A personalized gait adjustment method, system, electronic device and storage medium

Abstract

This application provides a personalized gait adjustment method, system, electronic device, and storage medium, relating to the field of gait adjustment technology. The method includes collecting a user's gait information at first intervals based on the currently playing music track; sequentially inputting each piece of gait information into a track recommendation model, recommending a predicted music track at second intervals; and determining the next music track to be played from multiple predicted music tracks based on preset conditions if the currently playing music track has finished playing, thereby achieving personalized gait adjustment for different users and improving the adjustment effect.

Description

Technical Field

[0001] This invention relates to the field of gait adjustment technology, and more particularly to a personalized gait adjustment method, system, electronic device, and storage medium. Background Technology

[0002] Due to diseases of the human nervous and musculoskeletal systems, pelvic tilt, unequal leg lengths, lateral flexion of the trunk, weakened physical strength, or other reasons, some users experience walking difficulties. Without gait adjustment, long-term walking difficulties can make users even more hesitant to walk independently due to safety concerns, significantly reducing their independence, lowering their quality of life, increasing the risk of falls, and potentially increasing the burden on the healthcare system.

[0003] Existing methods for rhythmic gait regulation involve a fixed rhythm, which makes the entire regulation process tedious and difficult for users to adapt to, and the regulation process is also lengthy. Although the regulation effect of precise manual intervention is obvious, the cost is high.

[0004] Therefore, a personalized gait adjustment method, system, electronic device, and storage medium are proposed. Summary of the Invention

[0005] Physiological studies have shown that the rich connections between rhythmic hearing and movement are linked throughout the brain in a distributed and parallel manner, meaning there is abundant connectivity between the auditory and motor systems. Specifically, it has been demonstrated that the auditory and motor systems can subconsciously synchronize with external auditory rhythmic cues.

[0006] This specification provides a personalized gait adjustment method, system, electronic device, and storage medium. During the process of adjusting gait based on the music being played, the music being played is determined based on the user's gait information and a music recommendation model, so as to perform personalized gait adjustment for the user and improve the adjustment effect.

[0007] The personalized gait adjustment method provided in this application adopts the following technical solution, including:

[0008] Based on the currently playing music track, the user's gait information is collected every first interval.

[0009] Each gait information is sequentially input into the track recommendation model, and a predicted music track is recommended every second interval.

[0010] If the currently playing music track has finished playing, the next music track to be played is determined from multiple predicted music tracks based on preset conditions, so as to perform personalized gait adjustment for the user.

[0011] Optionally, the step of sequentially inputting each gait information into the track recommendation model and recommending a predicted music track after every second time interval includes:

[0012] Multiple gait information items within the second interval are sequentially summarized to obtain a detection state, wherein the second interval is longer than the first interval.

[0013] Based on the gait adjustment strategy and a detection state, a predicted music track is determined.

[0014] Optionally, the step of sequentially inputting each of the gait information into the track recommendation model and recommending a predicted music track after every second time interval further includes:

[0015] Determine whether the currently playing music track has finished playing;

[0016] If the music is not played completely, record the predicted track number and the number of times it was recommended.

[0017] Optionally, if the currently playing music track has finished playing, determining the next music track to play from a plurality of predicted music tracks based on preset conditions to personalize the user's gait adjustment includes:

[0018] If the currently playing music track has finished playing, the predicted music track with the most recommended times will be used as the next music track to be played.

[0019] Optional, also includes:

[0020] Based on all the gait information of the music track, the current training gait data is obtained;

[0021] The current gait score is determined based on the matching degree between the current training gait data and the music track.

[0022] The current reward value is determined by the difference between the current gait score and the previous gait score.

[0023] The current training gait data, the currently playing music track, the current reward value, and the next training data are used as a tuning quadruple to optimize the gait tuning strategy.

[0024] Optionally, obtaining the current training gait data based on all gait information of the music track includes:

[0025] The gait information includes foot pressure data and gait trajectory data;

[0026] The foot pressure data and the gait trajectory data are respectively subjected to data normalization and standardization processing;

[0027] The processed foot pressure data and processed gait trajectory data are stitched together to obtain the current training gait data.

[0028] The personalized gait adjustment system provided in this application adopts the following technical solution, including:

[0029] The data acquisition module is used to collect the user's gait information at the first interval based on the currently playing music track;

[0030] The prediction module is used to input each gait information into the track recommendation model in sequence, and recommend a predicted music track every second interval.

[0031] The track output module is used to determine the next music track to be played from multiple predicted music tracks based on preset conditions if the currently playing music track has finished playing, so as to perform personalized gait adjustment for the user.

[0032] Optionally, the prediction module includes:

[0033] A determination submodule is used to sequentially summarize multiple gait information within the second interval time to obtain a detection state, wherein the second interval time is greater than the first interval time;

[0034] The prediction submodule is used to determine a predicted music track based on a gait adjustment strategy and a detection state.

[0035] Optionally, the prediction module further includes:

[0036] The judgment submodule is used to determine whether the currently playing music track has finished playing;

[0037] The storage submodule is used to record the number of the predicted music track and the number of recommendations if the music has not finished playing.

[0038] Optionally, the track output module includes:

[0039] The track output submodule is used to select the predicted music track with the most recommended times as the next music track to be played if the currently playing music track has finished playing.

[0040] Optionally, an optimization module may also be included;

[0041] The optimization module includes:

[0042] The preprocessing submodule is used to obtain the current training gait data based on all the gait information of the music track;

[0043] The score determination submodule is used to determine the current gait score based on the matching degree between the current training gait data and the music track.

[0044] The reward value determination submodule is used to determine the current reward value by the difference between the current gait score and the previous gait score;

[0045] The optimization submodule is used to combine the current training gait data, the currently playing music track, the current reward value, and the next training data into a regulation quadruple to optimize the gait regulation strategy.

[0046] Optionally, the preprocessing submodule includes:

[0047] The gait information includes foot pressure data and gait trajectory data;

[0048] The preprocessing unit is used to perform data normalization and standardization processing on the foot pressure data and the gait trajectory data respectively;

[0049] The stitching unit is used to stitch together the processed foot pressure data and the processed gait trajectory data to obtain the current training gait data.

[0050] This specification also provides an electronic device, wherein the electronic device includes:

[0051] Processor; and,

[0052] A memory that stores computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0053] This specification also provides a computer-readable storage medium that stores one or more programs that, when executed by a processor, implement any of the methods described above.

[0054] In this application, the user's gait information is collected every first interval based on the currently playing music track; each gait information is sequentially input into the track recommendation model, and a predicted music track is recommended every second interval; if the currently playing music track has finished playing, the next music track to be played is determined from multiple predicted music tracks based on preset conditions, thereby realizing personalized gait adjustment for different users and improving the adjustment effect. Attached Figure Description

[0055] Figure 1 A schematic diagram illustrating the principle of a personalized gait adjustment method provided in the embodiments of this specification;

[0056] Figure 2 A schematic diagram illustrating the principle of a personalized gait adjustment system provided in the embodiments of this specification;

[0057] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0058] Figure 4 This is a schematic diagram of a computer-readable medium provided for embodiments of this specification. Detailed Implementation

[0059] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0060] Exemplary embodiments of the invention will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limiting the invention to the embodiments set forth herein. Rather, these exemplary embodiments are provided to make the invention more comprehensive and complete, and to facilitate a full communication of the inventive concept to those skilled in the art. The same reference numerals in the drawings denote the same or similar elements, components, or parts, and therefore repeated descriptions of them will be omitted.

[0061] Subject to the technical concept of this invention, the features, structures, characteristics or other details described in a particular embodiment may be combined in one or more other embodiments in a suitable manner.

[0062] In the description of specific embodiments, the features, structures, characteristics, or other details described in this invention are intended to enable those skilled in the art to fully understand the embodiments. However, it is not excluded that those skilled in the art can practice the technical solutions of this invention without one or more of the specific features, structures, characteristics, or other details.

[0063] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0064] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0065] The terms “and / or” or “and / or” include all combinations of any one or more of the listed items.

[0066] In this manual, "user" refers to a user who needs gait adjustment or uses the personalized gait adjustment system provided in this manual.

[0067] This specification provides an embodiment of a personalized gait adjustment method, which includes:

[0068] S1 constructs a track recommendation model;

[0069] S2 collects the user's gait information based on the currently playing music track, after each first interval.

[0070] S3 sequentially inputs each of the gait information into the track recommendation model, and recommends a predicted music track every second interval.

[0071] S4 If the currently playing music track has finished playing, determine the next music track to be played from multiple predicted music tracks based on preset conditions, so as to perform personalized gait adjustment for the user.

[0072] For gait impairment, existing technologies primarily employ rhythmic auditory stimulation, which provides rhythmic stimuli (such as music and beats) to the motor center, prompting users to adjust their movement patterns to match the external rhythm, thereby enhancing motor ability. This application, based on the mechanism of action of rhythmic auditory stimulation and its positive impact on gait regulation, provides users with personalized gait regulation plans using their gait information, further optimizing the regulation effect while reducing labor costs.

[0073] Specifically, such as Figure 1 As shown, the method includes:

[0074] S1 constructs a track recommendation model;

[0075] Before gait adjustment, a track recommendation model is constructed; specifically, the track recommendation model is constructed using reinforcement learning algorithms, deep reinforcement learning algorithms, and deep Q-learning algorithms.

[0076] Collect and train a track recommendation model based on the original sample data.

[0077] Specifically, a music track library is constructed, which stores a number of music tracks and their corresponding track numbers, with each track and its number having a one-to-one correspondence. The music tracks include instrumental music with a clear rhythmic feel.

[0078] To reduce boredom, the music library is updated regularly or irregularly; since everyone's feelings about music and rhythm are different, personalized music libraries can also be used based on user preferences to optimize the user experience.

[0079] S11 collects raw sample data; the raw sample data comes from examples of precise human intervention, etc. The raw sample data includes the gait information of the sample users over a period of time and the corresponding music track numbers played.

[0080] S12 preprocesses the original sample data to obtain multiple sample training data.

[0081] In one embodiment of this specification, for the same sample user, sample groups are divided in sequence according to the track switching node. Each sample group includes the gait information of the first sample during the music track playback and the music track number at that time.

[0082] Then, the gait information of all first samples in the sample group is obtained and preprocessed. The first sample gait information includes first foot pressure data and first step gait trajectory data. Specifically, the first foot pressure data and the first step gait trajectory data are standardized and normalized. The processed first foot pressure data and the processed first step gait trajectory data are then concatenated to obtain the sample training gait data. This reduces the influence of outliers and different parameters, accelerating model convergence. (Sample training gait data follows.)

[0083] As a preferred method, data splicing is performed using feature fusion methods such as concat or add.

[0084] S13 inputs multiple sample training gait data into the track recommendation model for training.

[0085] Construct quadruples (S, A, R, S') based on the sample training gait data. Each quadruple contains the value at a given time step, i.e.:

[0086] “S” represents the current state, the gait information at the current moment, specifically the foot pressure data and gait trajectory data of both feet at the current moment;

[0087] “A” indicates the action taken in the current state, that is, the music track currently being played. Based on this, the number of the music track currently being played can be determined.

[0088] “R” represents the current reward value calculated based on the reward function;

[0089] “S” indicates the state at the next moment, that is, the gait information at the next moment, specifically the foot pressure data and gait trajectory data of both feet at the next moment.

[0090] In one embodiment of this specification, each sample training gait data corresponds to a time step. That is, since the sample groups are divided sequentially, the sample training gait data obtained based on the sample groups also have a chronological order.

[0091] The following is a brief description of the model training process using the Deep Q-Learning (DQN) algorithm as an example. In this process, the agent is like a music player, the action is selecting a music track to play, and the environment is gait information.

[0092] First, an initial state is randomly selected before the algorithm starts. Then, an action is selected based on this state. Here, a judgment needs to be made, that is, the action corresponding to the largest Q value is selected through Q-Network. Since the relevant parameters in Q-Network are random at the beginning, they are usually set very small before the experience pool is full. That is, in the early stage, the actions are basically randomly selected.

[0093] After the action selection is completed, the agent will execute the action (A) in the environment. The environment will then return the next state (S') and the current reward value (R), at which point the quadruple (S, A, R, S') is stored in the experience replay pool. The next state (S') is then treated as the current state (S), and the above steps are repeated until the experience replay pool is full.

[0094] S14 trains the track recommendation model based on sample training gait data and determines the gait adjustment strategy.

[0095] Specifically, the collected training gait data can not only calculate stress distribution and posture, but also customize the reward function, i.e., the gait adjustment strategy, based on the user's stride frequency and the relative position of the left and right feet. The higher the consistency between the user's gait rhythm and the beat of the music track, the higher their gait score. Since the reward value represented by "R" is determined based on the user's gait information and the change in gait score between the current action and the previous gait score, the music recommendation model predicts the music track that best matches the gait information in order to obtain a higher reward value. Considering that users' gait is relatively slow in the initial stage of gait adjustment, music tracks with a rhythm consistent with or slightly faster than the current gait information are considered to match the gait information.

[0096] The model aims for increasingly higher rewards, or at least for rewards to remain constant. Therefore, training the music recommendation model enables it to recommend music tracks that match the user's gait information, thereby improving the optimization effect of gait adjustment.

[0097] S2 collects the user's gait information based on the currently playing music track, after each first interval.

[0098] When a user first begins gait adjustment, a slow-paced music track will be played automatically, and then the music track will be switched according to the user's gait information.

[0099] Gait information includes foot pressure data and gait trajectory data;

[0100] The user walks according to the currently playing music track, and at each interval, the user's current gait information is obtained through plantar pressure sensors and posture sensors. Specifically, the plantar pressure sensor collects foot pressure data; the posture sensor collects gait trajectory data. The plantar pressure sensor senses the user's point of force during walking, i.e., gait; the posture sensor is used to construct the gait trajectory, i.e., the movement trajectory. Preferably, the posture sensor can be a gyroscope sensor.

[0101] In one embodiment of this specification, the attitude sensor is positioned relative to the circuit board of the plantar pressure sensor, typically by stacking two boards. Once the positions of the two sensors are determined, they should be kept fixed and changed as little as possible later to ensure the stability of data acquisition.

[0102] The gait cycle includes a stance phase and a swing phase. The stance phase includes initial ground contact, weight-bearing reaction period, mid-stance phase, and end-stance phase. The swing phase includes early swing phase, mid-switch phase, and end-switch phase. Foot pressure data corresponding to each phase can be collected. Foot pressure data changes continuously; the shorter the interval between data collections, the higher the match between the predicted music track and the user. To improve the adjustment effect, the first interval is preferably 0.5 seconds.

[0103] S3 sequentially inputs each of the gait information into the track recommendation model, and recommends a predicted music track every second interval.

[0104] Based on the gait cycle described above, the two feet are in different gait phases at the same time. For example, in the middle of the support phase, the supporting foot is fully on the ground, while the opposite foot is in the swing phase, which is the only phase in which a single foot bears the full weight.

[0105] To improve prediction accuracy, music prediction is based on the same temporal phase of both feet. Therefore, multiple gait information points within the second interval are sequentially summarized to obtain a detection state. The second interval is longer than the first interval, meaning the detection state includes multiple gait information points. The first interval is denoted as M, the second interval as N, and N = 2n*M, where n is a positive integer. M is preferably 0.5 seconds. Preferably, n is 1 or 2, meaning N is preferably 1 second or 2 seconds. At the end of the music track, N > 2n*M; in this case, the corresponding gait information is not used to obtain a detection state.

[0106] Based on the gait adjustment strategy and the detection state, the predicted music track is determined.

[0107] In the initial stage of gait adjustment, the user's gait is relatively slow. In order to improve gait speed, the music recommendation model will recommend music tracks that are consistent with the rhythm of the current gait information or have a slightly faster rhythm.

[0108] Determine whether the currently playing music track has finished playing; if not, record the predicted music track number and the number of times it has been recommended.

[0109] S4 If the currently playing music track has finished playing, determine the next music track to be played from multiple predicted music tracks based on preset conditions, so as to perform personalized gait adjustment for the user.

[0110] If the currently playing music track has finished playing, the predicted music track numbers during the current playback period are summarized and statistically analyzed, and the predicted music track with the most recommendations is selected as the next music track to be played. Personalized music track recommendations based on the user's gait information allow users to adjust their gait without professional guidance, and it can also be used at home, effectively reducing the cost of gait adjustment.

[0111] When playing the next music track, clear the previously recorded predicted music track number and recommendation count, and start recording again.

[0112] To further improve the adjustment effect, gait information during the gait adjustment process can be used to train and optimize the track recommendation model. As a preferred approach, the gait adjustment strategy in the track recommendation model can be optimized based on the influence of the music track on the gait during the corresponding playback time of the music track.

[0113] First, based on all gait information within the playback time corresponding to the music track, the current training gait data is obtained;

[0114] Specifically, gait information is acquired during the playback time corresponding to the music track. All gait information is preprocessed, foot pressure data is normalized, and gait trajectory data is normalized. The processed foot pressure data and processed gait trajectory data are then concatenated to obtain the current training gait data.

[0115] The current gait score is determined based on the matching degree between the current training gait data and the music track; specifically, the current gait score is determined by the rhythm matching degree between the current training gait data and the currently played music track; then the current reward value is determined by the difference between the current gait score and the previous gait score.

[0116] The current training gait data, the currently playing music track, the current reward value, and the next training data are used as a conditioning quadruple to optimize the track recommendation model, thereby optimizing the gait adjustment strategy and improving the fit between the music track and the user.

[0117] To help users understand the effectiveness of their gait adjustment in a timely and convenient manner, gait information and matching degree can also be displayed to users.

[0118] Figure 2 This specification provides a schematic diagram of a personalized gait adjustment system, which includes:

[0119] Module 210 is used to build the track recommendation model;

[0120] The acquisition module 220 is used to collect the user's gait information based on the currently playing music track, after each first interval.

[0121] The prediction module 230 is used to input each of the gait information into the track recommendation model in sequence, and recommend a predicted music track every second interval.

[0122] The track output module 240 is used to determine the next music track to be played from a plurality of predicted music tracks based on preset conditions if the currently playing music track has finished playing, so as to perform personalized gait adjustment for the user.

[0123] Optionally, the prediction module 230 includes:

[0124] A determination submodule is used to sequentially summarize multiple gait information within the second interval time to obtain a detection state, wherein the second interval time is greater than the first interval time;

[0125] The prediction submodule is used to determine a predicted music track based on a gait adjustment strategy and a detection state.

[0126] Optionally, the prediction module 230 further includes:

[0127] The judgment submodule is used to determine whether the currently playing music track has finished playing;

[0128] The storage submodule is used to record the number of the predicted music track and the number of recommendations if the music has not finished playing.

[0129] Optionally, the track output module 240 includes:

[0130] The track output submodule is used to select the predicted music track with the most recommended times as the next music track to be played if the currently playing music track has finished playing.

[0131] Optionally, an optimization module may also be included;

[0132] The optimization module includes:

[0133] The preprocessing submodule is used to obtain the current training gait data based on all the gait information of the music track;

[0134] The score determination submodule is used to determine the current gait score based on the matching degree between the current training gait data and the music track.

[0135] The reward value determination submodule is used to determine the current reward value by the difference between the current gait score and the previous gait score;

[0136] The optimization submodule is used to combine the current training gait data, the currently playing music track, the current reward value, and the next training data into a regulation quadruple to optimize the gait regulation strategy.

[0137] Optionally, the preprocessing submodule includes:

[0138] The gait information includes foot pressure data and gait trajectory data;

[0139] The preprocessing unit is used to perform data normalization and standardization processing on the foot pressure data and the gait trajectory data respectively;

[0140] The stitching unit is used to stitch together the processed foot pressure data and the processed gait trajectory data to obtain the current training gait data.

[0141] The functions of the system in this embodiment have been described in the above method embodiments. Therefore, for any parts not detailed in this embodiment, please refer to the relevant descriptions in the foregoing embodiments, which will not be repeated here.

[0142] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0143] The following describes embodiments of the electronic device of the present invention, which can be considered as implementations of the physical form of the methods and apparatus embodiments of the present invention described above. Details described in the embodiments of the electronic device of the present invention should be considered as supplements to the methods or apparatus embodiments described above; details not disclosed in the embodiments of the electronic device of the present invention can be implemented with reference to the methods or apparatus embodiments described above.

[0144] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Figure 3 The computer device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0145] like Figure 3 As shown, the computer device 300 of this exemplary embodiment is manifested in the form of a general-purpose data processing device. The components of the computer device 300 may include, but are not limited to, at least one processor 310, at least one memory 320, a network interface 330, a display unit 340, an input component 350, etc.

[0146] The memory 320 stores a computer-readable program, which may be source code or read-only code. The program can be executed by the processor 310, causing the processor 310 to perform the steps of various embodiments of the present invention. For example, the processor 310 can perform actions such as... Figure 1 The steps are shown.

[0147] The memory 320 may include a readable medium in the form of volatile memory cells, such as random access memory (RAM) and / or cache memory cells, and may further include read-only memory (ROM). The memory 320 may also include a program / utility having a set (at least one) of program modules, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0148] It also includes a bus (not shown) that can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0149] Computer device 300 can also communicate with one or more external devices (e.g., keyboard, monitor, network device, Bluetooth device, etc.), enabling users to interact with computer device 300 via these external devices, and / or enabling computer device 300 to communicate with one or more other data processing devices (e.g., router, modem, etc.). This communication can be made via network interface 330, or via a network adapter with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet). The network adapter can communicate with other modules of computer device 300 via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in computer device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0150] Figure 4 This is a schematic diagram of a computer-readable medium embodiment of the present invention. Figure 4 As shown, the computer program can be stored on one or more computer-readable media. The computer-readable medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. When the computer program is executed by one or more data processing devices, the computer-readable medium enables the implementation of the methods described above in this invention.

[0151] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described in this invention can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) or on a network, including several instructions to cause a data processing device (such as a personal computer, server, or network device, etc.) to execute the methods described above according to this invention.

[0152] The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0153] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0154] In summary, the present invention can be implemented by methods, apparatus, electronic devices, or computer-readable media that execute computer programs. In practice, some or all of the functions of the present invention can be implemented using general-purpose data processing devices such as microprocessors or digital signal processors (DSPs).

[0155] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above descriptions are merely specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method of individualized gait adjustment, characterized in that, The method comprises the following steps: Constructing a music track recommendation model, and inputting multiple sample training gait data into the music track recommendation model for training; Specifically, a quadruple is constructed according to the sample training gait data, the quadruple comprising: gait information at a current time, a currently played music track, a current reward value calculated according to a reward function, and gait information at a next time; wherein the reward value is determined according to the change in gait score of the user's gait information and the current action compared with the previous gait score; the higher the consistency between the user's gait rhythm and the beat of the music track, the higher the corresponding gait score; in order to obtain a higher reward value, the music track that best matches the gait information is predicted through the music track recommendation model; Based on the currently played music track, the user's gait information is collected every first interval time; specifically, the foot pressure data corresponding to the support phase and swing phase is collected through a foot pressure sensor; gait trajectory data is collected through a posture sensor; wherein the foot pressure sensor is used to sense the point of force of the user's walking; the posture sensor is used to construct the gait trajectory; the gait information comprises: foot pressure data and gait trajectory data; Each of the gait information is input into the music track recommendation model in sequence, and a predicted music track is recommended every second interval time, comprising: sequentially aggregating multiple gait information in the second interval time to obtain a detection state, the second interval time being greater than the first interval time; determining a predicted music track according to a gait adjustment strategy and the detection state; If the currently played music track has been played, the next played music track is determined from the multiple predicted music tracks based on a preset condition, so as to perform personalized gait adjustment on the user.

2. The method of claim 1, wherein, The method further comprises: determining whether the currently played music track has been played; if not, recording the number and recommendation times of the predicted music track.

3. The method of claim 1, wherein, If the currently played music track has been played, the predicted music track with the most recommendation times is determined as the next played music track. The method further comprises:

4. The method of claim 2, wherein, obtaining current training gait data according to all gait information of the music track; determining a current gait score according to the matching degree between the current training gait data and the music track; determining a current reward value through the difference between the current gait score and the previous gait score; using the current training gait data, the currently played music track, the current reward value, and the next training data as an adjustment quadruple to optimize the gait adjustment strategy. The method further comprises:

5. The method of claim 4, wherein, The gait information comprises foot pressure data and gait trajectory data; the foot pressure data and the gait trajectory data are subjected to data normalization processing respectively; ​ The processed foot pressure data and the processed gait trajectory data are spliced to obtain the current training gait data.

6. A personalized gait adjustment system, characterized by, The method comprises: a music recommendation model, wherein the plurality of sample training gait data is input into the music recommendation model for training; Specifically, a quadruple is constructed according to the sample training gait data, the quadruple comprising: gait information at a current time, a currently played music piece, a current reward value calculated according to a reward function, and gait information at a next time; wherein the reward value is determined according to the change in the gait score of the user under the current action compared with the previous gait score; the higher the consistency between the gait rhythm of the user and the beat of the music piece, the higher the corresponding gait score; in order to obtain a higher reward value, the music piece that best matches the gait information is predicted through the music recommendation model; a collection module, configured to collect gait information of the user based on the currently played music piece every first interval time; specifically, foot pressure data corresponding to the support phase and swing phase is collected through a plantar pressure sensor; gait trajectory data is collected through a posture sensor; wherein the plantar pressure sensor is used to sense the point of force of the user walking; the posture sensor is used to construct a gait trajectory; the gait information comprises: foot pressure data and gait trajectory data; a prediction module, configured to input each of the gait information into the music recommendation model in sequence, and recommend a predicted music piece every second interval time, comprising: sequentially aggregating a plurality of gait information within the second interval time to obtain a detection state, wherein the second interval time is greater than the first interval time; determining a predicted music piece according to a gait adjustment strategy and the detection state; a music output module, configured to determine a next played music piece from a plurality of predicted music pieces based on a preset condition if the currently played music piece has been played, so as to perform personalized gait adjustment on the user.

7. An electronic device, wherein, The electronic device comprises: a processor; and a memory storing computer-executable instructions that, when executed, cause the processor to perform the method according to any one of claims 1-5.

8. A computer readable storage medium, wherein, The computer-readable storage medium stores one or more programs that, when executed by a processor, implement the method of any one of claims 1-5.

Images