Personalized rehabilitation strategy generation method and related devices

Abstract

The application is suitable for the technical field of intelligent algorithm, and provides a personalized rehabilitation strategy generation method and related equipment, including: matching according to gene data of a target user and a preset target gene site to obtain a number of gene sites associated with different physiological characteristics, and obtaining feature association weights of corresponding genotypes according to the gene data and a preset gene-physiological characteristic database to calculate a total score of physiological characteristics of the target user; obtaining original data and action completion degree data of the target user when performing a rehabilitation action, and determining weight data of different risk dimensions by using an analytic hierarchy process algorithm, calculating risk values of each dimension by using a multi-factor linear regression algorithm to obtain risk point priority data; using a multi-condition constraint optimization algorithm, combining a preset training action library to construct a target function meeting a maximum high-risk point training proportion and meeting a strength safety threshold, solving the target function to obtain initial training plan parameters.

Description

Technical Field

[0001] This application belongs to the field of intelligent algorithm technology, and in particular relates to a method for generating personalized rehabilitation strategies and related equipment. Background Technology

[0002] Existing rehabilitation training strategies do not take individual differences into account during the development process. The developed rehabilitation training strategies are only general strategies. However, the rehabilitation effects of general strategies vary when facing different groups of people, and cannot guarantee good rehabilitation results for different groups of people. Summary of the Invention

[0003] This application provides a method and related equipment for generating personalized rehabilitation strategies, which can address the limitations of general strategies in the prior art.

[0004] In a first aspect, embodiments of this application provide a method for generating personalized rehabilitation strategies, including: The target user's genetic data is matched with preset target gene loci to obtain the number of gene loci associated with different physiological characteristics. Based on the genetic data and preset gene-physiological characteristic database, the feature association weight of the corresponding genotype is obtained. Then, the total physiological characteristic score of the target user is calculated based on the number of gene loci associated with different physiological characteristics and the feature association weight. Based on the target user's raw data and action completion data during rehabilitation exercises, and using the hierarchical analysis algorithm to determine the weight data of different risk dimensions, a multi-factor linear regression algorithm is then used to calculate the risk value of each dimension based on the weight data, the raw data, and the action completion data. The risk values ​​are then sorted from high to low to obtain the risk point priority data. A multi-constraint optimization algorithm is adopted, with the total score of the physiological characteristics as the intensity constraint and the priority data of the risk points as the action weight constraint. Combined with a preset training action library, an objective function is constructed that maximizes the training ratio of high-risk points and satisfies the intensity safety threshold. The objective function is solved to obtain the initial training plan parameters.

[0005] Optionally, before the step of matching based on the target user's genetic data and preset target genetic loci, the method further includes: A filtering algorithm based on preset rules is used to preprocess the initial gene data to identify and remove the initial gene data with incorrect data format, thereby obtaining the secondary gene data. Gene data is obtained by correcting the bias in gene locus labeling within the secondary gene data using the human genome reference sequence.

[0006] Optionally, the step of obtaining the feature association weights of corresponding genotypes based on the gene data and a preset gene-physiological feature database includes: A weighted rule matching algorithm is used to match the gene data based on a preset gene-physiological feature database.

[0007] Optionally, before the step of basing the data on the target user's raw data and movement completion data during rehabilitation exercises, the method further includes: A sliding window filtering algorithm is used to filter the initial data of the target user when performing rehabilitation movements to obtain smooth data; Calculate the standard deviation of the three-dimensional acceleration in the smoothed data, and quantify the gait stability in the original data based on the standard deviation.

[0008] Optionally, the risk dimensions include lower limb strength, balance ability, and joint flexibility.

[0009] Optionally, the method further includes: An initial strategy is generated based on the initial training plan parameters, and the target user's action completion rate and feedback rating for the initial strategy are obtained. Based on the action completion rate and the sensory feedback score, the model is updated using a preset risk value to obtain updated data; The initial strategy is updated based on the updated data to obtain the updated strategy.

[0010] Optionally, the preset training action library includes at least: action name, standard amplitude, and standard number of repetitions.

[0011] On the other hand, embodiments of this application provide a personalized rehabilitation strategy generation device, characterized in that the device includes: The first calculation module is used to match the target user's gene data with preset target gene loci to obtain the number of gene loci associated with different physiological characteristics, and to obtain the feature association weight of the corresponding genotype based on the gene data and preset gene-physiological characteristic database, and then calculate the target user's total physiological characteristic score based on the number of gene loci associated with different physiological characteristics and the feature association weight. The second calculation module is used to determine the weight data of different risk dimensions based on the target user's original data and action completion data when performing rehabilitation movements, and to calculate the risk value of each dimension based on the weight data, the original data and the action completion data through a multi-factor linear regression algorithm, and to sort the risk points from high to low to obtain risk point priority data. The strategy generation module is used to employ a multi-condition constraint optimization algorithm, using the total score of the physiological features as the intensity constraint and the priority data of the risk points as the action weight constraint, combined with a preset training action library, to construct an objective function that maximizes the training ratio of high-risk points and satisfies the intensity safety threshold, and solves the objective function to obtain the initial training plan parameters.

[0012] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the personalized rehabilitation strategy generation method as described in any one of the first aspects above.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the personalized rehabilitation strategy generation method as described in any one of the first aspects above.

[0014] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the personalized rehabilitation strategy generation method described in any one of the first aspects.

[0015] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0016] The beneficial effects of this application embodiment compared with the prior art are as follows: it interprets innate physiological differences by combining a preset database and outputs an "individual basic threshold report" to set a safety baseline for training intensity; the fall prevention risk dynamic assessment module collects dynamic data from the basic questionnaire and training, constructs a risk model to locate acquired weaknesses, and generates a "risk point priority report" to clarify the key training directions; the precise intervention training plan generation module integrates the output results of the first two modules, generates a plan according to the logic of "intensity baseline + action weight", and dynamically fine-tunes it based on weekly training data to achieve an upgrade from "generalized training" to "precise intervention". Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1This is a flowchart of a personalized rehabilitation strategy generation method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a personalized rehabilitation strategy generation device provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of this application. Detailed Implementation

[0019] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0020] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0021] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0022] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [the described condition or event] is detected," or "in response to detection of [the described condition or event]."

[0023] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0025] like Figure 1 As shown in the embodiments of this application, a method for generating personalized rehabilitation strategies is provided, including: S110. Match the target user's gene data with the preset target gene loci to obtain the number of gene loci associated with different physiological characteristics, and obtain the feature association weight of the corresponding genotype based on the gene data and the preset gene-physiological characteristic database. Then calculate the target user's total physiological characteristic score based on the number of gene loci associated with different physiological characteristics and the feature association weight. S120. Based on the target user's original data and action completion data during rehabilitation exercises, and using the hierarchical analysis algorithm to determine the weight data of different risk dimensions, a multi-factor linear regression algorithm is then used to calculate the risk value of each dimension based on the weight data, the original data, and the action completion data, and sorts the risk values ​​from high to low to obtain risk point priority data. S130. Using a multi-condition constraint optimization algorithm, with the total score of the physiological characteristics as the intensity constraint and the priority data of the risk points as the action weight constraint, and combined with a preset training action library, an objective function is constructed that maximizes the training ratio of high-risk points and satisfies the intensity safety threshold. The objective function is solved to obtain the initial training plan parameters.

[0026] For example, intensity constraint settings: determine the intensity limit (amplitude, number of times, load) of each action based on the genetic baseline threshold. Weight constraint settings: Based on the priority of risk points, allocate the training ratio and number of repetitions for each action; Objective function construction and solution: With the objective of "maximizing the proportion of training for high-risk point actions" and the constraint of "intensity not exceeding the genetic threshold", the action parameters (amplitude, number of times, number of sets) are obtained by solving.

[0027] Formula for calculating the number of actions: N = N_{standard} \times (1 + k \times (R - 0.5)) \timesf(G) Where N is the final number of repetitions; N_{standard} is the standard number of repetitions (e.g., 12 times); k is the risk weight coefficient (high risk k=0.3, medium risk k=0.1, low risk k=-0.1); R is the risk value of the risk dimension corresponding to the repetition; f(G) is the gene adjustment coefficient (high muscle enhancement potential f=1.2, medium f=1.0, low f=0.8; weak joint tolerance f=0.9, medium f=1.0, strong f=1.1).

[0028] Range of motion constraints: For example, the range of motion for a chair squat: strong joint tolerance → 90° (thigh parallel to the ground), medium → 105°, weak → 120° (half squat).

[0029] Optionally, before the step of matching based on the target user's genetic data and preset target genetic loci, the method further includes: A filtering algorithm based on preset rules is used to preprocess the initial gene data to identify and remove the initial gene data with incorrect data format, thereby obtaining the secondary gene data. Gene data is obtained by correcting the bias in gene locus labeling within the secondary gene data using the human genome reference sequence.

[0030] For example, the input gene data (locus name + genotype, such as "ACTN3:RR") is checked for format compliance to identify non-standard formats (such as missing delimiters, genotypes that are not the "A / T / C / G" combination). Reference sequence alignment: Aligning compliant data with target gene loci (ACTN3, COL5A1, FOXO3, etc.) in the human genome reference sequence (GRCh38 version); Invalid data removal: Invalid data with mismatched site names or genotypes that conflict with the reference sequence are removed, while valid gene data are retained.

[0031] For example, the target gene locus library includes 12 core loci that are strongly associated with muscles, joints, and endurance (ACTN3 rs1815739, COL5A1 rs12722, FOXO3 rs2802292, etc.); the genotype compliance threshold is: only two valid genotypes are retained: "homozygous (AA / TT / CC / GG)" and "heterozygous (AT / AC / AG / TC / TG / CG)," and other types are deemed invalid.

[0032] Optionally, the step of obtaining the feature association weights of corresponding genotypes based on the gene data and a preset gene-physiological feature database includes: A weighted rule matching algorithm is used to match the gene data based on a preset gene-physiological feature database.

[0033] For example, query a preset "gene-physiological characteristics" database to obtain the feature association weights of the corresponding genotype; Feature score calculation: summing the weights of associated gene loci for each physiological feature (muscle improvement potential, joint endurance strength, endurance adaptation time); Level Classification: Output the corresponding level based on the feature score range.

[0034] The formula for scoring a single physiological characteristic is: S = \sum_{i=1}^{n} (W_{i} \times V_{i}) Where S is the total score of the physiological characteristic; n is the number of gene loci associated with the characteristic; W_{i} is the genotype weight of the i-th locus (value ranges from 0.6 to 1.0); and V_{i} is the validity coefficient of the i-th locus (1 for valid data and 0 for invalid data).

[0035] Grading standards: Muscle building potential: S≥0.9 is high, 0.7≤S<0.9 is medium, and S<0.7 is low; Joint endurance strength: S≥0.85 is strong, 0.65≤S<0.85 is medium, and S<0.65 is weak; Endurance adaptation time: S≥0.8 is long, 0.6≤S<0.8 is medium, and S<0.6 is short.

[0036] Optionally, before the step of basing the data on the target user's raw data and movement completion data during rehabilitation exercises, the method further includes: A sliding window filtering algorithm is used to filter the initial data of the target user when performing rehabilitation movements to obtain smooth data; Calculate the standard deviation of the three-dimensional acceleration in the smoothed data, and quantify the gait stability in the original data based on the standard deviation.

[0037] For example, the three-dimensional acceleration (a_x, a_y, a_z) and angular velocity (ω_x, ω_y, ω_z) data of the user during training are collected at a sampling rate of 100Hz using the mobile phone's gyroscope and accelerometer. Set the time window length to 50ms (including 5 sampling points) and slide it in 20ms increments; average the acceleration and angular velocity data within each window and remove instantaneous jitter noise.

[0038] Average value of data within the window: X_{avg} = \frac{1}{k} \sum_{j=1}^{k} X_{j} Where X_{avg} is the smoothed acceleration / angular velocity value within the window; k is the number of sampling points within the window (k=5); and X_{j} is the j-th original sample value within the window.

[0039] For example, grayscale and Gaussian blur (to remove image noise) are applied to user action video frames (30fps). Edge detection: The Canny algorithm is used to extract the contours (edges) of user actions, and high and low thresholds are set; Similarity matching: The user's action profile is compared with the standard action profile (preset template) using Hausdorff distance calculation and converted into similarity.

[0040] Action completion similarity: Sim = (1 - \frac{H(U,S)}{\max(H(U,S)_{max},1)}) \times 100% Where Sim is the similarity of action completion (0-100%); H(U,S) is the Hausdorff distance between the user contour U and the standard contour S; H(U,S)_{max} is the preset maximum distance threshold (value is 50 pixels).

[0041] Optionally, the risk dimensions include lower limb strength, balance ability, and joint flexibility.

[0042] For example, the Analytic Hierarchy Process (AHP) algorithm is used to construct a "fall prevention risk - risk dimension" judgment matrix and calculate the weights of lower limb strength (W_1), balance ability (W_2), and joint flexibility (W_3); Single-dimensional risk value calculation: Combining basic questionnaire scores with dynamic data (gait stability, movement completion rate), the risk value of each dimension is calculated through multi-factor linear regression. Priority sorting: Sorting risk points from highest to lowest according to risk values ​​of each dimension to generate risk point priorities.

[0043] Risk values ​​for each dimension: Lower limb strength risk value R_1 = 0.4 × (1 - Sim_{squat} + Sim_{knee extension}}{2}) + 0.3 × (1 - V_{actual}}{V_{standard}}) + 0.3 × Q_1 The risk value of the balancing capability R_2 = 0.4 × σ_a + 0.3 × (1 - T_{actual}}{T_{standard}}) + 0.3 × Q_2 Joint flexibility risk value R_3 = 0.5 × (1 - Sim_{calf raises} + Sim_{torsion}}{2}) + 0.5 × Q_3 Sim_{action} represents the similarity of the corresponding action completion; V_{actual} / V_{standard} is the ratio of the actual action completion speed to the standard speed; σ_a is the standard deviation of gait stability; T_{actual} / T_{standard} is the ratio of the actual single-leg standing time to the standard time (10 seconds); Q_1 / Q_2 / Q_3 are the scores of the corresponding dimensions in the basic questionnaire (0-1, 1 is the highest risk).

[0044] - Overall risk value: R_{total} = W_1R_1 + W_2R_2 + W_3R_3 (W_1=0.4, W_2=0.35, W_3=0.25).

[0045] Optionally, the method further includes: An initial strategy is generated based on the initial training plan parameters, and the target user's action completion rate and feedback rating for the initial strategy are obtained. Based on the action completion rate and the sensory feedback score, the model is updated using a preset risk value to obtain updated data; The initial strategy is updated based on the updated data to obtain the updated strategy.

[0046] For example, user action completion rate (Sim) and feeling feedback rating (F, 1-5 points, 5 points is the easiest) are collected weekly. Risk value update: Establish a correlation model between feedback and risk value, and update the risk value of each dimension; Planned incremental adjustment: Based on the updated risk value, the number of actions and sets will be adjusted incrementally (each adjustment increment ≤ 2 times / set).

[0047] Risk value update formula: R_{new} = R_{old} \times (1 - 0.2 \times \frac{Sim -0.8}{0.2}) \times (1 - 0.1 \times (F - 3)) If Sim ≥ 80% and F ≥ 4 (feeling relaxed), R_{new} decreases; if Sim < 60% and F ≤ 2 (feeling difficult), R_{new} increases.

[0048] The formula for adjusting the number of actions is: N_{new} = N_{old} + ΔN Where ΔN is the adjustment increment: R_{new} decreases by ≥0.1 compared to R_{old} → ΔN = +2; R_{new} decreases by 0.05-0.1 → ΔN = +1; R_{new} remains unchanged → ΔN = 0; R_{new} increases → ΔN = -1.

[0049] Optionally, the preset training action library includes at least: action name, standard amplitude, and standard number of repetitions.

[0050] On the other hand, such as Figure 2 Specifically, this application provides a personalized rehabilitation strategy generation device, characterized in that the device includes: The first calculation module 201 is used to match the gene data of the target user with the preset target gene loci to obtain the number of gene loci associated with different physiological characteristics, and to obtain the feature association weight of the corresponding genotype based on the gene data and the preset gene-physiological characteristic database, and then calculate the total physiological characteristic score of the target user based on the number of gene loci associated with different physiological characteristics and the feature association weight. The second calculation module 202 is used to determine the weight data of different risk dimensions based on the target user's original data and action completion data when performing rehabilitation actions, and to calculate the risk value of each dimension based on the weight data, the original data and the action completion data through a multi-factor linear regression algorithm, and to sort the risk points from high to low to obtain risk point priority data. The strategy generation module 203 is used to employ a multi-condition constraint optimization algorithm, using the total score of the physiological characteristics as the intensity constraint, the priority data of the risk points as the action weight constraint, and combining a preset training action library to construct an objective function that maximizes the training ratio of high-risk points and satisfies the intensity safety threshold. The objective function is then solved to obtain the initial training plan parameters.

[0051] In one possible implementation, such as Figure 3 As shown, this application embodiment provides a terminal device 300, including: a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, it performs the following: matching the gene data of the target user with preset target gene loci to obtain the number of gene loci associated with different physiological characteristics, and obtaining the feature association weight of the corresponding genotype based on the gene data and the preset gene-physiological characteristic database, and then calculating the total physiological characteristic score of the target user based on the number of gene loci associated with different physiological characteristics and the feature association weight. Based on the target user's raw data and action completion data during rehabilitation exercises, and using the hierarchical analysis algorithm to determine the weight data of different risk dimensions, a multi-factor linear regression algorithm is then used to calculate the risk value of each dimension based on the weight data, the raw data, and the action completion data. The risk values ​​are then sorted from high to low to obtain the risk point priority data. A multi-constraint optimization algorithm is adopted, with the total score of the physiological characteristics as the intensity constraint and the priority data of the risk points as the action weight constraint. Combined with a preset training action library, an objective function is constructed that maximizes the training ratio of high-risk points and satisfies the intensity safety threshold. The objective function is solved to obtain the initial training plan parameters.

[0052] In one possible implementation, such as Figure 4 As shown, this application embodiment provides a computer-readable storage medium 400, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, it performs the following: matching the gene data of the target user with a preset target gene locus to obtain the number of gene loci associated with different physiological characteristics; obtaining the feature association weight of the corresponding genotype based on the gene data and a preset gene-physiological characteristic database; and calculating the total physiological characteristic score of the target user based on the number of gene loci associated with different physiological characteristics and the feature association weight. Based on the target user's raw data and action completion data during rehabilitation exercises, and using the hierarchical analysis algorithm to determine the weight data of different risk dimensions, a multi-factor linear regression algorithm is then used to calculate the risk value of each dimension based on the weight data, the raw data, and the action completion data. The risk values ​​are then sorted from high to low to obtain the risk point priority data. A multi-constraint optimization algorithm is adopted, with the total score of the physiological characteristics as the intensity constraint and the priority data of the risk points as the action weight constraint. Combined with a preset training action library, an objective function is constructed that maximizes the training ratio of high-risk points and satisfies the intensity safety threshold. The objective function is solved to obtain the initial training plan parameters.

[0053] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0054] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0055] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0056] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0057] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0058] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0059] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0060] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for generating personalized rehabilitation strategies, characterized in that, include: The target user's genetic data is matched with preset target gene loci to obtain the number of gene loci associated with different physiological characteristics. Based on the genetic data and preset gene-physiological characteristic database, the feature association weight of the corresponding genotype is obtained. Then, the total physiological characteristic score of the target user is calculated based on the number of gene loci associated with different physiological characteristics and the feature association weight. Based on the target user's raw data and action completion data during rehabilitation exercises, and using the hierarchical analysis algorithm to determine the weight data of different risk dimensions, a multi-factor linear regression algorithm is then used to calculate the risk value of each dimension based on the weight data, the raw data, and the action completion data. The risk values ​​are then sorted from high to low to obtain the risk point priority data. A multi-constraint optimization algorithm is adopted, with the total score of the physiological characteristics as the intensity constraint and the priority data of the risk points as the action weight constraint. Combined with a preset training action library, an objective function is constructed that maximizes the training ratio of high-risk points and satisfies the intensity safety threshold. The objective function is solved to obtain the initial training plan parameters.

2. The personalized rehabilitation strategy generation method as described in claim 1, characterized in that, Before the step of matching based on the target user's genetic data and preset target genetic loci, the method further includes: A filtering algorithm based on preset rules is used to preprocess the initial gene data to identify and remove the initial gene data with incorrect data format, thereby obtaining the secondary gene data. Gene data is obtained by correcting the bias in gene locus labeling within the secondary gene data using the human genome reference sequence.

3. The personalized rehabilitation strategy generation method as described in claim 1, characterized in that, The step of obtaining the feature association weights of corresponding genotypes based on the gene data and a preset gene-physiological feature database includes: A weighted rule matching algorithm is used to match the gene data based on a preset gene-physiological feature database.

4. The personalized rehabilitation strategy generation method as described in claim 1, characterized in that, Prior to the step of basing the data on the target user's raw data and movement completion data during rehabilitation exercises, the method further includes: A sliding window filtering algorithm is used to filter the initial data of the target user when performing rehabilitation movements to obtain smooth data; Calculate the standard deviation of the three-dimensional acceleration in the smoothed data, and quantify the gait stability in the original data based on the standard deviation.

5. The personalized rehabilitation strategy generation method as described in claim 1, characterized in that, The risk dimensions include lower limb strength, balance ability, and joint flexibility.

6. The personalized rehabilitation strategy generation method as described in claim 1, characterized in that, The method further includes: An initial strategy is generated based on the initial training plan parameters, and the target user's action completion rate and feedback rating for the initial strategy are obtained. Based on the action completion rate and the sensory feedback score, the model is updated using a preset risk value to obtain updated data; The initial strategy is updated based on the updated data to obtain the updated strategy.

7. The personalized rehabilitation strategy generation method as described in claim 6, characterized in that, The preset training action library includes at least: action name, standard amplitude, and standard number of repetitions.

8. A personalized rehabilitation strategy generation device, characterized in that, The device includes: The first calculation module is used to match the target user's gene data with preset target gene loci to obtain the number of gene loci associated with different physiological characteristics, and to obtain the feature association weight of the corresponding genotype based on the gene data and preset gene-physiological characteristic database, and then calculate the target user's total physiological characteristic score based on the number of gene loci associated with different physiological characteristics and the feature association weight. The second calculation module is used to determine the weight data of different risk dimensions based on the target user's original data and action completion data when performing rehabilitation movements, and to calculate the risk value of each dimension based on the weight data, the original data and the action completion data through a multi-factor linear regression algorithm, and to sort the risk points from high to low to obtain risk point priority data. The strategy generation module is used to employ a multi-condition constraint optimization algorithm, using the total score of the physiological features as the intensity constraint and the priority data of the risk points as the action weight constraint, combined with a preset training action library, to construct an objective function that maximizes the training ratio of high-risk points and satisfies the intensity safety threshold, and solves the objective function to obtain the initial training plan parameters.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the personalized rehabilitation strategy generation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the personalized rehabilitation strategy generation method as described in any one of claims 1 to 7.

Images