similarity corresponding to the rehabilitation time, the comprehensive similarity is summarized to obtain a comprehensive similarity set, the rehabilitation time corresponding to the maximum comprehensive similarity in the comprehensive similarity set is taken as an evaluation value, and the evaluation values are summarized to obtain the evaluation value set.

[0015] To achieve the above object, the application also provides a Chinese and Western medicine rehabilitation factor analysis system for osteoporotic pain, comprising: An analysis patient confirmation module is used for receiving a factor analysis instruction, and based on the factor analysis instruction, an analysis patient to be subjected to rehabilitation factor analysis is confirmed; The analysis patient monitoring module is used to acquire reference patient data of an analysis patient, wherein the reference patient data comprises patient age, patient gender, pain evaluation value, reference disease history and reference lesion image, a diseased area is acquired based on the reference lesion image, and a region monitoring stress set is acquired based on a preset monitoring region and the diseased area; The analysis patient index evaluation module is used to acquire an influence disease name set which has an influence on osteoporosis, to acquire a scale value by using the influence disease name set and the reference patient data, to acquire an initial history data set as a reference, and to search for a target history data set in the initial history data set by using the reference patient data, the region monitoring stress set and the scale value. The reference data sequence acquisition module is used to evaluate each screening history data in the screening history data set to obtain an evaluation value set, to acquire an evaluation data sequence according to the evaluation value set, and to realize analysis of TCM rehabilitation factors based on the evaluation data sequence. The reference data sequence acquisition module is used to evaluate each screening history data in the screening history data set to obtain an evaluation value set, to acquire an evaluation data sequence according to the evaluation value set, and to realize analysis of TCM rehabilitation factors based on the evaluation data sequence.

[0016] To solve the above problems, the application further provides an electronic device, which comprises: The memory stores at least one instruction, and the processor executes the instruction stored in the memory to realize the osteoporotic pain TCM rehabilitation factor analysis method.

[0017] To solve the above problems, the application further provides a computer readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to realize the osteoporotic pain TCM rehabilitation factor analysis method.

[0018] The present application is to solve the problems described in the background art, the present application obtains and analyzes reference patient data of a patient, wherein the reference patient data includes patient age, patient gender, pain evaluation value, reference disease history and reference lesion image, a diseased area is obtained based on the reference lesion image, a regional monitoring stress set is obtained based on a preset monitoring area and the diseased area, it can be seen that the present application considers the deviation of different processing methods for processing the reference lesion image when obtaining the diseased area, therefore, the result obtained by combining multiple initial models uses the reference lesion image to obtain a diseased area with credibility, and the regional monitoring stress set obtained in combination with the diseased area lays a foundation for accurately screening historical data in combination with the regional monitoring stress set subsequently, an impact disease name set that affects osteoporosis is obtained, the impact disease name set and the reference patient data are used to obtain a scale value, an initial historical data set is obtained as a reference, the reference patient data, the regional monitoring stress set and the scale value are used to retrieve a target historical data set in the initial historical data set, it can be seen that the embodiment of the present application takes the impact disease with the greatest impact in the impact disease name set as a reference for the patient's condition, reduces the data dimension while retaining the basic characteristics of the data, so as to improve the intelligent degree of processing data, and when retrieving the target historical data set in the initial historical data set, the difference between the diseased area is considered, that is, the difference in quantity between the obtained regional monitoring stress set and the regional retrieval stress set, therefore, the minimum value of the quantity of the regional monitoring stress set and the regional retrieval stress set is taken to process the regional monitoring stress set and the regional retrieval stress set, so as to improve the intelligent degree and accuracy of processing the initial historical data set, a component index set is obtained as a reference, the component index set is used to screen the target historical data set, and a screening historical data set is obtained, it can be seen that the embodiment of the present application not only considers objective indicators of the condition, but also considers subjective indicators related to the patient's living state, which can improve the accuracy and intelligent degree of the screening historical data set screened out by combining subjective and objective indicators, each screening historical data in the screening historical data set is evaluated to obtain an evaluation value set, an evaluation data sequence is obtained according to the evaluation value set, and analysis of traditional Chinese and western medicine rehabilitation factors is realized based on the evaluation data sequence, it can be seen that the embodiment of the present application uses the data with the shortest rehabilitation time in each scheme to construct the evaluation data sequence, so as to provide a quick reference for medical staff. Therefore, the present application can improve the intelligent degree and accuracy of processing historical data. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 A flowchart of a method for analyzing traditional Chinese and western medicine rehabilitation factors of osteoporotic pain is provided for an embodiment of the present application. Figure 2 A functional module diagram of a system for analyzing traditional Chinese and western medicine rehabilitation factors of osteoporotic pain is provided for an embodiment of the present application. Figure 3 Fig. 1 shows a structural schematic diagram of an electronic device for implementing the method for analyzing TCM rehabilitation factors of osteoporotic pain according to an embodiment of the present application.

[0020] Reference signs: 1, electronic device; 10, processor; 11, memory; 12, bus.

[0021] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are merely intended to explain the present application and not to limit the present application.

[0023] The embodiments of the present application provide a method for analyzing TCM rehabilitation factors of osteoporotic pain. The execution subject of the method for analyzing TCM rehabilitation factors of osteoporotic pain includes but is not limited to at least one of electronic devices such as a server and a terminal which can be configured to execute the method provided by the embodiments of the present application. In other words, the method for analyzing TCM rehabilitation factors of osteoporotic pain can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster.

[0024] Reference Figure 1 Fig. 1 shows a structural schematic diagram of an electronic device for implementing the method for analyzing TCM rehabilitation factors of osteoporotic pain according to an embodiment of the present application. S1, receiving a factor analysis instruction, and confirming an analysis patient to be analyzed based on the factor analysis instruction.

[0025] It should be explained that the factor analysis instruction is an instruction issued by medical staff for searching in combination with the actual state of the analysis patient. For example, in order to analyze the condition of a specific osteoporosis patient, the factor analysis instruction is issued by the medical staff, and the analysis patient is confirmed by the medical staff. The analysis patient refers to the patient to be analyzed, and the present application can search the condition of the analysis patient in combination with the historical data, so as to help the medical staff quickly understand the condition of the analysis patient, and give the treatment scheme of the analysis patient according to the treatment scheme of the searched patient.

[0026] Exemplarily, by collecting and analyzing index parameters of a patient under osteoporosis diagnosis, by inputting the index parameters into the pre-constructed factor analysis system, the factor analysis system can retrieve patient medical records and diagnosis methods corresponding to the index parameters of the analysis patient, so as to help medical staff quickly diagnose the analysis patient. Therefore, the embodiment of the present application improves the intelligent degree of processing medical record data.

[0027] S2, acquiring reference patient data of the analysis patient, wherein the reference patient data includes patient age, patient gender, pain assessment value, reference disease history and reference lesion image, acquiring a diseased area based on the reference lesion image, and acquiring a regional monitoring stress set based on a preset monitoring area and the diseased area.

[0028] It should be explained that the patient age is the age of the patient, the patient gender is the gender of the patient, the reference disease history refers to the disease history of the analysis patient, and the reference lesion image refers to an image including the diseased area of the patient. Optionally, a CT image of the discomfort area of the analysis patient is taken as the reference lesion image, and other technologies can achieve the same effect, which will not be repeated here. The pain assessment value is the value of the pain felt by the analysis patient. Optionally, a visual model evaluation method is used to obtain the pain assessment value, and other technologies can achieve the same effect, which will not be repeated here.

[0029] Further, the reference lesion image is based on the reference lesion image to acquire the diseased area, which includes: Acquiring an image analysis node set for analyzing the reference lesion image, wherein the image analysis node set includes a plurality of image analysis nodes, and the image analysis node includes an image analysis model and a model accuracy; Using the image analysis node set and the reference lesion image to acquire an analysis image set, wherein the analysis image set includes a plurality of analysis images, and the analysis image corresponds to the image analysis model one by one; Mapping the analysis image in the analysis image set to a pre-constructed coordinate system to obtain a mapping image coordinate set, counting the mapping times of the mapping image coordinate points in the mapping image coordinate set to obtain a mapping coordinate number set, extracting a model accuracy set from the image analysis node set, and sorting the model accuracy in the model accuracy set in ascending order to obtain a model accuracy sequence; Based on the preset initial value, a plurality of initial model accuracies are extracted from the model accuracy sequence, and the number of initial model accuracies is the initial value, the comprehensive accuracy is calculated by using the plurality of initial model accuracies and the pre-constructed comprehensive accuracy relationship, the comprehensive accuracy is compared with the preset comprehensive accuracy threshold, if the comprehensive accuracy is less than the comprehensive accuracy threshold, the initial value is incremented to obtain an updated value, the updated value is taken as the initial value, and the step of extracting a plurality of initial model accuracies from the model accuracy sequence based on the preset initial value is returned until the comprehensive accuracy is greater than or equal to the comprehensive accuracy threshold, and the initial value is taken as a reference quantity threshold; The diseased area is obtained according to the reference quantity threshold and the set of mapping coordinate quantities.

[0030] Further, the image analysis model refers to an image capable of identifying a lesion area in a reference lesion image. Optionally, a deep convolutional neural network is used as the image analysis model. The model accuracy refers to the accuracy of the image analysis model when the image analysis model is verified. For example, 100 lesion images are used to train the trained image analysis model, and the trained image analysis model can correctly identify 99 lesion image areas, so the accuracy of the image analysis model is 99%, that is, the model accuracy is 99%. The analysis image is the lesion area image obtained by identifying the reference lesion image by using the image analysis model. Therefore, the analysis image corresponds to the image analysis model one by one.

[0031] It should be explained that the purpose of mapping the analysis image to the coordinate system is to count the number of times each coordinate is mapped, so as to exclude the problem of inaccurate identification of the reference lesion image caused by the error of a single image analysis model. Optionally, an image coordinate system is used as the coordinate system, and other technologies can also achieve the same effect, which will not be described here. The mapping times refer to the number of times a same coordinate point in the coordinate system is mapped. For the sake of understanding, a two-dimensional coordinate point is taken as an example. For example, there are only two analysis images including the coordinate point (3, 3) in the analysis image set, and the mapping times of the mapping image coordinate point (3, 3) are counted as 2.

[0032] It should be understood that the initial value is used to extract the model accuracy from the model accuracy sequence.

[0033] Further, the comprehensive accuracy relationship is as follows: Wherein, represents the comprehensive accuracy, represents the i-th initial model accuracy in the plurality of initial model accuracies, represents the i-th initial model accuracy in the plurality of initial model accuracies, represents the total number of initial model accuracies in the plurality of initial model accuracies an initial model accuracy.

[0034] It can be understood that the comprehensive accuracy threshold is an evaluation value for representing the accuracy of the acquired diseased area. The comprehensive accuracy threshold can be set by a person, and other technologies can achieve the same effect, which will not be repeated here. The add-one operation on the initial value means calculating the sum of the initial value and one. The diseased area refers to an image area formed by the mapping image coordinate points in the mapping coordinate number set whose mapping coordinate number is greater than or equal to the reference number threshold.

[0035] Further, the region monitoring stress set based on the preset monitoring area and the diseased area is obtained by using the monitoring area, confirming a plurality of monitoring points in the diseased area, and detecting the plurality of monitoring points to obtain the region monitoring stress corresponding to the monitoring points, and the region monitoring stress corresponds to the monitoring points one by one. Optionally, a plurality of monitoring points are confirmed in the diseased area by using the uniform distribution method and the monitoring area, and other technologies can achieve the same effect, which will not be repeated here. Optionally, the region monitoring stress set is obtained by using the inertial sensor combined with the mechanical model, and other methods can achieve the same effect, which will not be repeated here.

[0036] S3, obtaining an influence disease name set affecting osteoporosis, obtaining a scale value by using the influence disease name set and reference patient data, obtaining an initial historical data set as a reference, and retrieving a target historical data set in the initial historical data set by using the reference patient data, the region monitoring stress set and the scale value.

[0037] It should be explained that the influence disease name refers to the name of the disease that affects osteoporosis, for example, hyperthyroidism, diabetes, etc.

[0038] Further, the scale value is obtained by using the influence disease name set and the reference patient data, which includes: extracting a diseased node sequence from the reference disease history corresponding to the reference patient data, wherein the diseased node sequence includes a plurality of diseased nodes, and the diseased node includes a historical disease name and a historical disease time; performing the following operation on each diseased node in the diseased node sequence: searching for the historical disease name corresponding to the diseased node in the influence disease name set, if a target disease name is searched in the influence disease name set based on the historical disease name, wherein the target disease name is the same as the historical disease name, then obtaining the absolute difference between the historical disease time corresponding to the diseased node and the pre-confirmed current time to obtain a disease time interval; Associating the disease time interval with the disease node to obtain an evaluation node, and summarizing the evaluation nodes to obtain an evaluation node set; The evaluation nodes in the evaluation node set are evaluated using a pre-built hierarchical analysis method to obtain an initial scale value set, wherein the initial scale value set includes one or more initial scale values, and the scale values ​​correspond one-to-one to the evaluation nodes, and the largest initial scale value in the initial scale value set is taken as the scale value.

[0039] Furthermore, the disease node sequence refers to a sequence obtained by sorting the diseases in the reference medical history in descending order according to the time corresponding to the disease. Here, the disease refers to the historical disease name, and the time corresponding to the disease refers to the historical disease time. Retrieving a target disease name from the set of affected disease names based on the historical disease name means retrieving a name identical to the historical disease name from the set of affected disease names using the historical disease name, wherein the identical name refers to the target disease name. The current time refers to the current time, which is used to calculate the time interval between the current time and the disease node, thereby enabling the assessment of the current impact of the disease node. Associating the disease time interval with the disease node refers to aggregating the disease time interval with the disease node. For example, if the disease node is (Disease A, Time A), and the disease time interval corresponding to the disease node is B, then the evaluation node obtained by associating the disease time interval and the disease node is: (Disease A, Time A, Disease Time Interval B), which facilitates the assessment of the impact of different diseases on osteoporosis over different time spans. The degree value refers to the value obtained after evaluating the evaluation node in the evaluation node set using the hierarchical analysis method, and the technology of evaluating the evaluation node using the hierarchical analysis method is a prior art and will not be described in detail here. For example, before evaluating the evaluation node using the hierarchical analysis method, a reference index set for evaluation is obtained, and the evaluation node is evaluated using the reference index set and the hierarchical analysis method. The reference index is an index used to evaluate the evaluation node. Optionally, the degree of abnormal bone absorption and the degree of abnormal calcium metabolism are used as the reference indexes. The absolute difference between bone density and bone density under normal circumstances can be used as the degree of abnormal bone absorption. Optionally, bone density can be obtained by imaging examination. Other technologies can achieve the same effect and will not be described in detail here. Optionally, the calcium metabolism value is obtained by blood testing, and the degree of deviation of the calcium metabolism value from the general value is calculated as the degree of abnormal calcium metabolism.

[0040] It should be understood that the initial historical data set refers to a data set that can be used as a reference and has been clarified. Optionally, by collecting the previous diagnostic records of multiple osteoporosis patients as the initial historical data set, the same effect can be achieved by using other technologies, which will not be repeated here.

[0041] It should be explained that the target historical data set is retrieved from the initial historical data set by using the reference patient data, the regional monitoring stress set and the scale value, including: A preliminary screening historical data set with the same gender as the patient is extracted from the initial historical data set, and the product of the patient's age and the preset first range ratio and the preset second range ratio is calculated to obtain a screening age range. The screening age range is used to screen a secondary screening historical data set from the preliminary screening historical data set; The historical disease name corresponding to the scale value is used to search in the secondary screening historical data set. If the historical disease name is searched in the initial historical data in the initial historical data set, the initial historical data is taken as the search historical data. The search evaluation value is obtained based on the search historical data, and the regional search stress set and the search pain value of the search historical data are obtained; The regional monitoring stresses in the regional monitoring stress set are sorted in descending order to obtain a regional monitoring stress sequence, and the regional search stress sequence is obtained based on the regional search stress set. The number of regional monitoring stresses in the regional monitoring stress sequence and the number of regional search stresses in the regional search stress sequence are counted respectively to obtain the monitoring stress number and the search stress number; The minimum value of the monitoring stress number and the search stress number is taken as the intercept number, and the target monitoring stress sequence and the target search stress sequence are intercepted from the regional monitoring stress sequence and the regional search stress sequence respectively by using the intercept number; The monitoring parameter is constructed by using the target monitoring stress sequence, the pain evaluation value and the scale value, wherein the monitoring parameter is as follows: wherein, represents the monitoring parameter, represents the pain evaluation value, represents the scale value, represents the first target monitoring stress and the second target monitoring stress in the target monitoring stress sequence respectively, represents the intercept number; The search parameter is constructed based on the target search stress sequence, the search pain value and the search evaluation value, and the search parameters are summarized to obtain a search parameter set; The target historical data set is obtained based on the monitoring parameter and the search parameter set.

[0042] Further, the purpose of calculating the screening age range according to the patient age is to consider the characteristics of the age range of the patient age, so as to be able to retrieve a more accurate secondary screening historical data set. For example, female patients are more prone to osteoporosis during menopause, so setting the screening age range helps to screen out patients corresponding to the age range of the patient. Both the first range ratio and the second range ratio are artificial preset values. Optionally, the first range ratio is set to 0.8, and the second range ratio is set to 1.1. Other numerical values can also achieve the same effect, which will not be repeated here. The ages of the patients corresponding to the secondary screening historical data in the secondary screening historical data set are in the screening age range. The retrieval evaluation value is obtained in the same way as the scale value, which will not be repeated here. The difference between the retrieval evaluation value and the scale value is that the disease corresponding to the retrieval evaluation value is the historical disease name corresponding to the scale value. The area retrieval stress set is obtained in the same way as the area monitoring stress set, which will not be repeated here. The retrieval pain value is obtained in the same way as the pain evaluation value, which will not be repeated here. The target monitoring stress sequence and the target retrieval stress sequence are obtained by using the interception quantity to intercept the target monitoring stress sequence and the target retrieval stress sequence in the area monitoring stress sequence and the area retrieval stress sequence respectively. Generally, different disease areas have different areas, so the number of stresses that can be detected when detecting stresses in different disease areas is different, and then the dimensions of the data need to be unified before similarity is calculated. Therefore, in the embodiment of the application, the relatively large area monitoring stress in the area monitoring stress set and the relatively large area detection stress in the area retrieval stress set are taken to construct the target monitoring stress sequence and the target retrieval stress sequence, so as to unify the dimensions when calculating the similarity in the subsequent calculation, and to retain the stress characteristics that can be detected. The method of obtaining the retrieval parameter is the same as the method of obtaining the monitoring parameter, which will not be repeated here.

[0043] It should be noted that the target historical data set is obtained based on the monitoring parameter and the retrieval parameter set, which includes:

[0044] The monitoring parameter is associated with the disease area to obtain a monitoring similarity node, and the following operations are performed on each retrieval parameter in the retrieval parameter set:

[0045] The retrieval area corresponding to the retrieval parameter is obtained, a retrieval similarity node is obtained, a node similarity is calculated based on the monitoring similarity node and the retrieval similarity node, the node similarities are summarized to obtain a node similarity set, the node similarities in the node similarity set are sorted in descending order of the node similarities to obtain a node similarity sequence, a target node similarity sequence is determined in the node similarity sequence by using the preset first screening threshold, wherein the target node similarities in the target node similarity sequence are greater than or equal to the first screening threshold, the number of target node similarities in the target node similarity sequence is counted to obtain a similar node number, and the similar node number is compared with a preset basic screening number. If the similar node number is less than or equal to the basic screening number, the product of a preset similarity reduction ratio and the first screening threshold is calculated to obtain an updated screening threshold, and the updated screening threshold is greater than or equal to a preset basic screening ratio. The basic screening ratio or the updated screening threshold is used as the first screening threshold, and the step of determining the target node similarity sequence in the node similarity sequence by using the preset first screening threshold is returned until the similar node number is greater than the basic screening number. The initial historical data corresponding to the target node similarity in the target node similarity sequence is used as the target historical data set.

[0046] It can be understood that the association of the monitoring parameter and the diseased area means that the monitoring parameter and the diseased area are summarized, and the retrieval area is obtained in the same way as the diseased area. Details are not repeated here. The purpose of ensuring that the number of target historical data in the target historical data set obtained is greater than the basic screening number is to ensure that the target historical data set has a certain reference target historical data. Further, the purpose of setting the updated screening threshold greater than the basic screening ratio for subsequent acquisition of reference target historical data is to ensure that the target historical data obtained has reference value. In general, when the updated screening threshold is greater than the basic screening threshold, the updated screening threshold is used as the first screening threshold, and when the updated screening threshold is less than or equal to the basic screening ratio, the basic screening ratio is used as the first screening threshold.

[0047] It should be understood that the node similarity is calculated based on the monitoring similarity node and the retrieval similarity node, and the calculation formula is as follows: wherein, the node similarity is represented by, both are preset coefficients, the retrieval pain value is represented by, the retrieval evaluation value is represented by, the first target retrieval stress in the target retrieval stress sequence is represented by, the mean square error of two images is represented by, the diseased area and the retrieval area are represented by, respectively.

[0048] It should be explained that the technology of calculating the mean square error of two images is prior art, which will not be described here. By setting different coefficients, the accuracy of the calculated node similarity can be improved. Alternatively, the coefficients required in calculating the node similarity can be obtained by principal component analysis, and other methods can achieve the same effect, which will not be described here.

[0049] S4, obtain a component index set as a reference, and filter the target historical data set by using the component index set to obtain a filtered historical data set.

[0050] It should be explained that the component index set is a collection of indexes for evaluating the influencing factors of osteoporosis. For example, the frequency of smoking.

[0051] Further, the filtering of the target historical data set by using the component index set to obtain a filtered historical data set comprises: obtaining a component index weight set by using a pre-constructed principal component analysis method and the component index set, wherein the component index weight set includes a plurality of component index weights, and each component index weight corresponds to one component index; confirming a target index weight set in the component index weight set, wherein each target index weight in the target index weight set is greater than or equal to a preset index weight threshold; performing the following operations on each target historical data in the target historical data set: obtaining a target index parameter value by using the target index weight set and the target historical data, wherein the target index parameter value includes a plurality of target index values, each target index value corresponds to one target index weight, and the target index parameter value set is obtained by aggregating the target index parameter values; obtaining an analysis index parameter value of the patient, clustering the analysis index parameter value and the target index parameter value set to obtain a clustered historical data set; obtaining the intersection of the clustered historical data set and the target historical data set to obtain the filtered historical data set.

[0052] Further, the component index weight refers to a weight value corresponding to the component index, and the weight value of the component index in the component index set is obtained by using the principal component analysis method, which is prior art and will not be described here. The purpose of confirming the target index weight set by using the component index weight set is to confirm the main factors that may affect osteoporosis, so as to reduce the difficulty of subsequent data processing. Optionally, the component index set is obtained by the empirical method, and other technologies can achieve the same effect, which will not be described here. The target index parameter value refers to a parameter including multiple target index values, and the target index parameter value is obtained in the same way as the monitoring parameter, which will not be described here. The target index value refers to the product of the component index value corresponding to the target index weight and the target index weight. For example, the component index is the number of excessive drinking, and the component index is 2, which means that the number of excessive drinking is 2, and the weight value corresponding to the component index is 0.2, and the target index value is 0.4. The analysis index parameter value is obtained in the same way as the target index parameter value, which will not be described here.

[0053] It should be explained that the clustering of the analysis index parameter value and the target index parameter value set to obtain the clustering historical data set refers to clustering the analysis index parameter value and the target index parameter set by using a pre-constructed clustering method, and searching for a cluster including the analysis index parameter value in the clustering result, and taking the target historical data corresponding to the multiple target index parameter values in the cluster including the analysis index parameter value as the clustering historical data set. Optionally, the k-means clustering algorithm is used as the clustering method, and other technologies can achieve the same effect, which will not be described here.

[0054] S5, evaluating each screening historical data in the screening historical data set to obtain an evaluation value set, obtaining an evaluation data sequence according to the evaluation value set, and analyzing the rehabilitation factors of traditional Chinese and Western medicine based on the evaluation data sequence.

[0055] It should be explained that the evaluation of each screening historical data in the screening historical data set to obtain the evaluation value set includes: extracting a diagnosis and treatment scheme set from the screening historical data set, and using the diagnosis and treatment schemes in the diagnosis and treatment scheme set to summarize the screening historical data in the screening historical data set to obtain multiple diagnosis and treatment data sets; performing the following operations on each diagnosis and treatment data set in the multiple diagnosis and treatment data sets: obtaining a rehabilitation time set based on the diagnosis and treatment data set, wherein the rehabilitation time set includes multiple rehabilitation times, and the rehabilitation time corresponds to the diagnosis and treatment data one by one; Obtaining a similarity between the analysis index parameter value corresponding to the diagnosis and treatment data and the target index parameter value, obtaining an index similarity, and obtaining an evaluation value set based on the index similarity and a rehabilitation time set.

[0056] Further, the diagnosis and treatment scheme refers to a scheme given when treating a patient. The diagnosis and treatment scheme corresponding to each of the plurality of diagnosis and treatment data sets is the same. For example, A medicine in traditional Chinese medicine and B medicine in western medicine are used to treat a patient. The rehabilitation time refers to a time interval experienced by a patient from being diagnosed with osteoporosis to being cured of osteoporosis. Optionally, the Euclidean distance is used as a method for calculating the similarity between the analysis index parameter value and the target index parameter value, and other technologies can achieve the same effect, which will not be described here.

[0057] It should be explained that the evaluation value set is obtained based on the index similarity and the rehabilitation time set, including: The following operations are performed on each rehabilitation time in the rehabilitation time set: The comprehensive similarity is calculated using the index similarity corresponding to the rehabilitation time and the node similarity corresponding to the rehabilitation time, the comprehensive similarities are summarized to obtain a comprehensive similarity set, the rehabilitation time corresponding to the maximum comprehensive similarity in the comprehensive similarity set is taken as an evaluation value, and the evaluation values are summarized to obtain an evaluation value set.

[0058] Further, the comprehensive similarity is calculated using the index similarity corresponding to the rehabilitation time and the node similarity corresponding to the rehabilitation time, which refers to calculating the weighted sum of the index similarity and the node similarity. The evaluation data sequence is obtained according to the evaluation value set, which refers to sorting the evaluation values in the evaluation value set in order from small to large to obtain an evaluation value sequence, and obtaining a sequence of initial historical data using the evaluation value sequence according to the one-to-one correspondence between the evaluation value and the initial historical data, and the bit order of the evaluation value in the evaluation value sequence is the same as the bit order of the initial historical data corresponding to the evaluation value in the evaluation data sequence.

[0059] The present application is to solve the problems described in the background art, the present application obtains reference patient data of the patient, wherein the reference patient data includes patient age, patient gender, pain assessment value, reference disease history and reference lesion image, obtains the diseased area based on the reference lesion image, obtains the regional monitoring stress set based on the preset monitoring area and the diseased area, it can be seen that the present application considers the deviation of the reference lesion image processed by different processing methods when obtaining the diseased area, therefore, the results obtained by combining multiple initial models use the reference lesion image to obtain the diseased area with credibility, and the regional monitoring stress set obtained in combination with the diseased area lays a foundation for accurately screening historical data combined with the regional monitoring stress set subsequently, obtains the influence disease name set which has an impact on osteoporosis, obtains the scale value using the influence disease name set and the reference patient data, obtains the initial historical data set as a reference, and retrieves the target historical data set in the initial historical data set using the reference patient data, the regional monitoring stress set and the scale value, it can be seen that the embodiment of the present application takes the influence disease with the greatest influence degree in the influence disease name set as the reference of the patient's condition, reduces the data dimension while retaining the basic characteristics of the data, so as to improve the intelligent degree of data processing, and when retrieving the target historical data set in the initial historical data set, the difference between the diseased area is considered, that is, the difference between the number of the obtained regional monitoring stress set and the regional retrieval stress set, therefore, the minimum value of the number of the regional monitoring stress set and the regional retrieval stress set is taken to process the regional monitoring stress set and the regional retrieval stress set, so as to improve the intelligent degree and accuracy of processing the initial historical data set, obtains the component index set as a reference, and screens the target historical data set using the component index set, obtains the screening historical data set, it can be seen that the embodiment of the present application not only considers the objective indicators of the condition, but also considers the subjective indicators related to the patient's life state, which can improve the accuracy and intelligent degree of the screening historical data set screened out by combining subjective and objective indicators, evaluates each screening historical data in the screening historical data set, obtains the evaluation value set, obtains the evaluation data sequence according to the evaluation value set, and realizes the analysis of the rehabilitation factors of traditional Chinese and western medicine based on the evaluation data sequence, it can be seen that the embodiment of the present application uses the data with the shortest rehabilitation time in each scheme to construct the evaluation data sequence, so as to provide a quick reference for medical staff. Therefore, the present application can improve the intelligent degree and accuracy of processing the historical data.

[0060] As Figure 2 shown, it is a functional module diagram of the osteoporotic pain rehabilitation factor analysis system of traditional Chinese and western medicine provided by an embodiment of the present application.

[0061] The osteoporosis pain TCM rehabilitation factor analysis system 100 can be installed in an electronic device. According to the functions implemented, the osteoporosis pain TCM rehabilitation factor analysis system 100 can include an analysis patient confirmation module 101, an analysis patient monitoring module 102, an analysis patient index evaluation module 103, and a reference data sequence acquisition module 104. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, which are stored in the memory of the electronic device.

[0062] The analysis patient confirmation module 101 is configured to receive a factor analysis instruction, and confirm an analysis patient to be subjected to rehabilitation factor analysis based on the factor analysis instruction. The analysis patient monitoring module 102 is configured to acquire reference patient data of the analysis patient, wherein the reference patient data includes patient age, patient gender, pain evaluation value, reference disease history, and reference lesion image, acquire a diseased area based on the reference lesion image, and acquire a region monitoring stress set based on a preset monitoring region and the diseased area. The analysis patient index evaluation module 103 is configured to acquire an influence disease name set that has an influence on osteoporosis, acquire a scale value by using the influence disease name set and the reference patient data, acquire an initial historical data set as a reference, and retrieve a target historical data set in the initial historical data set by using the reference patient data, the region monitoring stress set, and the scale value. The analysis patient index evaluation module 103 is configured to acquire an influence disease name set that has an influence on osteoporosis, acquire a scale value by using the influence disease name set and the reference patient data, acquire an initial historical data set as a reference, and retrieve a target historical data set in the initial historical data set by using the reference patient data, the region monitoring stress set, and the scale value. The reference data sequence acquisition module 104 is configured to evaluate each screening historical data in the screening historical data set to obtain an evaluation value set, acquire an evaluation data sequence according to the evaluation value set, and analyze TCM rehabilitation factors based on the evaluation data sequence.

[0063] In detail, the modules in the osteoporosis pain TCM rehabilitation factor analysis system 100 in the embodiments of the present application use the same technical means as the osteoporosis pain TCM rehabilitation factor analysis method described above in the Figure 1 same technical effects can be produced, which will not be described here.

[0064] As shown in Figure 3 , it is a structural schematic diagram of an electronic device for implementing the osteoporosis pain TCM rehabilitation factor analysis method according to an embodiment of the present application.

[0065] The electronic device 1 can include a processor 10, a memory 11 and a bus 12, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as a method for analyzing rehabilitation factors of osteoporotic pain in traditional Chinese and Western medicine.

[0066] The memory 11 includes at least one type of readable storage medium, such as flash memory, mobile hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1. Further, the memory 11 includes both the internal storage unit and the external storage device of the electronic device 1. The memory 11 can be used not only to store application software and various data installed on the electronic device 1, such as the code of the method for analyzing rehabilitation factors of osteoporotic pain in traditional Chinese and Western medicine, but also to temporarily store data that has been output or will be output.

[0067] The processor 10 can be composed of an integrated circuit in some embodiments, such as a single packaged integrated circuit or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, which connects various components of the entire electronic device through various interfaces and lines, executes or runs programs or modules stored in the memory 11 (such as the method for analyzing rehabilitation factors of osteoporotic pain in traditional Chinese and Western medicine, etc.), and calls data stored in the memory 11 to perform various functions and process data of the electronic device 1.

[0068] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable connection and communication between the memory 11, the at least one processor 10, and the like.

[0069] Figure 3 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and can include fewer or more components than shown, or combine certain components, or different component arrangements.

[0070] For example, although not shown, the electronic device 1 can also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, so that the power management system can implement functions such as charge management, discharge management, and power consumption management. The power supply can also include one or more DC or AC power sources, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like. The electronic device 1 can also include various sensors, Bluetooth modules, Wi-Fi modules, and the like, which are not described here.

[0071] Further, the electronic device 1 can also include a network interface, which can optionally include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is typically used to establish a communication connection between the electronic device 1 and other electronic devices.

[0072] Optionally, the electronic device 1 can also include a user interface, which can be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, and the like. The display can also be appropriately referred to as a display screen or a display unit, and is used to display information processed in the electronic device 1 and to display a visualized user interface.

[0073] The osteoporosis pain rehabilitation factor analysis method program stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, which can realize the following when running in the processor 10: receiving factor analysis instructions, and determining an analysis patient to be subjected to rehabilitation factor analysis based on the factor analysis instructions; obtaining reference patient data of the analysis patient, wherein the reference patient data includes patient age, patient gender, pain evaluation value, reference disease history and reference lesion image, obtaining a diseased area based on the reference lesion image, and obtaining a region monitoring stress set based on a preset monitoring region and the diseased area; obtaining an influence disease name set that has an influence on osteoporosis, obtaining a scale value by using the influence disease name set and the reference patient data, obtaining an initial historical data set as a reference, and searching for a target historical data set in the initial historical data set by using the reference patient data, the region monitoring stress set and the scale value; obtaining a component index set as a reference, screening the target historical data set by using the component index set to obtain a screened historical data set; evaluating each screened historical data in the screened historical data set to obtain an evaluation value set, obtaining an evaluation data sequence according to the evaluation value set, and realizing analysis of the rehabilitation factors of traditional Chinese medicine and Western medicine based on the evaluation data sequence.

[0074] Specifically, the processor 10 can refer to the specific implementation method of the above instructions Figures 1 to 3 The description of related steps in the corresponding embodiments is not repeated here.

[0075] Further, the modules / units integrated in the electronic device 1 can be stored in a computer readable storage medium if they are realized in the form of software function units and sold or used as independent products. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).

[0076] The application also provides a computer readable storage medium, which stores a computer program, and the computer program can realize the following when being executed by a processor of an electronic device: receiving factor analysis instructions, and determining an analysis patient to be subjected to rehabilitation factor analysis based on the factor analysis instructions; Reference patient data of the patient is acquired, wherein the reference patient data comprises patient age, patient gender, pain assessment value, reference disease history and reference lesion image, a diseased area is acquired based on the reference lesion image, and a region monitoring stress set is acquired based on a preset monitoring region and the diseased area; An influence disease name set which has an influence on osteoporosis is acquired, a scale value is acquired by using the influence disease name set and the reference patient data, an initial historical data set is acquired as a reference, and a target historical data set is searched in the initial historical data set by using the reference patient data, the region monitoring stress set and the scale value; A component index set is acquired as a reference, the target historical data set is filtered by using the component index set, and a filtered historical data set is obtained; Each filtered historical data in the filtered historical data set is evaluated, an evaluation value set is obtained, an evaluation data sequence is acquired according to the evaluation value set, and analysis of Chinese and Western medicine rehabilitation factors is realized based on the evaluation data sequence.

[0077] In several embodiments provided by the present application, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the above-described system embodiments are merely illustrative; actual implementation can have other division manners.

[0078] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs.

[0079] In addition, the functional modules in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0080] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for analyzing rehabilitation factors of osteoporosis pain using both traditional Chinese and western medicine, characterized in that: The method comprises: receiving a factor analysis instruction, and identifying a patient to be subjected to rehabilitation factor analysis based on the factor analysis instruction; Acquiring reference patient data of the patient for analysis, wherein the reference patient data includes patient age, patient gender, pain assessment value, reference medical history, and reference lesion image; acquiring a diseased area based on the reference lesion image; and acquiring a regional monitoring stress set based on a preset monitoring area and the diseased area; Obtaining a set of influencing disease names that affect osteoporosis, obtaining a scale value using the influencing disease name set and reference patient data, obtaining an initial historical data set as a reference, and retrieving a target historical data set from the initial historical data set using the reference patient data, the regional monitoring stress set, and the scale value; Obtaining a component index set as a reference, and using the component index set to filter the target historical data set to obtain a filtered historical data set; Each screening historical data in the screening historical data set is evaluated to obtain an evaluation value set, an evaluation data sequence is obtained according to the evaluation value set, and an analysis of traditional Chinese and Western medicine rehabilitation factors is implemented based on the evaluation data sequence.

2. The method for analyzing rehabilitation factors of osteoporosis pain using both traditional Chinese and western medicine according to claim 1, characterized in that: The acquiring of the diseased area based on the reference lesion image comprises: Acquire an image analysis node set for analyzing a reference lesion image, wherein the image analysis node set includes a plurality of image analysis nodes, and the image analysis nodes include an image analysis model and a model accuracy rate; Acquire an analysis image set using an image analysis node set and the reference lesion image, wherein the analysis image set includes a plurality of analysis images, and the analysis images correspond one-to-one to the image analysis model; Mapping the analysis images in the analysis image set to a pre-constructed coordinate system to obtain a mapping image coordinate set, counting the number of mappings of the mapping image coordinate points in the mapping image coordinate set to obtain a mapping coordinate quantity set, extracting a model accuracy set from the image analysis node set, and sorting the model accuracy in the model accuracy set in ascending order to obtain a model accuracy sequence; Based on a preset initial value, a plurality of initial model accuracy rates are extracted from a model accuracy sequence, and the number of the initial model accuracy rates is the initial value, a comprehensive accuracy rate is calculated using the plurality of initial model accuracy rates and a pre-constructed comprehensive accuracy rate relationship, the comprehensive accuracy rate is compared with a preset comprehensive accuracy rate threshold, and if the comprehensive accuracy rate is less than the comprehensive accuracy rate threshold, an addition operation is performed on the initial value to obtain an updated value, the updated value is used as the initial value, and the step of extracting a plurality of initial model accuracy rates from a model accuracy sequence based on the preset initial value is returned until the comprehensive accuracy rate is greater than or equal to the comprehensive accuracy rate threshold, with the initial value being used as a reference quantity threshold; The diseased area is acquired according to the reference quantity threshold and the mapping coordinate quantity set.

3. The method for analyzing rehabilitation factors of osteoporosis pain using both traditional Chinese and western medicine according to claim 2, characterized in that: The method of obtaining a scale value by using the affected disease name set and reference patient data includes: Extracting a disease node sequence from the reference medical history corresponding to the reference patient data, wherein the disease node sequence includes a plurality of disease nodes, and the disease nodes include historical disease names and historical disease times; The following operations are performed on each diseased node in the diseased node sequence: Using the historical disease name corresponding to the disease node to search the affected disease name set, if a target disease name is retrieved from the affected disease name set based on the historical disease name, where the target disease name is the same as the historical disease name, then obtaining the absolute difference between the historical disease time corresponding to the disease node and the pre-confirmed current time to obtain the disease time interval; Associating the disease time interval with the disease node to obtain an evaluation node, and summarizing the evaluation nodes to obtain an evaluation node set; The evaluation nodes in the evaluation node set are evaluated using a pre-built hierarchical analysis method to obtain an initial scale value set, wherein the initial scale value set includes one or more initial scale values, and the scale values ​​correspond one-to-one to the evaluation nodes, and the largest initial scale value in the initial scale value set is taken as the scale value.

4. The method for analyzing factors of rehabilitation of osteoporosis pain using both traditional Chinese and western medicine according to claim 3, characterized in that: The method of retrieving a target historical data set from an initial historical data set by using the reference patient data, the regional monitoring stress set, and the scale value includes: Extracting a primary screening historical data set with the same gender as the patient from the initial historical data set, calculating the product of the patient's age, a preset first range ratio, and a preset second range ratio to obtain a screening age range, and using the screening age range to filter out a secondary screening historical data set from the primary screening historical data set; Using the historical disease name corresponding to the scale value, searching in the secondary screening historical data set, if the historical disease name is retrieved in the initial historical data in the initial historical data set, using the initial historical data as the retrieval historical data, obtaining a retrieval evaluation value based on the retrieval historical data, and obtaining a regional retrieval stress set and a retrieval pain value of the retrieval historical data; sorting the regional monitoring stresses of the regional monitoring stress concentration in descending order to obtain a regional monitoring stress sequence, obtaining a regional retrieval stress sequence based on the regional retrieval stress set, and counting the number of regional monitoring stresses in the regional monitoring stress sequence and the number of regional retrieval stresses in the regional retrieval stress sequence to obtain the number of monitoring stresses and the number of retrieval stresses; Taking the minimum value of the monitoring stress quantity and the retrieval stress quantity as the interception quantity, and using the interception quantity to intercept the target monitoring stress sequence and the target retrieval stress sequence in the regional monitoring stress sequence and the regional retrieval stress sequence respectively; The target monitoring stress sequence, pain assessment value and scale value are used to construct monitoring parameters, wherein the monitoring parameters are as follows: in, represents the monitoring parameter, represents the pain assessment value, represents the scale value, They represent the first target monitoring stress and the second target monitoring stress in the target monitoring stress sequence respectively, Indicates the interception quantity; constructing retrieval parameters based on the target retrieval stress sequence, retrieval pain value, and retrieval evaluation value, and summarizing the retrieval parameters to obtain a retrieval parameter set; A target historical data set is obtained based on the monitoring parameters and the retrieval parameter set.

5. The method for analyzing factors of rehabilitation of osteoporosis pain using both traditional Chinese and western medicine according to claim 4, characterized in that: The acquiring of a target historical data set based on the monitoring parameters and the retrieval parameter set includes: The monitoring parameters are associated with the diseased areas to obtain monitoring similarity nodes. The following operations are performed for each retrieval parameter in the retrieval parameter set: Obtain the search area corresponding to the search parameter, obtain the search similarity node, calculate the node similarity based on the monitoring similarity node and the search similarity node, summarize the node similarity, obtain the node similarity set, sort the node similarities in the node similarity set in descending order of node similarity, obtain the node similarity sequence, use the preset first screening threshold to identify the target node similarity sequence in the node similarity sequence, wherein the target node similarities in the target node similarity sequence are all greater than or equal to the first screening threshold, count the number of target node similarities in the target node similarity sequence, obtain the number of similar nodes, compare the The number of similar nodes and the preset basic screening number. If the number of similar nodes is less than or equal to the basic screening number, the product of the preset similarity reduction ratio and the first screening threshold is calculated to obtain the updated screening threshold, and the updated screening threshold is greater than or equal to the preset basic screening ratio. The basic screening ratio or the updated screening threshold is used as the first screening threshold, and the process returns to the step of using the preset first screening threshold to confirm the target node similarity sequence in the node similarity sequence until the number of similar nodes is greater than the basic screening number, and the initial historical data corresponding to the target node similarity in the target node similarity sequence is used as the target historical data set.

6. The method for analyzing rehabilitation factors of osteoporosis pain using both traditional Chinese and western medicine according to claim 5, characterized in that: The node similarity is calculated based on monitoring similarity nodes and retrieving similarity nodes. The calculation formula is as follows: in, represents the node similarity, are all preset coefficients. Retrieve the pain value. Retrieve evaluation value. represents the first target retrieval stress in the target retrieval stress sequence, Indicates the calculation of the mean square error of two images. Represent the diseased area and the search area respectively.

7. The method for analyzing rehabilitation factors of osteoporosis pain using both traditional Chinese and western medicine according to claim 6, characterized in that: The method of screening the target historical data set by using the component indicator set to obtain a screened historical data set includes: Obtaining a component indicator weight set using a pre-constructed principal component analysis method and a component indicator set, wherein the component indicator weight set includes a plurality of component indicator weights, and the component indicator weights correspond one-to-one to the component indicators; Identifying a target indicator weight set from the component indicator weight set, wherein the target indicator weights in the target indicator weight set are all greater than or equal to a preset indicator weight threshold; Perform the following operations on each target historical data in the target historical data set: Obtaining a target indicator parameter value using the target indicator weight set and target historical data, wherein the target indicator parameter value includes multiple target indicator values, and the target indicator values ​​correspond to the target indicator weights one by one, and summarizing the target indicator parameter values ​​to obtain a target indicator parameter value set; Acquiring analysis indicator parameter values ​​of the analyzed patient, clustering the analysis indicator parameter values ​​and the target indicator parameter value set to obtain a clustering history data set; The intersection of the clustered historical data set and the target historical data set is taken to obtain the screening historical data set.

8. The method for analyzing rehabilitation factors of osteoporosis pain using both traditional Chinese and western medicine according to claim 7, characterized in that: The step of evaluating each screening history data in the screening history data set to obtain an evaluation value set includes: Extracting a diagnosis and treatment plan set from the screening historical data set, and using the diagnosis and treatment plans in the diagnosis and treatment plan set to respectively summarize the screening historical data in the screening historical data set to obtain multiple diagnosis and treatment data sets; The following operations are performed on each of the multiple diagnosis and treatment data sets: Acquire a recovery time set based on the diagnosis and treatment data set, wherein the recovery time set includes multiple recovery times and the recovery times correspond one-to-one to the diagnosis and treatment data; The similarity between the analysis indicator parameter value corresponding to the diagnosis and treatment data and the target indicator parameter value is obtained to obtain the indicator similarity, and the evaluation value set is obtained based on the indicator similarity and the recovery time set.

9. The method for analyzing rehabilitation factors of osteoporosis pain using both traditional Chinese and western medicine according to claim 8, characterized in that: The obtaining of the evaluation value set based on the indicator similarity and the recovery time set includes: For each recovery time in the recovery time set, perform the following operations: The comprehensive similarity is calculated using the indicator similarity corresponding to the recovery time and the node similarity corresponding to the recovery time. The comprehensive similarities are summarized to obtain a comprehensive similarity set. The recovery time corresponding to the largest comprehensive similarity in the comprehensive similarity set is taken as the evaluation value. The evaluation values ​​are summarized to obtain an evaluation value set.

10. A Chinese and Western medicine rehabilitation factor analysis system for osteoporosis pain, characterized by: The system comprises: An analysis patient confirmation module is used to receive a factor analysis instruction and confirm an analysis patient to be subjected to rehabilitation factor analysis based on the factor analysis instruction; An analysis patient monitoring module is configured to obtain reference patient data of the analyzed patient, wherein the reference patient data includes the patient's age, patient gender, pain assessment value, reference medical history, and reference lesion image; obtain the diseased area based on the reference lesion image; and obtain the regional monitoring stress set based on the preset monitoring area and the diseased area; a patient index analysis and evaluation module, configured to obtain a set of influencing disease names affecting osteoporosis, obtain a scale value using the influencing disease name set and reference patient data, obtain an initial historical data set as a reference, and retrieve a target historical data set from the initial historical data set using the reference patient data, the regional monitoring stress set, and the scale value; Obtaining a component index set as a reference, and using the component index set to filter the target historical data set to obtain a filtered historical data set; The reference data sequence acquisition module is used to evaluate each screening historical data in the screening historical data set to obtain an evaluation value set, obtain an evaluation data sequence based on the evaluation value set, and analyze the rehabilitation factors of traditional Chinese and Western medicine based on the evaluation data sequence.

Images