Method, device and computer equipment for guiding the activity of a limb of a hemi-neglect user

Abstract

The application relates to a method and device for guiding the activity of a user's limb on the basis of neglecting the activity of the limb on one side, and a computer device. The method comprises the following steps: acquiring current activity data transmitted by a wearing unit worn by each limb of a user, and identifying a current activity intensity index value of each limb on the basis of the current activity data of each limb; identifying activity asymmetry information of a contralateral limb through an activity asymmetry identification strategy on the basis of the current activity intensity index value of each limb, and identifying abnormal activity information of a diseased side of the user on the basis of the activity asymmetry information of the contralateral limb and the current activity intensity index value of each limb; generating activity guiding information of the diseased side of the user on the basis of the abnormal activity information of the diseased side of the user, and collecting new activity data of the diseased side of the limb; and adjusting the activity guiding information of the diseased side of the user on the basis of the new activity data of the diseased side of the limb to obtain target activity guiding information of the diseased side of the user. The method can improve the guiding effect of the activity of the diseased side of the user's limb.

Description

Technical Field

[0001] This application relates to the fields of rehabilitation medical devices, wearable devices and human-computer interaction technology, and in particular to a method, device and computer equipment for guiding the activity of a user's limbs that are neglected on one side. Background Technology

[0002] Hemispheric neglect following stroke has an incidence rate as high as 86% after right-sided hemisphere stroke. Patients often exhibit a lack of active attention to stimuli on the limbs and space contralateral to the lesion (usually the left side), leading to intentional neglect (unconscious use of the affected side) and motor neglect (significantly reduced activity on the affected side). Clinical observations show that patients over-rely on the healthy (right) side of their limbs in daily life, while the affected (left) side remains in a state of disuse for a long time, further exacerbating "learned disuse" and making it difficult to reverse neuroplasticity. Therefore, improving limb activity in patients with hemispheric neglect is a current research focus.

[0003] Traditional techniques for improving limb movement in patients with unilateral neglect involve using timed vibration reminder devices or unilateral activity monitoring devices to provide timely reminders and guide patients to consciously and voluntarily move their limbs. However, existing technologies provide limited information to patients, and given their limited experience with rehabilitation activities on the affected side, simply knowing the timing of activities is insufficient to effectively improve the rehabilitation progress of the affected limb, resulting in poor guidance for the user's affected limb movement. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, device, and computer equipment for guiding user movement that ignores the above-mentioned technical problems.

[0005] Firstly, this application provides a method for providing activity guidance that partially ignores the user's limbs, including:

[0006] The system acquires current activity data transmitted by the wearing units worn by the user's limbs, and identifies the current activity intensity index value of each limb based on the current activity data of each limb.

[0007] Based on the current activity intensity index value of each limb, the activity asymmetry information of the contralateral limb is identified through the activity asymmetry identification strategy, and based on the activity asymmetry information of the contralateral limb and the current activity intensity index value of each limb, the activity abnormality information of the user's affected side is identified.

[0008] Based on the user's abnormal activity information on the affected side, activity guidance information for the affected side is generated, and new activity data of the affected limb is collected.

[0009] Based on the new activity data of the affected limb, the user's affected side activity guidance information is adjusted to obtain the user's target affected side activity guidance information.

[0010] Optionally, the current activity data includes the current triaxial acceleration and the current angular velocity. The step of identifying the current activity intensity index value of each limb based on the current activity data of each limb includes:

[0011] For each limb, based on the limb's current triaxial acceleration and current angular velocity, the current value of the limb's activity intensity index is identified using an activity intensity index evaluation strategy.

[0012] The current value of the activity intensity index is used as the current activity intensity index value of the limb.

[0013] Optionally, the step of identifying activity asymmetry information of the contralateral limb based on the current activity intensity index value of each limb, using an activity asymmetry identification strategy, includes:

[0014] Based on the current activity intensity index values ​​of the contralateral limbs, the activity asymmetry value between the contralateral limbs is calculated using an activity asymmetry algorithm.

[0015] The asymmetry value of the activity between the contralateral limbs is used as the activity asymmetry information of the contralateral limbs.

[0016] Optionally, identifying the user's abnormal activity information on the affected side based on the asymmetric activity information of the contralateral limb and the current activity intensity index value of each limb includes:

[0017] Based on the asymmetric activity information of the contralateral limbs and the current activity intensity index value of each limb, the abnormal activity judgment strategy is used to identify the current limb abnormality type of the user's affected limb.

[0018] The current limb abnormality type of the user's affected limb is used as the user's affected limb activity abnormality information.

[0019] Optionally, generating the user's affected-side activity guidance information based on the user's affected-side activity abnormality information includes:

[0020] Based on the current limb abnormality type of the affected limb, activity change data of the contralateral limb are collected through an abnormal activity collection strategy.

[0021] Based on the activity change data, the user's current affected side activity plan and the user's activity prompt information are generated through the limb activity guidance strategy corresponding to the current limb abnormality type.

[0022] The user's current activity plan on the affected side, as well as the user's activity prompts, will be used as the user's activity guidance information on the affected side.

[0023] Optionally, adjusting the user's affected-side activity guidance information based on the new activity data of the affected limb to obtain the user's target affected-side activity guidance information includes:

[0024] Based on the new activity data of the affected limb, the activity analysis network identifies abnormal activity information of the user, and generates an activity adjustment plan for the user based on the abnormal activity information.

[0025] Collect the user's prompt feedback information, and adjust the user's activity prompt information based on the user's prompt feedback information to obtain the user's target activity prompt information;

[0026] The user's activity adjustment plan and the user's target activity prompts will be used as the user's target affected side activity guidance information.

[0027] Secondly, this application also provides a device for guiding user movement that ignores one side of the user's limbs, comprising:

[0028] The acquisition module is used to acquire the current activity data transmitted by the wearing units worn by the user's limbs, and to identify the current activity intensity index value of each limb based on the current activity data of each limb.

[0029] The identification module is used to identify the activity asymmetry information of the contralateral limb based on the current activity intensity index value of each limb, through an activity asymmetry identification strategy, and to identify the abnormal activity information of the user's affected side based on the activity asymmetry information of the contralateral limb and the current activity intensity index value of each limb.

[0030] The generation module is used to generate activity guidance information for the affected side of the user based on the user's abnormal activity information on the affected side, and to collect new activity data of the affected limb.

[0031] The adjustment module is used to adjust the user's affected side activity guidance information based on the new activity data of the affected limb, so as to obtain the user's target affected side activity guidance information.

[0032] Optionally, the acquisition module is specifically used for:

[0033] For each limb, based on the limb's current triaxial acceleration and current angular velocity, the current value of the limb's activity intensity index is identified using an activity intensity index evaluation strategy.

[0034] The current value of the activity intensity index is used as the current activity intensity index value of the limb.

[0035] Optionally, the identification module is specifically used for:

[0036] Based on the current activity intensity index values ​​of the contralateral limbs, the activity asymmetry value between the contralateral limbs is calculated using an activity asymmetry algorithm.

[0037] The asymmetry value of the activity between the contralateral limbs is used as the activity asymmetry information of the contralateral limbs.

[0038] Optionally, the identification module is specifically used for:

[0039] Based on the asymmetric activity information of the contralateral limbs and the current activity intensity index value of each limb, the abnormal activity judgment strategy is used to identify the current limb abnormality type of the user's affected limb.

[0040] The current limb abnormality type of the user's affected limb is used as the user's affected limb activity abnormality information.

[0041] Optionally, the generation module is specifically used for:

[0042] Based on the current limb abnormality type of the affected limb, activity change data of the contralateral limb are collected through an abnormal activity collection strategy.

[0043] Based on the activity change data, the user's current affected side activity plan and the user's activity prompt information are generated through the limb activity guidance strategy corresponding to the current limb abnormality type.

[0044] The user's current activity plan on the affected side, as well as the user's activity prompts, will be used as the user's activity guidance information on the affected side.

[0045] Optionally, the adjustment module is specifically used for:

[0046] Based on the new activity data of the affected limb, the activity analysis network identifies abnormal activity information of the user, and generates an activity adjustment plan for the user based on the abnormal activity information.

[0047] Collect the user's prompt feedback information, and adjust the user's activity prompt information based on the user's prompt feedback information to obtain the user's target activity prompt information;

[0048] The user's activity adjustment plan and the user's target activity prompts will be used as the user's target affected side activity guidance information.

[0049] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0050] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0051] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0052] The aforementioned method, apparatus, and computer device for unilaterally ignoring user limb activity guidance acquire current activity data transmitted by wearing units on each of the user's limbs, and identify the current activity intensity index value of each limb based on the current activity data of each limb; based on the current activity intensity index value of each limb, identify activity asymmetry information of the contralateral limb through an activity asymmetry identification strategy, and identify the user's affected side activity abnormality information based on the activity asymmetry information of the contralateral limb and the current activity intensity index value of each limb; generate the user's affected side activity guidance information based on the user's affected side activity abnormality information, and collect new activity data of the affected limb; adjust the user's affected side activity guidance information based on the new activity data of the affected limb to obtain the user's target affected side activity guidance information. This solution utilizes wearable units on each of the user's limbs to monitor activity data in real time. This not only monitors whether each limb is active but also provides comprehensive data collection, enhancing the overall monitoring of the user's real-time activity. Secondly, by addressing the asymmetry in activity on the contralateral side, this solution analyzes the activity abnormalities of the affected limb using data from the contralateral side. It then provides activity guidance for the affected side, ensuring that the guidance matches the guidance provided to the healthy contralateral limb, thus guaranteeing similar activity levels. Furthermore, it offers targeted guidance on movement and rehabilitation angles for the affected side, avoiding the limitations of single-point prompts that cannot effectively improve the recovery progress of the affected limb. By ensuring consistent changes on both sides, this solution effectively improves the recovery progress of the affected limb, thereby comprehensively enhancing the guidance effect on the user's affected limb activity. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a flowchart illustrating a method for unilaterally ignoring user limb movement guidance in one embodiment;

[0055] Figure 2 This is a flowchart illustrating an example of biased guidance that ignores user limb movement in one embodiment;

[0056] Figure 3 This is a structural block diagram of a device that selectively ignores the user's limb movement guidance in one embodiment.

[0057] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0059] The activity guidance method for unilaterally neglecting a user's limb provided in this application embodiment can be applied to an activity guidance system for unilaterally neglecting a user's limb. The system includes a first wearing unit, a second wearing unit, and a pairing host. The first wearing unit, the second wearing unit, and the pairing host are communicatively connected. The first wearing unit includes a first inertial measurement unit (IMU, including a three-axis accelerometer and a three-axis gyroscope), a first vibration motor, a first microcontroller, and a wireless communication module. The second wearing unit includes a second inertial measurement unit, a second vibration motor (for providing haptic feedback to the affected side), a second microcontroller, and a wireless communication module. The first and second wearing units are respectively positioned on two limbs on the opposite side, such as the left and right wrists, or the left and right feet. The two limbs include the unaffected limb (the healthy limb without disease) and the affected limb (the unhealthy limb with disease).

[0060] When worn on the left and right wrists, the device parameters for the first and second wearable units are as follows: Each wearable unit measures 40mm × 30mm × 12mm and weighs 18g. IMU: MPU6050 (six-axis), sampling rate 50Hz. Vibration motor: Flat linear resonant motor (LRA), adjustable vibration frequency (100~300Hz). MCU (Microcontroller Unit): nRF52832 (integrated Bluetooth 5.0), operating current approximately 6mA (active mode), 0.5mA (standby). Battery: 100mAh lithium polymer battery, providing approximately 48 hours of battery life. The wearing method is as follows: the patient wears the affected unit on the left wrist and the unaffected unit on the right wrist. An elastic fabric wristband is used, allowing for adjustable tightness. Initialization and calibration: After power-on, the patient remains still for 10 seconds, and the system records the resting baseline (IMU noise level). The patient is then asked to perform several bilateral symmetrical activities (such as simultaneously patting the legs with both hands), and the paired host automatically calculates the initial asymmetry ratio reference value. When worn on the left and right feet, the wristband is changed to an extended ankle strap in the device parameters of the first and second wearing units.

[0061] The paired host can be applied to a terminal, which can be, but is not limited to, various personal computers, laptops, mid-range computers, etc. The terminal uses wearable units on each of the user's limbs to monitor limb activity data, collecting real-time activity data for each limb. This not only monitors whether each limb is active but also comprehensively collects the user's activity data, improving the comprehensiveness of real-time activity monitoring. Secondly, this solution addresses the asymmetry of activity on the contralateral side by analyzing the activity data of the contralateral limb of the affected side to identify abnormalities. Then, it provides activity guidance for the affected side. This ensures that activity guidance for the affected side is matched with guidance for the healthy contralateral limb, ensuring similar activity levels. It also provides targeted guidance on movement and rehabilitation angles for the patient's affected side, avoiding the limited information provided by single prompts that cannot effectively improve the patient's recovery progress on the affected side. Therefore, while ensuring consistent changes on the contralateral side, it effectively improves the recovery progress of the patient's affected side, thus comprehensively enhancing the activity guidance effect for the user's affected side.

[0062] In one exemplary embodiment, such as Figure 1 As shown, a method for providing unilateral guidance that ignores user limb movement is provided. Taking the application of this method to a paired host, where the paired host is a terminal, as an example, the method includes the following steps S101 to S104. Wherein:

[0063] Step S101: Obtain the current activity data transmitted by the wearing units worn by the user on each limb, and identify the current activity intensity index value of each limb based on the current activity data of each limb.

[0064] In this embodiment, the terminal obtains the current activity data of each limb by transmitting real-time sensor data from the wearing units on each limb. This current activity data includes, but is not limited to, the limb's three-axis acceleration and angular velocity. Then, the terminal performs index evaluation processing on the current activity data of each limb using a preset activity intensity index evaluation strategy to obtain the current activity intensity index value for each limb. This activity intensity index is either the root mean square (RMS) of the high-frequency acceleration amplitude or gyroscope energy. The index evaluation strategy includes an index evaluation algorithm, which can be an algorithm for calculating the root mean square of the high-frequency acceleration amplitude or gyroscope energy. For example, the calculation formula could be:

[0065] A = RMS (high-frequency acceleration amplitude, sliding window length 1s);

[0066] In the above formula, A is the current activity intensity index value, the sliding window is fixed for 1 second, and the activity intensity index value of both limbs is refreshed every 0.5 seconds.

[0067] Step S102: Based on the current activity intensity index value of each limb, the activity asymmetry information of the contralateral limb is identified through the activity asymmetry identification strategy. Based on the activity asymmetry information of the contralateral limb and the current activity intensity index value of each limb, the abnormal activity information of the user's affected side is identified.

[0068] In this embodiment, the terminal identifies activity asymmetry information of the contralateral limb based on the current activity intensity index values ​​of each limb using an activity asymmetry identification strategy. Based on the activity asymmetry information of the contralateral limb and the current activity intensity index values ​​of each limb, the terminal identifies the user's affected side activity abnormality information. The activity asymmetry identification strategy calculates the activity asymmetry value of the contralateral limb using the activity asymmetry algorithm designed in this solution, and uses this value as the activity asymmetry information of that contralateral limb. The affected side activity abnormality information refers to the current limb abnormality type corresponding to the user's affected limb. This type of abnormality is not limited to, but includes, high activity in the healthy limb, low activity in the affected limb, or significant asymmetry. The specific identification process will be explained in detail later.

[0069] Step S103: Based on the user's abnormal activity information on the affected side, generate activity guidance information for the user's affected side and collect new activity data of the affected limb.

[0070] In this embodiment, the terminal generates activity guidance information for the affected side based on the user's abnormal activity information on the affected side, and collects new activity data of the affected limb. This activity guidance information includes activity prompts for the patient's affected side, as well as a current activity plan for the affected side. The current activity plan includes guidance on the activity mode, frequency, and duration of the affected limb. The specific generation process will be explained in detail later. The new activity data of the affected limb is collected in real time through a wearing unit on the affected limb, which collects sensor data changes of the affected limb. This sensor data change information includes the changes in the three-axis acceleration and angular velocity of the affected limb, arranged chronologically.

[0071] Step S104: Based on the new activity data of the affected limb, adjust the user's affected limb activity guidance information to obtain the user's target affected limb activity guidance information.

[0072] In this embodiment, the terminal adjusts the user's activity guidance information on the affected side based on new activity data of the affected limb, thereby obtaining the user's target activity guidance information on the affected side. The method for adjusting the user's activity guidance information is as follows: When the user's activity frequency is too high / too low, the activity duration is too long / too short, or the activity method is different, the terminal identifies the adjustment amount of the user's activity frequency and activity duration, and adaptively adjusts the guidance method according to the user's current activity method. This ensures that the activity method is adjusted to be more similar to the user's current activity method while meeting the actual activity needs of the affected limb. The specific adjustment process will be explained in detail later.

[0073] Based on the above solution, by wearing a device on each of the user's limbs to monitor the activity data of each limb, the system collects the activity data of each limb in real time. This not only monitors whether the user's limbs are active, but also comprehensively collects the user's activity data, improving the comprehensiveness of the monitoring of the user's real-time activity. Secondly, this solution addresses the asymmetry of activity on the contralateral limb by analyzing the activity data of the contralateral limb of the affected side to identify abnormalities in the activity of that limb, and then provides activity guidance for the affected side. This ensures that the activity guidance for the affected side is matched with the activity guidance for the healthy limb on the contralateral side, thus ensuring similar activity between the two sides. It also provides targeted guidance information on movement and rehabilitation angles for the patient's affected side, avoiding the problem that single prompts are limited and cannot effectively improve the patient's rehabilitation progress on the affected side. Therefore, while ensuring consistent changes on the contralateral side, it effectively improves the rehabilitation progress of the patient's affected side, thereby comprehensively improving the activity guidance effect for the user's affected side.

[0074] Optionally, based on the current activity data of each limb, the current activity intensity index value of each limb is identified, including: for each limb, based on the current three-axis acceleration and the current angular velocity of the limb, the current index value of the activity intensity index of the limb is identified through the index evaluation strategy of the activity intensity index; and the current index value of the activity intensity index is used as the current activity intensity index value of the limb.

[0075] The current activity data for each limb includes the current triaxial acceleration and the current angular velocity of each limb.

[0076] In this embodiment, the terminal extracts the current triaxial acceleration and current angular velocity of each limb from the current activity data of each limb. Then, for each limb, based on the current triaxial acceleration and current angular velocity of the limb, the terminal calculates the current index value of the activity intensity index of that limb using the activity intensity index algorithm in the index evaluation strategy. Finally, the terminal uses the current index value of the activity intensity index as the current activity intensity index value of the limb.

[0077] Based on the above scheme, the activity intensity index is used to analyze the difference in activity intensity between the affected limb and the healthy limb, thereby improving the accuracy of quantitative identification of the activity differences of the contralateral limb.

[0078] Optionally, based on the current activity intensity index values ​​of each limb, an activity asymmetry identification strategy is used to identify activity asymmetry information of the contralateral limb, including: based on the current activity intensity index values ​​of each contralateral limb, an activity asymmetry algorithm is used to calculate the activity asymmetry value between the contralateral limbs; and the activity asymmetry value between the contralateral limbs is used as the activity asymmetry information of the contralateral limb.

[0079] In this embodiment, the terminal calculates the activity asymmetry value between the contralateral limbs based on the current activity intensity index values ​​of each contralateral limb using an activity asymmetry algorithm. Then, the terminal uses this activity asymmetry value as the activity asymmetry information for the contralateral limbs. The calculation formula for the activity asymmetry algorithm designed in this scheme is as follows:

[0080] ;

[0081] In the above formula, The asymmetry coefficient of the activity. To prevent division by zero for extremely small positive numbers, This refers to the activity intensity index value of the left limbs (e.g., left wrist, left foot). This refers to the activity intensity index value of the right limb (e.g., right wrist, right foot).

[0082] Based on the above scheme, the activity asymmetry algorithm can quickly and accurately quantify the difference in activity intensity between contralateral limbs, while ensuring the accuracy of the identification of the difference in activity intensity between contralateral limbs and improving the efficiency of the identification of the difference in activity intensity between contralateral limbs.

[0083] Optionally, based on the asymmetric activity information of the contralateral limbs and the current activity intensity index value of each limb, the user's abnormal activity information on the affected side is identified, including: based on the asymmetric activity information of the contralateral limbs and the current activity intensity index value of each limb, the user's current limb abnormality type on the affected side is identified through an abnormal activity judgment strategy; and the user's current limb abnormality type on the affected side is used as the user's abnormal activity information on the affected side.

[0084] In this embodiment, the terminal identifies the current limb abnormality type of the user's affected limb based on the asymmetric activity information of the contralateral limb and the current activity intensity index value of each limb, using an abnormal activity judgment strategy. This abnormal activity judgment strategy includes sub-judgment strategies for different limb abnormality types. Specifically, the sub-judgment strategy for the high activity type of the healthy limb is as follows: (This threshold, for example, 0.1 gRMS), indicates that the patient is engaged in active activity (e.g., this active activity can be non-resting); the sub-strategy for determining the type of low activity in the affected limb is as follows: (This threshold is, for example, 0.02 g RMS), and continues (For example, the time is 20 seconds); the sub-judgment strategy for asymmetric saliency types is, (For example, ρ=0.2), meaning the activity on the affected side is less than 20% of that on the healthy side; where, if the user simultaneously meets all limb abnormality types, the terminal rolls back the current processing and re-acquires the current activity data transmitted by the wearing units on each of the user's limbs. Finally, the terminal uses the current limb abnormality type of the user's affected limb as the user's affected side activity abnormality information.

[0085] Based on the above scheme, the pre-set abnormal activity judgment strategy can quickly identify the current limb abnormality type of the user's affected limb, thereby improving the efficiency of identifying abnormal activity information of the user's affected limb.

[0086] Optionally, based on the user's abnormal activity information on the affected side, generate the user's activity guidance information on the affected side, including: based on the current limb abnormality type of the affected limb, collecting activity change data of the contralateral limb through an abnormal activity collection strategy; based on the activity change data, generating the user's current activity plan on the affected side and the user's activity prompt information through a limb activity guidance strategy corresponding to the current limb abnormality type; and using the user's current activity plan on the affected side and the user's activity prompt information as the user's activity guidance information on the affected side.

[0087] In this embodiment, the terminal collects activity change data of the contralateral limb based on the current limb abnormality type of the affected limb using an abnormal activity collection strategy. The collection method differs for each limb abnormality type. Specifically, when the limb abnormality type is a high-activity type for the healthy limb, the collection method is to collect activity data only from the healthy limb; when the limb abnormality type is a low-activity type for the affected limb, the collection method is to collect activity data only from the affected limb; and when the limb abnormality type is a significant asymmetry type, the collection method is to collect activity data from both the healthy and affected limbs simultaneously.

[0088] Then, based on activity change data, the terminal generates the user's current activity plan for the affected side and activity prompts for the user, using the limb activity guidance strategy corresponding to the current limb abnormality type. Specifically, when the current limb abnormality type is low activity on the affected side or significant asymmetry, the terminal identifies the current activity mode, frequency, and duration of the healthy side limb. Then, the terminal identifies the current activity frequency and duration of the affected side limb. Based on the current interaction frequency and duration of the affected side limb, the terminal generates the activity prompt interval for the affected side limb using a preset activity reminder table. This activity prompt interval is obtained by dividing the current activity duration by the activity frequency, with a lower limit for the prompt interval, meaning a maximum of 3 prompts can be triggered within 60 seconds. The terminal uses the current activity mode, frequency, and duration of the healthy side limb as the user's current activity plan for the affected side.

[0089] When the current limb abnormality type is detected as high limb activity, the terminal identifies the current activity mode, current activity frequency, and current activity duration of the affected limb. Then, the terminal identifies the current activity frequency and current activity duration of the healthy limb. Based on the current interaction frequency and current activity duration of the healthy limb, the terminal generates an activity reminder interval for the healthy limb using a preset activity reminder table. The terminal identifies the current activity mode of the healthy limb, and then uses a preset activity frequency, preset activity duration, and the current activity mode of the healthy limb as the current activity plan for the affected limb, thus obtaining the user's current activity plan for the affected side. The activity mode identification strategy involves the terminal generating limb trajectory change information for the user in the same coordinate system using a trajectory generation network based on a convolutional neural network, based on the acquired current activity data / activity change data. Then, the terminal uses a convolutional neural network based on a self-attention mechanism to identify the activity type corresponding to the limb trajectory change information and uses that activity type as the current activity mode. The activity type can be, but is not limited to, limb flexion and extension, limb swinging, limb joint rotation, large-range irregular limb movements, and small-range irregular limb movements. Each activity type includes a preset motion feature range on the terminal. The terminal uses a convolutional neural network based on a self-attention mechanism to identify the motion feature corresponding to the limb trajectory change information and to which the motion feature belongs. Finally, the terminal uses the activity type corresponding to the motion feature range as the current activity type.

[0090] Finally, the terminal uses the user's current activity plan on the affected side, along with the user's activity prompts, as guidance information for the user's activities on the affected side.

[0091] Based on the above scheme, by generating different activity plans for the affected side according to different current limb abnormality types, the effect of guiding users' movement of the affected limb is improved.

[0092] Optionally, based on new activity data of the affected limb, the user's activity guidance information on the affected side is adjusted to obtain the user's target activity guidance information on the affected side. This includes: based on new activity data of the affected limb, identifying abnormal activity information of the user through an activity analysis network, and generating an activity adjustment plan for the user based on the abnormal activity information; collecting the user's prompt feedback information, and adjusting the user's activity prompt information based on the prompt feedback information to obtain the user's target activity prompt information; and using the user's activity adjustment plan and the user's target activity prompt information as the user's target activity guidance information on the affected side.

[0093] In this embodiment, the terminal, based on new activity data of the affected limb, identifies abnormal activity information of the user through an activity analysis network, and generates an activity adjustment plan for the user based on this abnormal activity information. Specifically, the terminal first identifies the new activity frequency and duration of the affected limb. Then, the activity analysis network is a combination of a trajectory generation network based on a convolutional neural network (CNN) and a CNN based on a self-attention mechanism. Next, the terminal re-identifies the activity mode corresponding to the new activity data of the affected limb using the activity type identification method described above, and uses this as the new activity mode. Finally, the terminal calculates the deviation between the new activity frequency and duration and the activity frequency and duration in the affected limb activity guidance information.

[0094] Then, the terminal obtains the similarity between various activity types preset on the terminal, and filters out activity types with the same similarity as the first activity type corresponding to the activity method in the activity guidance information for the affected side, and the second activity type corresponding to the new activity method, as the adjusted activity method. The terminal uses the aforementioned deviation value and the adjusted activity method as the user's activity adjustment plan. The similarity between different activity types is calculated by the terminal using a feature similarity algorithm to calculate the average similarity between the action feature ranges of each pair of activity types, and using this average similarity as the similarity between different activity types. This feature similarity algorithm can be a cosine similarity algorithm, Euclidean distance algorithm, or other feature similarity algorithms.

[0095] Then, the terminal collects user feedback information and adjusts the user's activity prompts based on this feedback to obtain the user's target activity prompts. Specifically, the terminal uses a semantic recognition network to identify the user's suggestion regarding the prompt interval length and adjusts the interval length accordingly. This suggestion can be to increase or decrease the prompt interval length. The terminal presets a single increase / decrease amount for the prompt interval length. When the suggestion is to increase the prompt interval length, the terminal adds the preset increase amount to the prompt interval length in the feedback information to obtain a new prompt interval length. Conversely, when the suggestion is to increase the prompt interval length, the terminal subtracts the preset decrease amount from the prompt interval length in the feedback information to obtain a new prompt interval length. Finally, the terminal uses this new prompt interval length as the user's target activity prompt.

[0096] Finally, the terminal will use the user's activity adjustment plan and the user's target activity prompts as the user's target affected side activity guidance information.

[0097] Based on the above solution, by combining the user's actual activity data and prompt suggestions, the activity mode and prompt interval are adaptively adjusted, which improves the user experience while ensuring the accuracy of guiding the user's movement on the affected limb.

[0098] This application also provides an example of activity guidance that partially ignores the user's limbs, such as... Figure 2 As shown, the specific processing procedure includes the following steps:

[0099] Step S201: Obtain the current activity data transmitted by the wearing units worn on each of the user's limbs.

[0100] Step S202: For each limb, based on the limb's current triaxial acceleration and current angular velocity, the current value of the limb's activity intensity index is identified using an activity intensity index evaluation strategy.

[0101] Step S203: Use the current value of the activity intensity index as the current activity intensity index value of the limb.

[0102] Step S204: Based on the current activity intensity index values ​​of the contralateral limbs, calculate the activity asymmetry value between the contralateral limbs using the activity asymmetry algorithm.

[0103] Step S205: The asymmetry value of activity between the contralateral limbs is used as the asymmetry information of activity between the contralateral limbs.

[0104] Step S206: Based on the asymmetric activity information of the contralateral limb and the current activity intensity index value of each limb, the abnormal activity judgment strategy is used to identify the current limb abnormality type of the user's affected limb.

[0105] Step S207: The current limb abnormality type of the user's affected limb is used as the user's affected limb activity abnormality information.

[0106] Step S208: Based on the current limb abnormality type of the affected limb, collect activity change data of the contralateral limb through an abnormal activity collection strategy.

[0107] Step S209: Based on the activity change data, generate the user's current affected side activity plan and the user's activity prompt information through the limb activity guidance strategy corresponding to the current limb abnormality type.

[0108] Step S210: Use the user's current activity plan on the affected side and the user's activity prompts as the user's activity guidance information on the affected side.

[0109] Step S211: Collect new activity data of the affected limb.

[0110] Step S212: Based on the new activity data of the affected limb, the activity analysis network is used to identify abnormal activity information of the user, and an activity adjustment plan for the user is generated based on the abnormal activity information.

[0111] Step S213: Collect user feedback information and adjust user activity prompts based on user feedback information to obtain the user's target activity prompt information.

[0112] Step S214: The user's activity adjustment plan and the user's target activity prompts are used as the user's target affected side activity guidance information.

[0113] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0114] Based on the same inventive concept, this application also provides a device for implementing the above-described method for unilaterally ignoring user limb activity guidance. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the device for unilaterally ignoring user limb activity guidance provided below can be found in the limitations of the method for unilaterally ignoring user limb activity guidance described above, and will not be repeated here.

[0115] In one exemplary embodiment, such as Figure 3 As shown, a device for guiding user movement that ignores one's limbs is provided, comprising: an acquisition module 310, a recognition module 320, a generation module 330, and an adjustment module 340, wherein:

[0116] The acquisition module 310 is used to acquire the current activity data transmitted by the wearing units worn by the user on each limb, and to identify the current activity intensity index value of each limb based on the current activity data of each limb.

[0117] The identification module 320 is used to identify the activity asymmetry information of the contralateral limb based on the current activity intensity index value of each limb through an activity asymmetry identification strategy, and to identify the abnormal activity information of the user's affected side based on the activity asymmetry information of the contralateral limb and the current activity intensity index value of each limb.

[0118] The generation module 330 is used to generate activity guidance information for the affected side of the user based on the user's abnormal activity information on the affected side, and to collect new activity data of the affected limb.

[0119] The adjustment module 340 is used to adjust the user's affected side activity guidance information based on the new activity data of the affected limb, so as to obtain the user's target affected side activity guidance information.

[0120] Optionally, the acquisition module 310 is specifically used for:

[0121] For each limb, based on the limb's current triaxial acceleration and current angular velocity, the current value of the limb's activity intensity index is identified using an activity intensity index evaluation strategy.

[0122] The current value of the activity intensity index is used as the current activity intensity index value of the limb.

[0123] Optionally, the identification module 320 is specifically used for:

[0124] Based on the current activity intensity index values ​​of the contralateral limbs, the activity asymmetry value between the contralateral limbs is calculated using an activity asymmetry algorithm.

[0125] The asymmetry value of the activity between the contralateral limbs is used as the activity asymmetry information of the contralateral limbs.

[0126] Optionally, the identification module 320 is specifically used for:

[0127] Based on the asymmetric activity information of the contralateral limbs and the current activity intensity index value of each limb, the abnormal activity judgment strategy is used to identify the current limb abnormality type of the user's affected limb.

[0128] The current limb abnormality type of the user's affected limb is used as the user's affected limb activity abnormality information.

[0129] Optionally, the generation module 330 is specifically used for:

[0130] Based on the current limb abnormality type of the affected limb, activity change data of the contralateral limb are collected through an abnormal activity collection strategy.

[0131] Based on the activity change data, the user's current affected side activity plan and the user's activity prompt information are generated through the limb activity guidance strategy corresponding to the current limb abnormality type.

[0132] The user's current activity plan on the affected side, as well as the user's activity prompts, will be used as the user's activity guidance information on the affected side.

[0133] Optionally, the adjustment module 340 is specifically used for:

[0134] Based on the new activity data of the affected limb, the activity analysis network identifies abnormal activity information of the user, and generates an activity adjustment plan for the user based on the abnormal activity information.

[0135] Collect the user's prompt feedback information, and adjust the user's activity prompt information based on the user's prompt feedback information to obtain the user's target activity prompt information;

[0136] The user's activity adjustment plan and the user's target activity prompts will be used as the user's target affected side activity guidance information.

[0137] The modules in the aforementioned device that ignores user limb movement can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0138] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for guiding user movement while ignoring limb movement. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0139] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0140] In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of a method for unilaterally ignoring the activity guidance of a user's limbs.

[0141] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program being executed by a processor to implement the steps of a method for unilaterally ignoring the activity guidance of a user's limbs.

[0142] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of a method for guiding the movement of a user's limbs while ignoring lateral movement.

[0143] 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, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0144] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this 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), magnetic 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0145] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0146] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for providing activity guidance that unilaterally ignores the user's limbs, characterized in that, The method includes: The system acquires current activity data transmitted by the wearing units worn by the user's limbs, and identifies the current activity intensity index value of each limb based on the current activity data of each limb. Based on the current activity intensity index value of each limb, the activity asymmetry information of the contralateral limb is identified through the activity asymmetry identification strategy, and based on the activity asymmetry information of the contralateral limb and the current activity intensity index value of each limb, the activity abnormality information of the user's affected side is identified. Based on the user's abnormal activity information on the affected side, activity guidance information for the affected side is generated, and new activity data of the affected limb is collected. Based on the new activity data of the affected limb, the user's affected side activity guidance information is adjusted to obtain the user's target affected side activity guidance information.

2. The method according to claim 1, characterized in that, The current activity data includes the current triaxial acceleration and the current angular velocity. The step of identifying the current activity intensity index value of each limb based on the current activity data of each limb includes: For each limb, based on the limb's current triaxial acceleration and current angular velocity, the current value of the limb's activity intensity index is identified using an activity intensity index evaluation strategy. The current value of the activity intensity index is used as the current activity intensity index value of the limb.

3. The method according to claim 2, characterized in that, The method of identifying activity asymmetry information of the contralateral limb based on the current activity intensity index value of each limb, using an activity asymmetry identification strategy, includes: Based on the current activity intensity index values ​​of the contralateral limbs, the activity asymmetry value between the contralateral limbs is calculated using an activity asymmetry algorithm. The asymmetry value of the activity between the contralateral limbs is used as the activity asymmetry information of the contralateral limbs.

4. The method according to claim 1, characterized in that, The step of identifying abnormal activity information on the affected side of the user based on the asymmetric activity information of the contralateral limb and the current activity intensity index value of each limb includes: Based on the asymmetric activity information of the contralateral limbs and the current activity intensity index value of each limb, the abnormal activity judgment strategy is used to identify the current limb abnormality type of the user's affected limb. The current limb abnormality type of the user's affected limb is used as the user's affected limb activity abnormality information.

5. The method according to claim 4, characterized in that, The step of generating activity guidance information for the affected side of the user based on the user's abnormal activity information includes: Based on the current limb abnormality type of the affected limb, activity change data of the contralateral limb are collected through an abnormal activity collection strategy. Based on the activity change data, the user's current affected side activity plan and the user's activity prompt information are generated through the limb activity guidance strategy corresponding to the current limb abnormality type. The user's current activity plan on the affected side, as well as the user's activity prompts, will be used as the user's activity guidance information on the affected side.

6. The method according to claim 1, characterized in that, The process of adjusting the user's affected-side activity guidance information based on the new activity data of the affected limb to obtain the user's target affected-side activity guidance information includes: Based on the new activity data of the affected limb, the activity analysis network identifies abnormal activity information of the user, and generates an activity adjustment plan for the user based on the abnormal activity information. Collect the user's prompt feedback information, and adjust the user's activity prompt information based on the user's prompt feedback information to obtain the user's target activity prompt information; The user's activity adjustment plan and the user's target activity prompts will be used as the user's target affected side activity guidance information.

7. A device for guiding user limb movement that ignores one side, characterized in that, The device includes: The acquisition module is used to acquire the current activity data transmitted by the wearing units worn by the user's limbs, and to identify the current activity intensity index value of each limb based on the current activity data of each limb. The identification module is used to identify the activity asymmetry information of the contralateral limb based on the current activity intensity index value of each limb, through an activity asymmetry identification strategy, and to identify the abnormal activity information of the user's affected side based on the activity asymmetry information of the contralateral limb and the current activity intensity index value of each limb. The generation module is used to generate activity guidance information for the affected side of the user based on the user's abnormal activity information on the affected side, and to collect new activity data of the affected limb. The adjustment module is used to adjust the user's affected side activity guidance information based on the new activity data of the affected limb, so as to obtain the user's target affected side activity guidance information.

8. 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, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images