Health intervention and correction method, system and equipment based on vision and sensor

Abstract

The invention provides a health intervention and correction method, system and device based on vision and a sensor, and the method comprises the steps: obtaining various motion monitoring data obtained through the detection of a user in a target state; determining a target motion model of the user based on the various motion monitoring data; wherein the target motion model is used for indicating state information of the user at each detection moment; comparing the target motion model with a target reference model to obtain a comparison result; and generating health intervention and correction information based on the comparison result, and sending the health intervention and correction information to health intervention equipment.

Description

Technical Field

[0001] This disclosure relates to the field of health management technology, and more specifically, to a method, system, and device for health intervention and correction based on vision and sensors. Background Technology

[0002] In today's digital age, sedentary lifestyles, longer working hours, and the increasing prevalence of electronic devices have led to a rise in health problems related to the spine, joints, musculoskeletal system, and nervous system. These widespread health issues pose significant challenges to various groups, including office workers, athletes, the elderly, and people with physical disabilities.

[0003] In related technologies, people are helped to solve related problems through human assistance, exercise, and machine assistance. However, the solutions provided by these technologies cannot meet the unique health needs of each individual, nor can they adapt to their progress over time, resulting in poor targeting of existing health intervention programs and thus often hindering the effectiveness of existing health intervention measures. Summary of the Invention

[0004] This disclosure provides at least one method, system, and device for health intervention and correction based on vision and sensors.

[0005] In a first aspect, embodiments of this disclosure provide a health intervention and correction method based on vision and sensors, including:

[0006] Acquire various motion monitoring data obtained by detecting users in a target state;

[0007] The user's target motion model is determined based on the various motion monitoring data; wherein, the target motion model is used to indicate the user's state information at each detection time.

[0008] The target motion model and the target reference model are compared to obtain the comparison results;

[0009] Based on the comparison results, health intervention and correction information is generated and sent to the health intervention device.

[0010] In one optional implementation, acquiring various motion monitoring data obtained by detecting the user in a target state includes:

[0011] The user's motion is detected by various wearable devices that are connected to the terminal device, and the various motion monitoring data are obtained.

[0012] In one optional implementation, the multiple motion monitoring data are data obtained by motion detection of multiple monitoring parts of the user, wherein the monitoring parts include, but are not limited to, the following parts: bones, joints, and muscles; the data types of the multiple motion monitoring data include, but are not limited to, the following types: visual images, photoelectric data, neuroelectrophysiological data, audio data, and speed data.

[0013] In one optional implementation, determining the user's target motion model based on the multiple motion monitoring data includes:

[0014] Each type of motion monitoring data is transformed into the user's motion posture data;

[0015] Based on the detection time of the motion posture data, the motion posture data obtained after transforming various motion monitoring data are fused to obtain the target motion model.

[0016] In one optional implementation, the step of fusing motion posture data obtained after transforming various motion monitoring data based on the detection time of the motion posture data, and obtaining the target motion model after fusion, includes:

[0017] In each type of motion posture data after the motion monitoring data is transformed, determine the motion posture data that is at the same detection time;

[0018] The motion posture data at the same detection time are processed to obtain the target motion posture data at that detection time.

[0019] Based on the target motion posture data at each of the detection times, the target motion model is determined.

[0020] In one optional implementation, the target reference model is a reference motion model; the step of comparing the target motion model and the target reference model to obtain a comparison result includes:

[0021] Based on the target motion model, the user's object information is determined; wherein the object information is used to indicate the user's motion state and / or object attributes;

[0022] Determine a reference motion model that matches the object information; wherein the matching reference motion model is used to indicate the user's expected posture information in the motion state;

[0023] The matching reference motion model and the target motion model are compared to obtain the comparison result.

[0024] In one optional implementation, comparing the target motion model and the target reference model to obtain a comparison result includes:

[0025] Determine the target data pairs with corresponding timestamps in the target motion model and the target reference model;

[0026] Determine the data similarity of the target data pairs;

[0027] The comparison result is determined based on the data similarity of each target data pair.

[0028] In one optional implementation, the step of generating health intervention and correction information based on the comparison results and sending the health intervention and correction information to the health intervention device includes:

[0029] Based on the comparison results, the model differences between the target motion model and the target reference model are determined;

[0030] Determine health intervention strategies that match the differences in the model;

[0031] Identify health intervention devices that match the health intervention strategy, and generate health intervention and corrective information that matches the health intervention strategy;

[0032] The health intervention and correction information is sent to the matched health intervention device.

[0033] In one optional implementation, the step of generating health intervention and correction information based on the comparison results and sending the health intervention and correction information to the health intervention device includes:

[0034] Based on the comparison results, the model differences between the target motion model and the target reference model are determined;

[0035] Determine health intervention strategies that match the differences in the model;

[0036] Identify health intervention devices that match the health intervention strategy, and generate health intervention and corrective information that matches the health intervention strategy;

[0037] The health intervention and correction information is sent to the matched health intervention device.

[0038] In one optional implementation, the target reference model is medical image data; the step of comparing the target motion model and the target reference model to obtain a comparison result includes:

[0039] The state information of the user's monitored body parts is extracted based on the target motion model; wherein, the monitored body parts include, but are not limited to, the following: skeletal, joint, and muscular systems;

[0040] The status information of the monitored site is compared with the expected bone status of the monitored site in the medical imaging data to obtain the comparison result.

[0041] In one optional implementation, the target motion model is a sleep posture model determined based on body state data detected by the user during sleep, and the target reference model is a sleep reference model.

[0042] The acquisition of various motion monitoring data obtained by detecting the user in the target state includes:

[0043] The system acquires various body state data obtained by measuring the user's posture during sleep using sensors at various dimensions; wherein the body state data includes at least one of the following types of data: sleep posture monitoring data, body photoelectric monitoring signals, body electromyography monitoring signals, and body vital sign signals;

[0044] The step of comparing the target motion model and the target reference model to obtain the comparison result includes:

[0045] The sleep posture model and the sleep reference model are compared to obtain the comparison result; wherein, the sleep reference model is used to indicate the user's desired sleep posture.

[0046] In one optional implementation, the step of generating health intervention and correction information based on the comparison results and sending the health intervention and correction information to the health intervention device includes:

[0047] If, based on the comparison results, it is determined that there is a significant difference between the user's sleeping posture and the desired sleeping posture, health intervention and correction information is sent to the user's sleep intervention device; wherein, the health intervention and correction information is used to adjust the user's sleeping posture through the sleep intervention device.

[0048] In one optional implementation, generating health intervention and correction information based on the comparison results includes:

[0049] Based on the comparison results, health intervention and correction information matching the health intervention device is generated; wherein, the health intervention and correction information includes the following types: vibration information, video information, audio information, text information, and instruction information.

[0050] Secondly, embodiments of this disclosure provide a vision and sensor-based health intervention and correction system, including: multiple sensors and a processor;

[0051] The multiple sensors are configured to detect the user's motion in the target state and obtain various motion monitoring data;

[0052] The processor is configured to acquire the various motion monitoring data and determine the user's target motion model based on the various motion monitoring data; wherein the target motion model is used to indicate the user's state information at each detection time; compare the target motion model with a target reference model to obtain a comparison result; generate health intervention and correction information based on the comparison result, and send the health intervention and correction information to a health intervention device.

[0053] In one optional implementation, the processor includes: a processing module, a comparison module, and an intervention module;

[0054] The processing module is configured to acquire the various motion monitoring data and determine the user's target motion model based on the various motion monitoring data;

[0055] The comparison module is configured to compare the target motion model and the target reference model to obtain a comparison result;

[0056] The intervention module is configured to generate health intervention and correction information based on the comparison results, and send the health intervention and correction information to the health intervention device.

[0057] In one alternative implementation, the plurality of sensors include a wearable device and a camera device; wherein the wearable device and the camera device are configured to be wirelessly or wiredly connected to the processor.

[0058] Thirdly, embodiments of this disclosure also provide an electronic device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the steps of the first aspect above, or any possible implementation of the first aspect, are performed.

[0059] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the first aspect or any possible implementation of the first aspect.

[0060] In this embodiment, firstly, various motion monitoring data are obtained by detecting the user's motion in a target state; then, a target motion model for the user is determined based on the various motion monitoring data, wherein the user's state information at each detection moment can be determined through the target motion model; next, by comparing the target motion model with a target reference model, health intervention and correction information for the user can be generated and sent to a health intervention device.

[0061] In the above embodiments, by determining the target motion model based on various motion monitoring data of the user, a personalized health model can be generated for the user; by comparing the target motion model with the target reference model to generate health intervention and correction information, more accurate health intervention and correction information can be generated for the user, thereby providing the user with more accurate intervention measures.

[0062] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0063] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0064] Figure 1 A flowchart of a vision- and sensor-based health intervention and correction method provided in an embodiment of this disclosure is shown;

[0065] Figure 2 The flowchart illustrates a specific method for determining a user's target motion model based on multiple motion monitoring data in the vision and sensor-based health intervention and correction method provided in this disclosure embodiment.

[0066] Figure 3 The flowchart illustrates a specific method for comparing a target motion model and a target reference model to obtain a comparison result in the vision and sensor-based health intervention and correction method provided in this embodiment of the present disclosure.

[0067] Figure 4The flowchart illustrates another specific method for comparing a target motion model and a target reference model to obtain a comparison result in the vision and sensor-based health intervention and correction method provided in this disclosure embodiment.

[0068] Figure 5A This diagram illustrates the installation location of a health intervention device provided in an embodiment of the present disclosure.

[0069] Figure 5B This diagram illustrates the installation location of another health intervention device provided in an embodiment of the present disclosure;

[0070] Figure 6 This illustration shows a schematic diagram of a vision and sensor-based health intervention and correction system provided in an embodiment of the present disclosure;

[0071] Figure 7 A schematic diagram of an electronic device provided in an embodiment of the present disclosure is shown. Detailed Implementation

[0072] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0073] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0074] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0075] Research has found that in today's digital age, sedentary lifestyles, longer working hours, and the increasing prevalence of electronic devices have led to a rise in health problems related to the spine, joints, musculoskeletal system, and nervous system. These widespread health issues pose significant challenges to various groups, including office workers, athletes, the elderly, and people with physical disabilities.

[0076] In related technologies, people are helped to solve related problems through human assistance, exercise, and machine assistance. However, the solutions provided by these technologies cannot meet the unique health needs of each individual, nor can they adapt to their progress over time, resulting in poor targeting of existing health intervention programs and thus often hindering the effectiveness of existing health intervention measures.

[0077] In recent years, technological advancements have led to the emergence of wearable devices, smartphone apps, and camera-based systems designed to promote spinal and joint health. However, these tools often operate independently, failing to provide a holistic, synchronized, and personalized approach to vision- and sensor-based health interventions and corrections.

[0078] Based on the above research, this disclosure provides a method, system, electronic device, and storage medium for health intervention and correction based on vision and sensors. First, various motion monitoring data are acquired by detecting the user's motion in a target state. Then, a target motion model for the user is determined based on the various motion monitoring data, wherein the user's state information at each detection moment can be determined through this target motion model. Next, by comparing the target motion model with a target reference model, health intervention and correction information for the user can be generated and sent to a health intervention device.

[0079] In the above embodiments, by determining the target motion model based on various motion monitoring data of the user, a personalized health model can be generated for the user; by comparing the target motion model with the target reference model to generate health intervention and correction information, more accurate health intervention and correction information can be generated for the user, thereby providing the user with more accurate intervention measures.

[0080] To facilitate understanding of this embodiment, a detailed description of a vision- and sensor-based health intervention and correction method disclosed in this disclosure will be provided first. The execution entity of the vision- and sensor-based health intervention and correction method provided in this disclosure is generally an electronic device with a certain computing capability. This electronic device may include, for example, a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc. In some possible implementations, this vision- and sensor-based health intervention and correction method can be implemented by a processor calling computer-readable instructions stored in memory.

[0081] See Figure 1 The diagram shows a flowchart of a vision and sensor-based health intervention and correction method provided in this disclosure, the method including steps S101 to S107, wherein:

[0082] S101: Acquire various motion monitoring data obtained by detecting the user in the target state.

[0083] Here, the target state includes, but is not limited to, the following states: motion state, stationary state, and sleep state. Multiple motion monitoring data can be collected through various sensors that detect user movement. The data types of these different motion monitoring data are not entirely the same.

[0084] Here, various sensors are used, including wearable devices and camera equipment.

[0085] Here, motion monitoring data refers to data obtained by detecting motion in various monitoring parts of the user, including but not limited to the following parts: bones, joints, and muscles; the data types of various motion monitoring data include but are not limited to the following types: visual images, photoelectric data, neuroelectrophysiological data, audio data, and speed data.

[0086] By using exercise monitoring data, the following relevant exercise data of users can be determined: the user's exercise posture, exercise duration, exercise speed, exercise mode (e.g., cycling or walking), physical state during exercise (e.g., heart rate, blood oxygen concentration, blood pressure, pulse), exercise trajectory, and other exercise-related data.

[0087] In this embodiment, a target application can be installed in an electronic device. Here, the electronic device can acquire motion monitoring data collected by various sensors and send the motion monitoring data to the target application. After acquiring the motion monitoring data, the target application can execute steps S103 to S107. If the sensor is a wearable device, a client that communicates with the wearable device can be installed in the electronic device. The client can acquire the motion monitoring data collected by the wearable device through this communication connection and send the motion monitoring data to the target application.

[0088] In addition, communication connections can be established between electronic devices and various sensors. For example, a communication connection can be established between electronic devices and wearable devices. The wearable device can then transmit motion monitoring data to the electronic device through this communication connection, and after acquiring the motion monitoring data, it can execute steps S103 to S107.

[0089] S103: Determine the user's target motion model based on the multiple motion monitoring data; wherein, the target motion model is used to indicate the user's state information at each detection time.

[0090] Here, after acquiring multiple motion monitoring data, these multiple motion monitoring data can be fused together to obtain the target motion model.

[0091] Here, there can be multiple target motion models, and the types of data contained in different target motion models are different. In other words, multiple different target motion models for the same time period can be generated using various types of motion monitoring data.

[0092] Here, the target motion model can be represented in one or more of the following ways: mathematical model, statistical model, biomechanical model, kinematic model, or machine learning model.

[0093] Here, the target motion model can be converted into a motion sequence; this motion sequence can indicate the user's state information at each detection moment. Here, the detection moment is the moment when the sensor detects the user's motion.

[0094] For example, the motion sequence can be represented as: <(35, 24, 67), (16, 47, 24), (-24, 95, -3), (-61, 35, 24), (56, 33, 5)>; where each set of data in the motion sequence is used to indicate the user's Euler angles on the X, Y, and Z axes.

[0095] For example, the target motion model can be a sequence of images; wherein the sequence of images contains motion images obtained by detecting the user at each detection time.

[0096] S105: Compare the target motion model and the target reference model to obtain the comparison result.

[0097] Here, the target reference model can be a reference model generated from the user's normal motion monitoring data, or a reference model generated according to clinical standards. This target reference model can be used to determine the expected posture information of the object under normal circumstances.

[0098] Here, the target reference model can be represented in one or more of the following ways: mathematical model, statistical model, biomechanical model, kinematic model, or machine learning model.

[0099] Here, the target reference model can be converted into a corresponding reference sequence. For example, the reference sequence can be represented as: <(30, 42, 70), (12, 60, 2), (-24, 95, -3), (-61, 35, 24), (56, 33, 5)>; where each set of data in the reference sequence is used to characterize the user's expected pose information at each detection time under normal circumstances.

[0100] In addition, the target reference model can also be an image sequence; wherein the motion images contained in the image sequence can be used to indicate the user's expected pose information at each detection time under normal circumstances.

[0101] S107: Generate health intervention and correction information based on the comparison results, and send the health intervention and correction information to the health intervention device.

[0102] Here, after generating health intervention and correction information, the information can be sent directly to the health intervention device; or, it can be sent to the client, in which case the user can control the corresponding health intervention device based on the health intervention and correction information.

[0103] Here, after generating health intervention and correction information, it can also be sent to the user's body administrator. The body administrator logs into the client as the user's personal physician. After receiving the health intervention and correction information, the body administrator can develop a corresponding rehabilitation strategy for the user and send it to the user through the client. After receiving the rehabilitation strategy, the user can control the corresponding health intervention device according to the strategy. Alternatively, after receiving the health intervention and correction information, the body administrator can develop a corresponding rehabilitation strategy for the user and send it to the health intervention device.

[0104] In this embodiment, firstly, various motion monitoring data of the user under target conditions are acquired; then, the user's target motion model is determined based on the various motion monitoring data, wherein the user's posture information at each detection moment can be determined through the target motion model; next, by comparing the target motion model with the target reference model, the user's health intervention and correction information can be generated and sent to the health intervention device.

[0105] In this embodiment, the motion monitoring data is data obtained after user authorization. That is, before detection, an authorization request can be sent to the electronic device and / or wearable device, and various motion monitoring data can be detected upon detecting that the user has granted authorization.

[0106] In the above embodiments, by determining the target motion model based on various motion monitoring data of the user, a personalized health model can be generated for the user; by comparing the target motion model with the target reference model to generate health intervention and correction information, more accurate health intervention and correction information can be generated for the user, thereby providing the user with more accurate intervention measures.

[0107] The above steps will be described in detail below with reference to specific implementation methods.

[0108] In this embodiment of the application, firstly, various motion monitoring data obtained from motion detection of the user are acquired, specifically including the following steps:

[0109] The user's motion is detected by various wearable devices that are connected to the terminal device, and the various motion monitoring data are obtained.

[0110] In this embodiment, if the electronic device is a terminal device, and multiple wearable devices can communicate with the terminal device, then the terminal device can obtain motion monitoring data obtained by the connected wearable devices from motion detection of the user.

[0111] Wearable devices include, but are not limited to, the following devices: smartphones, smartwatches, smart bracelets, smart earrings, smart earbuds, smart glasses, and other wearable devices.

[0112] Each type of wearable device collects motion monitoring data, which includes a corresponding timestamp. This timestamp indicates the detection time of the corresponding motion monitoring data.

[0113] Here, the data types of motion monitoring data can be various, such as image data, numerical data, and video data.

[0114] In the above embodiments, by acquiring motion monitoring data detected by multiple wearable devices, more comprehensive motion monitoring data of the user can be obtained, thereby compensating for the missing data in motion monitoring data collected by a single sensor, and thus obtaining a more accurate target motion model.

[0115] In this embodiment of the application, after acquiring multiple types of motion monitoring data, the user's target motion model can be determined based on the multiple types of motion monitoring data.

[0116] Here, artificial intelligence algorithms can be used to analyze and process the motion monitoring data captured by sensors, thereby generating a personalized health model for an individual's exercise, namely a target exercise model.

[0117] In one alternative implementation, such as Figure 2 As shown, the specific steps include the following:

[0118] Step S11: Transform each type of motion monitoring data into the user's motion posture data;

[0119] Step S12: Based on the detection time of the motion posture data, perform data fusion on the motion posture data obtained after transforming various motion monitoring data, and obtain the target motion model after fusion.

[0120] In this embodiment, the motion monitoring data can be of various different data types, such as image data, coordinate data, or text data. Each type of motion monitoring data can then be converted into motion pose data to indicate the user's posture. For example, the motion pose data could be the Euler angles of the user along the X, Y, and Z axes at various detection times.

[0121] After obtaining the motion pose data at each detection time, the motion pose data can be fused based on the detection time to obtain a fused motion pose data sequence, and the fused motion pose data sequence can be determined as the target motion model.

[0122] Here, the category of motion pose data can be determined based on the category of data in the target reference model. For example, if the category of data in the target reference model is coordinate data, then each type of motion monitoring data can be transformed into coordinate-based motion pose data for that user.

[0123] In practice, the motion pose data of the target pose object can be sorted according to the order of detection time. Then, the motion pose data corresponding to the same detection time in the sorting results can be fused to obtain the target motion model.

[0124] By using the above processing methods, it is possible to combine multi-dimensional data to determine a personalized exercise model for the user, thereby more accurately reflecting the user's exercise status and generating health intervention and correction information for the user more accurately and reasonably.

[0125] In an optional implementation, the above steps involve fusing the motion posture data obtained after transforming the various motion monitoring data to obtain the target motion model, specifically including the following steps:

[0126] Step S121: In each type of motion posture data after the motion monitoring data is transformed, determine the motion posture data that is at the same detection time;

[0127] Step S122: Process the motion posture data at the same detection time to obtain the target motion posture data at that detection time;

[0128] Step S123: Determine the target motion model based on the target motion pose data at each of the detection times.

[0129] In this embodiment of the application, the motion posture data of the target pose object can be sorted according to the order of detection time, and then the motion posture data corresponding to the same detection time in the sorting result can be determined; then, the motion posture data can be processed based on the number of data corresponding to the same detection time.

[0130] Here, if there is only one set of motion pose data corresponding to the same detection time, then that motion pose data can be used as the final motion pose data for that detection time.

[0131] Here, if there are multiple motion pose data corresponding to the same detection time, these multiple motion pose data can be fused to obtain a fused motion pose data for that detection time, and this fused motion pose data can be used as the final motion pose data for that detection time.

[0132] For example, multiple motion posture data can be averaged to obtain fused motion posture data; or, the reliability of each type of motion posture data can be evaluated, and the motion posture data with the highest reliability can be used as the final motion posture data; in this case, the reliability of the motion posture data can be determined based on the acquisition reliability of the sensor corresponding to each type of motion posture data.

[0133] After determining the final motion pose data corresponding to each detection time, the target motion model can be determined based on the final motion pose data.

[0134] For detection moments where motion posture data is missing, the missing motion posture data at that detection moment can be estimated based on motion posture data from other detection moments before and / or after that detection moment.

[0135] The above processing method can more accurately reflect the user's exercise status, and thus generate health intervention and correction information for the user more accurately and reasonably.

[0136] In one alternative implementation, such as Figure 3 As shown, when the target reference model is a reference motion model, the above steps of comparing the target motion model and the target reference model to obtain the comparison result specifically include the following steps:

[0137] Step S31: Based on the target motion model, determine the user's object information; wherein the object information is used to indicate the user's motion state and / or object attributes;

[0138] Step S32: Determine a reference motion model that matches the object information; wherein the matching reference motion model is used to indicate the user's expected posture information in the motion state;

[0139] Step S33: Compare the matched reference motion model and the target motion model to obtain the comparison result.

[0140] In this embodiment, the target reference model includes a reference motion model and medical imaging data; wherein the reference motion model and medical imaging data are pre-stored in a database. The reference motion model is used to indicate the expected posture information corresponding to the user, and the medical imaging data is used to indicate the expected skeletal state corresponding to the user.

[0141] Here, object information includes the user's exercise status and / or object attributes. Exercise status includes, but is not limited to, the following: exercise type (e.g., XXX aerobics, XXX posture, cycling, XXX yoga pose), exercise duration, exercise method (e.g., exercising with XXX equipment), and exercise location (e.g., indoor exercise, outdoor exercise). Object attributes include, but are not limited to, the following: object gender (male or female), object age, object health status (e.g., suffering from XXX skeletal disease), and other attribute information associated with the user.

[0142] Here, multiple target reference models can be preset, and each target reference model can be assigned a corresponding type label, which is used to indicate the preset motion state and / or preset object attributes.

[0143] After determining the user's object information, the object information can be compared with the type label of the reference motion model to find the reference motion model that matches the object information.

[0144] Here, if the number of reference motion models that match the object information is determined to be multiple, the priority of each object information of the user can be determined. Then, the object information with the highest priority is determined, and the reference motion model that matches the object information with the highest priority is determined. The matching reference motion model and the target motion model are compared to obtain the comparison result.

[0145] Here, any one of the following algorithms can be used: pattern recognition algorithm, statistical analysis algorithm, optimization algorithm, machine learning algorithm, or artificial intelligence algorithm, to compare the target motion model and the reference motion model, thereby obtaining the comparison result.

[0146] This processing method enables more accurate analysis and comparison of the target motion model and the reference motion model, resulting in more accurate comparison results.

[0147] In this application embodiment, the reference motion model can be a motion model determined based on the user's motion monitoring data to indicate the user's expected posture information; in addition, the reference motion model can also be a motion model determined based on the motion monitoring data of other objects to indicate the user's expected posture information, wherein the other objects can be objects associated with the user, for example, the object information of the other objects is the same as the object information of the user, or the similarity is high.

[0148] By using the above processing methods, a more matching reference motion model can be determined for the target motion model, thereby obtaining more accurate comparison results and providing users with more accurate health intervention and correction information.

[0149] In one alternative implementation, such as Figure 4 As shown, the above steps compare the target motion model and the target reference model to obtain the comparison result, including:

[0150] Step S41: Determine the target data pairs with corresponding timestamps in the target motion model and the target reference model;

[0151] Step S42: Determine the data similarity of the target data pairs;

[0152] Step S43: Determine the comparison result based on the data similarity of each target data pair.

[0153] In this embodiment, the target motion model and the target reference model may have different model types when the wearable device is available or unavailable. In this case, different algorithms can be used to compare the target motion model and the target reference model.

[0154] Scenario 1: Wearable devices are available.

[0155] In this context, the target motion model can be referred to as the recorded sequence, and the target reference model as the reference sequence; the reference sequence contains the expected pose information (e.g., Euler angles in three-dimensional space) at each detection moment. The recorded sequence reflects the motion monitoring data collected by the user from the wearable device throughout the intervention. Here, target data pairs corresponding to the same timestamps in the recorded and reference sequences can be identified, and then the data similarity of the target data pairs can be determined. By comparing the similarity of the data between the reference and recorded sequences, a performance score can be obtained (e.g., a performance score between 0 and 100).

[0156] For example, the following reference sequence and recording sequence each contain data at 5 timestamps, where the Euler angles of the X, Y, and Z axes are measured at each timestamp:

[0157] Reference sequence: <(35, 24, 67), (16, 47, 24), (-24, 95, -3), (-61, 35, 24), (56, 33, 5)>.

[0158] Record sequence: <(30, 42, 70), (12, 60, 2), (-24, 95, -3), (-61, 35, 24), (56, 33, 5)>.

[0159] At this point, the target data pairs (Euler angles) with corresponding timestamps in the reference sequence and the record sequence can be determined. Then, the data similarity of the target data pairs is determined, and the data similarity of each target data pair is obtained. Finally, the alignment result can be determined based on the data similarity of all target data pairs.

[0160] For example, the average data similarity of each target data pair can be calculated, and then this average value can be used as the comparison result.

[0161] Scenario 2: Wearable device is unavailable.

[0162] In this case, the recorded sequence can be an image sequence obtained from a camera device, such as a mobile phone camera or a webcam. Here, a convolutional neural network model can be used to extract measurements from each video frame of the reference sequence and the recorded sequence, specifically comprising two parts:

[0163] Convolutional layer: A stack of convolutional layers and max-set layers used to interpret the salient features of the input video frame; the output of the convolutional layer is a flattened one-dimensional feature vector.

[0164] Fully connected layers: a dense set of layers used to compute measurements based on feature vectors extracted from two input images; the measurements typically involve Euler angles to determine pose variations between the two input images.

[0165] For example, given an image, denoted as X0, and a video frame, denoted as X1, convolutional layers are applied to X0 and X1 to extract corresponding pose feature vectors U0 and U1. Fully connected layers concatenate the two feature vectors, outputting a vector Y that reflects the pose change from X0 to X1. Vector Y is then added to the recording sequence as a measurement at a specific timestamp.

[0166] After obtaining the recorded sequences, a dynamic time warp algorithm is used to measure the similarity between the recorded sequences and the reference sequences. For example, a cosine similarity index can be used to calculate the similarity between two recorded sequences and the reference sequence.

[0167] Finally, the similarity score (S) is converted into a performance score (P), ranging from 0 to 100. Let L and H be predefined parameters reflecting the designer's expected range of similarity scores, i.e., the range in which users are most likely to obtain a similarity score. Then, the performance score can be calculated as follows:

[0168] P=min{max{(SL) / (HL)*100,0},100}.

[0169] The performance score p is guaranteed to be between 0 and 100. The choice of L and H determines the difficulty for users to obtain a high performance score.

[0170] By using the above processing methods, more accurate comparison results can be obtained, thereby providing users with more accurate health interventions.

[0171] In an optional implementation, when the target reference model is medical image data, the step of comparing the target motion model and the target reference model to obtain the comparison result specifically includes the following steps:

[0172] Step S51: Extract the state information of the user's monitored parts based on the target motion model; wherein, the monitored parts include, but are not limited to, the following parts: skeletal, joint, and muscular systems;

[0173] Step S52: Compare the status information of the monitored site with the expected bone status of the monitored site in the medical imaging data to obtain the comparison result.

[0174] As described above, the target reference model includes a reference motion model and medical imaging data; both are pre-stored in a database. The medical imaging data, specifically including MRI, CT, and X-ray images, is used to indicate the expected skeletal condition corresponding to the user.

[0175] For example, medical imaging data can be used to create models that indicate the expected skeletal state, such as models of spinal alignment, joint deformities, cervical lordosis, and cervical kyphosis.

[0176] At this point, the skeletal state information of the user's target skeletal parts can be extracted based on the target motion model. For example, the state information of the spine, joints, and cervical vertebrae can be extracted.

[0177] Next, the bone condition information can be compared with the expected bone condition in medical imaging data to obtain the comparison results. These results can then be used to determine the health status of the user's target bone region, such as whether a lesion has already occurred or is about to occur.

[0178] In this embodiment of the application, by capturing the user's motion monitoring data in real time, the skeletal status of the user's target skeletal parts can be continuously detected and evaluated, thereby enabling longitudinal tracking of an individual's spinal and joint health and promoting long-term evaluation of the intervention effect.

[0179] In an optional implementation, the above steps generate health intervention and correction information based on the comparison results, and send the health intervention and correction information to the health intervention device, specifically including the following steps:

[0180] Step S61: Based on the comparison results, determine the model differences between the target motion model and the target reference model;

[0181] Step S62: Determine health intervention strategies that match the differences in the model;

[0182] Step S63: Determine the health intervention device that matches the health intervention strategy, and generate health intervention and correction information that matches the health intervention strategy;

[0183] Step S64: Send the health intervention and correction information to the matched health intervention device.

[0184] In this application embodiment, an artificial intelligence-enabled algorithm can be used to identify situations where the target motion model deviates from the norm (i.e., model discrepancies), and based on these situations, appropriate intervention measures can be recommended to the user.

[0185] Here, the comparison results can be input into an artificial intelligence algorithm for analysis to obtain model differences; these model differences indicate the deviation of data in the target motion model from the normed values. Then, a matching health intervention strategy is searched in a correlation table; these strategies include, but are not limited to, video guidance, haptic feedback from wearable devices, active intervention using devices such as elastic bands, and therapeutic interventions using robots to assist rehabilitation.

[0186] After determining the health intervention strategy, suitable health intervention devices can be identified. These devices could be sensors or other equipment, such as a massage chair. Then, health intervention and corrective information tailored to the health intervention device can be generated.

[0187] Here, health intervention and correction information is used to indicate intervention measures for users' health. These intervention measures include active intervention measures and passive intervention measures.

[0188] For proactive intervention measures, the health intervention and correction information can be intervention command information. Specifically, by sending this intervention command information to the health intervention device, the device can be controlled to perform corresponding operations, such as haptic feedback-related operations or elastic stretching operations. Through this process, the user can be proactively controlled to perform corresponding rehabilitation movements.

[0189] Specifically, for passive intervention measures, the health intervention and correction information can be voice guidance information or video guidance information. For example, the voice guidance information can be voice information guiding the user to perform corresponding rehabilitation movements; the video guidance information can be video information guiding the user to perform corresponding rehabilitation movements.

[0190] In the above embodiments, the target motion model is aligned with the target reference model using AI-supported algorithms, and the user is guided to perform correct movements through visual detection or wearable devices, thereby providing automated therapy. Furthermore, real-time feedback on the user's motion state based on AI can automatically adjust intervention measures accordingly. The entire process can achieve physical therapy and real-time feedback for the user without human intervention.

[0191] In an optional implementation, health intervention and correction information is generated based on the comparison results, including:

[0192] Based on the comparison results, health intervention and correction information matching the health intervention device is generated; wherein, the health intervention and correction information includes the following types: vibration information, video information, audio information, text information, and instruction information.

[0193] Here, the health intervention device can be a sensor that collects motion monitoring data, or other devices that can communicate and connect with the target application (or electronic device). For example, the health intervention device could be a smart massager or a smart robot.

[0194] At this point, health intervention and correction information matching the health intervention device can be generated. For example, if the health intervention device is a media player, video or audio-based health intervention and correction information can be generated. If the health intervention device is a massage chair, instruction-based health intervention and correction information can be generated, which can be used to control the operation of the massage chair.

[0195] In an optional implementation, the above steps acquire various motion monitoring data obtained by detecting the user in the target state, specifically including the following steps:

[0196] The system acquires various body state data obtained by measuring the user's posture during sleep using sensors in various dimensions; wherein the body state data includes at least one of the following types of data: sleep posture monitoring data, body photoelectric monitoring signals, body electromyography monitoring signals, and body vital sign signals.

[0197] In this embodiment of the application, sleep posture monitoring data is used to indicate the user's body posture data during sleep, body electromyography monitoring signal is used to indicate the signal obtained by the user's body electromyography during sleep, and body vital sign signal is used to indicate the signal obtained by the user's body vital signs during sleep.

[0198] Here, various sensors can be used to measure the user's posture, thereby obtaining a variety of body state data. For example, a posture detector pre-positioned near the user's body can detect the user's posture data during sleep. This detector can be placed around specific body parts such as the cervical spine, shoulders, lumbar spine, and ankles. For instance, placing the posture detector around the user's cervical spine allows for the detection of cervical spine posture. Another example is the use of photoelectric sensors pre-positioned near the user's body to perform photoelectric detection, obtaining body photoelectric monitoring signals. Similarly, electromyography (EMG) sensors pre-positioned on the user's body can perform EMG detection, obtaining body EMG monitoring signals. Finally, vital sign sensors pre-positioned on the user's body can detect vital signs, obtaining vital sign signals.

[0199] In addition, image sensors can be used to collect images of users during sleep. By analyzing these images, the user's sleep posture monitoring data can be determined. Alternatively, sound acquisition devices can be used to collect sounds made by users during sleep, such as snoring and breathing, to predict their sleep posture monitoring data.

[0200] After acquiring the body state data, the user's target motion model can be determined based on the body state data. This target motion model can be understood as a sleep posture model determined based on sleep posture monitoring data obtained from the user's sleep state. In this case, if the target reference model is a sleep reference model, the above steps compare the target motion model with the target reference model to obtain the comparison result. Specifically, this includes the following steps:

[0201] The sleep posture model and the sleep reference model are compared to obtain the comparison result; wherein, the sleep reference model is used to indicate the user's desired sleep posture.

[0202] Here, when the target state is sleep, posture detection can be performed on the sleeping user to obtain sleep posture monitoring data. Then, a sleep posture model can be determined based on this data; this model can indicate the user's state information during sleep, such as sleep posture information.

[0203] Next, the sleep posture model and the target reference model can be compared to obtain the comparison results. Based on the comparison results, health intervention and correction information can be generated and sent to the health intervention device.

[0204] For example, the cervical spine posture of a sleeping user can be detected to obtain sleep posture monitoring data. Then, a sleep posture model can be determined based on this data, and this model can be compared with a target reference model used to indicate cervical spine posture in a standard sleeping position to obtain comparison results. Alternatively, sleep posture monitoring data can be compared with medical imaging data in a standard sleeping position to obtain comparison results.

[0205] The comparison results can determine whether the user's cervical spine is in the desired sleep posture. If it is determined that the user is not in the desired sleep posture, health intervention and correction information can be generated and sent to a health intervention device.

[0206] In an optional implementation, the above steps, which generate health intervention and correction information based on the comparison results and send the health intervention and correction information to the health intervention device, include:

[0207] If, based on the comparison results, a significant difference is found between the user's sleeping posture and the desired sleeping posture, health intervention and correction information is sent to the user's sleep intervention device. This health intervention and correction information is used to adjust the user's sleeping posture through the sleep intervention device. Here, intervention in the user's posture can be achieved through automatic inflation or mechanical adjustment. These intervention methods can automatically reduce pressure in high-stress areas such as those with eczema.

[0208] Here, the health intervention device can be a sleep intervention device; or it can be other auxiliary devices. The sleep intervention device can be an inflatable mattress or mechanical mattress that can inflate automatically; wherein the inflatable mattress or mechanical mattress has a built-in pressure sensor. Here, the sleep intervention device can include sub-devices, each of which can be an inflatable mattress or mechanical mattress, and each inflatable mattress or mechanical mattress can contain multiple inflation zones. For example, as... Figure 5A and Figure 5B As shown, an inflatable or mechanical pad 1 can be placed below the head, an inflatable or mechanical pad 2 can be placed in the area extending from the shoulder blades to below the neck, and another inflatable or mechanical pad 3 can be placed in the area from the hips to the waist. By following... Figure 5A and Figure 5B The sleep intervention device shown is designed to address forward head posture. Since nighttime sleep is more plentiful than daytime sleep, it can improve forward head posture during sleep. By using inflatable or mechanical pads 1, 2, and 3, the device can lift the shoulders and lower back, thereby improving forward head posture.

[0209] In this embodiment, the inflation volume of the air pad or mechanical pad can be set by inflation. For example, the inflation state of the air pad or mechanical pad can be adjusted based on body state data detected by sensors. For example, assuming the sleep intervention device includes multiple air pads, and each air pad includes multiple inflation areas, the air pad to be adjusted, the inflation area to be inflated within the air pad to be adjusted, and the inflation parameters of the inflation area to be inflated can be determined based on the body state data detected by sensors. For example, the inflation parameters may include, but are not limited to, the following parameters: inflation volume, deflation volume, inflation time, etc.

[0210] For example, the level of muscle tension in a user during sleep can be determined by collecting electromyographic signals from the user. Then, the inflation parameters of the area to be inflated in the inflatable pad can be determined based on the level of muscle tension. By adjusting the area to be inflated according to these inflation parameters, the user's muscles can be relaxed.

[0211] In this embodiment, a sleep intervention device can also be 3D printed based on each individual's medical diagnosis and recommendations (e.g., photographs, X-rays). This process enables personalized sleep intervention devices for each user, resulting in a device more closely matched to each user's physical condition. Here, the 3D-printed sleep intervention device can be a mechanical mat tailored to the user's spinal health.

[0212] In this embodiment of the application, the inflatable cushion or mechanical cushion is not limited to being disposed as shown in the example. Figure 5A and Figure 5B The location shown can also be set in other areas. This application does not make specific limitations on this, but only to the extent that it can be achieved.

[0213] In the embodiments of this application, such as Figure 5A As shown, a terminal device 4, such as a smartphone, can also be placed on the side of the user's body. The terminal device must be able to capture a complete image of the user's body. The placement of the terminal device is not specifically limited, as long as it can capture a complete image of the user's body. This terminal device can collect the user's visual images, breathing sounds, and other information. Based on this visual imagery and / or breathing sounds, the user's physical state data during sleep can be determined. This physical state data can then be used to adjust the inflation state of the inflatable or mechanical mattress. Alternatively, the terminal device can also detect the user's physical state data during sleep using microwave detection.

[0214] In practice, the inflatable or mechanical pad 1 in the head area can be lowered. If the user's posture does not meet the preset requirements after lowering the inflatable or mechanical pad 1, the inflatable or mechanical pad 2 can be inflated. Inflating the inflatable or mechanical pad 2 lowers the head area. In addition, the inflatable or mechanical pad 2 in the scapular area can also be lowered. If the user's posture does not meet the preset requirements after lowering the inflatable or mechanical pad 2, the inflatable or mechanical pad 3 can be inflated. Inflating the inflatable or mechanical pad 3 corrects lumbar forward tilt from the scapular area to the waist area.

[0215] In addition, the sleep intervention device can be a smart massage pillow. For example, health intervention and correction information can be sent to the smart massage pillow, which can adjust its own state to adjust the user's cervical spine posture, thereby enabling the user's cervical spine to be in the desired sleeping posture, so as to improve the user's sleep quality.

[0216] In the embodiments of this application, the type of sleep intervention device and the location of the sleep intervention device can be set for the problems that need to be improved, and this application does not make specific limitations in this regard.

[0217] Reference Figure 6 The diagram shown is a schematic of a vision and sensor-based health intervention and correction system provided in an embodiment of this disclosure. The system includes a plurality of sensors 51 and a processor 52.

[0218] Multiple sensors 51 are configured to detect the user's motion in a target state and obtain various motion monitoring data.

[0219] The processor 52 is configured to acquire the various motion monitoring data and determine the user's target motion model based on the various motion monitoring data; wherein the target motion model is used to indicate the user's state information at each detection time; compare the target motion model with a target reference model to obtain a comparison result; generate health intervention and correction information based on the comparison result, and send the health intervention and correction information to the health intervention device.

[0220] Here, various types of motion monitoring data can refer to motion monitoring data collected by detecting user movement through multiple sensors. The data types of these various motion monitoring data are not entirely the same.

[0221] Here, various sensors are used, including wearable devices and camera equipment.

[0222] Here, motion monitoring data refers to data obtained by detecting motion in various monitoring parts of the user, including but not limited to the following parts: bones, joints, and muscles; the data types of various motion monitoring data include but are not limited to the following types: visual images, photoelectric data, neuroelectrophysiological data, audio data, and speed data.

[0223] By using exercise monitoring data, the following relevant exercise data of users can be determined: the user's exercise posture, exercise duration, exercise speed, exercise mode (e.g., cycling or walking), physical state during exercise (e.g., heart rate, blood oxygen concentration, blood pressure, pulse), exercise trajectory, and other exercise-related data.

[0224] In this embodiment, a target application can be installed in an electronic device. Here, the processor in the electronic device can acquire motion monitoring data collected by various sensors and send the motion monitoring data to the target application. After acquiring the motion monitoring data, the target application can execute steps S103 to S107 as described above. If the sensor is a wearable device, a client that communicates with the wearable device can be installed in the electronic device. The client can acquire the motion monitoring data collected by the wearable device through this communication connection and send the motion monitoring data to the target application.

[0225] In addition, communication connections can be established between the processor and various sensors, such as between the processor and a wearable device. The wearable device can then transmit motion monitoring data to the processor via this communication connection, and after acquiring the motion monitoring data, it can execute steps S103 to S107 as described above.

[0226] Here, multiple sensors include: wearable devices and camera devices; wherein the wearable devices and camera devices are configured to be wirelessly or wiredly connected to the processor.

[0227] Here, after acquiring multiple motion monitoring data, these multiple motion monitoring data can be fused together to obtain the target motion model.

[0228] Here, there can be multiple target motion models, and the types of data contained in different target motion models are different. In other words, multiple different target motion models for the same time period can be generated using various types of motion monitoring data.

[0229] Here, the target motion model can be represented in one or more of the following ways: mathematical model, statistical model, biomechanical model, kinematic model, or machine learning model.

[0230] Here, the target motion model can be converted into a motion sequence; this motion sequence can indicate the user's posture information at each detection moment. Here, the detection moment is the moment when the sensor detects the user's motion.

[0231] Here, the target reference model can be a reference model generated from the user's normal motion monitoring data, or a reference model generated according to clinical standards. This target reference model can be used to determine the expected posture information of the object under normal circumstances.

[0232] Here, the target reference model can be represented in one or more of the following ways: mathematical model, statistical model, biomechanical model, kinematic model, or machine learning model.

[0233] In this embodiment, firstly, various motion monitoring data obtained from motion detection of the user are acquired; then, a target motion model of the user is determined based on the various motion monitoring data, wherein the user's posture information at each detection moment can be determined through the target motion model; next, by comparing the target motion model with a target reference model, health intervention and correction information of the user can be generated and sent to a health intervention device.

[0234] In the above embodiments, by determining the target motion model based on various motion monitoring data of the user, a personalized health model can be generated for the user; by comparing the target motion model with the target reference model to generate health intervention and correction information, more accurate health intervention and correction information can be generated for the user, thereby providing the user with more accurate intervention measures.

[0235] In an optional implementation, the processor 52 includes a processing module, a comparison module, and an intervention module.

[0236] The processing module is configured to acquire the various motion monitoring data and determine the user's target motion model based on the various motion monitoring data.

[0237] Here, the processing module can determine the user's target motion model in the manner described in the above embodiments, which will not be described in detail here.

[0238] The comparison module is configured to compare the target motion model with the target reference model to obtain the comparison result.

[0239] Here, the comparison module can compare the target motion model and the target reference model in the manner described in the above embodiments, which will not be described in detail here.

[0240] The intervention module is configured to generate health intervention and correction information based on the comparison results, and send the health intervention and correction information to the health intervention device.

[0241] Here, the intervention model can generate health intervention and correction information in the manner described in the above embodiments, which will not be described in detail here.

[0242] The following describes a vision- and sensor-based health intervention and correction system with specific embodiments. This system, with user authorization, can monitor and intervene in the bending movements and wear of the head, spine, and joints, as well as related neurological and cardiopulmonary functions.

[0243] Here, the vision and sensor-based health intervention and correction system includes sensors and processors, wherein the sensors include wearable devices, camera devices, and monitoring modules of wearable devices.

[0244] Here, wearable devices can be categorized into four monitoring modules: Module 1, Module 2, Module 3, and Module 4. Module 1 can detect ear hooks, smart glasses, and smart headbands; Module 2 can detect smart chest straps; Module 3 can detect smart waist belts; and Module 4 can detect visual sensors. These monitoring modules can detect the user's state and obtain various motion monitoring data.

[0245] For example, module one can detect changes in the angle of the cervical spine through ear loops, glasses, and headbands; module two can detect electrocardiogram, heart rate, and respiration through a chest strap and assist the head sensor in locating the angle of the thoracic and lumbar spine; module three can detect wear and tear on the spine and limb joints through a waist belt or rings around the large joints of the limbs, and record the electromyographic signals of the large muscles near the spinal joints, and the large muscles of the large joints of the limbs, such as the knee, ankle, elbow, or wrist joints; and module four can acquire visual images through a visual sensor.

[0246] Each monitoring module is equipped with a Bluetooth chip, which enables communication with clients in electronic devices.

[0247] For example, Module 1 includes a control chip, Bluetooth chip, battery, nine-axis motion sensor, and vibration motor. It may further include dual-color LED indicators and a buzzer. Module 2 includes a control chip, Bluetooth chip, battery, nine-axis motion sensor, and ECG monitoring module. Module 3 includes a control chip, Bluetooth chip, battery, EMG & MMG monitoring module, vibration and audio acquisition chip, and directional microphone. It may further include dual-color LED indicators, etc.

[0248] Here, the headband module one is placed on the head; the chest strap module two is placed on the left chest; and the waist strap module three is placed on the lower back. These modules respectively have additional functions including recording heart rate, electrocardiogram, respiratory status, vital capacity, respiratory rate, oxygen saturation, bowel sounds, and abdominal pressure, as well as detecting and intervening in lumbar spine tension and movement. Depending on the situation, users can use one, two, or all three modules individually.

[0249] In this embodiment, motion monitoring data collected by the corresponding wearable devices can be collected through modules one through four. After collection, the data is transmitted to the client via Bluetooth chip for processing. Here, the client can determine the user's target motion model based on the various motion monitoring data. The target motion model is used to indicate the user's state information at each detection time. The target motion model is compared with the target reference model to obtain a comparison result. Based on the comparison result, health intervention and correction information is generated and sent to the health intervention device.

[0250] The specific implementation of the client is as described above, and will not be repeated in detail here.

[0251] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0252] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0253] Corresponding to Figure 1 In addition to vision- and sensor-based health intervention and correction methods, this disclosure also provides an electronic device 700, such as... Figure 7 The diagram shown is a structural schematic of an electronic device 700 provided in an embodiment of this disclosure, including:

[0254] The system includes a processor 71, a memory 72, and a bus 73. The memory 72 stores execution instructions and includes main memory 721 and external memory 722. The main memory 721, also called internal memory, temporarily stores the computational data in the processor 71, as well as data exchanged with external memory such as a hard disk. The processor 71 exchanges data with the external memory 722 through the main memory 721. When the electronic device 700 is running, the processor 71 communicates with the memory 72 through the bus 73, causing the processor 71 to execute the following instructions:

[0255] Acquire various motion monitoring data obtained by detecting users in a target state;

[0256] The user's target motion model is determined based on the various motion monitoring data; wherein, the target motion model is used to indicate the user's state information at each detection time.

[0257] The target motion model and the target reference model are compared to obtain the comparison results;

[0258] Based on the comparison results, health intervention and correction information is generated and sent to the health intervention device.

[0259] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the vision- and sensor-based health intervention and correction method described in the above-described method embodiments. The storage medium can be volatile or non-volatile computer-readable storage.

[0260] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the vision and sensor-based health intervention and correction method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0261] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0262] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0263] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0264] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0265] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0266] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A health intervention and correction method based on vision and sensors, characterized in that, include: Acquire various motion monitoring data obtained by detecting users in a target state; The user's target motion model is determined based on the various motion monitoring data; wherein, the target motion model is used to indicate the user's state information at each detection time. The target motion model and the target reference model are compared to obtain the comparison results; Based on the comparison results, health intervention and correction information is generated and sent to the health intervention device.

2. The method according to claim 1, characterized in that, The acquisition of various motion monitoring data obtained by detecting the user in the target state includes: The user's motion is detected by various wearable devices that are connected to the terminal device, and the various motion monitoring data are obtained.

3. The method according to claim 2, characterized in that, The various motion monitoring data are data obtained by detecting motion in various monitoring parts of the user, including but not limited to the following parts: bones, joints, and muscles; the data types of the various motion monitoring data include but are not limited to the following types: visual images, photoelectric data, neuroelectrophysiological data, audio data, and speed data.

4. The method according to claim 1, characterized in that, The process of determining the user's target motion model based on the various motion monitoring data includes: Each type of motion monitoring data is transformed into the user's motion posture data; Based on the detection time of the motion posture data, the motion posture data obtained after transforming various motion monitoring data are fused to obtain the target motion model.

5. The method according to claim 4, characterized in that, The detection time based on the motion posture data involves fusing the motion posture data obtained after transforming various motion monitoring data to obtain the target motion model, including: In each type of motion posture data after the motion monitoring data is transformed, determine the motion posture data that is at the same detection time; The motion posture data at the same detection time are processed to obtain the target motion posture data at that detection time. Based on the target motion posture data at each of the detection times, the target motion model is determined.

6. The method according to claim 1, characterized in that, The target reference model is a reference motion model; the comparison between the target motion model and the target reference model to obtain the comparison result includes: Based on the target motion model, the user's object information is determined; wherein the object information is used to indicate the user's motion state and / or object attributes; Determine a reference motion model that matches the object information; wherein the matching reference motion model is used to indicate the user's expected posture information in the motion state; The matching reference motion model and the target motion model are compared to obtain the comparison result.

7. The method according to claim 1, characterized in that, The step of comparing the target motion model and the target reference model to obtain the comparison result includes: Determine the target data pairs with corresponding timestamps in the target motion model and the target reference model; Determine the data similarity of the target data pairs; The comparison result is determined based on the data similarity of each target data pair.

8. The method according to claim 1, characterized in that, The process of generating health intervention and correction information based on the comparison results and sending the health intervention and correction information to the health intervention device includes: Based on the comparison results, the model differences between the target motion model and the target reference model are determined; Determine health intervention strategies that match the differences in the model; Identify health intervention devices that match the health intervention strategy, and generate health intervention and corrective information that matches the health intervention strategy; The health intervention and correction information is sent to the matched health intervention device.

9. The method according to claim 1, characterized in that, The target reference model is medical image data; the comparison between the target motion model and the target reference model to obtain the comparison result includes: The state information of the user's monitored body parts is extracted based on the target motion model; wherein, the monitored body parts include, but are not limited to, the following: skeletal, joint, and muscular systems; The status information of the monitored site is compared with the expected bone status of the monitored site in the medical imaging data to obtain the comparison result.

10. The method according to claim 1, characterized in that, The target motion model is a sleep posture model determined based on the body state data detected by the user in a sleep state, and the target reference model is a sleep reference model; The acquisition of various motion monitoring data obtained by detecting the user in the target state includes: The system acquires various body state data obtained by measuring the user's posture during sleep using sensors at various dimensions; wherein the body state data includes at least one of the following types of data: sleep posture monitoring data, body photoelectric monitoring signals, body electromyography monitoring signals, and body vital sign signals; The step of comparing the target motion model and the target reference model to obtain the comparison result includes: The sleep posture model and the sleep reference model are compared to obtain the comparison result; wherein, the sleep reference model is used to indicate the user's desired sleep posture.

11. The method according to claim 10, characterized in that, The process of generating health intervention and correction information based on the comparison results and sending the health intervention and correction information to the health intervention device includes: If, based on the comparison results, it is determined that there is a significant difference between the user's sleeping posture and the desired sleeping posture, health intervention and correction information is sent to the user's sleep intervention device; wherein, the health intervention and correction information is used to adjust the user's sleeping posture through the sleep intervention device.

12. The method according to claim 1, characterized in that, The generation of health intervention and correction information based on the comparison results includes: Based on the comparison results, health intervention and correction information matching the health intervention device is generated; wherein, the health intervention and correction information includes the following types: vibration information, video information, audio information, text information, and instruction information.

13. A health intervention and correction system based on vision and sensors, characterized in that, include: Multiple sensors and processors; The multiple sensors are configured to detect the user's motion in the target state and obtain various motion monitoring data; The processor is configured to acquire the various motion monitoring data and determine the user's target motion model based on the various motion monitoring data; wherein the target motion model is used to indicate the user's state information at each detection time; compare the target motion model with a target reference model to obtain a comparison result; generate health intervention and correction information based on the comparison result, and send the health intervention and correction information to a health intervention device.

14. The system according to claim 13, characterized in that, The processor includes: a processing module, a comparison module, and an intervention module; The processing module is configured to acquire the various motion monitoring data and determine the user's target motion model based on the various motion monitoring data; The comparison module is configured to compare the target motion model and the target reference model to obtain a comparison result; The intervention module is configured to generate health intervention and correction information based on the comparison results, and send the health intervention and correction information to the health intervention device.

15. The system according to claim 13, characterized in that, The plurality of sensors include: a wearable device and a camera device; wherein the wearable device and the camera device are configured to be wirelessly or wiredly connected to the processor.

16. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the vision and sensor-based health intervention and correction method as described in claim 1.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the vision- and sensor-based health intervention and correction method as described in claim 1.

Images