Neck movement guiding system based on mixed reality glasses

Abstract

The embodiment of the invention discloses a neck movement guiding system based on mixed reality glasses. A specific embodiment of the system comprises mixed reality glasses, a server and a doctor end, wherein the server is configured to execute the following detection steps: receiving user input information, activity data, pain arc marking data and head motion angular velocity data; carrying out shake removal processing on the head motion angular velocity data; objective motion function detection is carried out; generating a detection report and neck and back movement guide parameter data; the doctor end is configured to generate interactive virtual motion guidance rendering information and target motion parameter information, and send the interactive virtual motion guidance rendering information and the target motion parameter information to the mixed reality glasses, so that the mixed reality glasses execute neck motion guidance operation. According to the implementation mode, the neck rehabilitation treatment effect is improved.

Description

Technical Field

[0001] Embodiments of this disclosure relate to the field of computer technology, and more specifically to a neck motion guidance system based on mixed reality glasses. Background Technology

[0002] With the rapid development of mixed reality (MR) and wearable sensing technologies, digital and immersive rehabilitation therapy has become an important trend in modern medicine. Neck movement guidance systems based on mixed reality glasses provide patients with precise, visualized neck rehabilitation training guidance based on a fusion of real-world environments, enabling remote quantitative assessment and management. Currently, the common approach to generating neck rehabilitation movement guidance plans is for therapists to observe patients through two-dimensional images (such as video calls) or in person, while patients practice independently using standardized videos on their mobile phones.

[0003] However, when using the above methods to guide neck rehabilitation training, the following technical problems often arise: Standardized videos or movement templates are used to guide patients in their exercises, but each patient's situation is different, especially in terms of neck and back flexibility, pain levels, and recovery progress. Therefore, standardized videos often fail to meet the individual needs of patients and may even lead to exercises that are too intense or too weak. Furthermore, when patients practice on their own using videos, the lack of feedback and guidance results in poor outcomes for neck rehabilitation treatment.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not form prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure propose a neck motion guidance system based on mixed reality glasses and a method for generating neck and back motion guidance parameter data to address one or more of the technical intentions mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide a neck movement guidance system based on mixed reality glasses. The system includes mixed reality glasses, a server, and a doctor's terminal. The server is configured to perform the following detection steps: receiving user input information, activity data, pain arc marker data, and head motion angular velocity data collected by the mixed reality glasses; performing anti-shake processing on the head motion angular velocity data to obtain anti-shake angular velocity data; performing objective motion function detection on the anti-shake angular velocity data, the activity data, and the pain arc marker data to obtain motion function detection information; generating a detection report and neck and back movement guidance parameter data based on the motion function detection information and the user input information; sending the detection report and the neck and back movement guidance parameter data to the doctor's terminal; and the doctor's terminal is configured to display the received detection report and neck and back movement guidance parameter data on a preset parameter adjustment page to generate interactive virtual motion guidance rendering information and target motion parameter information, and to send the interactive virtual motion guidance rendering information and target motion parameter information to the mixed reality glasses for the mixed reality glasses to perform neck movement guidance operations.

[0008] Secondly, some embodiments of this disclosure provide a method for generating neck and back motion guidance parameter data. The method includes: receiving user input information, activity level data, pain arc marker data, and head motion angular velocity data collected by the mixed reality glasses; performing anti-shake processing on the head motion angular velocity data to obtain anti-shake angular velocity data; performing objective motion function detection on the anti-shake angular velocity data, the activity level data, and the pain arc marker data to obtain motion function detection information; generating a detection report and neck and back motion guidance parameter data based on the motion function detection information and the user input information; and sending the detection report and the neck and back motion guidance parameter data to the doctor's terminal.

[0009] The various embodiments of this disclosure have the following beneficial effects: the neck movement guidance system based on mixed reality glasses according to some embodiments of this disclosure improves the effect of neck rehabilitation treatment. Specifically, the reason for the poor effect of neck rehabilitation treatment is that standardized videos or action templates are used to guide patients to practice, but each patient's situation is different, especially in terms of neck and back flexibility, pain level, and recovery status. Therefore, standardized videos often cannot meet the individual needs of patients, and may even lead to excessive or insufficient exercise intensity. Moreover, when patients practice on their own through videos, there is a lack of feedback guidance, resulting in poor neck rehabilitation treatment effect. Based on this, the neck movement guidance system based on mixed reality glasses according to some embodiments of this disclosure includes: mixed reality glasses, a server, and a doctor's end, wherein: the server is configured to perform the following detection steps: receiving user input information, activity data, pain arc marker data, and head motion angular velocity data collected by the mixed reality glasses. Thus, multi-dimensional user input information, activity data, pain arc marker data, and head motion angular velocity data that reflect the individual functional state and subjective feelings of the user can be obtained. Then, the head motion angular velocity data is subjected to anti-shake processing to obtain anti-shake angular velocity data. Therefore, noise introduced by head tremors or environmental vibrations can be detected, resulting in accurate and stable data reflecting the user's voluntary neck movement intentions. Next, objective motor function testing is performed on the aforementioned de-shaking angular velocity data, range of motion data, and pain arc marker data to obtain motor function testing information. This provides motor function testing information that quantifies the individualized functional impairment patterns of the patient. Subsequently, based on the aforementioned motor function testing information and the aforementioned user input information, a testing report and neck and back movement guidance parameter data are generated. Thus, a testing report and neck and back movement guidance parameter data can be generated by integrating subjective assessment (i.e., motor function testing information) and subjective feelings. Then, the aforementioned testing report and neck and back movement guidance parameter data are sent to the doctor's end. As can be seen from the above, the server uses raw, multimodal user data from mixed reality glasses, through a series of calculations and intelligent analyses, to provide accurate motor function assessments and personalized treatment guidance, offering decision support for doctors and data support for telemedicine collaboration. The doctor's terminal is configured to display the received test report and neck and back movement guidance parameters on a preset parameter adjustment page to generate interactive virtual movement guidance rendering information and target movement parameter information. This interactive virtual movement guidance rendering information and target movement parameter information are then sent to the mixed reality glasses for the mixed reality glasses to perform neck movement guidance operations.By using mixed reality glasses, personalized virtual movement guidance information (i.e., the animated guidance information rendered from interactive virtual movement guidance) is presented intuitively to users. Patients can perform neck exercises according to precise guidance, avoiding situations where inappropriate exercise intensity affects the treatment effect, thus effectively improving the treatment outcome. Furthermore, because the server generates a test report and neck and back movement guidance parameters suitable for the user based on multimodal user data from the mixed reality glasses, doctors can use this data to develop personalized guidance plans—including interactive virtual movement guidance rendering information and target movement parameter information—and present these plans intuitively to patients through the mixed reality glasses, meeting the personalized needs of patients' neck movements and improving treatment effectiveness. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0011] Figure 1 This is an architecture diagram of an exemplary system for a neck movement guidance system based on mixed reality glasses according to the present disclosure; Figure 2 Flowcharts of some embodiments of the neck and back motion guidance parameter data generation method according to this disclosure; Figure 3 These are internal test diagrams of some embodiments of a neck motion guidance system based on mixed reality glasses according to this disclosure. Detailed Implementation

[0012] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0013] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0014] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0015] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0016] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0017] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0018] Figure 1 An exemplary system architecture 100 for a neck motion guidance system based on mixed reality glasses, to which some embodiments of the present disclosure may be applied, is shown.

[0019] like Figure 1 As shown, the system architecture 100 may include: mixed reality glasses 103, server 102 and doctor's terminal 101, network 104, network 105, and network 106. Network 104 serves as the medium for providing a communication link between server 102 and doctor's terminal 101. Network 105 serves as the medium for providing a communication link between doctor's terminal 101 and mixed reality glasses 103. Network 106 serves as the medium for providing a communication link between server 102 and mixed reality glasses 103. Networks 104, 105, and 106 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc. The server 102 may be a server or a backend service software system deployed on a server (or cloud server cluster). The doctor's terminal 101 may be a doctor's remote control terminal (e.g., a desktop or laptop computer). The mixed reality glasses 103 may be MR glasses (mixed reality glasses) used by the user (patient).

[0020] In some embodiments, the database server 102 described above can be configured to perform the following detection steps: First, the system receives user input information, activity data, pain arc marker data, and head motion angular velocity data collected by the mixed reality glasses 103. The user input information can be information provided by a virtual assistant (such as a friendly animated character) that appears in the user's field of vision after they put on the MR glasses, guiding the user's input through voice and a floating menu. This user input information can include user information, pain area information, and a virtual VAS pain scale count. The user information can include basic personal information such as age, height, and name. The pain area information can be the location of the pain (which can be selected via gestures on a virtual cervical spine model). The virtual VAS pain scale count can be a VAS pain score determined by the user using a virtual visual analogue scale (VAS). For example, a scale from 0 (no pain) to 10 (severe pain), where the patient uses gestures to move a slider to score the pain.

[0021] In some alternative implementations of some embodiments, the mixed reality glasses 103 described above can perform neck movement guidance operations through the following steps: The first step involves responding to the user's input of neck and back movement guidance instructions, presenting a virtual guidance scene corresponding to the aforementioned interactive virtual movement guidance rendering information in the display module, and providing real-time tracking and feedback guidance for the user's neck and hand movements based on the aforementioned neck and back movement guidance instructions and the aforementioned target movement parameter information. The aforementioned neck and back movement guidance instructions can be instructions representing the execution of back movement guidance or neck movement guidance (e.g., converting the user's voice instructions into a system-recognizable signal through speech recognition technology, or receiving manually input instructions from the user through input devices such as a touchscreen or keyboard). The aforementioned interactive virtual movement guidance rendering information can be a set of data containing various element information used to construct the virtual guidance scene, such as the virtual character's posture and movement trajectory, which integrates virtual elements with the real scene (in mixed reality technology) or displays them separately (in a pure virtual scene), allowing the user to clearly see the correct movement actions and postures displayed by the virtual guidance character. The aforementioned display module can be a display screen used to display the virtual guidance scene. The neck movement guidance system based on mixed reality glasses 103 also includes a handheld locator, and the aforementioned target movement parameter information includes neck safety boundary parameter information and back safety boundary parameter information. The aforementioned handheld locator can be a device associated with the mixed reality glasses 103 that tracks the spatial position of the upper limbs and hands and enables interactive functions (e.g., a handheld spatial positioning controller or MR handle controller). The aforementioned neck safety boundary parameter information can be the safe range of neck movement (e.g., the safe angle range for left neck rotation is set to 0° to 50°). The aforementioned back safety boundary parameter information can be the safe range of shoulder joint rotation angle in the horizontal plane (e.g., 30°-40°).

[0022] In some optional implementations of certain embodiments, the mixed reality glasses 103 described above can perform real-time tracking and feedback guidance of the user's neck and hand movements based on the aforementioned neck and back movement guidance instructions and the aforementioned target movement parameter information through the following steps: The first step, in response to determining the characteristics of neck and back movement guidance instructions, is to execute back movement guidance, and to perform the following first real-time tracking and feedback guidance: The first sub-step involves collecting real-time spatial location information of the user's hand using a handheld locator. The second sub-step involves converting the collected spatial position information of the user's hand into back motion parameters. In practice, the mixed reality glasses 103 can obtain the arm projection length on the horizontal plane by inputting the horizontal and vertical coordinates of the user's hand spatial position information into a first preset formula. The arm projection length on the horizontal plane can be... express, ,in, It can be the x-coordinate of the hand's spatial position coordinates, as mentioned above. This can be the y-coordinate of the hand's spatial position. (The above...) This can be the x-coordinate of a preset initial shoulder joint position (e.g., the lateral coordinate of the initial shoulder joint position pre-input by the user, or a coordinate pre-detected by the mixed reality glasses). The y-coordinate can be the preset initial position coordinates of the shoulder joint (for example, the longitudinal coordinates of the initial shoulder joint position pre-input by the user, or pre-detected by the mixed reality glasses). Then, the rotation angle of the shoulder joint in the horizontal plane can be... This means that the length of the arm's projection on the horizontal plane will be represented. and the preset user arm length (For example, the arm length can be pre-entered by the user) Enter into The rotation angle of the shoulder joint in the horizontal plane is obtained. Then, the mixed reality glasses 103 described above can determine the rotation angle of the shoulder joint in the horizontal plane as back motion parameter information.

[0023] The third sub-step involves performing back motion feedback guidance based on the aforementioned back motion parameter information and back safety boundary parameter information. In practice, in response to the determination that the rotation angle represented by the back motion parameter information is not within the range represented by the back safety boundary parameter information, the aforementioned mixed reality glasses 103 can prominently prompt the user to make adjustments in the virtual scene or issue voice prompts through the headphones.

[0024] The second step, in response to the determination of the neck and back movement guidance instructions, involves executing neck movement guidance and performing the following second real-time tracking and feedback guidance: The first sub-step involves acquiring the user's neck motion parameters in real time using an inertial measurement unit. These neck motion parameters can be data on the actual movement of the neck, including at least one motion parameter (e.g., angle, velocity, etc.).

[0025] The second sub-step involves performing neck movement feedback guidance based on the aforementioned user neck movement parameter information and neck safety boundary parameter information. The aforementioned neck safety boundary parameter information includes at least one range of movement parameters. Each of the at least one movement parameter corresponds to one of the ranges of movement parameters within the at least one range of movement parameters. In practice, for each of the at least one movement parameter included in the user's neck movement parameter information, the movement parameter can be compared with the corresponding range of movement parameters in the neck safety boundary parameter information. In response to determining that the movement parameter is outside the range of movement parameters, the mixed reality glasses 103 can prominently prompt the user to adjust in the virtual scene or issue a voice prompt through the headphones. For example, the neck safety boundary parameter information could be a 46-degree left rotation, and the corresponding range of movement parameters for left rotation could be less than or equal to 45 degrees. With a small rotation, the angle reaches 46 degrees. At this point, in the virtual neck movement guidance scene presented by the mixed reality glasses 103 (e.g., displaying an animation of a green figure performing a standard left neck rotation), a prominent red warning box suddenly appears, displaying in large yellow text: "Neck left rotation angle too large, please adjust!"

[0026] In some embodiments, the mixed reality glasses 103 described above can be configured to collect user input information, activity data, pain arc marker data, and head motion angular velocity data through the following steps: The first step is to collect user input information through the preset virtual interface presented by the aforementioned display module.

[0027] The second step involves using an integrated motion capture system, combined with an inertial measurement unit (IMU) and a sound recognition module, to collect motion range data, pain arc marker data, and head motion angular velocity data. In practice, the IMU can collect head motion angular velocity data, and the maximum angle during the movement is recorded as the motion range. This motion range data includes sub-data for each direction (e.g., left rotation motion range data is the maximum angle during left rotation, and right rotation motion range data is the maximum angle during right rotation). The pain arc marker data records the angle position of the marker when pain occurs during movement. The sound recognition module identifies the user's voice reporting pain during movement, and upon detecting this voice, the motion capture system automatically records the angle position at that moment as the pain arc marker data. The head motion angular velocity data includes at least one angular velocity sub-data, each containing an angular velocity sequence and a corresponding direction identifier (e.g., the direction identifier for the angular velocity sub-data collected during left rotation could be left rotation). This angular velocity sequence reflects the change in angular velocity over time when the head moves in one direction (e.g., left rotation). As an example, the motion guidance is as follows: The virtual assistant says, "Now we will conduct a neck range of motion assessment. Please slowly follow the movement of the green cursor." Data acquisition: A green bullseye appears directly in front of the user's field of vision, and then slowly moves to its limit position in six directions: left rotation, right rotation, left lateral flexion, right lateral flexion, etc. Throughout the process, the inertial measurement unit (IMU) continuously acquires the head's angular velocity sequence at a frequency of 100Hz. Simultaneously, the system records data on pain markers appearing during the movement through voice prompts and real-time monitoring. When the user reports pain, the system automatically records the angle position at that moment. The entire data acquisition process ensures the synchronous recording of range of motion data, pain marker data, and head movement angular velocity data. The aforementioned defibrillation angular velocity data includes at least one defibrillation angular velocity sequence: left rotation defibrillation angular velocity sequence, right rotation defibrillation angular velocity sequence, left lateral flexion defibrillation angular velocity sequence, and right lateral flexion defibrillation angular velocity sequence. This motion capture system can be a system that integrates an inertial measurement unit (IMU) and a voice recognition module to recognize the user's voice reporting pain during movement, and automatically records the angle position at that moment as pain arc marker data upon recognizing the voice reporting pain. The aforementioned voice recognition module can be a dedicated functional unit that converts user speech into pain marker signals that can be recorded and processed by the system in real time.

[0028] Second, the head motion angular velocity data is processed to remove jitter, resulting in jitter-removed angular velocity data.

[0029] In some optional implementations of certain embodiments, the server 102 can perform jitter removal processing on the head motion angular velocity data through the following steps to obtain jitter-removed angular velocity data: First, for each angular velocity sub-data point in at least one of the above head motion angular velocity data, perform the following steps: The first sub-step is to determine the angular velocity sequence included in the above angular velocity sub-data as the angular velocity sequence to be de-jittered; The second sub-step involves performing sliding window grouping on the aforementioned angular velocity sequence to be de-jittered, resulting in a sequence of angular velocity groups to be de-jittered. Each angular velocity group in this sequence corresponds to two consecutive angular velocities to be de-jittered in the sequence. In practice, a sliding window technique can be used, employing a fixed-size window that slides across the angular velocity sequence with a preset sliding step (e.g., 1). Each time the window slides, the data within the window is treated as a angular velocity group to be de-jittered, resulting in the sequence of angular velocity groups to be de-jittered. For example, if the angular velocity sequence to be de-jittered is [angular velocity to be de-jittered 1, angular velocity to be de-jittered 2, angular velocity to be de-jittered 3], through sliding window grouping (window size 2, sliding step 1), the sequence of angular velocity groups to be de-jittered can be [group 1: [angular velocity to be de-jittered 1, angular velocity to be de-jittered 2], group 2: [angular velocity to be de-jittered 2, angular velocity to be de-jittered 3]].

[0030] The third sub-step involves identifying at least one set of angular velocities in the aforementioned set of angular velocities to be de-jittered that meets a preset condition as at least one set of jittery angular velocities. The preset condition may be that the absolute value of the difference between two angular velocities to be de-jittered in the set is greater than a first preset threshold.

[0031] The fourth sub-step involves filtering the angular velocity sequence to be de-jittered based on at least one set of jittered angular velocities to obtain a de-jittered angular velocity sequence.

[0032] The second step is to determine the obtained de-jitter angular velocity sequences as de-jitter angular velocity data.

[0033] In some optional implementations of certain embodiments, the server 102 may perform filtering on the angular velocity sequence to be de-jittered based on at least one jitter angular velocity group to obtain a de-jittered angular velocity sequence through the following steps: First, for each of the at least one jitter angular velocity groups mentioned above, perform the following steps: The first sub-step is to determine two consecutive angular velocities in the angular velocity sequence to be de-jittered that correspond to the jitter angular velocity group.

[0034] The second sub-step involves determining the two consecutive dejittering angular velocities as the preceding and subsequent dejittering angular velocities, respectively. In practice, the aforementioned execution entity can determine the dejittering angular velocity that appears earlier in the dejittering angular velocity sequence as the preceding dejittering angular velocity, and the other dejittering angular velocity as the subsequent dejittering angular velocity.

[0035] The third sub-step is to determine the previous angular velocity to be dejittered in the sequence of angular velocities to be dejittered as the target previous angular velocity to be dejittered.

[0036] The fourth sub-step is to determine the next angular velocity to be dejittered in the sequence of angular velocities to be dejittered as the target subsequent angular velocity to be dejittered.

[0037] The fifth sub-step involves filtering the preceding and subsequent angular velocities to be de-jittered in the angular velocity sequence based on the preceding and following angular velocities to be de-jittered, in order to update the angular velocity sequence. In practice, the execution entity can determine the absolute value of the difference between the preceding and following angular velocities to be de-jittered as the first target difference. In response to determining that the first target difference is greater than a second preset threshold, the preceding angular velocities to be de-jittered are removed from the angular velocity sequence to be de-jittered, thus updating the angular velocity sequence. Similarly, the absolute value of the difference between the following and following angular velocities to be de-jittered can be determined as the second target difference. In response to determining that the second target difference is greater than a third preset threshold, the following angular velocities to be de-jittered are removed from the angular velocity sequence to be de-jittered, thus updating the angular velocity sequence.

[0038] The second step is to determine the updated angular velocity sequence to be de-jittered as the de-jittered angular velocity sequence.

[0039] Third, objective motor function tests were performed on the aforementioned de-shaking angular velocity data, the aforementioned range of motion data, and the aforementioned pain arc marker data to obtain motor function test information.

[0040] In addressing the technical problems mentioned above, the application scenario of neck motor function detection and assessment often presents the following challenges: relying solely on single data points (e.g., pain arc marker data) to detect neck pain avoidance behaviors, or depending solely on patient complaints or observed overt pain responses (pain arcs), may overlook subtle compensatory movement patterns (such as stiffness, speed regulation, and microtremors) resulting from long-term pain or subconscious protection. This leads to poor accuracy in the detected motor function information. Furthermore, using mixed reality glasses to guide neck rehabilitation training based on this inaccurate motor function detection information results in poor rehabilitation outcomes. Therefore, this application scenario requires the following characteristics: suitability for identifying complex motor dysfunctions, including compensatory patterns. To address these technical problems, we have decided to adopt the following solution: In some optional implementations of certain embodiments, the server 102 may perform objective motor function detection on the aforementioned de-jitter angular velocity data, the aforementioned activity data, and the aforementioned pain arc marker data through the following steps to obtain motor function detection information: The first step involves inputting each de-jitter angular velocity sequence from the aforementioned de-jitter angular velocity data into a pre-trained pain-avoidance movement pattern detection model to obtain pain-avoidance movement detection information corresponding to the de-jitter angular velocity sequence. This pain-avoidance movement pattern detection model can be a classification / recognition model that takes the de-jitter angular velocity sequence as input and pain-avoidance movement detection information as output. The model can analyze the smoothness of movement in pain-related de-jitter angular velocity sequences to obtain pain avoidance identification labels (e.g., "pain-avoidance movement exists" or "normal movement"). The direction identifier corresponding to the de-jitter angular velocity sequence can be determined. Then, the executing entity can use the direction identifier and pain avoidance identification label as the pain-avoidance movement detection information.

[0041] The second step involves detecting latent pain avoidance behaviors using the generated pain avoidance movement detection information, thus obtaining latent pain avoidance detection information. At least one pain avoidance movement detection information that meets preset conditions is identified as latent pain avoidance detection information. These preset conditions can be pain avoidance identification tags that characterize pain avoidance movements.

[0042] The third step involves generating overt pain avoidance detection information based on the aforementioned pain arc marking data. In practice, the executing entity can determine the marking angle position represented by the body's pain arc marking data as the pain location and use it as overt pain avoidance detection information.

[0043] The fourth step is to identify the aforementioned implicit pain avoidance detection information and the aforementioned explicit pain avoidance detection information as neck pain avoidance detection information.

[0044] The fifth step is to determine the aforementioned activity level data as activity restriction detection data. This activity restriction detection data includes individual activity level sub-data points in each direction, and each of these sub-data points corresponds to a direction identifier. The aforementioned activity level sub-data points include the upper limit of the activity angle.

[0045] Step 6: Perform antagonistic direction activity entrapment detection on the aforementioned activity restriction detection data, including each activity degree sub-data in each direction, to obtain neck movement entrapment detection information. In practice, the server can determine two activity degree sub-data with opposite direction identifiers in each activity degree sub-data as an activity degree sub-data group. For each activity degree sub-data group, perform the following steps: First, if the two activity angle upper limits represented by the activity degree sub-data group are different, determine the direction identifier corresponding to one activity degree sub-data in the aforementioned activity degree sub-data group as the target direction identifier, and query the activity angle threshold corresponding to the aforementioned target direction identifier from a preset file. For each of the two activity angles included in the aforementioned activity degree sub-data group, compare the activity angle with the activity angle threshold. In response to determining that the activity angle is less than the activity angle threshold, determine the direction identifier corresponding to the aforementioned activity angle as the entrapment direction identifier. Determine at least one entrapment direction identifier and a preset entrapment identifier (e.g., entrapment exists) as neck movement entrapment detection information.

[0046] Step 7: The above-mentioned neck pain avoidance detection information and the above-mentioned neck movement restriction detection information are identified as motor function detection information.

[0047] The above technical solution and its related content, combined with the following solution, involve generating a test report and neck and back movement guidance parameter data based on the aforementioned motor function detection information and user input information; sending the aforementioned test report and neck and back movement guidance parameter data to the aforementioned doctor's terminal; the aforementioned doctor's terminal being configured to display the received test report and neck and back movement guidance parameter data on a preset parameter adjustment page to generate interactive virtual movement guidance rendering information and target movement parameter information, and sending the aforementioned interactive virtual movement guidance rendering information and target movement parameter information to mixed reality glasses for the mixed reality glasses to perform neck movement guidance exercises. As an inventive point of this disclosure, it solves the technical problem that "relying solely on single data (e.g., solely on pain arc marker data) to detect neck pain avoidance behavior, and relying solely on the patient's reported or observed overt pain response (pain arc), may overlook the user's subtle compensatory movement patterns (such as stiffness, speed regulation, and micro-tremors) resulting from long-term pain or subconscious protection, leading to poor accuracy of the detected motor function detection information. When using mixed reality glasses to guide neck movement rehabilitation training based on this inaccurate motor function detection information, the effect of mixed reality glasses-guided neck rehabilitation treatment will be poor." To improve the effect of mixed reality glasses-guided neck rehabilitation treatment, firstly, for each de-shaking angular velocity sequence in the above-mentioned de-shaking angular velocity data, the de-shaking angular velocity sequence is input into the pain avoidance movement pattern detection model to obtain pain avoidance movement detection information corresponding to the above-mentioned de-shaking angular velocity sequence. Therefore, a pain-avoidance movement pattern detection model can be used to analyze the processed angular velocity sequence (de-shaking angular velocity sequence) to identify subtle movement patterns that may represent subconscious protection, rigidity, or compensation, generating corresponding pain-avoidance movement detection information, thereby objectively quantifying implicit pain-avoidance behavior. Then, implicit pain-avoidance behavior is detected using the generated pain-avoidance movement detection information, yielding implicit pain-avoidance detection information. Thus, integrating the analysis results of all sequences forms an overall judgment on whether a user exhibits implicit pain-avoidance behavior, i.e., implicit pain-avoidance detection information, filling the information gap left by relying solely on subjective pain descriptions. Subsequently, based on the aforementioned pain arc labeling data, explicit pain-avoidance detection information is generated. Thus, explicit pain-avoidance detection information can be generated using the user's reported pain arc data, preserving key explicit pain information. Then, the aforementioned implicit and explicit pain-avoidance detection information are identified as neck pain-avoidance detection information. Therefore, neck pain-avoidance detection information that includes both explicit pain responses and subtle compensatory movement patterns can be obtained. Subsequently, the aforementioned activity data is determined as activity-restricted detection data, which includes various activity sub-data in each direction, and each of the aforementioned activity sub-data has a corresponding direction identifier.Next, the restricted activity detection data, including the activity degree sub-data in each direction, is used to detect antagonistic direction activity restriction, resulting in neck movement restriction detection information. Based on directional markers, the activity degree data in antagonistic directions (e.g., flexion and extension, left and right rotation) can be compared and analyzed to detect any imbalance (activity restriction) caused by muscle synergy impairment leading to significant restriction in one direction while the antagonistic direction remains relatively normal. This generates neck movement restriction detection information, supplementing functional assessment from a motor coordination perspective. Then, the aforementioned neck pain avoidance detection information and neck movement restriction detection information are identified as motor function detection information. Thus, through the above steps, multi-dimensional data (de-shaking angular velocity sequence, pain arc, multi-directional activity degree) are systematically analyzed. In particular, the model identifies implicit pain avoidance behaviors and antagonistic direction activity restriction detection, overcoming the shortcomings of traditional methods that rely solely on single overt pain data and improving the accuracy of motor function detection information. Finally, combining the aforementioned motor function detection information and user input information, a detection report and neck and back movement guidance parameter data are generated. Therefore, based on more accurate motor function detection information, more accurate detection reports and neck and back movement guidance parameter data can be generated. Next, the aforementioned detection report and neck and back movement guidance parameter data are sent to the doctor's end. The doctor's end is configured to display the received detection report and neck and back movement guidance parameter data on a preset parameter adjustment page to generate interactive virtual movement guidance rendering information and target movement parameter information, and to send the interactive virtual movement guidance rendering information and target movement parameter information to the mixed reality glasses for the mixed reality glasses to perform neck movement guidance operations. Thus, based on more accurate detection reports and neck and back movement guidance parameter data, more precise interactive virtual movement guidance rendering information and target movement parameter information—i.e., rehabilitation guidance plans—can be generated, enabling the mixed reality glasses to perform more personalized training that matches the user's actual functional impairments, thereby improving the effectiveness of neck rehabilitation treatment guided by mixed reality glasses.

[0048] Fourth, based on the above-mentioned motor function detection information and user input information, a detection report and neck and back movement guidance parameter data are generated.

[0049] In employing technological solutions to address the aforementioned assessment and rehabilitation guidance of motor dysfunction, the following technical challenges often arise in the application scenario: personalized rehabilitation assessment and motor guidance for patients with cervical dysfunction. When integrating multi-source heterogeneous data (such as user subjective input and objective motion detection data) to generate accurate rehabilitation plans, it is crucial to ensure the automation of the assessment process, the standardization of reports, and the personalization and scientific rigor of prescription generation. This is essential to avoid inaccurate assessments, lack of targeted rehabilitation plans, or low clinical compliance due to fragmented information processing, insufficient knowledge integration, or rigid decision-making logic, resulting in poor rehabilitation outcomes and user experience. Considering the following requirements for this application scenario: structured integration of multi-source information, clinical knowledge-driven rehabilitation decisions, and automated and personalized assessment and prescription generation, we have decided to adopt the following solution: In some optional implementations of certain embodiments, the server 102 may generate a detection report and neck and back movement guidance parameter data based on the aforementioned motion function detection information and user input information through the following steps: The first step involves abstracting and structuring the aforementioned motor function detection information to obtain filled motor function detection information. In practice, the server can employ information extraction to identify and extract key information from the motor function detection information. Next, the extracted key information is organized and stored according to a predetermined data structure to obtain filled motor function detection information. This predetermined data structure can be in tabular form. For example, if the motor function detection information is presented in text form, it may contain various descriptive statements, such as "Patient rotates left: pain-avoiding movement exists." Using information extraction technology, named entity recognition (NER) technology in Natural Language Processing (NLP) can be used to identify the key entity: "left rotation," and the numerical information: "pain-avoiding movement exists," resulting in the key information: key entity: "left rotation," numerical information: "pain-avoiding movement exists." This information is then filled into the columns of the table, such as filling the "detection item" column with "left rotation" and the "detection result description" column with "pain-avoiding movement exists," thus obtaining structured filled motor function detection information presented in tabular form.

[0050] The second step involves inputting the aforementioned motor function detection information and user input information into a pre-created template-based natural language generation system to obtain a detection report. This template-based NLG system can be a system that generates detection reports using predefined templates. For example, the template might contain a statement structure like "Patient [Name], Age [Age] years old, during motor function testing, the result of [Detection Item] is [Detection Result Description]". The system will fill in the actual name, age, detection item, and detection result into the corresponding positions in the template and output the template filled with the motor function detection information and user input information as a detection report in a preset format (e.g., Word format).

[0051] The third step involves feature extraction and fusion of the aforementioned motor function detection information and user input information to construct a digital twin of cervical dysfunction. This digital twin can represent the patient's cervical dysfunction state. In practice, the server can use word embedding technology to convert the motor function detection information into feature vectors as motor function detection vectors. Then, using word embedding technology (e.g., word embedding models such as Word2Vec or pre-trained language models such as BERT), the user input information is converted into feature vectors as user input vectors. Finally, vector fusion technology is used to integrate the motor function detection vectors and user input vectors into a multi-dimensional feature vector as the digital twin of cervical dysfunction.

[0052] The fourth step involves inputting the aforementioned digital twin of cervical dysfunction into a prescription engine integrated with a clinical knowledge graph. This prescription engine compares and matches the digital twin model with the clinical knowledge graph to obtain cervical and back movement guidance parameter data. This prescription engine can be an intelligent system that receives the digital twin model of cervical dysfunction and generates cervical and back movement guidance parameter data for the patient through interaction with the clinical knowledge graph. The clinical knowledge graph is stored in a graph structure, where nodes represent clinical entities characterizing disease types and symptoms (e.g., "restricted left cervical rotation with left rotational pain avoidance movement"). Each node is associated with a specific treatment plan node storing movement guidance parameters (e.g., movement name, angle, number of repetitions, frequency). This knowledge is derived from publicly available clinical guidelines, expert consensus, etc. The prescription engine performs similarity matching between the input digital twin (feature vector) and nodes in the knowledge graph. Specifically, nodes in the knowledge graph can also be represented as vectors (e.g., through embedded vectors of descriptive text or predefined feature vectors). The engine calculates the similarity between the digital twin of cervical dysfunction and node vectors (i.e., related entity vectors) in the knowledge graph using well-known similarity metrics such as cosine similarity. It determines the matching result based on a similarity threshold and searches the knowledge graph for the node that best matches the input vector. The motion guidance parameters (such as action name, angle, number of repetitions, and frequency) associated with the found node are used as the neck and back motion guidance parameter data. For example, the engine calculates the similarity between the digital twin of cervical dysfunction and node vectors in the knowledge graph using similarity metrics such as cosine similarity. For instance, assuming the digital twin of cervical dysfunction contains a pain-avoidance movement directional identifier of "left-side rotational pain avoidance," the engine finds the symptom node "left-side rotational pain avoidance movement" in the knowledge graph and calculates the cosine similarity between these two vectors. If the similarity is high, it indicates that the cervical dysfunction reflected by the digital twin is similar to the clinical symptoms represented by that node. The matching result is determined based on a pre-set similarity threshold. If the vector similarity between the digital twin of cervical dysfunction and a certain node exceeds the threshold, the node is considered a successful match with the digital twin. For example, setting a similarity threshold of 0.8, a successful match is determined when the vector similarity between the digital twin of cervical dysfunction and the node "left-side rotation pain-avoidance exercise" is 0.85, exceeding the threshold. The knowledge graph is then searched for movement guidance parameters associated with the successfully matched node. For instance, if the treatment plan node associated with the "left-side rotation pain-avoidance exercise" node includes "left-side cervical rotation rehabilitation exercise," the corresponding movement parameter node is further searched to obtain specific movement guidance parameter data, such as "the left-side cervical rotation angle range is 0-30 degrees, each rotation is held for 5 seconds, 3 sets per day, 10 repetitions per set," etc.

[0053] The above-mentioned operation steps, combined with the fifth and subsequent solutions, "sending the above-mentioned test report and the above-mentioned neck and back movement guidance parameter data to the above-mentioned doctor's terminal; the above-mentioned doctor's terminal is configured to display the received test report and neck and back movement guidance parameter data on the preset parameter adjustment page to generate interactive virtual movement guidance rendering information and target movement parameter information, and sending the above-mentioned interactive virtual movement guidance rendering information and target movement parameter information to the mixed reality glasses for the mixed reality glasses to perform neck movement guidance operations," serve as an inventive point of this disclosure, solving the technical problem that "when integrating multi-source heterogeneous data (such as user subjective input and objective movement detection data) and generating accurate rehabilitation plans, it ensures the automation of the assessment process, the standardization of reports, and the personalization and scientific nature of prescription generation, avoiding inaccurate assessments, lack of targeted rehabilitation plans, or low clinical compliance due to fragmented information processing, insufficient knowledge integration, or rigid decision-making logic, resulting in poor rehabilitation effects and user experience." In practice, traditional rehabilitation treatment relies on doctors manually interpreting fragmented test data and patient complaints. This is not only inefficient but also struggles to systematically integrate massive amounts of clinical knowledge, resulting in low standardization of assessment reports, highly subjective rehabilitation plans lacking evidence-based support, and often abstract and dry guidance delivered to patients, leading to misunderstandings and poor adherence. This disclosure presents a fully automated and precise solution encompassing data normalization, intelligent decision generation, and human-machine collaborative delivery. It unifies data semantics through information abstraction and structured processing, automatically outputs reports using a template-based natural language generation system, achieves holographic fusion modeling of patient status through digital twin construction, drives scientific and personalized prescription generation using clinical knowledge graphs, and ensures clinical acceptability and patient accuracy through doctor review and mixed reality interactive guidance. Therefore, it achieves highly efficient automation and standardized output of the assessment and prescription generation process, improves the individualized accuracy and evidence-based scientific rigor of rehabilitation decisions, and enhances clinical operability and patient adherence through human-machine collaboration and immersive guidance, thereby systematically optimizing rehabilitation treatment efficiency and final rehabilitation outcomes.

[0054] Fifth, send the above test report and the above neck and back movement guidance parameter data to the above doctor terminal 101.

[0055] In some embodiments, the doctor terminal 101 can be configured to display the received test report and neck and back movement guidance parameters on a preset parameter adjustment page to generate interactive virtual movement guidance rendering information and target movement parameter information, and send the interactive virtual movement guidance rendering information and target movement parameter information to the mixed reality glasses 103 so that the mixed reality glasses 103 can perform neck movement guidance operations.

[0056] In addressing the aforementioned technical problems using this solution, the intended application scenario—personalized mixed reality interactive guidance for neck and back rehabilitation / fitness exercises—often presents the following technical challenges: the lack of real-time monitoring and correction based on safety boundaries during neck movement guidance increases the risk of secondary injury, leading to poor rehabilitation outcomes or low training adherence. This application scenario requires real-time safety monitoring and closed-loop feedback to reduce the risk of secondary injury. To address these technical issues, we have decided to adopt the following solution: In some optional implementations of certain embodiments, the doctor's terminal 101 may, through the following steps, display the received test report and neck and back movement guidance parameters on a preset parameter adjustment page to generate interactive virtual movement guidance rendering information and target movement parameter information, and send the interactive virtual movement guidance rendering information and target movement parameter information to the mixed reality glasses 103 for the mixed reality glasses 103 to perform neck movement guidance operations: The first step involves detecting a modification operation performed on the preset parameter adjustment page corresponding to the displayed neck and back movement guidance parameter data. The modified neck and back movement guidance parameter data is then identified as the target neck and back movement guidance parameter data. This target neck and back movement guidance parameter data includes at least one of the following: neck movement guidance parameter information and back movement guidance parameter information. The preset parameter adjustment page can be a page used to display and allow doctors to modify the neck and back movement guidance parameter data. The neck movement guidance parameter information can be parameters used to guide neck movement training (e.g., left rotation training upper limit 50°, 10 repetitions / set, 3 sets). The back movement guidance parameter information can be parameters used to guide back movement training (e.g., wall sliding exercise, 10 minutes, safe range of shoulder joint rotation angle in the horizontal plane 30°-40°).

[0057] The second step is to extract safety boundary parameter information from the above-mentioned target neck and back motion guidance parameter data as target motion parameter information. The above-mentioned safety boundary parameter information includes neck safety boundary parameter information and back safety boundary parameter information.

[0058] The third step involves inputting the aforementioned target neck and back motion guidance parameter data into a preset rendering instruction generator to obtain interactive virtual motion guidance rendering information. This preset rendering instruction generator can be a code generator that converts structured target neck and back motion guidance parameter data into visual rendering instructions that mixed reality devices can understand and execute. The aforementioned interactive virtual motion guidance rendering information can be code or instructions used to render complete interactive training guidance in a mixed reality environment (e.g., rendering a simplified human model standing against a wall with shoulders rotating horizontally within a 30°-40° range).

[0059] Fourth, the interactive virtual motion guidance information and target motion parameter information are sent to the mixed reality glasses 103 so that the mixed reality glasses 103 can perform the following neck motion guidance operation: The first step involves driving a pre-defined instantiated virtual coach model based on the aforementioned interactive virtual motion guidance rendering information to generate at least one guidance animation frame, and storing these frames in a pre-defined guidance animation frame queue in chronological order of their generation. In practice, the mixed reality glasses can perform rendering operations corresponding to the interactive virtual motion guidance rendering information. This is achieved by driving the pre-defined instantiated virtual coach model to move through a rendering engine (e.g., Unreal Engine) to generate at least one guidance animation frame, and storing these frames in a pre-defined guidance animation frame queue in chronological order of their generation. Specifically, when the mixed reality glasses receive the interactive virtual motion guidance rendering information, they first parse the information using the rendering engine, extracting key motion command parameters such as joint rotation angles and limb displacements, and converting them into a format recognizable by the model. Simultaneously, the pre-defined instantiated virtual coach model is loaded and its initial state is set. Next, based on the interactive virtual motion guidance rendering information, the rendering engine performs transformation operations on the model's skeletal joints. If the movement is continuous, the model's state is updated frame-by-frame according to the divided time steps, causing the model's posture to change dynamically over time. Then, geometric transformations are performed, rotating and translating the model's vertex coordinates based on joint angles. Combined with preset camera parameters, view calculations are then performed to determine the model's projection onto the screen. Next, the rendering pipeline performs vertex processing, including lighting and normal calculations, assembling primitives and rasterizing them to convert them into pixels. Finally, pixel processing determines the color before outputting a single frame of the guiding animation. If the motion requires multiple frames, the rendering engine will loop through the above process, generating a series of animation frames in chronological order and storing them in a preset queue.

[0060] The second step involves sequentially merging the preset guide animation frames into the real-world frames captured in real time, performing spatiotemporal alignment and perspective blending, and then displaying the merged frames to the user through the display module.

[0061] The third step involves real-time acquisition of the user's head rotation angle and hand position information, as well as feedback guidance based on these real-time acquisitions and safety boundary parameters. In practice, back movement feedback guidance or neck movement feedback guidance can be performed based on the real-time acquisitions of these parameters.

[0062] The above-described technical solution and its related content, as an inventive point of this disclosure, solve the technical problem of "poor rehabilitation effect or low training compliance". Factors leading to poor rehabilitation effect or low training compliance often include: failure to monitor and correct in real time according to safety boundaries during neck movement guidance operations, increasing the risk of secondary injury and resulting in poor rehabilitation effect or low training compliance. Solving these factors can improve rehabilitation effect and training compliance. To achieve this effect, firstly, in response to detecting a modification operation acting on the preset parameter adjustment page corresponding to the displayed neck and back movement guidance parameter data, the modified neck and back movement guidance parameter data is determined as the target neck and back movement guidance parameter data, wherein the target neck and back movement guidance parameter data includes at least one of the following: neck movement guidance parameter information and back movement guidance parameter information. Then, safety boundary parameter information is extracted from the target neck and back movement guidance parameter data as the target movement parameter information, wherein the safety boundary parameter information includes neck safety boundary parameter information and back safety boundary parameter information. Thus, safety constraints (such as the maximum neck rotation angle and the limit position of back flexion), i.e., safety boundary parameter information, can be extracted. Next, the target neck and back movement guidance parameter data is input into a preset rendering instruction generator to obtain interactive virtual movement guidance rendering information. This allows the generation of underlying rendering instructions—interactive virtual movement guidance rendering information—that the mixed reality glasses can understand and execute, driving the virtual coach model. This completes the transformation from an abstract "parameter scheme" to a concrete "visual guidance action." Then, the interactive virtual movement guidance information and target movement parameter information are sent to the mixed reality glasses for the glasses to perform the following neck movement guidance operations: First, based on the interactive virtual movement guidance rendering information, a preset instantiated virtual coach model is driven to generate at least one guidance animation frame, and these frames are stored in a preset guidance animation frame queue in chronological order of generation. Second, the guidance animation frames in the preset queue are spatiotemporally aligned and perspective-fused with real-world frames captured in real time, and the fused frame is displayed to the user through a display module. Thus, through spatiotemporal alignment technology, the virtual coach's demonstration movements are seamlessly and stably superimposed and fused into the user's real physical space (e.g., fixed in front of the user). This "virtual and real-world co-presentation" display method greatly enhances the immersiveness, presence, and positional credibility of the guidance, enabling users to understand and follow the actions more intuitively, thus improving the effectiveness of the guidance. Finally, real-time data collection of the user's head rotation angle and hand position in the empty space, along with feedback guidance based on these real-time data and safety boundary parameters, is used to execute the guidance.Therefore, by implementing feedback guidance, the risk of secondary injury can be reduced, thereby improving rehabilitation outcomes and training adherence.

[0063] Figure 3 These are internal test diagrams of some embodiments of a neck motion guidance system based on mixed reality glasses according to this disclosure.

[0064] Figure 2 A flow 200 is shown illustrating some embodiments of a method for generating neck and back motion guidance parameter data using a server included in the above-described mixed reality glasses-based neck motion guidance system according to this disclosure. The method for generating neck and back motion guidance parameter data includes the following steps: Step 201: Receive user input information, activity data, pain arc marker data, and head motion angular velocity data collected by the mixed reality glasses.

[0065] In some embodiments, the entity that generates the neck and back motion guidance parameter data (e.g., the server included in a neck motion guidance system based on mixed reality glasses) can receive user input information, range of motion data, pain arc marker data, and head motion angular velocity data collected by the mixed reality glasses.

[0066] Step 202: Perform jitter removal on the head motion angular velocity data to obtain jitter-removed angular velocity data.

[0067] In some embodiments, the execution entity may perform jitter removal processing on the head motion angular velocity data to obtain jitter-removed angular velocity data.

[0068] Step 203: Perform objective motor function testing on the de-shaking angular velocity data, range of motion data, and pain arc marker data to obtain motor function testing information.

[0069] In some embodiments, the aforementioned execution entity may perform objective motor function testing on the aforementioned de-shaking angular velocity data, the aforementioned activity data, and the aforementioned pain arc marker data to obtain motor function testing information.

[0070] Step 204: Based on the motion function detection information and user input information, generate a detection report and neck and back motion guidance parameter data.

[0071] In some embodiments, the aforementioned execution entity may generate a detection report and neck and back movement guidance parameter data based on the aforementioned motion function detection information and the aforementioned user input information.

[0072] Step 205: Send the test report and neck and back movement guidance parameter data to the doctor.

[0073] In some embodiments, the aforementioned executing entity may send the aforementioned test report and the aforementioned neck and back movement guidance parameter data to the aforementioned doctor's terminal.

[0074] The various embodiments of this disclosure have the following beneficial effects: the neck movement guidance system based on mixed reality glasses according to some embodiments of this disclosure improves the effect of neck rehabilitation treatment. Specifically, the reason for the poor effect of neck rehabilitation treatment is that standardized videos or action templates are used to guide patients to practice, but each patient's situation is different, especially in terms of neck and back flexibility, pain level, and recovery status. Therefore, standardized videos often cannot meet the individual needs of patients, and may even lead to excessive or insufficient exercise intensity. Moreover, when patients practice on their own through videos, there is a lack of feedback guidance, resulting in poor neck rehabilitation treatment effect. Based on this, the neck movement guidance system based on mixed reality glasses according to some embodiments of this disclosure includes: mixed reality glasses, a server, and a doctor's end, wherein: the server is configured to perform the following detection steps: receiving user input information, activity data, pain arc marker data, and head motion angular velocity data collected by the mixed reality glasses. Thus, multi-dimensional user input information, activity data, pain arc marker data, and head motion angular velocity data that reflect the individual functional state and subjective feelings of the user can be obtained. Then, the head motion angular velocity data is subjected to anti-shake processing to obtain anti-shake angular velocity data. Therefore, noise introduced by head tremors or environmental vibrations can be detected, resulting in accurate and stable data reflecting the user's voluntary neck movement intentions. Next, objective motor function testing is performed on the aforementioned de-shaking angular velocity data, range of motion data, and pain arc marker data to obtain motor function testing information. This provides motor function testing information that quantifies the individualized functional impairment patterns of the patient. Subsequently, based on the aforementioned motor function testing information and the aforementioned user input information, a testing report and neck and back movement guidance parameter data are generated. Thus, a testing report and neck and back movement guidance parameter data can be generated by integrating subjective assessment (i.e., motor function testing information) and subjective feelings. Then, the aforementioned testing report and neck and back movement guidance parameter data are sent to the doctor's end. As can be seen from the above, the server uses raw, multimodal user data from mixed reality glasses, through a series of calculations and intelligent analyses, to provide accurate motor function assessments and personalized treatment guidance, offering decision support for doctors and data support for telemedicine collaboration. The doctor's terminal is configured to display the received test report and neck and back movement guidance parameters on a preset parameter adjustment page to generate interactive virtual movement guidance rendering information and target movement parameter information. This interactive virtual movement guidance rendering information and target movement parameter information are then sent to the mixed reality glasses for the mixed reality glasses to perform neck movement guidance operations.By using mixed reality glasses, personalized virtual movement guidance information (i.e., the animated guidance information rendered from interactive virtual movement guidance) is presented intuitively to users. Patients can perform neck exercises according to precise guidance, avoiding situations where inappropriate exercise intensity affects the treatment effect, thus effectively improving the treatment outcome. Furthermore, because the server generates a test report and neck and back movement guidance parameters suitable for the user based on multimodal user data from the mixed reality glasses, doctors can use this data to develop personalized guidance plans—including interactive virtual movement guidance rendering information and target movement parameter information—and present these plans intuitively to patients through the mixed reality glasses, meeting the personalized needs of patients' neck movements and improving treatment effectiveness.

[0075] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of technical features, but should also cover other technical solutions formed by arbitrary combinations of technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A neck motion guidance system based on mixed reality glasses, comprising: Mixed reality glasses, server-side, and doctor-side components, including: The server is configured to perform the following detection steps: Receive user input information, activity data, pain arc marker data, and head motion angular velocity data collected by the mixed reality glasses; The head motion angular velocity data is subjected to de-jitter processing to obtain de-jittered angular velocity data; Objective motor function detection is performed on the de-shaking angular velocity data, the range of motion data, and the pain arc marker data to obtain motor function detection information; Based on the motion function detection information and the user input information, a detection report and neck and back motion guidance parameter data are generated; The test report and the neck and back movement guidance parameter data are sent to the doctor's terminal; The doctor's terminal is configured to display the received test report and neck and back movement guidance parameters on a preset parameter adjustment page to generate interactive virtual movement guidance rendering information and target movement parameter information, and to send the interactive virtual movement guidance rendering information and target movement parameter information to the mixed reality glasses for the mixed reality glasses to perform neck movement guidance operations.

2. The neck motion guidance system based on mixed reality glasses according to claim 1, wherein, The mixed reality glasses are further configured to: In response to receiving a neck and back movement guidance command input by the user, the display module presents a virtual guidance scene corresponding to the interactive virtual movement guidance rendering information, and performs real-time tracking and feedback guidance on the user's neck and hand movements based on the neck and back movement guidance command and the target movement parameter information.

3. The neck motion guidance system based on mixed reality glasses according to claim 1 further includes a handheld locator, wherein the target motion parameter information includes neck safety boundary parameter information and back safety boundary parameter information, wherein the mixed reality glasses are further configured to: In response to the determination of the neck and back movement guidance instructions, the following first real-time tracking and feedback guidance is performed: The user's hand position information is collected in real time using a handheld locator. The collected spatial position information of the user's hand is converted into back motion parameter information; Based on the back motion parameter information and back safety boundary parameter information, back motion feedback guidance is performed. In response to the determination of the neck and back movement guidance instructions, the following second real-time tracking and feedback guidance is performed: The inertial measurement unit collects the user's neck movement parameters in real time. Based on the user's neck movement parameters and the neck safety boundary parameters, neck movement feedback guidance is performed.

4. The neck motion guidance system based on mixed reality glasses according to claim 1, wherein, The mixed reality glasses are further configured to: The preset virtual interface presented by the display module is used to collect user input information as user input information; The system uses an integrated motion capture system, combined with an inertial measurement unit and a sound recognition module, to collect activity data, pain arc marker data, and head motion angular velocity data.

5. The neck motion guidance system based on mixed reality glasses according to claim 1, wherein, The head motion angular velocity data includes at least one angular velocity sub-data, each angular velocity sub-data including an angular velocity sequence, and the server is further configured to: For each angular velocity sub-data in at least one of the angular velocity sub-data included in the head motion angular velocity data, perform the following steps: The angular velocity sequence included in the angular velocity sub-data is determined as the angular velocity sequence to be de-jittered; The angular velocity sequence to be de-jittered is subjected to sliding window grouping processing to obtain a sequence of angular velocity groups to be de-jittered, wherein each angular velocity group to be de-jittered in the sequence corresponds to two consecutive angular velocities to be de-jittered in the sequence. At least one set of angular velocities that meets the preset conditions in the sequence of angular velocities to be de-jittered is identified as at least one set of jittering angular velocities. Based on the at least one jittered angular velocity group, the angular velocity sequence to be de-jittered is filtered to obtain a de-jittered angular velocity sequence. The obtained de-jitter angular velocity sequences are defined as de-jitter angular velocity data.

6. The neck motion guidance system based on mixed reality glasses according to claim 5, wherein, The server is further configured to: For each of the at least one jitter angular velocity groups, perform the following steps: Determine the two consecutive angular velocities to be de-jittered in the sequence of angular velocities to be de-jittered that correspond to the jitter angular velocity group; Two consecutive angular velocities to be dejittered are respectively defined as the preceding angular velocity to be dejittered and the subsequent angular velocity to be dejittered; The preceding angular velocity to be dejittered in the sequence of angular velocities to be dejittered is determined as the target preceding angular velocity to be dejittered. The next angular velocity to be dejittered in the sequence of angular velocities to be dejittered is determined as the target subsequent angular velocity to be dejittered. Based on the preceding angular velocity to be de-jittered for the first target and the preceding angular velocity to be de-jittered for the second target, the preceding angular velocity to be de-jittered and the subsequent angular velocity to be de-jittered in the angular velocity to be de-jittered sequence are filtered in order to update the angular velocity to be de-jittered sequence. The updated angular velocity sequence to be de-jittered is determined as the de-jittering angular velocity sequence.

7. A method for generating neck and back motion guidance parameter data, applied to the server included in the neck motion guidance system based on mixed reality glasses as described in any one of claims 1-6, the method comprising: Receive user input information, activity data, pain arc marker data, and head motion angular velocity data collected by the mixed reality glasses; The head motion angular velocity data is subjected to de-jitter processing to obtain de-jittered angular velocity data; Objective motor function detection is performed on the de-shaking angular velocity data, the range of motion data, and the pain arc marker data to obtain motor function detection information; Based on the motion function detection information and the user input information, a detection report and neck and back motion guidance parameter data are generated; The test report and the neck and back movement guidance parameter data are sent to the doctor's terminal.

Images