Motion strategy determination method for human body parameter measurement equipment and rehabilitation management system

Abstract

The invention relates to an exercise strategy determination method for human body parameter measurement equipment and a rehabilitation management system. The method comprises the following steps: acquiring a plurality of candidate motion strategies and a digital twinborn model of a target object, and determining the motion strategy of the target object according to the plurality of candidate motion strategies and the digital twinborn model. In the method, the digital twinborn model is a digital model obtained by training according to the historical state data and the individual data of the target object, the physical state and the personalized characteristics of the target object are considered, the obtained digital twinborn model can accurately simulate the target object, the integrating degree between the determined motion strategy and the target object is improved, and the motion accuracy of the target object is improved. Therefore, the rehabilitation effect achieved by the exercise strategy is improved.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a method for determining a motion strategy for human body parameter measurement equipment and a rehabilitation management system. Background Art

[0002] In the field of rehabilitation, exercise strategy is a key factor affecting the progress of rehabilitation, and overall it shows an obvious dose-effect relationship, that is, the higher the patient's completion of the exercise strategy, the better the rehabilitation effect achieved.

[0003] Taking cardiac rehabilitation as an example, in related technologies, doctors usually formulate exercise strategies for patients based on their actual condition, for patients to refer to for exercise to promote their cardiac rehabilitation.

[0004] However, the rehabilitation effect achieved by the exercise strategies in related technologies is poor. Summary of the invention

[0005] Based on this, it is necessary to provide a motion strategy and rehabilitation management system for human body parameter measurement equipment to address the above technical issues.

[0006] In a first aspect, the present application provides a method for determining a motion strategy for a human body parameter measurement device, comprising:

[0007] Acquire multiple candidate motion strategies and digital twin models of the target object; the digital twin model is a digital model trained based on historical state data and individual data of the target object;

[0008] Determine the motion strategy of the target object based on multiple candidate motion strategies and the digital twin model.

[0009] In one embodiment, determining a motion strategy of a target object according to a plurality of candidate motion strategies and a digital twin model includes:

[0010] Inputting multiple candidate motion strategies into the digital twin model, and expanding the multiple candidate motion strategies through the digital twin model to obtain a candidate motion strategy set;

[0011] The motion strategy of the target object is determined based on the candidate motion strategy set and the digital twin model.

[0012] In one embodiment, determining a motion strategy of a target object according to a candidate motion strategy set and a digital twin model includes:

[0013] Obtain reference physiological parameters output by each candidate motion strategy in the candidate motion strategy set implemented by the digital twin model;

[0014] The motion strategy of the target object is determined from a set of candidate motion strategies according to the reference physiological parameters.

[0015] In one embodiment, the method further comprises:

[0016] Obtaining target physical sign data and the degree of movement completion of the target subject during the execution of the movement strategy;

[0017] Determine whether the target object and the exercise strategy match based on the target physical sign data and the degree of exercise completion;

[0018] When the target object and the motion strategy do not match, the motion strategy is adjusted to obtain an adjusted motion strategy.

[0019] In one embodiment, determining whether the target object and the exercise strategy match according to the target vital sign data and the degree of exercise completion includes:

[0020] Determine the safety risk assessment results of the target object based on the target vital sign data;

[0021] Determine the target object operation execution evaluation result according to the degree of movement completion;

[0022] Determine whether the target object and the movement strategy match based on the security risk assessment results and the movement execution assessment results.

[0023] In one embodiment, determining whether the target object matches the motion strategy according to the security risk assessment result and the motion execution assessment result includes:

[0024] When the security risk assessment result shows that the target object does not have a security risk, and the motion execution assessment result shows that the target object meets the execution requirements, determining that the target object and the motion strategy match;

[0025] When the security risk assessment result indicates that the target object has a security risk, or the motion execution assessment result indicates that the target object does not meet the execution requirements, it is determined that the target object and the motion strategy do not match.

[0026] In one embodiment, adjusting the motion strategy to obtain the adjusted motion strategy includes:

[0027] When the security risk assessment result indicates that the target object has a security risk, or the motion execution assessment result indicates that the target object does not meet the minimum execution requirement, the execution difficulty of the motion strategy is reduced to obtain a motion strategy with reduced execution difficulty;

[0028] When the security risk assessment result is that there is no security risk for the target object, and the motion execution assessment result is that the target object exceeds the maximum execution requirement, the execution difficulty of the motion strategy is increased to obtain a motion strategy with increased execution difficulty.

[0029] In one embodiment, the method further comprises:

[0030] Determine historical state data of the target object according to historical vital sign data and historical motion data of the target object;

[0031] Determine individual data of the target object according to at least one of the diagnosis and treatment information, exercise habit information, and bone information of the target object;

[0032] The historical status data and individual data of the target object are input into the initial digital model, and the digital twin model is trained.

[0033] In one embodiment, acquiring historical vital sign data and historical motion data of the target object and determining historical state data of the target object includes:

[0034] Determine historical vital sign parameters of the target object according to the historical vital sign data of the target object;

[0035] Determine historical motion parameters of the target object based on historical motion data of the target object;

[0036] The historical vital sign data, historical motion data, historical vital sign parameters and historical motion parameters are determined as historical state parameters of the target object.

[0037] In a second aspect, the present application also provides a rehabilitation management system, comprising: a wearable monitoring device and a digital twin device that communicate with each other;

[0038] Among them, the wearable monitoring device is used to obtain the status data of the target object and send the status data of the target object to the digital twin device;

[0039] The digital twin device is used to obtain multiple candidate motion strategies and digital twin models of the target object, and determine the motion strategy of the target object based on the multiple candidate motion strategies and the digital twin models; the digital twin model is a digital model trained based on the historical state data and individual data of the target object.

[0040] In one embodiment, the wearable monitoring device includes: a vital sign collection device, a motion collection device, and a data transmission center communicating with the vital sign collection device and the motion collection device;

[0041] A physical sign collecting device, used to obtain physical sign data of a target object and determine physical sign parameters of the target object according to the physical sign data;

[0042] A motion acquisition device, used to acquire motion data of a target object and determine motion parameters of the target object based on the motion data;

[0043] The data transmission center is used to receive vital sign data, motion data, vital sign parameters and motion parameters, and send the vital sign data, motion data, vital sign parameters and motion parameters as status data of the target object to the digital twin device.

[0044] In one embodiment, the vital sign data includes an electrocardiogram signal and a photoplethysmogram; the vital sign parameters include an electrocardiogram parameter and a blood oxygen parameter; the vital sign acquisition device includes an electrocardiogram signal acquisition unit and a pulse wave sensor;

[0045] The ECG signal acquisition unit is used to acquire the ECG signal of the target object and determine the ECG parameters of the target object;

[0046] The pulse wave sensor is used to collect the chest pulse wave of the target object and determine the blood oxygen parameters of the target object.

[0047] In one embodiment, the motion data includes limb motion data; the motion parameters include joint range of motion; the motion acquisition device includes an upper limb motion acquisition device and a lower limb motion acquisition device;

[0048] The upper limb motion acquisition device and the lower limb motion acquisition device both include motion sensors for acquiring limb motion data of the target object and determining the joint activity of the target object.

[0049] In one embodiment, the digital twin model includes a convolutional neural network, a bidirectional long short-term memory network, a cascade neural network, a fully connected neural network, and a normalized network connected in sequence.

[0050] In a third aspect, the present application further provides a motion strategy determination device for human body parameter measurement equipment, comprising:

[0051] A data acquisition module is used to obtain a plurality of candidate motion strategies and a digital twin model of a target object; the digital twin model is a digital model trained based on historical state data and individual data of the target object;

[0052] The strategy determination module is used to determine the motion strategy of the target object based on multiple candidate motion strategies and the digital twin model.

[0053] In a fourth aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above-mentioned motion strategy determination methods when executing the computer program.

[0054] In a fifth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above-mentioned motion strategy determination methods when the computer program is executed by a processor.

[0055] In a sixth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned motion strategy determination methods.

[0056] In the above-mentioned method, device, equipment, medium, product and rehabilitation management system for determining the motion strategy of the human body parameter measurement equipment, the motion strategy of the target object is determined based on the multiple candidate motion strategies and the digital twin model by obtaining the digital twin model of the target object. In the above-mentioned method, the digital twin model is a digital model trained based on the historical state data and individual data of the target object, taking into account the physical state and personalized characteristics of the target object. The obtained digital twin model can accurately simulate the target object, improve the fit between the determined motion strategy and the target object, and thus improve the rehabilitation effect achieved by the motion strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a structural schematic diagram of a rehabilitation management system in one embodiment;

[0058] Figure 2 A schematic diagram of a flow chart of a method for determining a motion strategy in one embodiment;

[0059] Figure 3 A schematic diagram of a flow chart of determining a motion strategy of a target object in one embodiment;

[0060] Figure 4 A schematic diagram of a flow chart for determining a motion strategy of a target object in another embodiment;

[0061] Figure 5 A schematic flow chart of a strategy determination method in another embodiment;

[0062] Figure 6 A schematic diagram of a process for determining whether a target object and a motion strategy match each other in one embodiment;

[0063] Figure 7 A schematic diagram of a flow chart for determining whether a target object and a motion strategy match each other in another embodiment;

[0064] Figure 8 A schematic diagram of a flow chart of adjusting a motion strategy in one embodiment;

[0065] Fig. 9 A schematic diagram of a process for training a digital twin model in an embodiment;

[0066] Fig.10 A schematic diagram of a process for determining historical state parameters in one embodiment;

[0067] Fig.11A schematic diagram of a process for determining an optimal motion strategy in one embodiment;

[0068] Fig.12 is a structural block diagram of a wearable monitoring device in one embodiment;

[0069] Fig.13 A schematic diagram of a target object wearing a wearable monitoring device in one embodiment;

[0070] Fig.14 is a structural block diagram of a vital sign collection device in one embodiment;

[0071] Fig.15 is a structural block diagram of an upper limb motion acquisition device in one embodiment;

[0072] Fig.16 It is a schematic diagram of the structure of a wrap-around upper limb motion acquisition device in one embodiment;

[0073] Fig.17 is a structural block diagram of a data transmission center in one embodiment;

[0074] Fig.18 This is a schematic diagram of an interface of a data transmission center in an embodiment;

[0075] Fig.19 A schematic diagram of a process in which a data aggregation unit receives data in one embodiment;

[0076] Fig. 20 Schematic diagram of the structure of a digital twin model in one embodiment;

[0077] Fig.21 A schematic diagram of a process for training a digital twin model in an embodiment;

[0078] Fig. 22 A schematic diagram of a process of adjusting a motion strategy in one embodiment;

[0079] Fig.23 is a structural block diagram of a rehabilitation management center in one embodiment;

[0080] Fig.24 It is a structural block diagram of a strategy determination device in one embodiment;

[0081] Fig.25 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0082] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0083] The method for determining a motion strategy for a human body parameter measurement device provided in the embodiment of the present application can be applied to Figure 1 In the rehabilitation management system shown. Among them, the wearable monitoring device 100 communicates with the digital twin device 200 through the network. The wearable monitoring device 100 is worn on the target object to obtain the state data of the target object. The digital twin device 200 is used to receive the historical state data of the target object sent by the wearable monitoring device 100, and train the digital twin model of the target object according to the historical state data and individual data of the target object, and then obtain multiple candidate motion strategies to determine the motion strategy of the target object according to the multiple candidate motion strategies and the digital twin model.

[0084] It should be noted that the wearable monitoring device is a human body parameter measurement device, which can be used to obtain human body parameters, which are human physiological parameters, and can include physical sign related data and motion related data. The human body parameter measurement equipment can be an independent device to obtain the human body parameters of the target type in a targeted manner, or it can be an integrated device constructed by multiple measurement units to obtain different types of human body parameters with diversity. Among them, the physical sign related data includes the original physical sign data collected by the human body parameter measurement equipment and the physical sign parameters determined based on the original physical sign data. The motion related data includes the original motion data collected by the human body parameter measurement equipment and the motion parameters determined based on the original motion data. Exemplarily, the original physical sign data may include electrocardiogram data and chest pulse wave, and the physical sign parameters may include the heart rate determined according to the electrocardiogram data, the blood oxygen saturation determined according to the chest pulse wave, and the blood pressure determined according to the electrocardiogram data and the chest pulse wave. The original motion data may include limb movement information, and the motion parameters may include the limb joint activity determined according to the limb movement information.

[0085] The method for determining a motion strategy for human body parameter measurement equipment provided in the embodiments of the present application is a method for determining a motion strategy that matches the human body parameters obtained by the human body parameter measurement equipment based on the human body parameters.

[0086] In one embodiment, Figure 2 As shown, a method for determining a motion strategy for a human body parameter measurement device is provided, and the method is applied to Figure 1 The digital twin device in the embodiment of the present invention is described by taking the digital twin device as a computer device as an example, including the following steps:

[0087] S210: Obtain multiple candidate motion strategies and digital twin models of the target object.

[0088] The digital twin model is a digital model trained based on the historical state data and individual data of the target object. The historical state data of the target object is used to characterize the physical state of the target object, and may include various data, such as physical sign data, motion data, etc. The individual data of the target object is used to characterize the personalized characteristics of the target user, and may include diagnosis and treatment information, sports preferences, etc. The candidate motion strategy is a candidate motion training task that can be used to improve the physical state of the target object.

[0089] It should be noted that digital twin (DT) is a virtual model of a physical entity created in a digital way. The digital twin model of the target object is a simulation body of the target object and can be used to simulate the physiological state of the target object.

[0090] Optionally, the computer device may obtain a plurality of pre-stored candidate motion strategies from a local or cloud, and obtain a trained digital twin model of the target object. The computer device may also obtain historical state data of the target object based on communication with the wearable monitoring device, and receive individual data of the target object input by the operator, so as to train the digital twin model of the target object based on the historical state data and individual data of the target object.

[0091] S220. Determine a motion strategy of the target object based on multiple candidate motion strategies and the digital twin model.

[0092] Optionally, after obtaining multiple candidate motion strategies and digital twin models of the target object, the computer device can input the multiple candidate motion strategies into the digital twin models respectively to implement each candidate motion strategy in the digital twin model, thereby simulating the process of the target object executing each candidate motion strategy, and then determining the motion strategy of the target object based on the information output by the digital twin model.

[0093] Optionally, the computer device may use the information output by the digital twin model that implements different candidate motion strategies as an evaluation criterion, compare the output information to determine the information that meets the requirements, and determine the motion strategy of the target object using the candidate motion strategy that obtains the information that meets the requirements.

[0094] In this embodiment, the motion strategy of the target object is determined based on the multiple candidate motion strategies and the digital twin model by obtaining multiple candidate motion strategies and the digital twin model. In the above method, the digital twin model is a digital model trained based on the historical state data and individual data of the target object, taking into account the physical state and personalized characteristics of the target object. The obtained digital twin model can accurately simulate the target object, improve the fit between the determined motion strategy and the target object, and thus improve the rehabilitation effect achieved by the motion strategy.

[0095] The candidate motion strategies are pre-set and the number is small. Based on this, in one embodiment, as Figure 3 As shown, the above S220, determining the motion strategy of the target object according to multiple candidate motion strategies and the digital twin model, includes:

[0096] S310: Input multiple candidate motion strategies into the digital twin model, and expand the multiple candidate motion strategies through the digital twin model to obtain a candidate motion strategy set.

[0097] The expansion of the plurality of candidate motion strategies is to obtain more and different candidate motion strategies on the basis of the plurality of candidate motion strategies, and the obtained more and different candidate motion strategies form a candidate motion strategy set.

[0098] Optionally, the computer device can input multiple candidate motion strategies into the digital twin model, and the digital twin model can generate new candidate motion strategies similar to the templates based on each candidate motion strategy. For example, new candidate motion strategies can be generated by modifying the motion intensity (such as motion type, motion duration, and motion amplitude) in the corresponding candidate motion strategies, and the old candidate motion strategies can be aggregated with the new candidate motion strategies to form a candidate motion strategy set.

[0099] Optionally, in the process of expanding and generating new candidate motion strategies, the computer device may receive individual data of the target object input by the operator, such as motion preferences, and the computer device may modify the existing candidate motion strategies according to the target object's motion preferences to generate new operation strategies. For example, if the target object's motion preferences are equipment sports, the computer device may modify the non-equipment sports in the existing candidate motion strategies to equipment sports to obtain new candidate motion strategies.

[0100] S320: Determine the motion strategy of the target object according to the candidate motion strategy set and the digital twin model.

[0101] Optionally, after obtaining the candidate motion strategy set, the computer device can implement each candidate motion strategy in the candidate motion strategy set in the digital twin model respectively to simulate the process of the target object executing each candidate motion strategy, and then determine the motion strategy of the target object in the candidate motion strategy set based on the information output by the digital twin model.

[0102] In this embodiment, multiple candidate motion strategies are input into the digital twin model, and the multiple candidate motion strategies are expanded through the digital twin model to obtain a candidate motion strategy set, and then the motion strategy of the target object is determined according to the candidate motion strategy set and the digital twin model. In the above method, by expanding the limited candidate motion strategies, a candidate motion strategy set including more candidate motion strategies is formed, so that the motion strategy of the target object can be determined in the candidate motion strategy set including more candidate motion strategies in the subsequent step, which expands the selection range of the motion strategy, thereby improving the fit between the determined motion strategy and the target object, and correspondingly improving the rehabilitation effect achieved by the motion strategy for the target object.

[0103] In practical applications, the reference physiological parameters output by the digital twin model when implementing the candidate motion strategy can be used as the criterion for determining the motion strategy of the target object. Figure 4 As shown, the above S320, determining the motion strategy of the target object according to the candidate motion strategy set and the digital twin model, includes:

[0104] S410, obtaining reference physiological parameters output by each candidate motion strategy in the candidate motion strategy set implemented by the digital twin model.

[0105] The reference physiological parameter is a preset type of physiological parameter, and the specific type is related to the rehabilitation goal. For example, when the rehabilitation goal of the above exercise strategy is cardiac rehabilitation, the reference physiological parameter can be a heart-related physical sign parameter, such as heart rate; when the rehabilitation goal of the above exercise strategy is lower limb exercise rehabilitation, the reference physiological parameter can be a lower limb-related exercise parameter, such as a lower limb joint range of motion parameter.

[0106] It should be noted that the digital twin model can be used to simulate the physiological state of the target object. Implementing the candidate motion strategy on the digital twin model is to simulate the target object to execute the candidate motion strategy through the digital twin model. The digital twin model can output the physiological parameters of the target object when simulating the target object to execute the candidate motion strategy.

[0107] Optionally, in the process of implementing each candidate motion strategy in the candidate motion strategy set to the digital twin model, the computer device may obtain preset physiological parameters in the physiological parameters output by the digital twin model when each candidate motion strategy set is implemented. For example, when the rehabilitation goal is cardiac rehabilitation, the computer device obtains the heart rate output by the digital twin model when each candidate motion strategy is implemented.

[0108] S420: Determine the motion strategy of the target object from the candidate motion strategy set according to the reference physiological parameters.

[0109] Among them, the reference physiological parameters can be used to evaluate the rehabilitation effect achieved by the target subject executing the candidate exercise strategy.

[0110] Optionally, after obtaining the reference physiological parameters of each candidate motion strategy implemented by the digital twin model, the computer device may compare each reference physiological parameter with a preset parameter range, and determine that the candidate motion strategy that obtains the reference physiological parameters that meet the preset parameter range is the motion strategy of the target object. Wherein, the reference physiological parameters meet the preset parameter range, indicating that the degree of fit between the target object and the corresponding candidate motion strategy is high, and the target object has a better rehabilitation effect when executing the corresponding candidate motion strategy; conversely, the reference physiological parameters do not meet the preset parameter range, indicating that the degree of fit between the target object and the corresponding candidate motion strategy is low, and the target object has a poor rehabilitation effect when executing the corresponding candidate motion strategy. For example, in the case where the reference physiological parameter is heart rate, the computer device may compare the heart rate corresponding to each candidate motion strategy with the preset heart rate range, and determine that the candidate motion strategy that obtains the heart rate that meets the preset heart rate range is the motion strategy of the target object.

[0111] Optionally, when there are multiple candidate exercise strategies for heart rates that meet the preset heart rate range, the computer device may further determine the fluctuation range of the comparison heart rate, and use the candidate exercise strategy with the smallest fluctuation range as the exercise strategy for the target object.

[0112] In this embodiment, the reference physiological parameters output by each candidate motion strategy in the candidate motion strategy set are obtained by implementing the digital twin model, and then the motion strategy of the target object is determined in the candidate motion strategy set according to the reference physiological parameters. In the above method, the reference physiological parameters output by the digital twin model can be used to evaluate the rehabilitation effect achieved by the target object executing the candidate motion strategy. Using the reference physiological parameters as a judgment indicator to determine the motion strategy of the target object in the candidate motion strategy set is to determine the candidate motion strategy with the best rehabilitation effect that can be achieved in the candidate motion strategy set for the target object, thereby improving the rehabilitation effect achieved by the determined motion strategy for the target object.

[0113] After obtaining the exercise strategy of the target object, the target object executes the exercise strategy, and the rehabilitation effect achieved by the exercise strategy for the target object varies with the execution of the exercise strategy by the target object. Figure 5 As shown, the above method also includes:

[0114] S510: Obtain target vital sign data and exercise completion degree of the target object during the execution of the exercise strategy.

[0115] The execution status of the movement strategy by the target object includes the target vital sign data and the degree of movement completion of the target object during the execution of the movement strategy.

[0116] Optionally, the computer device can obtain the state data of the target object in the process of executing the exercise strategy through a wearable monitoring device worn on the target object, and determine the target vital sign data of the target object based on the vital sign data in the state data, and determine the degree of completion of the exercise of the target object based on the motion data in the state data. For example, the heart rate of the target object is determined based on the electrocardiogram signal collected by the wearable monitoring device, and used as the target vital sign data of the target object; the limb movement amplitude of the target object is determined based on the limb movement information collected by the wearable monitoring device, and the limb movement amplitude is compared with the movement amplitude requirement to obtain the degree of completion of the exercise of the target object.

[0117] S520: Determine whether the target object and the exercise strategy match according to the target vital sign data and the degree of exercise completion.

[0118] Whether the target object and the motion strategy match refers to whether the target object and the currently executed motion strategy match, that is, whether the currently executed motion strategy of the target object is suitable for the target object.

[0119] Optionally, after obtaining the target vital sign data and the degree of exercise completion, the computer device may analyze the target vital sign data and the degree of exercise completion to determine whether the exercise strategy poses a safety risk to the target object based on the target vital sign data, and determine whether the exercise strategy is of appropriate difficulty for the target object based on the degree of exercise completion, thereby determining whether the target object matches the currently executed exercise strategy.

[0120] S530: When the target object and the motion strategy do not match, adjust the motion strategy to obtain an adjusted motion strategy.

[0121] The target object and the motion strategy do not match, indicating that the motion strategy currently executed by the target object is not suitable for the target object.

[0122] Optionally, when the target object and the motion strategy do not match, the computer device may determine the type of the mismatch to adjust the motion strategy according to the type of the mismatch to obtain an adjusted motion strategy so that the target object and the adjusted motion strategy match.

[0123] Optionally, the computer device may adjust at least one of the type, intensity, duration and frequency of the exercise strategy.

[0124] The types of mismatch include mismatch caused by target vital sign data, mismatch caused by exercise completion degree, and mismatch caused by both target vital sign data and exercise completion degree.

[0125] Optionally, when it is determined that the type of mismatch is caused by the target vital sign data, the computer device adjusts the motion strategy to improve the target vital sign data; when it is determined that the type of mismatch is caused by the degree of exercise completion, the computer device adjusts the motion strategy to improve the degree of exercise completion; when it is determined that the type of mismatch is caused by both the target vital sign data and the degree of exercise completion, the computer device adjusts the motion strategy to improve both the target vital sign data and the degree of exercise completion.

[0126] In this embodiment, by obtaining the target vital sign data and the degree of exercise completion of the target object during the execution of the exercise strategy, it is determined whether the target object and the exercise strategy match according to the target vital sign data and the degree of exercise completion, and then in the case where the target object and the exercise strategy do not match, the exercise strategy is adjusted to obtain the adjusted exercise strategy. In the above method, the exercise strategy is dynamically adjusted according to the target vital sign data and the degree of exercise completion actually generated by the target object executing the exercise strategy, which improves the accuracy of the adjustment, so that the exercise strategy can be updated in time based on the actual execution of the target object, thereby improving the rehabilitation effect achieved by the adjusted exercise strategy for the target object.

[0127] Whether the target object and the exercise strategy match is determined based on the comprehensive influence of two factors: the target physical sign data and the degree of exercise completion. Based on this, in one embodiment, Figure 6 As shown, the above S520, determining whether the target object and the exercise strategy match according to the target physical sign data and the degree of exercise completion, includes:

[0128] S610: Determine a safety risk assessment result of the target object according to the target vital sign data.

[0129] Among them, the safety risk assessment results are used to characterize whether the target object has safety risks that affect the life and health.

[0130] Optionally, the computer device compares the obtained target vital sign data with the corresponding security requirements to determine the security risk assessment result according to the comparison result. If the comparison result is that the target vital sign data meets the corresponding security requirements, the computer device determines that the security risk assessment result is that there is no security risk to the target object; conversely, if the comparison result is that the target vital sign data does not meet the corresponding security requirements, the computer device determines that the security risk assessment result is that there is a security risk to the target object.

[0131] S620: Determine the target object movement execution evaluation result according to the movement completion degree.

[0132] Among them, the motion execution evaluation result is used to characterize whether the target object meets the execution requirements set by the motion strategy.

[0133] Optionally, the computer device compares the obtained degree of completion of the movement with the corresponding execution requirement to determine the movement execution evaluation result according to the comparison result. If the comparison result is that the target vital sign data meets the corresponding execution requirement, the computer device determines that the movement execution evaluation result is that the target object meets the execution requirement; conversely, if the comparison result is that the target vital sign data does not meet the corresponding execution requirement, the computer device determines that the safety risk assessment result is that the target object does not meet the execution requirement.

[0134] S630: Determine whether the target object and the movement strategy match according to the security risk assessment result and the movement execution assessment result.

[0135] Optionally, after obtaining the assessment results of both the security risk assessment result and the motion execution assessment result, the computer device may comprehensively determine whether the target object and the motion strategy match based on the specific assessment conditions of the security risk assessment result and the motion execution assessment result.

[0136] In an alternative embodiment, Figure 7 As shown, the above S630, determining whether the target object and the motion strategy match according to the security risk assessment result and the motion execution assessment result, includes:

[0137] S710: When the security risk assessment result shows that there is no security risk for the target object and the motion execution assessment result shows that the target object meets the execution requirements, determine that the target object matches the motion strategy.

[0138] Among them, when the security risk assessment result is that there is no security risk for the target object, and the motion execution assessment result is that the target object meets the execution requirements, it is characterized that when the target object executes the motion strategy, it will not cause security risks to the target object, and at the same time, the motion strategy is of appropriate difficulty for the target object, indicating that the motion strategy is suitable for the target object.

[0139] Optionally, the computer device may determine that the target object matches the motion strategy when a security risk assessment result indicates that the target object does not have a security risk and a motion execution assessment result indicates that the target object meets execution requirements.

[0140] S720: When the security risk assessment result indicates that the target object has a security risk, or the motion execution assessment result indicates that the target object does not meet the execution requirements, the target object and the motion strategy do not match.

[0141] Among them, when the security risk assessment result is that the target object has a security risk, it indicates that the target object will cause a security risk when executing the motion strategy; and when the motion execution assessment result is that the target object does not meet the execution requirements, it indicates that the motion strategy is not suitable for the target object. Whether it will cause a security risk to the target object or the difficulty is not suitable for the target object, it means that the motion strategy is not suitable for the target object.

[0142] Optionally, the computer device may determine that the target object and the motion strategy do not match when the security risk assessment result is that the target object has a security risk, or the motion execution assessment result is that the target object does not meet the execution requirements, and at least one of the conditions is met.

[0143] In this embodiment, the safety risk assessment result of the target object is determined according to the target vital sign data, and the operation execution assessment result of the marked object is determined according to the degree of completion of the movement, and then whether the target object and the movement strategy match is determined according to the safety risk assessment result and the movement execution assessment result. Specifically, when the safety risk assessment result is that there is no safety risk for the target object, and the movement execution assessment result is that the target object meets the execution requirements, it is determined that the target object and the movement strategy match; when the safety risk assessment result is that there is a safety risk for the target object, or the movement execution assessment result is that the target object does not meet the execution requirements, it is determined that the target object and the movement strategy do not match. In the above method, the comprehensive judgment based on the two influencing factors of the target vital sign data and the degree of completion of the movement improves the comprehensiveness and accuracy of the judgment, and then improves the accuracy of the matching result of whether the target object and the movement strategy match.

[0144] In the case where the target object and the motion strategy do not match, the motion strategy that matches the target object can be obtained by adjusting the execution difficulty of the motion strategy. Based on this, in one embodiment, Figure 8 As shown, the above-mentioned step S530 adjusts the motion strategy to obtain the adjusted motion strategy, including:

[0145] S810: When the security risk assessment result indicates that the target object has a security risk, or the motion execution assessment result indicates that the target object does not meet the minimum execution requirement, the execution difficulty of the motion strategy is reduced to obtain a motion strategy with reduced execution difficulty.

[0146] When the security risk assessment result indicates that the target object has a security risk, it indicates that the execution difficulty of the motion strategy is too high, and the target object has a security risk caused by an abnormal physiological state during the execution process. In this case, the computer device can reduce the execution difficulty of the motion strategy and obtain a motion strategy with reduced execution difficulty, so that the target object can execute the motion strategy relatively easily, maintain a good and stable physiological state, and reduce the security risk.

[0147] Optionally, there are multiple ways to reduce the difficulty of executing the exercise strategy, which may include at least one of changing the type, reducing the intensity, reducing the duration, or reducing the frequency.

[0148] The execution requirements set by the exercise strategy include the minimum execution requirements. When the exercise execution evaluation result shows that the target object does not meet the minimum execution requirements, it indicates that the execution difficulty of the exercise strategy is too high, the actual exercise situation of the target object cannot meet the minimum standard, and the training effect of the exercise strategy cannot be fully exerted. In this case, the computer device can reduce the execution difficulty of the exercise strategy and obtain an exercise strategy with reduced execution difficulty, so that the target object can relatively easily execute the exercise strategy, achieve continuous exercise and improve the degree of exercise completion, so that the training effect of the exercise strategy can be fully exerted.

[0149] S820. When the security risk assessment result shows that the target object has no security risk and the motion execution assessment result shows that the target object exceeds the maximum execution requirement, the execution difficulty of the motion strategy is increased to obtain a motion strategy with increased execution difficulty.

[0150] The execution requirements set by the exercise strategy also include the highest execution requirements. When the safety risk assessment result shows that the target object does not have safety risks, and the exercise execution assessment result shows that the target object does not meet the minimum execution requirements, it indicates that the execution difficulty of the exercise strategy is too low. The target object will not have safety risks caused by abnormal physiological state during the execution process, and the actual exercise situation of the target object has exceeded the highest standard. Continuing to execute the exercise strategy will not have a training effect or the effect will not be obvious. In this case, the computer device can increase the execution difficulty of the exercise strategy and obtain an exercise strategy with increased execution difficulty, so that the target object can execute the exercise strategy relatively difficultly, so as to improve the training effect of the exercise strategy on the target object.

[0151] Optionally, there are multiple ways to increase the difficulty of executing the exercise strategy, which may include at least one of changing the type, increasing the intensity, increasing the duration, or increasing the frequency.

[0152] In this embodiment, when the safety risk assessment result shows that the target object has a safety risk, or the exercise execution assessment result shows that the target object does not meet the minimum execution requirement, the execution difficulty of the exercise strategy is reduced to obtain an exercise strategy with reduced execution difficulty; when the safety risk assessment result shows that the target object does not have a safety risk, and the exercise execution assessment result shows that the target object exceeds the maximum execution requirement, the execution difficulty of the exercise strategy is increased to obtain an exercise strategy with increased execution difficulty. In the above method, the exercise strategy is adjusted in a targeted manner based on the safety risk assessment result and the exercise execution assessment result, so that the adjusted exercise strategy is more suitable for the target object, thereby improving the rehabilitation effect achieved for the target object.

[0153] The digital twin model is trained using a variety of data. Based on this, in one embodiment, Fig. 9 As shown, the above method also includes:

[0154] S910: Determine historical state data of the target object according to historical vital sign data and historical motion data of the target object.

[0155] Optionally, the computer device can obtain the historical vital sign data and historical motion data of the target object through a wearable monitoring device worn by the target object, and determine relevant vital sign parameters based on the historical vital sign data and historical motion data, so as to use the historical vital sign data and historical motion data, and the determined relevant vital sign parameters as the historical status data of the target object.

[0156] S920: Determine individual data of the target object based on at least one of the diagnosis and treatment information, exercise habit information, and bone information of the target object.

[0157] Optionally, the diagnosis and treatment information of the target object may include medical diagnosis information, medical examination information or disease history information for the target object.

[0158] Optionally, the computer device receives at least one of the diagnosis and treatment information, exercise habit information and bone information of the target object input by the operator or extracted locally as the individual data of the target object.

[0159] S930: Input the historical status data and individual data of the target object into the initial digital model, and train to obtain a digital twin model.

[0160] Optionally, the computer device may input the historical state data and individual data of the target object acquired above into the initial digital model to train a digital twin model that matches the target object.

[0161] In an optional embodiment, if Fig.10As shown, the above S910, determining the historical state data of the target object according to the historical vital sign data and historical motion data of the target object, includes:

[0162] S1010. Determine historical vital sign parameters of the target object according to the historical vital sign data of the target object.

[0163] Among them, different types of vital sign data are used to determine different vital sign parameters.

[0164] Optionally, the historical vital sign data includes electrocardiogram data and chest pulse wave, and the computer device can determine the heart rate according to the electrocardiogram data, determine the blood oxygen saturation according to the chest pulse wave, and determine the blood pressure according to the electrocardiogram data and the chest pulse wave.

[0165] S1020: Determine historical motion parameters of the target object according to historical motion data of the target object.

[0166] Optionally, the historical motion data includes sensor data of limb motion, and the computer device can determine the joint mobility of the limb based on the sensor data of limb motion.

[0167] S1030: Determine the historical vital sign data, historical motion data, historical vital sign parameters, and historical motion parameters as historical state parameters of the target object.

[0168] Optionally, the computer device may summarize the acquired historical vital sign data, historical motion data, historical vital sign parameters and historical motion parameters, and determine them as historical state parameters of the target object.

[0169] In this embodiment, the historical state data of the target object is determined according to the historical vital sign data and historical motion data of the target object, and the individual data of the target object is determined according to at least one of the diagnosis and treatment information, exercise habit information and skeletal information of the target object, and then the historical state data and individual data of the target object are input into the initial digital model, and the digital twin model is obtained by training. Specifically, the historical vital sign parameters of the target object can be determined according to the historical vital sign data of the target object, and the historical motion parameters of the target object can be determined according to the historical motion data of the target object, so as to determine the historical vital sign data, historical motion data, historical vital sign parameters and historical motion parameters as the historical state parameters of the target object. In the above method, the vital sign data and motion data comprehensively and accurately reflect the physiological state of the target object, and the digital twin model of the target object is obtained by training based on the multi-dimensional data (vital sign data and motion data), which improves the matching degree between the target object and the digital twin model, and thus improves the accuracy of the motion strategy determined for the target object based on the digital twin model.

[0170] In one embodiment, Figure 1As shown, this embodiment also provides a rehabilitation management system, including: a wearable monitoring device 100 and a digital twin device 200 that communicate with each other.

[0171] Among them, the wearable monitoring device 100 is used to obtain the status data of the target object and send the status data of the target object to the digital twin device 200.

[0172] The digital twin device 200 is used to obtain multiple candidate motion strategies and a digital twin model of a target object, and determine the motion strategy of the target object based on the multiple candidate motion strategies and the digital twin model. The digital twin model is a digital model trained based on the historical state data and individual data of the target object.

[0173] It should be noted that the rehabilitation management system is used to implement the exercise strategy determination method in any of the above embodiments. The specific process is shown in the above embodiments and will not be repeated here.

[0174] Optionally, the process of the digital twin device 200 determining the motion strategy of the target object from multiple candidate motion strategies is as follows: Fig.11 The process of determining the best motion strategy is shown. After the digital twin device 200 inputs the candidate motion strategies 1, 2, ..., N into the digital twin model, the digital twin model can expand the original candidate motion strategy set composed of the candidate motion strategies 1, 2, ..., N to generate a new candidate motion strategy set. Each candidate motion strategy in the new candidate motion strategy set is implemented in the digital twin model to obtain the best motion strategy after traversal and optimization, that is, the motion strategy of the target object.

[0175] In one embodiment, if Fig.12 As shown, the wearable monitoring device 100 includes: a vital sign collection device 110 , a motion collection device 120 , and a data transmission center 130 communicating with the vital sign collection device 110 and the motion collection device 120 .

[0176] The vital sign collecting device 110 is used to obtain vital sign data of the target object and determine vital sign parameters of the target object according to the vital sign data.

[0177] The motion acquisition device 120 is used to obtain motion data of the target object and determine motion parameters of the target object according to the motion data.

[0178] The data transmission center 130 is used to receive vital sign data, motion data, vital sign parameters and motion parameters, and send the vital sign data, motion data, vital sign parameters and motion parameters as status data of the target object to the digital twin device 200.

[0179] Optionally, the vital sign collection device 110 and the motion collection device 120 may communicate with the data transmission center 130 by wired communication or wireless communication. In the case of wireless communication, the vital sign collection device 110, the motion collection device 120 and the data transmission center 130 include communication modules to realize wireless communication.

[0180] In one embodiment, the vital sign data includes an electrocardiogram signal and a chest pulse wave, and the vital sign parameters include an electrocardiogram parameter and a blood oxygen parameter. The vital sign acquisition device 110 includes an electrocardiogram signal acquisition unit and a pulse wave sensor.

[0181] Among them, the ECG signal acquisition unit is used to acquire the ECG signal of the target object and determine the ECG parameters of the target object; the pulse wave sensor is used to acquire the chest pulse wave of the target object and determine the blood oxygen parameters of the target object.

[0182] For example, Fig.13 As shown, the vital sign collection device 110 is disposed on the chest of the target object. For the convenience of wearing, the vital sign collection device 110 can be in the form of an electrocardiogram patch to be attached to the chest of the target object.

[0183] like Fig.14 As shown, the vital sign acquisition device 110 includes a signal acquisition unit 111, a pulse wave sensor 112, and a data processing module 113. The electrocardiogram signal acquisition unit 111 and the pulse wave sensor 112 are respectively connected to the data processing module 113 for communication.

[0184] Among them, the ECG signal acquisition unit 111 is used to collect a single-lead / three-lead electrocardiogram (ECG) of the target object. The pulse wave sensor 112 can be a photoplethysmogram sensor, which is used to obtain the photoplethysmogram (PPG) at the chest of the target object. The data processing device 113 is used to determine the heart rate of the target object according to the ECG data, determine the blood oxygen saturation according to the PPG data, and determine the blood pressure according to the ECG data and the PPG data, and send the ECG data, PPG data, heart rate, blood oxygen saturation and blood pressure to the data transmission center 130.

[0185] In one embodiment, the motion data includes limb motion data, and the motion parameters include joint range of motion. The motion acquisition device 120 includes an upper limb motion acquisition device and a lower limb motion acquisition device.

[0186] Wherein, the upper limb motion acquisition device and the lower limb motion acquisition device both include motion sensors for acquiring limb motion data of the target object and determining the joint activity of the target object.

[0187] For example, Fig.13 As shown, the upper limb motion collection device in the motion collection device 120 is set on the upper limbs of the target object in the form of left elbow pads and right elbow pads, and the lower limb motion collection device is set on the lower limbs of the target object in the form of left knee pads and right knee pads. For easy wearing, the motion collection device 120 can be set around the upper and lower limbs of the target object in the form of Velcro.

[0188] The upper limb motion collection device and the lower limb motion collection device in the motion collection device 120 have the same structure. Fig.15 As shown, taking the upper limb motion acquisition device 121 as an example, it includes a motion sensing module 1211 , a power module 1212 and a data processing module 1213 .

[0189] Among them, the motion sensing module 1211 is an inertial measurement unit (IMU), which includes a nine-axis inertial sensor. The motion sensing module 1211 is used to obtain the limb motion data of the target object, such as the IMU data of the upper limbs, which may specifically include the data detected by the three-axis acceleration, the three-axis gyroscope, and the three-axis magnetometer. The power supply module 1212 is used to power the entire upper limb motion acquisition device 121, and the data processing module 1213 is used to determine the joint activity of the target object according to the limb motion data collected by the motion sensing module 1211, and send the limb motion data and joint activity to the data transmission center 130.

[0190] like Fig.16 As shown, the upper limb motion acquisition device 121 includes two IMUs. After being wrapped around the upper limbs of the target object, the two IMUs are distributed on both sides of the upper limbs.

[0191] For example, Fig.13 As shown, the data transmission center 130 is disposed on the wrist of the target object, and specifically may be a smart wristband including a hub.

[0192] The data transmission center 130 is used to communicate with the digital twin device 200 to send data to the digital twin device 200, and is also used to determine the risk status of the target object based on the received vital sign data, and to issue an alarm when it is determined that the target object has a safety risk. There are many ways to implement the alarm, such as issuing an alarm tone, or sending an alarm message to a pre-stored emergency contact / emergency center.

[0193] For example, Fig.17As shown, the data transmission center 130 includes a data aggregation unit 131 and a motion display unit 132. The data aggregation unit 131 is used to receive and store data sent by the vital sign collection device 110 and the motion collection device 120, or send the received data to the digital twin device 200 in response to the acquisition requirements of the digital twin device 200. The motion display unit 132 is used to display the execution information when the target object executes the motion strategy. Fig.18 As shown, the displayed execution information includes the target object's real-time heart rate, blood oxygen and joint mobility, and may also include related information such as the number of alarms, exercise duration and exercise load plan.

[0194] like Fig.19 As shown, the data received by the data aggregation unit 131 includes ECG data, blood oxygen and blood pressure acquired by the vital sign acquisition device 110, as well as upper limb joint range of motion and upper limb joint IMU data acquired by the upper limb motion acquisition device 121, and lower limb joint range of motion and lower limb joint IMU data acquired by the lower limb motion acquisition device 122.

[0195] Since the sampling frequencies of different data vary greatly, the data aggregation unit 1131 can also perform frequency unification processing on the data. For example, under normal circumstances, the sampling frequencies of ECG data and IMU data are relatively high, while the sampling frequencies of heart rate, blood oxygen, blood pressure, and joint mobility are relatively low. The data aggregation unit 1131 can downsample the ECG data and IMU data, and upsample the heart rate, blood oxygen, blood pressure, and joint mobility to obtain ECG data, IMU data, heart rate, blood oxygen, blood pressure, and joint mobility with unified frequencies.

[0196] In one embodiment, the digital twin model includes a convolutional neural network, a bidirectional long short-term memory network, a cascade neural network, a fully connected neural network, and a normalized network connected in sequence.

[0197] For example, Fig. 20 As shown, the ECG raw data is the historical ECG data collected by the vital sign acquisition device 110, and the left and right elbow pad IMU raw data and the left and right knee pad IMU raw data are the historical motion data collected by the motion acquisition device 120. After the historical ECG data and the historical motion data are feature extracted by the convolutional neural network, the extracted feature information is input into the bidirectional long short-term memory network for processing, and then the target object's historical vital sign parameters, historical motion parameters and individual data are taken as additional inputs, and together with the data output by the bidirectional long short-term memory network, they are sequentially input into the cascade neural network, the fully connected neural network and the normalized network for processing.

[0198] For example, Fig.21As shown, the digital twin device 200 can use the historical ECG data and historical motion data collected by the wearable monitoring device 100 as the historical status data of the target object, and the medical diagnosis information, medical examination information, disease history information, life and exercise habit information, and bone information input by the operator as the individual data of the target object, so as to use the historical status data and individual data of the target object as the input of the initial digital model, train the initial digital model, and obtain the digital twin model of the target object.

[0199] For example, Fig. 22 As shown in FIG. 1 , taking cardiac rehabilitation as an example, the rehabilitation management system performs a single adjustment on the target object's exercise strategy as follows:

[0200] When the target object is executing the exercise strategy, the ECG device in the rehabilitation management system obtains the target object's vital sign data, and the left and right knee pads and left and right elbow pads in the rehabilitation management system obtain the target object's movement data and input them into the digital twin model. The digital twin model determines the target object's heart risk identification based on the feature data, and determines the target object's exercise completion degree based on the movement data. When the target object is executing the exercise strategy for training, the exercise strategy currently executed by the target object is adaptively adjusted once based on the recognition results of heart risk identification and the exercise completion degree.

[0201] In one embodiment, Fig.23 As shown, this embodiment also provides a rehabilitation management center, including:

[0202] Multiple wearable monitoring devices 100, a data gateway 300, a database 400, a server 500 and an application terminal 600.

[0203] Among them, different wearable monitoring devices 100 correspond to different target objects, and are used to obtain the status data of the corresponding target objects, and transmit all the status data to the data gateway 300, and then the data gateway 300 stores the status data of each target object in the cloud database 400. The server 500 can obtain the status data of different target objects in the database 400 according to actual needs, so as to train the digital twin model of the target object, and send the digital twin model of the target object to the corresponding application terminal 600 for application.

[0204] The application process of the digital twin model is detailed in the aforementioned embodiment and will not be repeated here.

[0205] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0206] Based on the same inventive concept, the embodiment of the present application also provides a motion strategy determination device for implementing the motion strategy determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more motion strategy determination devices provided below can refer to the limitations of the motion strategy determination method above, and will not be repeated here.

[0207] In one embodiment, Fig.24 As shown, a motion strategy determination device is provided, including: a data acquisition module 2401 and a strategy determination module 2402, wherein:

[0208] The data acquisition module 2401 is used to acquire a plurality of candidate motion strategies and a digital twin model of a target object; the digital twin model is a digital model trained based on the historical state data and individual data of the target object;

[0209] The strategy determination module 2402 is used to determine the motion strategy of the target object based on multiple candidate motion strategies and the digital twin model.

[0210] In one embodiment, the policy determination module 2402 includes:

[0211] An expansion submodule, used for inputting a plurality of candidate motion strategies into the digital twin model, and expanding the plurality of candidate motion strategies through the digital twin model to obtain a candidate motion strategy set;

[0212] The strategy submodule is used to determine the motion strategy of the target object based on the candidate motion strategy set and the digital twin model.

[0213] In one embodiment, the policy submodule includes:

[0214] A reference unit, used to obtain reference physiological parameters output by each candidate motion strategy in the candidate motion strategy set implemented by the digital twin model;

[0215] The determination unit is used to determine the motion strategy of the target object in the candidate motion strategy set according to the reference physiological parameters.

[0216] In one embodiment, the above device further comprises:

[0217] A data acquisition module is used to acquire target vital sign data and the degree of movement completion of the target object during the execution of the movement strategy;

[0218] A matching confirmation module is used to determine whether the target object and the exercise strategy match according to the target vital sign data and the degree of exercise completion;

[0219] The strategy adjustment module is used to adjust the motion strategy when the target object and the motion strategy do not match, so as to obtain the adjusted motion strategy.

[0220] In one embodiment, the matching confirmation module includes:

[0221] A risk assessment submodule is used to determine the safety risk assessment result of the target object based on the target vital sign data;

[0222] A motion evaluation submodule is used to determine the target object operation execution evaluation result according to the degree of motion completion;

[0223] The result determination submodule is used to determine whether the target object and the motion strategy match according to the security risk assessment result and the motion execution assessment result.

[0224] In one embodiment, the result determination submodule includes:

[0225] A matching unit, for determining that the target object matches the motion strategy when the security risk assessment result is that the target object does not have a security risk and the motion execution assessment result is that the target object meets the execution requirements;

[0226] The mismatch unit is used to determine that the target object and the motion strategy do not match when the security risk assessment result shows that the target object has a security risk, or the motion execution assessment result shows that the target object does not meet the execution requirements.

[0227] In one embodiment, the policy adjustment module includes:

[0228] The difficulty reduction submodule is used to reduce the execution difficulty of the motion strategy and obtain a motion strategy with reduced execution difficulty when the security risk assessment result shows that the target object has a security risk, or the motion execution assessment result shows that the target object does not meet the minimum execution requirement;

[0229] The difficulty increasing submodule is used to increase the execution difficulty of the motion strategy when the security risk assessment result shows that the target object has no security risk and the motion execution assessment result shows that the target object exceeds the maximum execution requirement, thereby obtaining a motion strategy with increased execution difficulty.

[0230] In one embodiment, the above device further comprises:

[0231] A state determination module, used to determine historical state data of the target object based on historical vital sign data and historical motion data of the target object;

[0232] An individual determination module, used to determine individual data of the target object according to at least one of the diagnosis and treatment information, exercise habit information and bone information of the target object;

[0233] The model training module is used to input the historical status data and individual data of the target object into the initial digital model and train it to obtain the digital twin model.

[0234] In one embodiment, the state determination module includes:

[0235] A physical sign submodule, used to determine historical physical sign parameters of the target object according to the historical physical sign data of the target object;

[0236] A motion submodule, used to determine historical motion parameters of the target object according to historical motion data of the target object;

[0237] The state submodule is used to determine the historical vital sign data, historical motion data, historical vital sign parameters and historical motion parameters as the historical state parameters of the target object.

[0238] Each module in the above-mentioned motion strategy determination device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0239] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.25As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for determining a motion strategy is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0240] Those skilled in the art will understand that Fig.25 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0241] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0242] A plurality of candidate motion strategies and a digital twin model of a target object are obtained; the digital twin model is a digital model trained based on historical state data and individual data of the target object; and the motion strategy of the target object is determined based on the plurality of candidate motion strategies and the digital twin model.

[0243] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0244] Multiple candidate motion strategies are input into the digital twin model, and the multiple candidate motion strategies are expanded through the digital twin model to obtain a candidate motion strategy set; the motion strategy of the target object is determined according to the candidate motion strategy set and the digital twin model.

[0245] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0246] Obtain the reference physiological parameters output by each candidate motion strategy in the candidate motion strategy set implemented by the digital twin model; determine the motion strategy of the target object in the candidate motion strategy set based on the reference physiological parameters.

[0247] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0248] Obtain target vital sign data and the degree of movement completion of the target object during the execution of the movement strategy; determine whether the target object and the movement strategy match according to the target vital sign data and the degree of movement completion; if the target object and the movement strategy do not match, adjust the movement strategy to obtain the adjusted movement strategy.

[0249] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0250] Determine the safety risk assessment result of the target object based on the target vital sign data; determine the operation execution assessment result of the target object based on the degree of completion of the movement; determine whether the target object and the movement strategy match based on the safety risk assessment result and the movement execution assessment result.

[0251] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0252] When the security risk assessment result shows that there is no security risk for the target object, and the motion execution assessment result shows that the target object meets the execution requirements, it is determined that the target object and the motion strategy match; when the security risk assessment result shows that there is a security risk for the target object, or the motion execution assessment result shows that the target object does not meet the execution requirements, it is determined that the target object and the motion strategy do not match.

[0253] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0254] When the security risk assessment result shows that there is a security risk for the target object, or the motion execution assessment result shows that the target object does not meet the minimum execution requirements, the execution difficulty of the motion strategy is reduced to obtain a motion strategy with reduced execution difficulty; when the security risk assessment result shows that there is no security risk for the target object, and the motion execution assessment result shows that the target object exceeds the maximum execution requirements, the execution difficulty of the motion strategy is increased to obtain a motion strategy with increased execution difficulty.

[0255] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0256] Determine the historical status data of the target object based on the historical vital sign data and historical motion data of the target object; determine the individual data of the target object based on at least one of the diagnosis and treatment information, exercise habit information and bone information of the target object; input the historical status data and individual data of the target object into the initial digital model, and train to obtain a digital twin model.

[0257] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0258] Determine the historical vital sign parameters of the target object according to the historical vital sign data of the target object; determine the historical motion parameters of the target object according to the historical motion data of the target object; determine the historical vital sign data, historical motion data, historical vital sign parameters and historical motion parameters as the historical state parameters of the target object.

[0259] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0260] Obtain multiple candidate motion strategies and a digital twin model of the target object; the digital twin model is a digital model trained based on historical state data and individual data of the target object; determine the motion strategy of the target object based on the multiple candidate motion strategies and the digital twin model.

[0261] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0262] Multiple candidate motion strategies are input into the digital twin model, and the multiple candidate motion strategies are expanded through the digital twin model to obtain a candidate motion strategy set; the motion strategy of the target object is determined according to the candidate motion strategy set and the digital twin model.

[0263] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0264] Obtain the reference physiological parameters output by each candidate motion strategy in the candidate motion strategy set implemented by the digital twin model; determine the motion strategy of the target object in the candidate motion strategy set based on the reference physiological parameters.

[0265] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0266] Obtain target vital sign data and the degree of movement completion of the target object during the execution of the movement strategy; determine whether the target object and the movement strategy match according to the target vital sign data and the degree of movement completion; if the target object and the movement strategy do not match, adjust the movement strategy to obtain the adjusted movement strategy.

[0267] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0268] Determine the safety risk assessment result of the target object based on the target vital sign data; determine the operation execution assessment result of the target object based on the degree of completion of the movement; determine whether the target object and the movement strategy match based on the safety risk assessment result and the movement execution assessment result.

[0269] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0270] When the security risk assessment result shows that there is no security risk for the target object, and the motion execution assessment result shows that the target object meets the execution requirements, it is determined that the target object and the motion strategy match; when the security risk assessment result shows that there is a security risk for the target object, or the motion execution assessment result shows that the target object does not meet the execution requirements, it is determined that the target object and the motion strategy do not match.

[0271] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0272] When the security risk assessment result shows that there is a security risk for the target object, or the motion execution assessment result shows that the target object does not meet the minimum execution requirements, the execution difficulty of the motion strategy is reduced to obtain a motion strategy with reduced execution difficulty; when the security risk assessment result shows that there is no security risk for the target object, and the motion execution assessment result shows that the target object exceeds the maximum execution requirements, the execution difficulty of the motion strategy is increased to obtain a motion strategy with increased execution difficulty.

[0273] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0274] Determine the historical status data of the target object based on the historical vital sign data and historical motion data of the target object; determine the individual data of the target object based on at least one of the diagnosis and treatment information, exercise habit information and bone information of the target object; input the historical status data and individual data of the target object into the initial digital model, and train to obtain a digital twin model.

[0275] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0276] Determine the historical vital sign parameters of the target object according to the historical vital sign data of the target object; determine the historical motion parameters of the target object according to the historical motion data of the target object; determine the historical vital sign data, historical motion data, historical vital sign parameters and historical motion parameters as the historical state parameters of the target object.

[0277] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0278] Obtain multiple candidate motion strategies and a digital twin model of the target object; the digital twin model is a digital model trained based on historical state data and individual data of the target object; determine the motion strategy of the target object based on the multiple candidate motion strategies and the digital twin model.

[0279] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0280] Multiple candidate motion strategies are input into the digital twin model, and the multiple candidate motion strategies are expanded through the digital twin model to obtain a candidate motion strategy set; the motion strategy of the target object is determined according to the candidate motion strategy set and the digital twin model.

[0281] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0282] Obtain the reference physiological parameters output by each candidate motion strategy in the candidate motion strategy set implemented by the digital twin model; determine the motion strategy of the target object in the candidate motion strategy set based on the reference physiological parameters.

[0283] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0284] Obtain target vital sign data and the degree of movement completion of the target object during the execution of the movement strategy; determine whether the target object and the movement strategy match according to the target vital sign data and the degree of movement completion; if the target object and the movement strategy do not match, adjust the movement strategy to obtain the adjusted movement strategy.

[0285] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0286] Determine the safety risk assessment result of the target object based on the target vital sign data; determine the operation execution assessment result of the target object based on the degree of completion of the movement; determine whether the target object and the movement strategy match based on the safety risk assessment result and the movement execution assessment result.

[0287] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0288] When the security risk assessment result shows that there is no security risk for the target object, and the motion execution assessment result shows that the target object meets the execution requirements, it is determined that the target object and the motion strategy match; when the security risk assessment result shows that there is a security risk for the target object, or the motion execution assessment result shows that the target object does not meet the execution requirements, it is determined that the target object and the motion strategy do not match.

[0289] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0290] When the security risk assessment result shows that there is a security risk for the target object, or the motion execution assessment result shows that the target object does not meet the minimum execution requirements, the execution difficulty of the motion strategy is reduced to obtain a motion strategy with reduced execution difficulty; when the security risk assessment result shows that there is no security risk for the target object, and the motion execution assessment result shows that the target object exceeds the maximum execution requirements, the execution difficulty of the motion strategy is increased to obtain a motion strategy with increased execution difficulty.

[0291] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0292] Determine the historical status data of the target object based on the historical vital sign data and historical motion data of the target object; determine the individual data of the target object based on at least one of the diagnosis and treatment information, exercise habit information and bone information of the target object; input the historical status data and individual data of the target object into the initial digital model, and train to obtain a digital twin model.

[0293] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0294] Determine the historical vital sign parameters of the target object according to the historical vital sign data of the target object; determine the historical motion parameters of the target object according to the historical motion data of the target object; determine the historical vital sign data, historical motion data, historical vital sign parameters and historical motion parameters as the historical state parameters of the target object.

[0295] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0296] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0297] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0298] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining a motion strategy for human body parameter measurement equipment, characterized in that: The method comprises: Acquire a plurality of candidate motion strategies and a digital twin model of a target object; the digital twin model is a digital model trained based on historical state data and individual data of the target object; Determine a motion strategy of the target object based on the multiple candidate motion strategies and the digital twin model.

2. The method according to claim 1, characterized in that Determining the motion strategy of the target object according to the multiple candidate motion strategies and the digital twin model includes: Inputting the multiple candidate motion strategies into the digital twin model, and expanding the multiple candidate motion strategies through the digital twin model to obtain a candidate motion strategy set; The motion strategy of the target object is determined according to the candidate motion strategy set and the digital twin model.

3. The method according to claim 2, characterized in that Determining the motion strategy of the target object according to the candidate motion strategy set and the digital twin model includes: Obtaining reference physiological parameters output by the digital twin model when implementing each candidate motion strategy in the candidate motion strategy set; The motion strategy of the target object is determined in the candidate motion strategy set according to the reference physiological parameters.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Acquiring target vital sign data and exercise completion degree of the target object during the execution of the exercise strategy; Determining whether the target object and the exercise strategy match according to the target vital sign data and the degree of exercise completion; In the case where the target object and the motion strategy do not match, the motion strategy is adjusted to obtain an adjusted motion strategy.

5. The method according to claim 4, characterized in that The determining whether the target object matches the exercise strategy according to the target vital sign data and the exercise completion degree includes: Determining a safety risk assessment result of the target object according to the target vital sign data; Determining the target object operation execution evaluation result according to the movement completion degree; Determine whether the target object matches the motion strategy according to the security risk assessment result and the motion execution assessment result.

6. The method according to claim 5, characterized in that The determining whether the target object matches the motion strategy according to the security risk assessment result and the motion execution assessment result includes: When the security risk assessment result is that there is no security risk to the target object, and the motion execution assessment result is that the target object meets the execution requirements, determining that the target object matches the motion strategy; When the security risk assessment result indicates that the target object has a security risk, or the motion execution assessment result indicates that the target object does not meet the execution requirement, it is determined that the target object does not match the motion strategy.

7. The method according to claim 5, characterized in that The step of adjusting the movement strategy to obtain an adjusted movement strategy includes: When the security risk assessment result indicates that the target object has a security risk, or the movement execution assessment result indicates that the target object does not meet the minimum execution requirement, the execution difficulty of the movement strategy is reduced to obtain the movement strategy with reduced execution difficulty; When the security risk assessment result is that there is no security risk to the target object, and the motion execution assessment result is that the target object exceeds the maximum execution requirement, the execution difficulty of the motion strategy is increased to obtain the motion strategy with increased execution difficulty.

8. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Determining historical state data of the target object according to historical vital sign data and historical motion data of the target object; Determining individual data of the target object according to at least one of the diagnosis and treatment information, exercise habit information, and bone information of the target object; The historical state data of the target object and the individual data are input into the initial digital model, and the digital twin model is obtained by training.

9. The method according to claim 8, characterized in that The acquiring of historical vital sign data and historical motion data of the target object and determining historical state data of the target object includes: Determining historical vital sign parameters of the target object according to the historical vital sign data of the target object; Determine the historical motion parameters of the target object according to the historical motion data of the target object The historical vital sign data, the historical motion data, the historical vital sign parameters and the historical motion parameters are determined as historical state parameters of the target object.

10. A rehabilitation management system, characterized in that: The system includes: a wearable monitoring device and a digital twin device that communicate with each other; Wherein, the wearable monitoring device is used to obtain the status data of the target object and send the status data of the target object to the digital twin device; The digital twin device is used to obtain multiple candidate motion strategies and a digital twin model of the target object, and determine the motion strategy of the target object based on the multiple candidate motion strategies and the digital twin model; the digital twin model is a digital model trained based on the historical state data and individual data of the target object.

11. The system according to claim 10, characterized in that The wearable monitoring device includes: a vital sign collection device, a motion collection device, and a data transmission center communicating with the vital sign collection device and the motion collection device; The physical sign collecting device is used to obtain physical sign data of the target object and determine the physical sign parameters of the target object according to the physical sign data; The motion acquisition device is used to obtain motion data of the target object and determine motion parameters of the target object according to the motion data; The data transmission center is used to receive the vital sign data, the motion data, the vital sign parameters and the motion parameters, and send the vital sign data, the motion data, the vital sign parameters and the motion parameters as the status data of the target object to the digital twin device.

12. The system according to claim 11, characterized in that The physical sign data includes an electrocardiogram signal and a photoplethysmogram; the physical sign parameters include an electrocardiogram parameter and a blood oxygen parameter; the physical sign acquisition device includes an electrocardiogram signal acquisition unit and a pulse wave sensor; The ECG signal acquisition unit is used to acquire the ECG signal of the target object and determine the ECG parameters of the target object; The pulse wave sensor is used to collect the chest pulse wave of the target object and determine the blood oxygen parameter of the target object.

13. The system according to claim 11, characterized in that The motion data includes limb motion data; the motion parameters include joint range of motion; the motion acquisition device includes an upper limb motion acquisition device and a lower limb motion acquisition device; The upper limb motion acquisition device and the lower limb motion acquisition device both include motion sensors for acquiring limb motion data of the target object and determining the joint activity of the target object.

14. The system according to any one of claims 10 to 13, characterized in that: The digital twin model includes a sequentially connected convolutional neural network, a bidirectional long short-term memory network, a cascade neural network, a fully connected neural network and a normalized network.

15. A motion strategy determination device for human body parameter measurement equipment, characterized in that: The device comprises: A data acquisition module, used to acquire a plurality of candidate motion strategies and a digital twin model of a target object; the digital twin model is a digital model trained based on historical state data and individual data of the target object; A strategy determination module is used to determine the motion strategy of the target object based on the multiple candidate motion strategies and the digital twin model.

16. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

18. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images