A spine rehabilitation program screening method and system based on user characteristics

Abstract

The application provides a spine rehabilitation scheme screening method and system based on user characteristics, and relates to the technical field of data processing. The method comprises the following steps: collecting multiple characteristic information to obtain a user characteristic information set, testing multiple test indexes to obtain a muscle strength data set, inputting the user characteristic information set into a spine rehabilitation scheme database to obtain multiple primary spine rehabilitation schemes, analyzing multiple training indexes to obtain multiple importance parameters, inputting the muscle strength data set and the multiple primary spine rehabilitation schemes into a training effect analysis model to obtain multiple training score sets, taking the primary spine rehabilitation scheme corresponding to the maximum primary score as the spine rehabilitation scheme screening result of a target user, solving the technical problem that the prior art cannot accurately obtain a training scheme suitable for itself, leading to poor training effect, and realizing accurate formulation of a spine rehabilitation training scheme from the characteristics of a patient, and improving the applicability of scheme recommendation and the training effect.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to a method and system for screening spinal rehabilitation programs based on user characteristics. Background Technology

[0002] Many jobs nowadays require long hours spent at a desk, leading to various spinal problems in the neck and lower back that affect modern life. When these problems impact patients' lives, they often seek out professional rehabilitation doctors and therapists for in-person rehabilitation guidance and training. However, professional rehabilitation guidance and training require face-to-face understanding, analysis, and implementation by professionals, and it requires long-term adherence, which takes a significant amount of time, money, and energy from patients.

[0003] In existing technologies, patients can independently complete relevant exercises according to the movements in the spinal rehabilitation training program. However, since the self-training program is not tailored to the individual patient, it is easy for the training movements to be unreasonable, resulting in poor rehabilitation effects or even secondary injuries.

[0004] Existing technologies present a technical problem: patients cannot accurately obtain training programs suitable for themselves when performing spinal rehabilitation training independently, resulting in poor training effects. Summary of the Invention

[0005] This application provides a method and system for selecting spinal rehabilitation programs based on user characteristics, which addresses the technical problem in the prior art where users cannot accurately obtain suitable training programs when conducting spinal rehabilitation training independently, resulting in poor training effects.

[0006] In view of the above problems, this application provides a method and system for screening spinal rehabilitation programs based on user characteristics.

[0007] Firstly, this application provides a method for screening spinal rehabilitation programs based on user characteristics. The method includes: collecting multiple characteristic information of a target user to obtain a user characteristic information set, wherein the target user is a user to be screened for a spinal rehabilitation program; testing the spinal muscle strength of the target user according to multiple test indicators to obtain a muscle strength data set including multiple muscle strength test data; inputting the user characteristic information set into a spinal rehabilitation program database for preliminary indexing and screening to obtain multiple preliminary spinal rehabilitation programs, each preliminary spinal rehabilitation program including training parameters for rehabilitation training on multiple training indicators. The training indicators correspond to multiple test indicators; based on the muscle strength data set, the importance of the multiple training indicators to the target user is analyzed to obtain multiple importance parameters; according to the multiple training indicators, the muscle strength data set and the muscle strength data and training parameters in the multiple preliminary spinal rehabilitation programs are respectively input into multiple analysis units in the training effect analysis model to obtain multiple training score sets; using the multiple importance parameters, the multiple training score sets are weighted and calculated to obtain multiple preliminary scores, and the preliminary spinal rehabilitation program corresponding to the largest preliminary score is used as the spinal rehabilitation program screening result for the target user.

[0008] Secondly, this application provides a user-feature-based spinal rehabilitation program screening system. The system includes: a set acquisition module, used to collect multiple feature information of a target user to obtain a user feature information set, wherein the target user is a user to be screened for a spinal rehabilitation program; a testing module, used to test the spinal muscle strength of the target user according to multiple test indicators to obtain a muscle strength data set including multiple muscle strength test data; and a preliminary indexing and screening module, used to input the user feature information set into a spinal rehabilitation program database for preliminary indexing and screening to obtain multiple preliminary spinal rehabilitation programs, each of which includes training parameters for rehabilitation training of multiple training indicators. The system includes multiple training indicators and multiple test indicators; an analysis module, which analyzes the importance of the multiple training indicators to the target user based on the muscle strength data set, and obtains multiple importance parameters; a first input module, which inputs the muscle strength data set and the muscle strength data and training parameters from the multiple preliminary spinal rehabilitation programs into multiple analysis units within the training effect analysis model according to the multiple training indicators, and obtains multiple training score sets; and a weighted calculation module, which uses the multiple importance parameters to perform weighted calculations on the multiple training score sets, obtains multiple preliminary scores, and uses the preliminary spinal rehabilitation program corresponding to the largest preliminary score as the screening result for the spinal rehabilitation program of the target user.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application provides a method and system for selecting spinal rehabilitation programs based on user characteristics, which relates to the field of data processing technology. It solves the technical problem in the prior art that when patients are conducting spinal rehabilitation training independently, they cannot accurately obtain training programs suitable for themselves, resulting in poor training effects. The system enables the formulation of spinal rehabilitation training programs suitable for patients based on their characteristics, guides patients to conduct independent rehabilitation training, and improves the applicability of program recommendations and the effectiveness of training. Attached Figure Description

[0010] Figure 1 This application provides a schematic diagram of a method for selecting spinal rehabilitation programs based on user characteristics; Figure 2 This application provides a schematic diagram of the process for obtaining a set of user feature information in a method for screening spinal rehabilitation programs based on user features; Figure 3 This application provides a schematic diagram of the muscle strength data set process in a spinal rehabilitation program selection method based on user characteristics; Figure 4 This application provides a schematic diagram of the process for selecting multiple initial spinal rehabilitation programs in a user-feature-based spinal rehabilitation program screening method. Figure 5 This application provides a flowchart illustrating multiple important parameters in a user-characteristic-based spinal rehabilitation program selection method. Figure 6 This application provides a flowchart illustrating multiple training score sets in a spinal rehabilitation program selection method based on user characteristics; Figure 7 This application provides a schematic diagram of multiple initial selection scores in a spinal rehabilitation program screening method based on user characteristics; Figure 8 This application provides a schematic diagram of a spinal rehabilitation program screening system based on user characteristics.

[0011] Figure labeling: Set acquisition module 1, test module 2, preliminary index filtering module 3, analysis module 4, first input module 5, weighted calculation module 6. Detailed Implementation

[0012] This application provides a method and system for selecting spinal rehabilitation programs based on user characteristics, which addresses the technical problem in the prior art where users cannot accurately obtain suitable training programs when conducting spinal rehabilitation training independently, resulting in poor training effects.

[0013] Example 1 like Figure 1 As shown in the figure, this application provides a method for screening spinal rehabilitation programs based on user characteristics. The method includes: Step S100: Collect multiple feature information of the target user to obtain a user feature information set, wherein the target user is the user to be screened for a spinal rehabilitation program; Specifically, the spinal rehabilitation program selection method based on user characteristics provided in this application is applied to a spinal rehabilitation program selection system based on user characteristics. To ensure the adaptability of the spinal rehabilitation program generated for the target user, it is first necessary to collect multiple characteristics of the target user. The target user is the user for whom the system is to select a spinal rehabilitation program. At the same time, the multiple characteristics of the target user may include the target user's age information, gender information, weight information, height information, and past medical history information such as the spine. By integrating and summarizing the target user's age information, gender information, weight information, height information, and past medical history information such as the spine, the user characteristic information set is obtained, which serves as an important reference for generating a spinal rehabilitation program suitable for the target user in the later stage.

[0014] Step S200: Test the spinal muscle strength of the target user according to multiple test indicators to obtain a muscle strength data set including multiple muscle strength test data; Specifically, because it is necessary to test the current spinal muscle strength of the target user in order to adaptively generate a rehabilitation plan corresponding to the target user's spinal rehabilitation, multiple test indicators need to be set. These multiple test indicators include the strength of the left and right sides of the neck, the left and right sides of the lumbar spine, the left and right flexion of the neck, the left and right flexion of the neck, the anterior and posterior sides of the neck, the anterior and posterior flexion of the neck, and the spinal deformation muscle strength of the target user is further tested according to multiple test indicators. Each test indicator corresponds to a muscle strength test data. Finally, all muscle strength data are summarized and recorded as a muscle strength data set, thereby ensuring the realization of generating a spinal rehabilitation plan suitable for the target user.

[0015] Step S300: Input the user feature information set into the spinal rehabilitation program database for preliminary indexing and filtering to obtain multiple preliminary spinal rehabilitation programs. Each preliminary spinal rehabilitation program includes training parameters for rehabilitation training of multiple training indicators, and the multiple training indicators correspond to multiple test indicators. Specifically, based on the existing spinal rehabilitation programs, a collection of programs is conducted. These collected programs include, but are not limited to, spinal stretching exercises, three-point support exercises, kneeling trunk stretching exercises, and cross-arm limb exercises, as well as the training frequency and intensity of different training content. A spinal rehabilitation program database is then constructed based on this data. Furthermore, the aforementioned user characteristic information is input into the constructed database for adaptive preliminary indexing and filtering. Each initially selected spinal rehabilitation program in the database contains training parameters for multiple training indicators. This means that training parameters are collected based on these indicators when performing rehabilitation training on the target user. Simultaneously, multiple training indicators correspond to multiple test indicators, laying a solid foundation for subsequently generating spinal rehabilitation programs suitable for the target user.

[0016] Step S400: Based on the muscle strength data set, analyze the importance of the multiple training indicators to the target user to obtain multiple importance parameters; Specifically, based on a set of muscle strength data obtained from tests on the spinal muscle strength of the target user, including multiple muscle strength test data, the importance of multiple training indicators to the target user is analyzed according to the problems existing in the target user's spine. At the same time, training indicators that are effective for the target user's spinal rehabilitation are extracted. The more effective the training indicator is for the target user's spinal rehabilitation, the higher its importance. Furthermore, all training indicators are sorted from highest to lowest importance, and parameters with an importance of 60% or more are integrated and summarized. This process obtains multiple important parameters, which plays a limiting role in generating a spinal rehabilitation plan suitable for the target user.

[0017] Step S500: According to the multiple training indicators, input the muscle strength data set and the muscle strength data and training parameters in the multiple preliminary spinal rehabilitation programs into multiple analysis units in the training effect analysis model to obtain multiple training score sets; Specifically, multiple training indicators are used as a foundation. The muscle strength data set, along with the muscle strength data and training parameters included in the multiple preliminary spinal rehabilitation programs, are input into multiple analysis units in the training effect analysis model. First, based on the BP neural network, analysis units that meet preset conditions are constructed and supervised to obtain results. Then, an analysis unit is constructed by arbitrarily selecting a test indicator, the training parameters included in the corresponding training indicator, and the training score after rehabilitation training for the user. Similarly, multiple analysis units corresponding to other test indicators and training indicators are constructed. All analysis units form the training effect analysis model, which is then input into the corresponding analysis units for analysis. Finally, the muscle strength data set, the muscle strength data and training parameters from the multiple preliminary spinal rehabilitation programs are sequentially input into the corresponding analysis units in the training effect analysis model. The different training scores output by the different analysis units are integrated and recorded as multiple training score sets, which serve as reference data for generating spinal rehabilitation programs suitable for the target user in the later stages.

[0018] Step S600: Using the multiple importance parameters, perform weighted calculations on the multiple training score sets to obtain multiple preliminary selection scores, and take the preliminary spinal rehabilitation plan corresponding to the largest preliminary selection score as the screening result of the spinal rehabilitation plan for the target user.

[0019] Specifically, the multiple training score sets obtained above are weighted according to several importance parameters after screening. The weighting calculation requires a large amount of data aggregation and precise determination of weights before targeted calculation. The weights of the multiple training score sets are assigned according to the magnitude of the multiple importance parameters. The larger the importance parameter, the higher the weight allocation. At the same time, the training scores contained in the multiple training score sets are weighted according to the assigned weight values. The weighted calculation results in multiple preliminary scores, and each preliminary score corresponds to a preliminary spinal rehabilitation plan. Furthermore, all preliminary spinal rehabilitation plans are sorted from largest to smallest according to the preliminary score. Thus, the preliminary spinal rehabilitation plan with the largest preliminary score is used as the final spinal rehabilitation plan for the target user. This achieves accurate formulation of spinal rehabilitation training plans based on patient characteristics, improving the applicability of the plan recommendation and the training effect.

[0020] Furthermore, such as Figure 2 As shown, step S100 of this application further includes: Step S110: Collect the target user's age, gender, weight, height, and past medical history information; Step S120: Combine the age information, gender information, weight information, height information and past medical history information to obtain the user characteristic information set.

[0021] Specifically, to ensure the final spinal rehabilitation plan matches the target user, it is necessary to collect the target user's age, gender, weight, height, and past medical history information. Past medical history can include the target user's current medical history, genetic history, previous medical history, and chronic disease history. Furthermore, the target user's age, gender, weight, height, and past medical history information are combined with other features. Age information indicates that spinal characteristics differ across age groups; gender information allows for the selection of a rehabilitation plan based on gender; weight information suggests that greater weight generally means higher spinal load; height information indicates that excessively rapid growth increases the likelihood of scoliosis; and past medical history extracts any past medical conditions that may affect the spine. This process of extracting the target user's feature set provides a crucial basis for generating a suitable spinal rehabilitation plan for the target user.

[0022] Furthermore, such as Figure 3 As shown, step S200 of this application further includes: Step S210: Obtain the multiple test indicators, which include the strength of the left side of the neck muscles, the strength of the right side of the neck muscles, the strength of the left side of the waist muscles, the strength of the right side of the waist muscles, the left side of the neck flexion, the right side of the neck flexion, the left side of the waist flexion, the right side of the waist flexion, the strength of the anterior side of the neck muscles, the strength of the posterior side of the neck muscles, the strength of the anterior side of the neck flexion muscles, and the strength of the posterior side of the neck flexion muscles. Step S220: According to the multiple test indicators, perform spinal deformation muscle strength detection on the target user to obtain multiple muscle strength test data of multiple test indicators, which are used as the muscle strength data set.

[0023] Specifically, the spinal deformation muscle strength of the target user is detected through multiple test indicators, including the strength of the left and right cervical muscles, the left and right lumbar muscles, the left and right cervical flexion, the left and right lumbar flexion, the anterior and posterior cervical muscles, the anterior and posterior cervical flexion muscles, and the posterior cervical flexion muscles. The detection of the target user's spinal deformation muscle strength is based on the voltage changes caused by spinal deformation, which are converted into force magnitude. This can be performed using existing spinal muscle strength detection methods. Specifically, the patient rotates their neck and lower back, applying pressure to a sensor. This causes the sensor to deform, and the pressure on the sensor is related to the magnitude of the force, resulting in a change in the sensor's impedance and excitation voltage. This outputs a changing analog signal, and the magnitude of this pressure is obtained according to a preset analog signal standard. This results in a set of muscle strength data, which includes multiple test indicators, ensuring a more accurate spinal rehabilitation plan for the target user in the later stages.

[0024] Furthermore, such as Figure 4 As shown, step S300 of this application further includes: Step S310: Based on users who have formulated spinal rehabilitation plans in the past, obtain multiple sets of historical user feature information for multiple historical users, and divide them into multiple sets of historical feature information according to the multiple feature information. Step S320: Construct multiple sets of index elements based on the multiple sets of historical feature information; Step S330: Obtain a set of historical spinal rehabilitation plans based on the historical spinal rehabilitation plans developed by the multiple historical users; Step S340: Construct multiple data elements based on the historical spinal rehabilitation program set; Step S350: Construct the spinal rehabilitation program database based on the index relationships of the multiple sets of index elements and the multiple data elements; Step S360: Input the user feature information set into the spinal rehabilitation program database for indexing to obtain multiple corresponding historical spinal rehabilitation programs as the multiple preliminary spinal rehabilitation programs.

[0025] Specifically, the feature information of users who have previously developed spinal rehabilitation plans is extracted. These plans were typically developed by professional physicians. This process yields multiple sets of historical user feature information, each containing several historical user feature sets. Furthermore, these sets are segmented according to different characteristics within these user feature sets, resulting in multiple historical feature information sets. Each historical feature information set includes multiple historical data points related to a single user feature.

[0026] Furthermore, fixed index elements are constructed for the multiple historical feature information sets, that is, an index is created for each feature. At the same time, after summarizing the corresponding historical spinal rehabilitation plans for multiple historical users, data elements are constructed for each historical spinal rehabilitation plan, and multiple index element sets are indexes for multiple data elements. Multi-level index queries are performed on multiple data elements through multiple index element sets. On this basis, the spinal rehabilitation plan database is constructed. After multi-level indexing in the database, spinal rehabilitation plans for users with the same user feature information set in the past are obtained and used as preliminary spinal rehabilitation plans. Further, the user feature information set is input into the constructed spinal rehabilitation plan database for indexing operations, thereby obtaining multiple historical spinal rehabilitation plans and recording them as multiple preliminary spinal rehabilitation plans for output. This achieves the goal of generating a spinal rehabilitation plan suitable for the target user based on multiple preliminary spinal rehabilitation plans.

[0027] Furthermore, such as Figure 5 As shown, step S400 of this application further includes: Step S410: Obtain spinal muscle strength test data of historical users with the user feature information set in the past time period, and obtain multiple historical muscle strength data sets; Step S420: Calculate the mean of the multiple test indicators within the multiple historical muscle strength data sets to obtain the mean of the multiple test indicators; Step S430: Calculate the degree of deviation between the muscle strength data of multiple test indicators in the muscle strength data set and the mean value of the corresponding test indicators, and obtain multiple deviation parameters; Step S440: Use the plurality of deviation parameters as the plurality of importance parameters.

[0028] Specifically, by testing the spinal muscle strength of target users over a past period, a historical dataset of spinal muscle strength tests containing user characteristic information is obtained. Further, the mean values ​​of muscle strength data for multiple test indicators within the obtained historical muscle strength datasets are calculated. Then, the deviation between the muscle strength data for each test indicator of the target user and the corresponding mean value is calculated. This means that based on the mean value of spinal muscle strength test data with the same user characteristic information set, a deviation parameter is calculated between the target user's muscle strength data for each test indicator and the mean value of that test indicator. This deviation parameter is the ratio of the difference between the target user's muscle strength data and the mean value of that test indicator to the mean value of that test indicator. Multiple deviation parameters are then recorded as importance parameters. The larger the deviation parameter, the less standard the target user's muscle strength data for that test indicator, and the greater the importance of rehabilitation training for that test indicator for the target user. Based on this, a spinal rehabilitation plan suitable for the target user is generated.

[0029] Furthermore, such as Figure 6 As shown, step S500 of this application further includes: Step S510: Based on the first test index and the corresponding first training index, obtain the sample first muscle strength data set and the sample first training parameter set; Step S520: Obtain the training score after performing rehabilitation training on a user with muscle strength data in the first set of sample muscle strength data using the training parameters in the first set of sample training parameters, and obtain the first set of sample training scores. Step S530: Using the first training parameter set of the sample, the first muscle strength data set of the sample, and the first training score set of the sample as construction data, a first analysis unit that meets the preset conditions is constructed and supervised to be trained based on a BP neural network. Step S540: Continue to construct multiple analysis units corresponding to multiple other test indicators and multiple training indicators to obtain the training effect analysis model; Step S550: Input the muscle strength data set and the muscle strength data and training parameters in the multiple preliminary spinal rehabilitation programs into the multiple analysis units in sequence to obtain the multiple training score sets.

[0030] Specifically, one test indicator is arbitrarily selected from multiple test indicators as the first test indicator, and there is a one-to-one correspondence between the multiple test indicators and multiple training indicators. Therefore, by using the selected first test indicator and its corresponding first training indicator, the sample first muscle strength data set and the sample first training parameter set based on the first test indicator are extracted. Furthermore, the training parameters within the sample first training parameter set are used to score the rehabilitation training of users with muscle strength data within the sample first muscle strength data set. The higher the score, the better the rehabilitation training effect. Thus, the sample first training score set is obtained. Based on the BP neural network, data construction is adopted. Data construction refers to using the sample first training parameter set, the sample first muscle strength data set, and the sample first training score set to construct and supervise training to obtain a first analysis unit that meets the preset conditions. The construction process of the first analysis unit can be that each set of training data in the training dataset is input into the first analysis unit, and the output of the first analysis unit is adjusted by the supervision data corresponding to this set of training data, thereby adjusting the training of the first analysis unit. Each training dataset includes construction data, and the supervised dataset is the supervised data that corresponds one-to-one with the training dataset. When the output of the first analysis unit is consistent with the supervised data, the training of the current group ends. The first analysis unit is completed when all the training data in the training dataset has been trained.

[0031] To ensure the accuracy of the first analysis unit, it can be tested using a test dataset. For example, the test accuracy rate can be set to 85%. When the test accuracy rate of the test dataset meets 85%, the first analysis unit is completed.

[0032] Simultaneously, each test indicator corresponds to a training indicator and an analysis unit. The input data for the analysis unit consists of the muscle strength data of the corresponding test indicator and the training parameters of the corresponding training indicator, specifically including data such as training plan, training frequency, and training intensity. Therefore, the same approach is used to construct multiple analysis units corresponding to other test indicators and multiple training indicators. Based on all the constructed analysis units, a training effect analysis model is formed. Finally, the muscle strength data set and the muscle strength data and training parameters from multiple initial spinal rehabilitation programs are sequentially input into the constructed multiple analysis units to obtain the training scores of multiple training indicators for each initial spinal rehabilitation program, which serve as the training score set. Then, multiple training score sets are obtained to ensure high efficiency in generating spinal rehabilitation programs suitable for the target user.

[0033] Furthermore, such as Figure 7 As shown, step S600 of this application further includes: Step S610: Based on the magnitude of the multiple importance parameters, perform weight allocation to obtain multiple weight values; Step S620: Using the multiple weight values, perform weighted calculations on the training scores in the multiple training score sets respectively to obtain the multiple initial selection scores.

[0034] Specifically, multiple training score sets are weighted according to the magnitude of several importance parameters; the larger the importance parameter, the higher the weight allocation. Weight allocation can be performed using the analytic hierarchy process (AHP). Based on the data of multiple indicators within the muscle strength dataset, the importance of each evaluation indicator for the target user is compared pairwise. Then, a judgment matrix is ​​established using the pairwise comparison matrix scaling table already available in the AHP. Furthermore, a consistency check is performed on the judgment matrix according to the consistency ratio. The formula for calculating the consistency ratio is: ; ; To determine the largest eigenvalue of the matrix, n is the number of evaluation indicators; This represents the average random consistency index, which can be found by looking up a table.

[0035] When the consistency ratio is less than 0.1, the consistency of the judgment matrix is ​​considered acceptable, and the next step is executed. Otherwise, the judgment matrix is ​​modified, and the weights of the judgment matrix are calculated using a normalization algorithm. These weights serve as the evaluation index weights for the training branches corresponding to multiple training indicators within multiple training score sets. Then, based on the weights of the multiple evaluation indexes, the weighted arithmetic mean corresponding to the multiple training score sets is calculated using the weighted arithmetic mean operator formula. The specific formula for calculating the weighted arithmetic mean is as follows: ; ; ; ; ; Among them, A, B, C, D, and E represent the initial spinal rehabilitation plans; , , , , , , , , , , , This represents the weight values ​​of multiple training metrics and multiple test metrics after the weights of multiple importance parameters have been assigned.

[0036] , , , , This represents the weighted arithmetic mean of each initially selected spinal rehabilitation program.

[0037] a, b, c, d, e, f, g, h, i, j, k, l represent the training scores of the training programs for multiple training indicators corresponding to multiple test indicators within each initially selected spinal rehabilitation program.

[0038] Sort the weighted arithmetic mean from largest to smallest, and then output the corresponding preliminary screening results in sequence as multiple preliminary selection scores.

[0039] In one embodiment, weights can also be directly assigned based on the magnitude of multiple importance parameters to obtain the weight assignment result. Specifically, the ratio of multiple importance parameters to the sum of multiple importance parameters is calculated to obtain multiple weight values, which serve as the weight assignment result.

[0040] In summary, the spinal rehabilitation program selection method and system based on user characteristics provided in this application embodiment has at least the following technical effects: it solves the technical problem in the prior art that when patients are conducting spinal rehabilitation training independently, they cannot accurately obtain a training program suitable for themselves, resulting in poor training effects. It realizes the formulation of spinal rehabilitation training programs suitable for patients based on their characteristics, guides patients to conduct independent rehabilitation training, and improves the applicability of program recommendations and the effectiveness of training.

[0041] Example 2 Based on the same inventive concept as the user-feature-based spinal rehabilitation program selection method in the foregoing embodiments, such as Figure 8 As shown, this application provides a spinal rehabilitation program screening system based on user characteristics. The system includes: The set acquisition module 1 is used to collect multiple feature information of the target user to obtain a set of user feature information, wherein the target user is the user to be screened for a spinal rehabilitation program; Test module 2 is used to test the spinal muscle strength of the target user based on multiple test indicators to obtain a muscle strength data set including multiple muscle strength test data. The preliminary indexing and filtering module 3 is used to input the user feature information set into the spinal rehabilitation program database for preliminary indexing and filtering to obtain multiple preliminary spinal rehabilitation programs. Each preliminary spinal rehabilitation program includes training parameters for rehabilitation training of multiple training indicators, and the multiple training indicators correspond to multiple test indicators. Analysis module 4 is used to analyze the importance of the multiple training indicators to the target user based on the muscle strength data set, and obtain multiple importance parameters; The first input module 5 is used to input the muscle strength data set and the muscle strength data and training parameters in the multiple preliminary spinal rehabilitation programs into multiple analysis units in the training effect analysis model according to the multiple training indicators, so as to obtain multiple training score sets. The weighted calculation module 6 is used to perform weighted calculation on the multiple training score sets using the multiple importance parameters to obtain multiple preliminary selection scores, and to take the preliminary selection spinal rehabilitation plan corresponding to the largest preliminary selection score as the screening result of the spinal rehabilitation plan for the target user.

[0042] Furthermore, the system also includes: An information collection module is used to collect the target user's age, gender, weight, height, and past medical history. The combination module is used to combine the age information, gender information, weight information, height information and past medical history information to obtain the user feature information set.

[0043] Furthermore, the system also includes: The indicator acquisition module is used to acquire the plurality of test indicators, including the strength of the left side of the neck muscles, the strength of the right side of the neck muscles, the strength of the left side of the waist muscles, the strength of the right side of the waist muscles, the left side of the neck flexion, the right side of the neck flexion, the left side of the waist flexion, the right side of the waist flexion, the strength of the anterior side of the neck muscles, the strength of the posterior side of the neck muscles, the strength of the anterior side of the neck flexion muscles, and the strength of the posterior side of the neck flexion muscles. The strength detection module is used to perform spinal deformation muscle strength detection on the target user according to the multiple test indicators, and obtain multiple muscle strength test data of multiple test indicators as the muscle strength data set.

[0044] Furthermore, the system also includes: The segmentation module is used to obtain multiple sets of historical user feature information for multiple historical users based on users who have formulated spinal rehabilitation plans in the past time period, and to segment multiple sets of historical feature information according to the multiple feature information. An element set construction module is used to construct multiple index element sets based on the multiple sets of historical feature information. The solution set acquisition module is used to obtain a set of historical spinal rehabilitation solutions based on the historical spinal rehabilitation solutions formulated by the multiple historical users. A data element construction module is used to construct multiple data elements based on the historical spinal rehabilitation program set. A database construction module is used to construct the spinal rehabilitation program database based on the index relationships of the multiple sets of index elements and the multiple data elements; An indexing module is used to input the user feature information set into the spinal rehabilitation program database for indexing, and obtain multiple corresponding historical spinal rehabilitation programs as the multiple preliminary spinal rehabilitation programs.

[0045] Furthermore, the system also includes: The strength data set acquisition module is used to acquire spinal muscle strength test data of historical users with the user characteristic information set in the past time period, and to obtain multiple historical muscle strength data sets. The first calculation module is used to calculate the mean of the multiple test indicators within the multiple historical muscle strength data sets to obtain the mean of the multiple test indicators. The second calculation module is used to calculate the degree of deviation between the muscle strength data of multiple test indicators in the muscle strength data set and the mean value of the corresponding test indicators, and obtain multiple deviation parameters. The parameter module is used to treat the plurality of deviation parameters as the plurality of importance parameters.

[0046] Furthermore, the system also includes: A set acquisition module is used to obtain a sample first muscle strength data set and a sample first training parameter set based on a first test index and a corresponding first training index. The training module is used to obtain the training score after performing rehabilitation training on a user with muscle strength data in the first set of sample muscle strength data using training parameters in the first set of sample training parameters, and to obtain the first set of sample training scores. The first construction module is used to use the first training parameter set of the sample, the first muscle strength data set of the sample, and the first training score set of the sample as construction data, and to construct and supervise training based on the BP neural network to obtain a first analysis unit that meets the preset conditions. The second construction module is used to continue to construct multiple analysis units corresponding to multiple other test indicators and multiple training indicators to obtain the training effect analysis model; The second input module is used to sequentially input the muscle strength data set and the muscle strength data and training parameters in the multiple preliminary spinal rehabilitation programs into the multiple analysis units to obtain the multiple training score sets.

[0047] Furthermore, the system also includes: A weight allocation module is used to allocate weights according to the magnitude of the multiple importance parameters to obtain multiple weight values; The third calculation module is used to perform weighted calculations on the training scores in the multiple training score sets using the multiple weight values ​​to obtain the multiple initial selection scores.

[0048] Through the foregoing detailed description of a user-feature-based spinal rehabilitation program screening method, those skilled in the art can clearly understand the user-feature-based spinal rehabilitation program screening system in this embodiment. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant parts can be referred to the method section description.

[0049] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for selecting spinal rehabilitation programs based on user characteristics, characterized in that, The method includes: Collect multiple feature information of the target user to obtain a user feature information set, wherein the target user is the user to be screened for spinal rehabilitation program; The spinal muscle strength of the target user is tested based on multiple test indicators to obtain a muscle strength data set including multiple muscle strength test data. The user feature information set is input into the spinal rehabilitation program database for preliminary indexing and filtering to obtain multiple preliminary spinal rehabilitation programs. Each preliminary spinal rehabilitation program includes training parameters for rehabilitation training of multiple training indicators, and the multiple training indicators correspond to multiple test indicators. Based on the muscle strength data set, the importance of the multiple training indicators to the target user is analyzed to obtain multiple importance parameters; According to the multiple training indicators, the muscle strength data set and the muscle strength data and training parameters in the multiple preliminary spinal rehabilitation programs are respectively input into multiple analysis units in the training effect analysis model to obtain multiple training score sets; Using the aforementioned multiple importance parameters, the multiple training score sets are weighted and calculated to obtain multiple preliminary selection scores. The preliminary selection spinal rehabilitation plan corresponding to the largest preliminary selection score is used as the screening result of the spinal rehabilitation plan for the target user. This involves collecting multiple feature information of the target user to obtain a set of user feature information, including: Collect the target user's age, gender, weight, height, and past medical history information; The user characteristic information set is obtained by combining the age information, gender information, weight information, height information and past medical history information.

2. The method according to claim 1, characterized in that, The spinal muscle strength of the target user was tested based on multiple test indicators, including: The multiple test indicators are obtained, including the strength of the left side of the neck muscles, the strength of the right side of the neck muscles, the strength of the left side of the waist muscles, the strength of the right side of the waist muscles, the left side of the neck flexion, the right side of the neck flexion, the left side of the waist flexion, the right side of the waist flexion, the strength of the anterior side of the neck muscles, the strength of the posterior side of the neck muscles, the strength of the anterior side of the neck flexion muscles, and the strength of the posterior side of the neck flexion muscles. Based on the aforementioned multiple test indicators, spinal deformation muscle strength is tested on the target user to obtain multiple muscle strength test data for multiple test indicators, which are used as the muscle strength data set.

3. The method according to claim 1, characterized in that, The user feature information set is input into the spinal rehabilitation program database for preliminary indexing and filtering, resulting in several preliminary spinal rehabilitation programs, including: Based on users who have developed spinal rehabilitation plans in the past, multiple sets of historical user characteristic information are obtained for multiple historical users, and multiple sets of historical characteristic information are obtained by dividing according to the multiple sets of characteristic information. Based on the aforementioned sets of historical feature information, construct multiple sets of index elements; Based on the historical spinal rehabilitation plans developed by the multiple historical users, a set of historical spinal rehabilitation plans is obtained. Based on the aforementioned collection of historical spinal rehabilitation programs, multiple data elements are constructed; Based on the index relationships of the multiple sets of index elements and the multiple data elements, the spinal rehabilitation program database is constructed. The user feature information set is input into the spinal rehabilitation program database for indexing to obtain multiple corresponding historical spinal rehabilitation programs, which are then used as the multiple initial spinal rehabilitation programs.

4. The method according to claim 1, characterized in that, Based on the muscle strength data set, the importance of the multiple training indicators to the target user is analyzed to obtain multiple importance parameters, including: Obtain spinal muscle strength test data of historical users with the aforementioned user characteristic information set within a past time period to obtain multiple historical muscle strength data sets; Calculate the mean of the multiple test indicators within the multiple historical muscle strength data sets to obtain the mean of multiple test indicators; Calculate the degree of deviation between the muscle strength data of multiple test indicators in the muscle strength data set and the mean value of the corresponding test indicators, and obtain multiple deviation parameters; The plurality of deviation parameters are used as the plurality of importance parameters.

5. The method according to claim 1, characterized in that, According to the multiple training indicators, the muscle strength data set and the muscle strength data and training parameters from the multiple initially selected spinal rehabilitation programs are respectively input into multiple analysis units within the training effect analysis model, including: Based on the first test index and the corresponding first training index, obtain the first muscle strength data set and the first training parameter set of the sample; And obtain the training score of the user with muscle strength data in the first set of muscle strength data after rehabilitation training using the training parameters in the first set of training parameters in the sample, and obtain the first set of training scores in the sample; Using the first set of training parameters, the first set of muscle strength data, and the first set of training scores of the samples as construction data, a first analysis unit that meets the preset conditions is constructed and supervised to be obtained based on a BP neural network. Continue to construct multiple analysis units corresponding to multiple test indicators and multiple training indicators to obtain the training effect analysis model; The muscle strength data set and the muscle strength data and training parameters from the multiple preliminary spinal rehabilitation programs are sequentially input into the multiple analysis units to obtain the multiple training score sets.

6. The method according to claim 1, characterized in that, Using the aforementioned multiple importance parameters, the multiple training score sets are weighted and calculated to obtain multiple preliminary selection scores, including: Based on the magnitude of the multiple importance parameters, weights are assigned to obtain multiple weight values; The training scores within the multiple training score sets are weighted using the multiple weight values ​​to obtain the multiple initial selection scores.

7. A spinal rehabilitation program selection system based on user characteristics, characterized in that, The system is used to perform the user-feature-based spinal rehabilitation program screening method according to any one of claims 1 to 6, the system comprising: The set acquisition module is used to collect multiple feature information of the target user to obtain a set of user feature information, wherein the target user is the user to be screened for a spinal rehabilitation program; The testing module is used to test the spinal muscle strength of the target user based on multiple testing indicators, and obtain a muscle strength data set including multiple muscle strength test data. The preliminary indexing and filtering module is used to input the user feature information set into the spinal rehabilitation program database for preliminary indexing and filtering to obtain multiple preliminary spinal rehabilitation programs. Each preliminary spinal rehabilitation program includes training parameters for rehabilitation training of multiple training indicators, and the multiple training indicators correspond to multiple test indicators. An analysis module is used to analyze the importance of the multiple training indicators to the target user based on the muscle strength data set, and obtain multiple importance parameters; The first input module is used to input the muscle strength data set and the muscle strength data and training parameters in the multiple preliminary spinal rehabilitation programs into multiple analysis units in the training effect analysis model according to the multiple training indicators, so as to obtain multiple training score sets. The weighted calculation module is used to perform weighted calculation on the multiple training score sets using the multiple importance parameters to obtain multiple preliminary selection scores, and to use the preliminary selection spinal rehabilitation plan corresponding to the largest preliminary selection score as the screening result of the spinal rehabilitation plan for the target user.

Images