Remote rehabilitation training system based on nine-axis and pressure sensor

Abstract

The present invention discloses a remote rehabilitation training system based on nine axes and pressure sensors, which relates to the field of electronic digital data processing, including a target course selection perception module, a target course verification data statistics module, a rehabilitation data matching module and a remote rehabilitation training guidance module. The present invention can realize high-precision motion data capture and real-time analysis through nine axes and pressure sensors, and support users to perform personalized rehabilitation training in a remote environment. The system can perceive the rehabilitation training courses selected by the user and perform remote rehabilitation training according to the selected rehabilitation training courses, simultaneously match and comprehensively analyze rehabilitation data, and simultaneously provide accurate training guidance, providing effective support and guarantee for the user's rehabilitation training.

Description

Technical Field

[0001] The invention relates to the field of electronic digital data processing, in particular to a remote rehabilitation training system based on nine axes and a pressure sensor. Background Art

[0002] During rehabilitation training, users' physiological indicators and exercise performance are monitored by sensors. Using wireless communication technology, users can conduct real-time remote rehabilitation training without being restricted or constrained by geographical location. They can adjust their training status and methods based on real-time feedback.

[0003] The prior art, such as the invention patent with announcement number: CN112451306B, is a VR-based arm muscle rehabilitation training system, including: muscle rehabilitation equipment, used to perform training actions according to rehabilitation training type instructions, and collect motion data corresponding to the training actions; rehabilitation training evaluation equipment, used to process and analyze the motion data to obtain evaluation data characterizing the user's arm muscle indicators; computer equipment, used to generate virtual training information according to one or more of the rehabilitation training type, the motion data, and the evaluation data; virtual reality equipment, used to display the rehabilitation training process based on the virtual training information. The above system displays the effect and rehabilitation status of the user's arm muscles in the rehabilitation training process in a visual form on the virtual reality device, thereby improving the user's sense of participation and interest, and stimulating the user's senses through visual stimulation, thereby stimulating the enthusiasm and initiative of rehabilitation training.

[0004] The prior art, such as the invention patent with announcement number: CN113164314B, is an immersive upper limb rehabilitation training system, including: a dual-arm rehabilitation robot, a base, a position tracker, a VR helmet, a data force feedback glove, a host computer control center, and a passive compliant end effector. The dual-arm rehabilitation robot is installed on the base, and drives the user's arm movement through two passive compliant end effectors; the visual sensor is used to record the movement of the user's upper limbs and feedback control the movement of the dual-arm rehabilitation robot; the position tracker is used to collect the user's arm position and posture information in real time and transmit it to the host computer control center; the VR helmet is worn on the user's head; the data force feedback glove is worn on the user's hand; the passive compliant end effector is worn on the user's forearm and upper arm respectively; the host computer control center is used to give quantitative indicators and control the display of virtual training pictures, thereby realizing the safety, scientificity, fun, systematization and dataization of the upper limb rehabilitation training process.

[0005] Based on the above solutions, it can be seen that the cost of hardware equipment such as VR equipment and rehabilitation robots is relatively high, which limits the popularization and application for users or medical institutions with limited economic conditions. Secondly, different users have different physiological indicators. Relying solely on a single sensor monitoring system cannot adapt to the individual differences of each user, resulting in low efficiency of rehabilitation training and failure to effectively meet the rehabilitation training needs of users. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a remote rehabilitation training system based on nine axes and a pressure sensor. To achieve the above purpose, the present invention is implemented through the following technical solutions: A remote rehabilitation training system based on nine axes and a pressure sensor, comprising:

[0007] The target course selection perception module is used to perceive the rehabilitation training courses selected by the user on the rehabilitation training platform and mark them as target courses;

[0008] The target course verification data statistics module is used to divide the target course into sub-course periods and count the initial training verification data of each sub-course period;

[0009] Based on the training verification data of each rehabilitation training course stored in the rehabilitation training platform, the training verification data of the target course is collected;

[0010] Based on the divided sub-course periods, the training verification data of each sub-course period is counted from the training verification data of the target course, and recorded as the initial training verification data of each sub-course period;

[0011] The initial training verification data for each sub-course period includes the expected value of the sensing heading angle, the expected value of the sensing pitch angle, the expected value of the sensing roll angle, and the expected value of the sensing acceleration of the nine-axis sensor at each position corresponding to each sub-course period, and also includes the expected value of the sensing pressure of the pressure sensor at each position corresponding to each sub-course period.

[0012] The rehabilitation data matching module is used to collect the archived physiological data of the user on the rehabilitation training platform and input it into the platform data processing center, and then process it through the platform data processing center to match and obtain the user's rehabilitation training comparison data set;

[0013] The remote rehabilitation training guidance module is used to provide remote rehabilitation training for users according to the target course, and conducts comprehensive perception analysis based on the sensor training data of each sub-course period and the user's rehabilitation training comparison data set, locks the demand-guided sub-course period, and guides the user to correct the training movements.

[0014] As a preferred technical solution, the processing is performed by the platform data processing center, specifically including:

[0015] Based on the user's archived physiological data on the rehabilitation training platform, the archived physiological data includes heart rate, blood pressure, blood oxygen saturation and body temperature;

[0016] Obtaining basic user information from the rehabilitation training platform, wherein the basic user information specifically includes height, weight and age;

[0017] Extracting reference physiological data from the rehabilitation training platform and processing it with the archived physiological data to generate a first rehabilitation training verification value, wherein the first rehabilitation training verification value is used to characterize the user's physiological profile and serves as a matching numerical basis for the rehabilitation training comparison data set;

[0018] The reference basic information is extracted from the rehabilitation training platform and processed with the user basic information to generate a second rehabilitation training verification value, which is used to quantify the user basic information and simultaneously serves as a matching numerical basis for the rehabilitation training comparison data set.

[0019] As a preferred technical solution, the matching obtains the user's rehabilitation training comparison data set, specifically including:

[0020] generating a comprehensive rehabilitation training verification value for the user based on the first rehabilitation training verification value and the second rehabilitation training verification value, wherein the comprehensive rehabilitation training verification value is used to comprehensively represent the archived physiological data and basic information of the user;

[0021] According to the user's rehabilitation training comprehensive verification value, the rehabilitation training comparison data set corresponding to each comprehensive verification value interval stored in the rehabilitation training platform is matched to obtain the user's rehabilitation training comparison data set;

[0022] The rehabilitation training comparison data set includes a rehabilitation training sensor critical score value, a heading angle allowable error value, a pitch angle allowable error value, a roll angle allowable error value, an acceleration allowable error value and a pressure allowable error value.

[0023] As a preferred technical solution, the comprehensive perception analysis based on the sensor training data of each sub-course period and the user's rehabilitation training comparison data set specifically includes:

[0024] Count several moments in each sub-course period, and obtain the sensor training data at each moment in each sub-course period, specifically including the sensing heading angle value, sensing pitch angle value, sensing roll angle value and sensing acceleration value of the nine-axis sensor at each position corresponding to each moment in each sub-course period, and also including the sensing pressure value of the pressure sensor at each position corresponding to each moment in each sub-course period;

[0025] Based on the sensor training data at each moment in each sub-course period, combined with the initial training verification data of each sub-course period and the user's rehabilitation training comparison data set, comprehensive processing is performed to generate the rehabilitation progress abnormality score value of each sub-course period.

[0026] As a preferred technical solution, the locking requirement guides the sub-course period and guides the user to correct the training action, specifically including:

[0027] Based on the abnormal rehabilitation progress score of each sub-course period, it is compared with the critical rehabilitation training sensor score. If the abnormal rehabilitation progress score of a sub-course period is higher than the critical rehabilitation training sensor score, the sub-course period is defined as a demand-guided sub-course period and the user is guided to correct the training movements.

[0028] As a preferred technical solution, the specific processing conditions for the abnormal rehabilitation progress score values ​​of each sub-course period are as follows:

[0029]

[0030] Among them, SC i is the abnormal score of rehabilitation progress in the i-th sub-course period, θ yaw (t,i,r) is the sensing heading angle value of the nine-axis sensor at the r-th position at the t-th time in the i-th sub-course period, θ pitch (t,i,r) is the pitch angle value of the nine-axis sensor at the r-th position at the t-th time in the i-th sub-course period, θ roll (t,i,r) is the roll angle value of the nine-axis sensor at the r-th position corresponding to the t-th time in the i-th sub-course period, a(t,i,r) is the acceleration value of the nine-axis sensor at the r-th position corresponding to the t-th time in the i-th sub-course period, p(t,i,q) is the pressure value of the pressure sensor at the q-th position corresponding to the t-th time in the i-th sub-course period, θ yaw，m (i,r) is the expected value of the sensing heading angle of the rth nine-axis sensor in the i-th sub-course period, θ pitch,m (i,r) is the expected value of the pitch angle sensed by the rth nine-axis sensor in the i-th sub-course period, θ roll,m (i,r) is the expected value of the roll angle of the rth nine-axis sensor in the i-th sub-course period, a m (i,r) is the expected value of the sensor acceleration of the rth nine-axis sensor at time t in the i-th sub-course period, p m (i,q) is the expected value of the sensor pressure of the qth pressure sensor at time t in the ith sub-course period, Δθ yaw is the allowable error value of the heading angle, Δθ pitch is the allowable error value of the pitch angle, Δθ rollis the allowable error value of the roll angle, Δa is the allowable error value of the acceleration, Δp is the allowable error value of the pressure, r is the number of the nine-axis sensor, r=1,2,3,...,z, z is the total number of nine-axis sensors, q is the number of the pressure sensor, q=1,2,3,...,h, h is the total number of pressure sensors, i is the sub-course period number, i=1,2,3,...,j, j is the total number of sub-course periods, t is the time number, t=1,2,3,...,n, n is the total number of times.

[0031] As a preferred technical solution, the remote rehabilitation training guidance module further includes:

[0032] The physiological sensor monitoring unit is used to monitor the user's real-time physiological data, generate an abnormality score value for the user's real-time physiological data, lock the abnormal time point of the user's physiological data and issue an early warning.

[0033] As a preferred technical solution, the generation of abnormal scoring values ​​of real-time physiological data of users and locking the abnormal time point of physiological data of users for early warning specifically include:

[0034] Collect real-time physiological data of users, including real-time heart rate, real-time blood pressure, real-time blood oxygen saturation and real-time body temperature at each rehabilitation training time point;

[0035] Extracting real-time physiological data permissible change values ​​from the rehabilitation training platform, wherein the real-time physiological data permissible change values ​​specifically include: real-time heart rate permissible change value, real-time blood pressure permissible change value, real-time blood oxygen saturation permissible change value and real-time body temperature permissible change value;

[0036] Based on the user's real-time physiological data and the permitted change value of the real-time physiological data, the user's real-time physiological data abnormality score value is generated, wherein the user's real-time physiological data abnormality score value specifically includes the real-time heart rate abnormality score value, the real-time blood pressure abnormality score value, the real-time blood oxygen saturation abnormality score value and the real-time body temperature abnormality score value at each rehabilitation training time point, and is recorded in turn as and

[0037] If there is a or or or The rehabilitation training time point is defined as the abnormal time point of the user's physiological data and an early warning is issued.

[0038] As a preferred technical solution, the user's real-time physiological data abnormality score specifically includes a real-time heart rate abnormality score, a real-time blood pressure abnormality score, a real-time blood oxygen saturation abnormality score and a real-time body temperature abnormality score at each rehabilitation training time point, and the specific generation conditions are:

[0039]

[0040] in, is the rehabilitation training time point t τ Real-time heart rate abnormality score value, is the rehabilitation training time point t τ Real-time blood pressure abnormality score value, is the rehabilitation training time point t τ Real-time blood oxygen saturation abnormality score value, is the rehabilitation training time point t τ Real-time abnormal temperature score, R HB (t τ ) is the rehabilitation training time point t τ Real-time heart rate, P B (t τ ) is the rehabilitation training time point t τ Real-time blood pressure, is the rehabilitation training time point t τ Real-time blood oxygen saturation, T(t τ ) is the rehabilitation training time point t τ Real-time body temperature, R HB (t τ-1 ) is the time point of rehabilitation training (t τ-1 )'s real-time heart rate, P B (t τ-1 ) is the time point of rehabilitation training (t τ-1 )'s real-time blood pressure, is the time point of rehabilitation training (t τ-1 )’s real-time blood oxygen saturation, T(t τ-1 ) is the time point of rehabilitation training (t τ-1 )'s real-time body temperature, ΔR HB is the permissible change value of real-time heart rate, ΔP B is the real-time blood pressure allowable change value, is the allowable change value of real-time blood oxygen saturation, ΔT is the allowable change value of real-time body temperature, τ is the number of rehabilitation training time point t, τ=2,3,4,...,τ', τ' is the total number of time points r.

[0041] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0042] (1) The present invention provides a remote rehabilitation training system based on nine axes and pressure sensors, which can realize remote rehabilitation training for users according to target courses, and collect the archived physiological data of users on the rehabilitation training platform for processing, so as to match the user's rehabilitation training comparison data set, instead of relying solely on single sensor monitoring to perform remote rehabilitation training on users. It can fully adapt to the individual differences of each user, promote the improvement of the benefits of rehabilitation training, and effectively meet the rehabilitation training needs of users.

[0043] (2) Provide locking demand guidance for sub-course time periods and guide users to correct their training movements. By analyzing the abnormal rehabilitation progress scores of each sub-course period, the system provides users with instant feedback and provides timely rehabilitation training guidance, ensuring that users can correct their postures and movements in a timely manner during rehabilitation training, thereby effectively avoiding the adverse consequences caused by incorrect training postures.

[0044] (3) By setting up a physiological sensor and monitoring unit in the remote rehabilitation training guidance module, real-time monitoring of the user's physiological state can be achieved to prevent large fluctuations in physiological data during rehabilitation training, which would have a negative impact on the user and ensure the user's safety.

[0045] Of course, any product implementing the present invention does not necessarily need to achieve all of the above advantages at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the system module of the present invention.

[0047] Figure 2 It is a line graph showing changes in abnormal score values ​​of real-time physiological data involved in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "thickness", "top", "middle", "length", "inside", "all around" and the like indicating orientation or positional relationship are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0050] See also Figure 1As shown, an embodiment of the present invention provides a remote rehabilitation training system based on nine axes and pressure sensors, including: a target course selection perception module, which is used to perceive the rehabilitation training courses selected by the user on the rehabilitation training platform and mark them as target courses.

[0051] In an embodiment, after the user selects a rehabilitation training course on the rehabilitation training platform and confirms the selection, the rehabilitation training platform sends the rehabilitation training course selected by the user and related course information to the rehabilitation training device. On the rehabilitation training platform, the selected course is marked as a target course and archived. After the rehabilitation training device senses the target course from the rehabilitation training platform, it automatically matches the pre-stored training verification data.

[0052] Among them, the rehabilitation training platform is a digital platform that integrates a variety of rehabilitation training resources, which is used to store various rehabilitation training courses and training verification data of each rehabilitation training course. In an embodiment, the rehabilitation training platform is also used to store various comparison information, and the various comparison information includes the training verification data of each rehabilitation training course involved in this embodiment, user archived physiological data, user archived basic information, reference physiological data and reference basic information. It should be noted that the various comparison information and reference information are jointly set by the professional medical team and the professional information team before the platform is established.

[0053] The target course verification data statistics module is used to divide the target course into sub-course time periods and count the initial training verification data of each sub-course time period.

[0054] Specifically, the specific process of collecting the initial training verification data of each sub-course period is as follows:

[0055] Based on the training verification data of each rehabilitation training course stored in the rehabilitation training platform, the training verification data of the target course is collected;

[0056] Based on the divided sub-course periods, the training verification data of each sub-course period is counted from the training verification data of the target course, and recorded as the initial training verification data of each sub-course period;

[0057] The initial training verification data for each sub-course period includes the expected value of the sensing heading angle, the expected value of the sensing pitch angle, the expected value of the sensing roll angle, and the expected value of the sensing acceleration of the nine-axis sensor at each position corresponding to each sub-course period, and also includes the expected value of the sensing pressure of the pressure sensor at each position corresponding to each sub-course period.

[0058] The nine-axis sensor is usually composed of three main sensors, including an accelerometer, a gyroscope, and a magnetometer, each of which uses different physical principles to measure and record the motion state of an object.

[0059] An accelerometer determines the acceleration of an object by measuring the inertial acceleration in different axes. When an object moves or changes speed, the tiny mass inside is affected by the inertial force and moves slightly. This movement causes the charge distribution between capacitors to change, generating a current signal, which the accelerometer measures to determine the magnitude and direction of the acceleration.

[0060] Gyroscopes use the law of conservation of angular momentum to measure the angular velocity of an object as it rotates around its various axes. A gyroscope contains a rotating vibrating body. When the object rotates, the vibration state of the vibrating body changes due to the influence of rotational inertia. This change is converted into a voltage or current signal, and the gyroscope determines the magnitude and direction of the angular velocity by measuring this signal.

[0061] A magnetometer measures the strength and direction of the magnetic field around an object using a built-in magnetic field sensor. This sensor is able to detect the Earth's magnetic field because it can measure changes in the strength and direction of the magnetic field on three axes.

[0062] The pressure sensor is a device for measuring medium pressure, and is used to measure the pressure distribution and size of a stress-bearing area.

[0063] It is worth mentioning that the heading angle (Yaw) is the rotation angle around the Z axis of the object, also known as the yaw angle or azimuth angle, the pitch angle (Pitch) is the rotation angle around the Y axis of the object, and the roll angle (Roll) is the rotation angle around the X axis of the object. In three-dimensional space, the posture of an object can be described by these three angles.

[0064] The rehabilitation data matching module is used to collect the user's archived physiological data on the rehabilitation training platform and input it into the platform data processing center, and then process it through the platform data processing center to match the user's rehabilitation training comparison data set.

[0065] The processing by the platform data processing center specifically includes:

[0066] Based on the user's archived physiological data on the rehabilitation training platform, the archived physiological data includes heart rate, blood pressure, blood oxygen saturation and body temperature;

[0067] Obtaining basic user information from the rehabilitation training platform, wherein the basic user information specifically includes height, weight and age;

[0068] Extracting reference physiological data from the rehabilitation training platform and processing it with the archived physiological data to generate a first rehabilitation training verification value, wherein the first rehabilitation training verification value is used to characterize the user's physiological profile and serves as a matching numerical basis for the rehabilitation training comparison data set;

[0069] The reference basic information is extracted from the rehabilitation training platform and processed with the user basic information to generate a second rehabilitation training verification value, which is used to quantify the user basic information and simultaneously serves as a matching numerical basis for the rehabilitation training comparison data set.

[0070] Among them, the reference physiological data refers to a set of standardized and representative physiological data extracted from the rehabilitation training platform. These data are based on the health statistics of a large number of people or the average data of a specific rehabilitation group, and are used as a standard or control for evaluating the user's physiological condition. Specifically, they include heart rate range, blood pressure level, blood oxygen saturation and body temperature. By comparing and processing the user's archived physiological data with these reference physiological data, a first rehabilitation training verification value can be generated, which characterizes the degree of deviation of the user's physiological state from the general standard.

[0071] Reference basic information refers to the average data corresponding to the user's basic information and obtained based on a large amount of statistical analysis. This information is used to quantify the user's basic physical condition. The reference basic information includes: height and weight range, age. Individuals of different age groups have differences in physiological functions, metabolic rates, etc. By comparing and processing the user's basic information such as height, weight, age, etc. with the corresponding reference basic information, a second rehabilitation training verification value can be generated. The second rehabilitation training verification value is used to quantify the difference between the user's basic information and the general standard or specific rehabilitation goal.

[0072] The matching obtains the user's rehabilitation training comparison data set, specifically including:

[0073] generating a comprehensive rehabilitation training verification value for the user based on the first rehabilitation training verification value and the second rehabilitation training verification value, wherein the comprehensive rehabilitation training verification value is used to comprehensively represent the archived physiological data and basic information of the user;

[0074] It should be noted that the specific processing conditions for generating the user's comprehensive rehabilitation training verification value based on the first rehabilitation training verification value and the second rehabilitation training verification value are as follows:

[0075] C = ω1*FCV+ω2*SCV;

[0076] Among them, C is the user's comprehensive rehabilitation training verification value, FCV is the first rehabilitation training verification value, SCV is the second rehabilitation training verification value, ω1 and ω2 are the weights of the first rehabilitation training verification value and the second rehabilitation training verification value, respectively. In this embodiment, the user's physiological data and basic information factors are combined to obtain a comprehensive rehabilitation training verification value through comprehensive analysis. The first rehabilitation training verification value and the second rehabilitation training verification value in the formula together constitute a multi-dimensional perspective for evaluating the user's physiological state. The first rehabilitation training verification value focuses on the user's current physiological state and directly reflects the user's physiological function and health status. The second rehabilitation training verification value focuses on the user's basic information and reflects the user's long-term physiological characteristics and basic physical condition. The combination of the two can more comprehensively understand the user's physical condition, including both the current physiological state and its basic physiological characteristics. The first check value and the second check value of rehabilitation training also have mutual influence and feedback. The user's physiological data will fluctuate due to changes in basic information. With age, the body's physiological functions will gradually decline, such as weakened heart function and reduced vascular elasticity. These changes will directly affect physiological indicators such as heart rate and blood pressure. Abnormalities in the user's physiological data also indicate problems in the basic information. For example, long-term high blood pressure may mean that the individual has a difference in weight from the reference physiological data. By quantifying physiological data and basic information, we can fully adapt to the individual differences of each user, promote the effectiveness of rehabilitation training, and effectively meet the user's rehabilitation training needs.

[0077] It should be noted that the weight of the first verification value of rehabilitation training and the weight of the second verification value of rehabilitation training both range from 0 to 1. In an embodiment, the preset value can be directly extracted from the rehabilitation training platform. In an application, a mapping set of the comprehensive verification value of rehabilitation training and the first verification value of rehabilitation training, the second verification value of rehabilitation training and their corresponding weights of the first verification value of rehabilitation training and the second verification value of rehabilitation training is established through the relationship between the comprehensive verification value of rehabilitation training in historical data and the first verification value of rehabilitation training and the second verification value of rehabilitation training. The real-time first verification value of rehabilitation training and the second verification value of rehabilitation training are input to obtain the corresponding weight of the first verification value of rehabilitation training and the weight of the second verification value of rehabilitation training from the mapping set.

[0078] Table 1 below provides five sets of examples of rehabilitation training comprehensive verification values ​​and rehabilitation training first verification values ​​and rehabilitation training second verification values. In this example, the weight of the rehabilitation training first verification value and the weight of the rehabilitation training second verification value are set to 0.6 and 0.4, respectively.

[0079] Table 1 Example of comprehensive calibration values ​​for rehabilitation training

[0080] User Number FCV <![CDATA[ω1]]> SCV <![CDATA[ω2]]> C 1 4.00 0.60 3.00 0.40 3.60 2 5.50 0.60 3.00 0.40 4.50 3 6.52 0.60 17.49 0.40 10.91 4 11.01 0.60 6.10 0.40 9.05 5 10.11 0.60 0.47 0.40 6.26

[0081] The FCV is the first verification value of rehabilitation training, which is used to characterize the physiological profile of the user. The larger the FCV of a user, the greater the difference between the physiological data of the user and the reference physiological data. The SCV is the second verification value of rehabilitation training, which is used to quantify the basic information of the user. The larger the SCV of a user, the greater the difference between the basic information of the user and the reference basic information. It can be seen from the above table that the comprehensive verification value of rehabilitation training of user No. 3 is the highest, indicating that the physiological data and basic information of user No. 3 have the largest deviation from the reference physiological data and basic information, and there is a difference compared with the comprehensive verification value of rehabilitation training of other users. This indicates that the user may have more invalid rehabilitation training movements during the rehabilitation training process. In actual rehabilitation training, more rigorous data perception processing is required to ensure that the user is guided to conduct effective rehabilitation training.

[0082] In this embodiment, the specific processing conditions of the first verification value of the rehabilitation training are:

[0083]

[0084] Among them, R HB , P B , and T are the heart rate, blood pressure, blood oxygen saturation and body temperature in the user's archived physiological data, respectively. and μ T They are the mean values ​​of heart rate samples, blood pressure samples, blood oxygen saturation samples, and body temperature samples in the reference physiological data, respectively. and σ T They are the standard deviation of heart rate samples, blood pressure samples, blood oxygen saturation samples, and body temperature samples of the reference physiological data extracted from the rehabilitation training platform.

[0085] In this embodiment, the specific processing conditions of the second verification value of the rehabilitation training are:

[0086]

[0087] Among them, SCV is the second calibration value of rehabilitation training, W is the user's weight, H is the user's height, A is the user's age, μ H is the mean of the height samples in the reference basic information, μ W is the weight sample mean in the reference basic information, μ A is the age sample mean in the reference basic information, σ H is the standard deviation of height in the reference basic information, σ W is the standard deviation of weight in the reference basic information, σ A is the standard deviation of age in the reference basic information.

[0088] According to the user's rehabilitation training comprehensive verification value, the rehabilitation training comparison data set corresponding to each comprehensive verification value interval stored in the rehabilitation training platform is matched to obtain the user's rehabilitation training comparison data set;

[0089] The rehabilitation training comparison data set corresponding to each comprehensive verification value interval stored in the rehabilitation training platform is matched according to the user's rehabilitation training comprehensive verification value to obtain the user's rehabilitation training comparison data set. The present invention collects rehabilitation training case data similar to the current user through the rehabilitation training platform, analyzes the collected data, and evaluates the patient's initial functional level and physical condition according to the user's rehabilitation training comprehensive verification value, evaluates the difference and consistency between the two, and appropriately adjusts the rehabilitation training comparison data set corresponding to each comprehensive verification value interval to obtain the matching value of the rehabilitation training comparison data set, which can fully adapt to the individual differences of each user, promote the improvement of the effectiveness of rehabilitation training, and effectively meet the rehabilitation training needs of users.

[0090] The rehabilitation training comparison data set includes a rehabilitation training sensor critical score value, a heading angle allowable error value, a pitch angle allowable error value, a roll angle allowable error value, an acceleration allowable error value and a pressure allowable error value.

[0091] Among them, the allowable error value of the heading angle refers to the maximum allowable deviation between the expected value of the sensor heading angle calculated by the rehabilitation training platform and the sensor heading angle value. The allowable error value of the pitch angle refers to the maximum allowable deviation between the expected value of the sensor pitch angle calculated by the rehabilitation training platform and the sensor pitch angle value. The allowable error value of the roll angle refers to the maximum allowable deviation between the expected value of the sensor roll angle calculated by the rehabilitation training platform and the sensor roll angle value. The allowable error value of acceleration refers to the maximum allowable deviation between the expected value of the sensor acceleration calculated by the rehabilitation training platform and the sensor acceleration value. The allowable error value of pressure refers to the maximum allowable deviation between the expected value of the sensor pressure calculated by the rehabilitation training platform and the sensor pressure value.

[0092] The remote rehabilitation training guidance module is used to conduct remote rehabilitation training for users according to the target course, and combines the sensor training data of each sub-course period, and conducts a comprehensive perception analysis of the user's rehabilitation training comparison data set, locks the demand-guided sub-course period, and guides the user to correct the training movements.

[0093] The comprehensive perception analysis based on the sensor training data of each sub-course period and the user's rehabilitation training comparison data set specifically includes:

[0094] Count several moments in each sub-course period, and obtain the sensor training data at each moment in each sub-course period, specifically including the sensing heading angle value, sensing pitch angle value, sensing roll angle value and sensing acceleration value of the nine-axis sensor at each position corresponding to each moment in each sub-course period, and also including the sensing pressure value of the pressure sensor at each position corresponding to each moment in each sub-course period;

[0095] Based on the sensor training data at each moment in each sub-course period, combined with the initial training verification data of each sub-course period and the user's rehabilitation training comparison data set, comprehensive processing is performed to generate the rehabilitation progress abnormality score value of each sub-course period.

[0096] The rehabilitation training sensor critical score value is generated by the rehabilitation training platform through comprehensive analysis of the user's rehabilitation training comparison data set, and is used to evaluate whether the user's rehabilitation training error in each sub-course period exceeds the critical value. If it exceeds the critical value, the sub-course period is marked as a demand-guided sub-course period.

[0097] The specific processing conditions for abnormal rehabilitation progress scores in each sub-course period are as follows:

[0098]

[0099] Among them, SC i is the abnormal score of rehabilitation progress in the i-th sub-course period, θ yaw (t,i,r) is the sensing heading angle value of the nine-axis sensor at the r-th position at the t-th time in the i-th sub-course period, θ pitch (t,i,r) is the pitch angle value of the nine-axis sensor at the r-th position at the t-th time in the i-th sub-course period, θ roll (t,i,r) is the roll angle value of the nine-axis sensor at the r-th position corresponding to the t-th time in the i-th sub-course period, a(t,i,r) is the acceleration value of the nine-axis sensor at the r-th position corresponding to the t-th time in the i-th sub-course period, p(t,i,q) is the pressure value of the pressure sensor at the q-th position corresponding to the t-th time in the i-th sub-course period, θ yaw，m (i,r) is the expected value of the sensing heading angle of the rth nine-axis sensor in the i-th sub-course period, θ pitch,m (i,r) is the expected value of the pitch angle sensed by the rth nine-axis sensor in the i-th sub-course period, θ roll,m (i,r) is the expected value of the roll angle of the rth nine-axis sensor in the i-th sub-course period, a m (i,r) is the expected value of the sensor acceleration of the rth nine-axis sensor at time t in the i-th sub-course period, p m (i,q) is the expected value of the sensor pressure of the qth pressure sensor at time t in the ith sub-course period, Δθ yawis the allowable error value of the heading angle, Δθ pitch is the allowable error value of the pitch angle, Δθ roll is the allowable error value of the roll angle, Δa is the allowable error value of the acceleration, Δp is the allowable error value of the pressure, r is the number of the nine-axis sensor, r=1,2,3,...,z, z is the total number of nine-axis sensors, q is the number of the pressure sensor, q=1,2,3,...,h, h is the total number of pressure sensors, i is the sub-course period number, i=1,2,3,...,j, j is the total number of sub-course periods, t is the time number, t=1,2,3,...,n, n is the total number of times.

[0100] It is worth noting that these angles may be indirectly affected by each other due to the installation position of the nine-axis sensor, the design of the mechanical structure, and other physical limitations. For example, an extreme change in one angle may cause stress on the structure, thereby affecting the measurement of other angles. In practical applications, due to environmental influences, the accelerometer, gyroscope, and magnetometer in the nine-axis sensor may have errors, and these errors may affect the measurement of all three angles at the same time. For example, temperature changes may affect the sensitivity of the sensor, thereby affecting the readings of all angles. In this embodiment, by jointly analyzing the changes in the three angles, the indirect influence of these angles on each other is weakened, making the final analysis result more accurate.

[0101] The remote rehabilitation training guidance module also includes: a physiological sensor monitoring unit, which is used to monitor the user's real-time physiological data, generate an abnormal score value of the user's real-time physiological data, and lock the abnormal time point of the user's physiological data for early warning.

[0102] The generating of the abnormality score value of the user's real-time physiological data and the locking of the abnormal time point of the user's physiological data for early warning specifically include:

[0103] Collect real-time physiological data of users, including real-time heart rate, real-time blood pressure, real-time blood oxygen saturation and real-time body temperature at each rehabilitation training time point;

[0104] Extracting real-time physiological data permissible change values ​​from the rehabilitation training platform, wherein the real-time physiological data permissible change values ​​specifically include: real-time heart rate permissible change value, real-time blood pressure permissible change value, real-time blood oxygen saturation permissible change value and real-time body temperature permissible change value;

[0105] Based on the user's real-time physiological data and the permitted change value of the real-time physiological data, the user's real-time physiological data abnormality score value is generated, wherein the user's real-time physiological data abnormality score value specifically includes the real-time heart rate abnormality score value, the real-time blood pressure abnormality score value, the real-time blood oxygen saturation abnormality score value and the real-time body temperature abnormality score value at each rehabilitation training time point, and is recorded in turn as and

[0106] If there is a or or or The rehabilitation training time point is defined as the time point of abnormal user physiological data for early warning.

[0107] The real-time heart rate abnormality score value, real-time blood pressure abnormality score value, real-time blood oxygen saturation abnormality score value and real-time body temperature abnormality score value at each rehabilitation training time point are specifically generated under the following conditions:

[0108]

[0109] in, is the rehabilitation training time point t τ Real-time heart rate abnormality score value, is the rehabilitation training time point t τ Real-time blood pressure abnormality score value, is the rehabilitation training time point t τ Real-time blood oxygen saturation abnormality score value, is the rehabilitation training time point t τ Real-time abnormal temperature score, R HB (t τ ) is the rehabilitation training time point t τ Real-time heart rate, P B (t τ ) is the rehabilitation training time point t τ Real-time blood pressure, is the rehabilitation training time point t τ Real-time blood oxygen saturation, T(t τ ) is the rehabilitation training time point t τ Real-time body temperature, R HB (t τ-1 ) is the time point of rehabilitation training (t τ-1 )'s real-time heart rate, P B (t τ-1 ) is the time point of rehabilitation training (t τ-1 )'s real-time blood pressure, is the time point of rehabilitation training (t τ-1 )’s real-time blood oxygen saturation, T(t τ-1 ) is the time point of rehabilitation training (t τ-1 )'s real-time body temperature, ΔR HB is the permissible change value of real-time heart rate, ΔP B is the real-time blood pressure allowable change value, is the allowable change value of real-time blood oxygen saturation, ΔT is the allowable change value of real-time body temperature, τ is the number of rehabilitation training time point t, τ=2,3,4,...,τ', τ' is the total number of time points t.

[0110] like Figure 2 As shown in FIG. 1 , a line graph of abnormal score changes of real-time physiological data involved in an embodiment of the present invention is shown. Each data point represents the abnormal score value of the corresponding physiological index at the time point of rehabilitation training. is the real-time heart rate abnormality score. is the real-time blood pressure abnormality score value, is the real-time blood oxygen saturation abnormality score value, is the real-time body temperature abnormality score value, the horizontal axis represents different time points of rehabilitation training. In the embodiment of the present invention, starting from the rehabilitation training time point t2, the vertical axis represents the user's real-time physiological data abnormality score value. The higher the user's real-time physiological data abnormality score value, the greater the change in the physiological data at the current time point, and the more significant it is relative to the permitted range.

[0111] In this embodiment, the present invention provides a remote rehabilitation training system based on nine axes and pressure sensors, which realizes remote rehabilitation training for users according to target courses, and collects and processes the archived physiological data of users on the rehabilitation training platform, so as to match the rehabilitation training comparison data set of users, instead of relying solely on a single sensor monitoring to perform remote rehabilitation training on users, which can fully adapt to the individual differences of each user, promote the improvement of the benefits of rehabilitation training, and effectively meet the rehabilitation training needs of users. Provide locking demand guidance sub-course time periods, and guide users to correct training movements. By analyzing the abnormal rehabilitation progress score values ​​of each sub-course time period, provide users with instant feedback, and provide timely rehabilitation training guidance, ensuring that users can correct postures and movements in time during rehabilitation training, thereby effectively avoiding the adverse consequences caused by incorrect training postures. By setting a physiological sensor and monitoring unit in the remote rehabilitation training guidance module, real-time monitoring of the user's physiological state is achieved, preventing the physiological data from fluctuating significantly during rehabilitation training, causing negative impacts on users, and ensuring the safety of users.

[0112] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0113] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. As long as they do not deviate from the structure of the present invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. A remote rehabilitation training system based on nine axes and pressure sensors, characterized in that: include: The target course selection perception module is used to perceive the rehabilitation training courses selected by the user on the rehabilitation training platform and mark them as target courses; The target course verification data statistics module is used to divide the target course into sub-course periods and count the initial training verification data of each sub-course period; Based on the divided sub-course periods, the training verification data of each sub-course period is counted from the training verification data of the target course, and recorded as the initial training verification data of each sub-course period; The initial training verification data for each sub-course period includes the expected value of the sensing heading angle, the expected value of the sensing pitch angle, the expected value of the sensing roll angle, and the expected value of the sensing acceleration of the nine-axis sensor at each position corresponding to each sub-course period, and also includes the expected value of the sensing pressure of the pressure sensor at each position corresponding to each sub-course period; The rehabilitation data matching module is used to collect the archived physiological data of the user on the rehabilitation training platform and input it into the platform data processing center, and then process it through the platform data processing center to match and obtain the user's rehabilitation training comparison data set; The remote rehabilitation training guidance module is used to conduct remote rehabilitation training for users according to the target course, and conduct a comprehensive perception analysis based on the sensor training data of each sub-course period and the user's rehabilitation training comparison data set, lock the sub-course period for demand guidance, and guide the user to correct the training movements; The comprehensive perception analysis based on the sensor training data of each sub-course period and the user's rehabilitation training comparison data set specifically includes: Count several moments in each sub-course period, and obtain the sensor training data at each moment in each sub-course period, specifically including the sensing heading angle value, sensing pitch angle value, sensing roll angle value and sensing acceleration value of the nine-axis sensor at each position corresponding to each moment in each sub-course period, and also including the sensing pressure value of the pressure sensor at each position corresponding to each moment in each sub-course period; Based on the sensor training data at each moment in each sub-course period, combined with the initial training verification data of each sub-course period and the user's rehabilitation training comparison data set, comprehensive processing is performed to generate the abnormal rehabilitation progress score value of each sub-course period; The locking requirement guides the sub-course period and guides the user to correct the training action, specifically including: Based on the abnormal rehabilitation progress score of each sub-course period, it is compared with the critical rehabilitation training sensor score. If the abnormal rehabilitation progress score of a sub-course period is higher than the critical rehabilitation training sensor score, the sub-course period is defined as a demand-guided sub-course period and the user is guided to correct the training movements.

2. A remote rehabilitation training system based on nine axes and pressure sensors according to claim 1, characterized in that: The processing by the platform data processing center specifically includes: Based on the user's archived physiological data on the rehabilitation training platform, the archived physiological data includes heart rate, blood pressure, blood oxygen saturation and body temperature; Obtaining basic user information from the rehabilitation training platform, wherein the basic user information specifically includes height, weight and age; Extracting reference physiological data from the rehabilitation training platform and processing it with the archived physiological data to generate a first rehabilitation training verification value, wherein the first rehabilitation training verification value is used to characterize the user's physiological profile and serves as a matching numerical basis for the rehabilitation training comparison data set; The reference basic information is extracted from the rehabilitation training platform and processed with the user basic information to generate a second rehabilitation training verification value, which is used to quantify the user basic information and simultaneously serves as a matching numerical basis for the rehabilitation training comparison data set.

3. A remote rehabilitation training system based on nine axes and pressure sensors according to claim 2, characterized in that: The matching obtains the user's rehabilitation training comparison data set, specifically including: generating a comprehensive rehabilitation training verification value for the user based on the first rehabilitation training verification value and the second rehabilitation training verification value, wherein the comprehensive rehabilitation training verification value is used to comprehensively represent the archived physiological data and basic information of the user; According to the user's rehabilitation training comprehensive verification value, the rehabilitation training comparison data set corresponding to each comprehensive verification value interval stored in the rehabilitation training platform is matched to obtain the user's rehabilitation training comparison data set; The rehabilitation training comparison data set includes a rehabilitation training sensor critical score value, a heading angle allowable error value, a pitch angle allowable error value, a roll angle allowable error value, an acceleration allowable error value and a pressure allowable error value.

4. The remote rehabilitation training system based on nine axes and pressure sensors according to claim 1, characterized in that: The specific processing conditions for abnormal rehabilitation progress scores in each sub-course period are as follows: Among them, SC i is the abnormal score of rehabilitation progress in the i-th sub-course period, θ yaw (t,i,r) is the sensing heading angle value of the nine-axis sensor at the r-th position at the t-th time in the i-th sub-course period. θ pitch (t,i,r) is the pitch angle value of the nine-axis sensor at the r-th position at the t-th time in the i-th sub-course period, θ roll (t,i,r) is the roll angle value of the nine-axis sensor at the r-th position corresponding to the t-th time in the i-th sub-course period, a(t,i,r) is the acceleration value of the nine-axis sensor at the r-th position corresponding to the t-th time in the i-th sub-course period, p(t,i,q) is the pressure value of the pressure sensor at the q-th position corresponding to the t-th time in the i-th sub-course period, θ yaw , m (i,r) is the expected value of the sensing heading angle of the rth nine-axis sensor in the i-th sub-course period, θ pitch,m (i,r) is the expected value of the pitch angle sensed by the rth nine-axis sensor in the i-th sub-course period, θ roll,m (i,r) is the expected value of the roll angle of the rth nine-axis sensor in the i-th sub-course period, a m (i,r) is the expected value of the sensor acceleration of the rth nine-axis sensor at time t in the i-th sub-course period, p m (i,q) is the expected value of the sensor pressure of the qth pressure sensor at time t in the ith sub-course period, Δθ yaw is the allowable error value of the heading angle, Δθ pitch is the allowable error value of the pitch angle, Δθ roll is the allowable error value of the roll angle, Δa is the allowable error value of the acceleration, Δp is the allowable error value of the pressure, r is the number of the nine-axis sensor, r=1,2,3,...,z, z is the total number of nine-axis sensors, q is the number of the pressure sensor, q=1,2,3,...,h, h is the total number of pressure sensors, i is the sub-course period number, i=1,2,3,...,j, j is the total number of sub-course periods, t is the time number, t=1,2,3,...,n, n is the total number of times.

5. The remote rehabilitation training system based on nine axes and pressure sensors according to claim 1, characterized in that: The remote rehabilitation training guiding module further includes: The physiological sensor monitoring unit is used to monitor the user's real-time physiological data, generate an abnormality score value for the user's real-time physiological data, lock the abnormal time point of the user's physiological data and issue an early warning.

6. The remote rehabilitation training system based on nine axes and pressure sensors according to claim 5, characterized in that: The generating of the abnormality score value of the user's real-time physiological data and the locking of the abnormal time point of the user's physiological data for early warning specifically include: Collect real-time physiological data of users, including real-time heart rate, real-time blood pressure, real-time blood oxygen saturation and real-time body temperature at each rehabilitation training time point; Extracting real-time physiological data permissible change values ​​from the rehabilitation training platform, wherein the real-time physiological data permissible change values ​​specifically include: real-time heart rate permissible change value, real-time blood pressure permissible change value, real-time blood oxygen saturation permissible change value and real-time body temperature permissible change value; Based on the user's real-time physiological data and the permitted change value of the real-time physiological data, the user's real-time physiological data abnormality score value is generated, wherein the user's real-time physiological data abnormality score value specifically includes the real-time heart rate abnormality score value, the real-time blood pressure abnormality score value, the real-time blood oxygen saturation abnormality score value and the real-time body temperature abnormality score value at each rehabilitation training time point, and is recorded in turn as and If there is a or or or The rehabilitation training time point is defined as the abnormal time point of the user's physiological data and an early warning is issued.

7. A remote rehabilitation training system based on nine axes and pressure sensors according to claim 6, characterized in that: The user's real-time physiological data abnormality score specifically includes a real-time heart rate abnormality score, a real-time blood pressure abnormality score, a real-time blood oxygen saturation abnormality score and a real-time body temperature abnormality score at each rehabilitation training time point, and the specific generation conditions are: in, is the rehabilitation training time point t τ Real-time heart rate abnormality score value, is the rehabilitation training time point t τ Real-time blood pressure abnormality score value, is the rehabilitation training time point t τ Real-time blood oxygen saturation abnormality score value, is the rehabilitation training time point t τ Real-time abnormal temperature score, R HB (t τ ) is the rehabilitation training time point t τ Real-time heart rate, P B (t τ ) is the rehabilitation training time point t τ Real-time blood pressure, is the rehabilitation training time point t τ Real-time blood oxygen saturation, T(t τ ) is the rehabilitation training time point t τ Real-time body temperature, R HBB (t τ-1 ) is the time point of rehabilitation training (t τ-1 )'s real-time heart rate, P B (t τ-1 ) is the time point of rehabilitation training (t τ-1 )'s real-time blood pressure, is the time point of rehabilitation training (t τ-1 )’s real-time blood oxygen saturation, T(t τ-1 ) is the time point of rehabilitation training (t τ-1 )'s real-time body temperature, ΔR HB is the permissible change value of real-time heart rate, ΔP B is the real-time blood pressure allowable change value, is the allowable change value of real-time blood oxygen saturation, ΔT is the allowable change value of real-time body temperature, τ is the number of rehabilitation training time point t, τ=2,3,4,...,τ′, τ′ is the total number of time points t.

Images