Gait feature acquisition method and device, medium and electronic equipment

Abstract

The invention provides a gait feature obtaining method and device, a medium and electronic equipment, the method is applied to the field of wearable equipment, according to the method, a plurality of pressure sensors are evenly distributed in a sole area of an insole, and according to pressure values collected by the evenly distributed pressure sensors in real time, the gait feature is obtained. The pressure distribution condition of the plantar area of a user of the insole can be determined in real time, and then the gait characteristics of the user are determined. The gait features of the user are determined according to the pressure distribution conditions of all areas of the sole at the multiple collection moments, and the real-time performance and accuracy of gait feature obtaining are improved.

Description

Technical Field

[0001] The present application relates to the field of wearable devices, and more specifically, to a gait feature acquisition method, apparatus, medium, and electronic device in the field of wearable devices. Background Art

[0002] The human body is a fascinating and complex structure, and our understanding of its mechanisms continues to deepen. In recent years, technological advances have enabled humans to identify biometric features such as fingerprints, palm prints, and voiceprints, which are difficult to discern with the naked eye but exhibit high individual variability. These features typically require specialized equipment to accurately capture and analyze.

[0003] Similarly, the sole of the foot, the only area of the human body in direct contact with the external environment, also exhibits unique "pressure patterns" due to the subtle pressure distribution generated on its surface under different conditions. These pressure patterns can be divided into static pressure patterns and dynamic pressure patterns. The former reflects the force pattern of the sole of the foot in static states such as standing, while the latter depicts the temporal changes in pressure during movement states such as gait, running and jumping. More importantly, these plantar pressure characteristics are not determined by genetic genes and cannot be changed like fingerprints and voiceprints. Instead, they are closely related to the anatomical and physiological conditions of the human body, such as skeletal arrangement, muscle tension, and neural regulation, and have dynamic plasticity. They not only reflect the individual's current physical condition, but also serve as feedback indicators in the process of health management and functional rehabilitation, guiding the optimization of intervention strategies and the evaluation of their effectiveness.

[0004] To monitor plantar pressure, wearable insole-based devices have emerged. These devices, equipped with pressure sensors, collect pressure data from the wearer's plantar surface, providing a gait reference. However, existing insoles equipped with pressure sensors cannot precisely segment the sole of the foot, thus failing to capture a sufficiently detailed picture of pressure distribution and changes across the sole, reducing the accuracy of the resulting gait characteristics. Summary of the Invention

[0005] The present application provides a gait feature acquisition method, device, medium and electronic device. The method can obtain the pressure distribution of the sole area of the user of the insole in real time, determine the user's gait characteristics based on the pressure distribution at multiple acquisition moments, and improve the real-time and accuracy of gait feature acquisition.

[0006] In a first aspect, a gait feature acquisition method is provided, the method comprising: acquiring a target pressure value collected by a pressure sensor of an insole at each collection moment, wherein each collection moment is a plurality of collection moments within a preset time period, the insole comprising a plurality of pressure sensors, and the plurality of pressure sensors being evenly distributed in a sole area of the insole; determining a target pressure distribution matrix of the insole at each collection moment based on the target pressure value at each collection moment and the distribution position of the pressure sensors in the sole area; and determining a target gait feature of a user of the insole based on the target pressure distribution matrix at each collection moment.

[0007] The above technical solution evenly distributes multiple pressure sensors across the sole of the insole. Based on the pressure values collected in real time by these evenly distributed pressure sensors, the pressure distribution across the sole of the insole user can be determined in real time, thereby identifying the user's gait characteristics. Determining the user's gait characteristics based on the pressure distribution across the sole of the foot at multiple acquisition times improves the real-time and accuracy of gait feature acquisition.

[0008] In combination with the first aspect, in some possible implementations, the step of obtaining the target pressure value collected by the insole pressure sensor at each collection moment includes: collecting the target resistance value output by the insole pressure sensor at the target collection moment, where the target collection moment is any collection moment within a preset time period; and determining the target pressure value corresponding to the target resistance value at the target collection moment based on a mapping relationship between resistance value and pressure value.

[0009] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the step of determining the target pressure distribution matrix of the insole at each collection moment based on the target pressure value at each collection moment and the distribution position of the pressure sensor in the plantar area includes: determining the initial pressure distribution matrix of the insole at each collection moment based on the target pressure value at each collection moment and the distribution position of the pressure sensor in the plantar area; performing dimensionality reduction compression on each initial pressure distribution matrix to obtain a target pressure distribution matrix corresponding to each initial pressure distribution matrix.

[0010] The above technical solution can obtain the pressure distribution of the insole, which helps to analyze the force on the user's sole area. The initial pressure distribution matrix is compressed by dimensionality reduction, which reduces the amount of data to be processed and improves data transmission and processing efficiency.

[0011] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, after the step of determining the target pressure distribution matrix of the insole at each collection moment based on the target pressure value at each collection moment and the distribution position of the pressure sensor in the sole area, it also includes: determining the pressure change data of the sole pressure exerted on the insole based on the target pressure distribution matrix and the historical pressure distribution matrix; obtaining the pressure center drift trend of the user of the insole based on the pressure change data, and constructing the three-dimensional structure of the user's sole.

[0012] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the insole also includes a gyroscope sensor and an acceleration sensor. Before the step of determining the target pressure distribution matrix of the insole at each collection moment based on the target pressure value at each collection moment and the distribution position of the pressure sensor in the sole area, it also includes: obtaining the three-axis angular velocity value collected by the gyroscope sensor at each collection moment, obtaining the three-axis acceleration value collected by the acceleration sensor at each collection moment, the three-axis angular velocity value being the rate at which the user of the insole rotates around the three-dimensional coordinate axis in three-dimensional space, and the three-axis acceleration value being the acceleration of the user along the three-dimensional coordinate axis in three-dimensional space; obtaining the user's center of gravity trajectory based on the three-axis angular velocity value and the three-axis acceleration value at each collection moment.

[0013] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, after the step of obtaining the pressure center drift trend of the user of the insole based on the pressure change data and constructing the three-dimensional structure of the user's sole, it also includes: determining the force direction of the user's sole based on the user's center of gravity trajectory, pressure center drift trend and pressure change data.

[0014] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the step of determining the target gait characteristics of the user of the insole based on the target pressure distribution matrix at each acquisition moment includes: extracting gait spatial features from the target pressure distribution matrix at each acquisition moment through a convolutional neural network, and extracting gait time features from the target pressure distribution matrix through a long short-term memory network; combining the gait spatial features with the gait time features to determine the target gait characteristics of the user of the insole.

[0015] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, after the step of determining the target gait characteristics of the user of the insole based on the target pressure distribution matrix at each acquisition moment, it also includes: determining the user's gait change data based on the target gait characteristics and historical gait characteristics.

[0016] Through the above technical solution, the target gait characteristics are combined with the historical gait characteristics to obtain the user's gait change data, which is helpful for comparing and analyzing the user's gait characteristics.

[0017] In a second aspect, a gait feature acquisition device is provided, the device comprising:

[0018] a pressure acquisition unit, configured to acquire a target pressure value acquired by a pressure sensor of the insole at each acquisition moment, where each acquisition moment is a plurality of acquisition moments within a preset period, and the insole includes a plurality of pressure sensors, which are evenly distributed over the sole area of the insole;

[0019] a pressure distribution determining unit, configured to determine a target pressure distribution matrix of the insole at each acquisition moment based on the target pressure value at each acquisition moment and the distribution positions of the pressure sensors in the sole area;

[0020] The gait feature determination unit is used to determine the target gait feature of the user of the insole based on the target pressure distribution matrix at each acquisition moment.

[0021] In a third aspect, an electronic device is provided, the electronic device comprising: a memory for storing executable program code;

[0022] A processor is used to call and run executable program code from a memory to execute the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0023] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0024] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 Schematic diagram of a gait feature acquisition method provided in an embodiment of the present application;

[0026] Figure 2 This is a flow chart of a method for acquiring gait features provided in an embodiment of the present application;

[0027] Figure 3 This is a schematic diagram illustrating an example of the distribution position of a pressure sensor provided in an embodiment of the present application;

[0028] Figure 4 This is a flow chart of a method for acquiring gait features provided in an embodiment of the present application;

[0029] Figure 5Schematic diagram of a gait feature acquisition device provided in an embodiment of the present application;

[0030] Figure 6 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will clearly and thoroughly describe the technical solutions in this application in conjunction with the accompanying drawings. In the description of the embodiments of this application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more than two.

[0032] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0033] See Figure 1 , Figure 1 Schematic diagram of a gait feature acquisition method provided in an embodiment of the present application. Figure 1 As shown, the gait feature acquisition method provided in the embodiment of the present application can be applied to sports scenes. The sports scenes can be real sports scenes or virtual reality sports scenes realized by virtual reality equipment. Sports include dynamic foot movements such as walking, running, golf, skateboarding, and also static foot movements such as squats, deadlifts, and standing. When exercising, the user uses an insole containing a pressure sensor, and the electronic device obtains the pressure value applied to the insole by the sole of the user's foot detected by the pressure sensor, thereby obtaining the gait characteristics of the user during exercise. Electronic devices include but are not limited to terminal devices such as mobile phones, personal computers, and laptops. In the related art, the position or number of the pressure sensors provided in the insole will affect the pressure detection of the insole, thereby affecting the accuracy of the obtained gait characteristics of the user.

[0034] To address the above issues, an embodiment of the present application provides a method for acquiring gait characteristics. Multiple pressure sensors are evenly distributed across the sole area of an insole. Based on the pressure values collected in real time by the evenly distributed pressure sensors, the pressure distribution in the sole area of the user wearing the insole can be determined in real time, thereby determining the user's gait characteristics. By determining the user's gait characteristics based on the pressure distribution in each sole area at multiple collection moments, the real-time and accuracy of gait characteristic acquisition is improved.

[0035] based on Figure 1 The scene diagram shown below will be combined with Figure 2-Figure 6 , the gait feature acquisition method provided in the embodiment of the present application is introduced in detail.

[0036] See Figure 2 , Figure 2 FIG. 1 is a flow chart of a gait feature acquisition method provided in an embodiment of the present application. Figure 2 As shown, the method of the embodiment of the present application may include the following steps S101 to S103.

[0037] S101, obtaining target pressure values collected by a pressure sensor of an insole at each collection moment, where each collection moment is a plurality of collection moments within a preset time period, and the insole includes a plurality of pressure sensors, and the plurality of pressure sensors are evenly distributed on a sole area of the insole;

[0038] Specifically, the insole includes multiple pressure sensors, and the multiple pressure sensors are evenly distributed in the sole area of the insole. At multiple collection moments within a preset time period, the target pressure value of the insole is obtained through the pressure sensor. Preferably, the pressure sensor used in the embodiment of the present application can be a flexible film pressure sensor. The flexible film pressure sensor is based on a flexible material, has strong flexibility, and can be bent to a certain extent. At the same time, the flexible film pressure sensor has high sensitivity and low latency, and can detect slight changes in sole pressure in real time.

[0039] S102, determining a target pressure distribution matrix of the insole at each acquisition moment based on the target pressure value at each acquisition moment and the distribution positions of the pressure sensors in the sole area;

[0040] Specifically, based on the target pressure values obtained by the pressure sensors at each acquisition moment within a preset time period, as well as the distribution of the pressure sensors within the sole of the foot, a target pressure distribution matrix for the insole at each acquisition moment is determined. The pressure distribution matrix is a two-dimensional matrix that arranges the pressure data according to the distribution of the pressure sensors within the insole.

[0041] See Figure 3 , Figure 3 FIG. 1 is an example diagram of the distribution position of a pressure sensor provided in an embodiment of the present application. Figure 3As shown, the pressure sensors in the embodiment of the present application fully cover the sole area of the insole, with each grid in the figure representing a pressure sensor. The sole area is divided into multiple sub-areas, namely the first toe area, the second toe area, the third toe area, the fourth toe area, the fifth toe area, the first metatarsal sub-area, the second metatarsal sub-area, the third metatarsal sub-area, the fourth metatarsal sub-area, the fifth metatarsal sub-area, the medial arch sub-area, the lateral arch sub-area, the anterior heel sub-area, and the posterior heel sub-area.

[0042] S103: Determine target gait characteristics of the user of the insole based on the target pressure distribution matrix at each acquisition moment.

[0043] Specifically, after obtaining the target pressure distribution matrix, the pressure conditions of the user's sole area at each acquisition moment can be determined based on the target pressure distribution matrix at each acquisition moment, thereby determining the user's current gait spatial characteristics. The gait spatial characteristics of each acquisition moment are combined according to the time sequence of each acquisition moment to obtain a continuous target gait characteristic. Gait characteristics include cadence characteristics, stride characteristics, and bilateral symmetry characteristics. Among them, the cadence characteristic is the number of steps taken by the user in a preset period, which is used to reflect the user's walking speed. By detecting the number of ground contact times in any sub-area of the sole area of the same insole, the total number of steps taken by the user in the preset period is obtained, and then the cadence characteristic is determined based on the total number of steps and the preset period. The stride characteristic is the distance between two consecutive ground contact times of the same foot of the user, which is used to reflect the span of the user's step. The total walking distance of the user in the preset period is obtained, and the stride characteristic of the user is determined based on the total walking distance and the total number of steps of the user in the total walking distance. The left-right symmetry feature is used to indicate the consistency of the mechanical characteristics of the left and right feet during movement, including the balance of the pressure distribution on the left and right feet. The left-right symmetry feature of the user is determined by comparing the target pressure distribution matrices of the left and right feet.

[0044] In an embodiment of the present application, multiple pressure sensors are evenly distributed across the sole area of the insole. Based on the pressure values collected in real time by these evenly distributed pressure sensors, the pressure distribution across the sole area of the user wearing the insole can be determined in real time, thereby further determining the user's gait characteristics. Determining the user's gait characteristics based on the pressure distribution across the sole area at multiple collection moments improves the real-time and accuracy of gait feature acquisition.

[0045] See Figure 4 , Figure 4 FIG. 1 is a flow chart of a gait feature acquisition method provided in an embodiment of the present application. Figure 4 As shown, the method of the embodiment of the present application may include the following steps S201 to S209.

[0046] S201, collecting a target resistance value output by a pressure sensor of the insole at a target collection time, where the target collection time is any collection time within a preset time period;

[0047] Specifically, the insole includes multiple pressure sensors, which are evenly distributed in the sole area of the insole. At each collection moment within a preset time period, the resistance value output by the pressure sensor is collected. Preferably, the pressure sensor used in the embodiment of the present application can be a flexible film pressure sensor. The flexible film pressure sensor is based on a flexible material, has strong flexibility, and can be bent to a certain extent. At the same time, the flexible film pressure sensor has high sensitivity and low latency, and can detect slight changes in sole pressure in real time. Optionally, according to the classification of the output signal, the pressure sensor can be a piezoresistive sensor, a capacitive sensor, a piezoelectric sensor, a resonant sensor, or other types of sensors, or any combination of the above pressure sensors. Among them, the piezoresistive sensor utilizes the characteristic that the resistance of the piezoresistive material changes with pressure. When pressure is applied, the contact area of the conductive particles or structures in the pressure sensor increases, the conductive path is shortened, and the overall resistance is reduced. The capacitive sensor changes the distance between the capacitor plates or the dielectric constant through pressure, thereby causing a change in capacitance. The piezoelectric sensor is based on the characteristic that the piezoelectric material generates charge under pressure and outputs a voltage signal according to the applied pressure. Resonant sensors use pressure to alter the resonant frequency of the sensor structure, thereby changing the frequency when pressure is detected. Alternatively, embodiments of this application utilize a piezoresistive sensor made of a flexible film material. This sensor detects the resistance output by the pressure sensor to obtain the pressure value, improving the insole's wearability and anti-interference capabilities.

[0048] Optionally, before determining the target pressure value based on the target resistance value, the target resistance value can be denoised by a resistance-capacitance (RC) low-pass filter connected to the pressure sensor in the insole to remove Gaussian noise and high-frequency vibration noise in the target resistance value, reduce environmental interference, ensure the accuracy of the pressure data subsequently obtained, and at the same time reduce the amount of data and improve data processing efficiency.

[0049] S202, determining a target pressure value corresponding to a target resistance value at a target acquisition time based on a mapping relationship between resistance values and pressure values;

[0050] Specifically, based on a predetermined mapping relationship between resistance and pressure, a target pressure value corresponding to a target resistance value collected at each collection time within a preset time period is determined. This mapping relationship between resistance and pressure is obtained through data fitting. Different sample pressure values are applied to the pressure sensor, and sample resistance values output by the pressure sensor at each sample pressure value are obtained. Data fitting is performed on the sample pressure values and the corresponding sample resistance values to obtain a mapping function between resistance and pressure. This mapping function is the mapping relationship between resistance and pressure. When the target resistance value at the target collection time is obtained, the target resistance value is substituted into the mapping function to obtain the target pressure value corresponding to the target resistance value.

[0051] S203, determining an initial pressure distribution matrix of the insole at each collection moment based on the target pressure value at each collection moment and the distribution positions of the pressure sensors in the sole area;

[0052] Specifically, when the target pressure value at each acquisition moment is obtained according to the pressure sensor, the initial pressure distribution matrix of the insole at each acquisition moment is determined according to the distribution position of the pressure sensor in the sole area. The pressure distribution matrix is a two-dimensional matrix, and the pressure data is arranged according to the distribution position of the pressure sensor in the insole. The pressure sensors in the embodiment of the present application are evenly distributed in the sole area of the insole, and the sole area is divided into multiple sub-areas, namely the first toe area, the second toe area, the third toe area, the fourth toe area, the fifth toe area, the first metatarsal sub-area, the second metatarsal sub-area, the third metatarsal sub-area, the fourth metatarsal sub-area, the fifth metatarsal sub-area, the medial arch sub-area, the lateral arch sub-area, the front heel sub-area, and the rear heel sub-area.

[0053] S204, performing dimensionality reduction compression on each initial pressure distribution matrix to obtain a target pressure distribution matrix corresponding to each initial pressure distribution matrix;

[0054] Specifically, after obtaining the initial pressure distribution matrix, the electronic device can transmit the initial pressure distribution matrix to the cloud and store the initial pressure distribution matrix in the cloud, thereby reducing the storage pressure of the electronic device. Before transmitting the initial pressure distribution matrix, the initial pressure distribution matrix is subjected to dimensionality reduction compression to obtain the target pressure distribution matrix. By compressing the high-dimensional pressure data into low-dimensional features through dimensionality reduction compression, the transmission rate and the efficiency of the electronic device's subsequent data analysis of gait characteristics from the pressure distribution matrix are improved. The specific process of dimensionality reduction compression is to divide the initial pressure distribution matrix into multiple local regions, perform average pooling on each local region, calculate the average value of the pressure value in each local region, and only store the average value in each local region, thereby reducing the matrix dimension of the initial pressure distribution matrix to obtain a coarse-grained matrix. For example, if the initial pressure distribution matrix is a 4×4 matrix, it is divided into 2×2 local regions, and the edge data is padded or truncated with zeros. The final coarse-grained matrix is a 2×2 matrix, with the dimension reduced to 1 / 4 of the original data volume. After obtaining the coarse-grained matrix, key features used in the gait feature acquisition process are extracted from the coarse-grained matrix, such as the center of pressure trajectory, the area of maximum pressure, and the ratio of the ground contact area. After extracting these key features, the data dimensions are further compressed. Principal component analysis or t-Distributed Stochastic Neighbor Embedding (t-SNE) is performed on the coarse-grained matrix to reduce the matrix data to a low-dimensional space, resulting in the target pressure distribution matrix.

[0055] S205, determining pressure change data of the plantar pressure exerted on the insole based on the target pressure distribution matrix and the historical pressure distribution matrix;

[0056] Specifically, the pressure values of each sub-region in the plantar area displayed by the target pressure distribution matrix are combined with the pressure values of each sub-region in the plantar area displayed by the historical pressure distribution matrix through a time series algorithm to obtain the pressure change data of each sub-region in the plantar area of the insole. Based on the pressure change data, the plantar pressure distribution of the user during the continuous collection time can be determined. Optionally, the pressure change data can be the pressure change data within a preset time period, and the historical pressure distribution matrix is the pressure distribution matrix of each collection time before the target collection time in the preset time period; the pressure change data can also be the pressure change data for each day / week / month / year, and the historical pressure distribution matrix is the pressure distribution matrix of the past preset days. The electronic device can provide the user with a change period selection for the pressure change data, so that the user can select the pressure change data for each day / week / month / year as needed. At the same time, embodiments of the present application can also obtain the user's age, gender, height, weight, foot size, and athletic level, and obtain the plantar pressure distribution matrix and pressure change data of people of the same age, gender, height, weight, foot size, and athletic level as the user when exercising in a standard posture, providing the user with standard data of the plantar pressure distribution matrix and pressure change data for comparative analysis. Exercises include dynamic foot exercises such as walking, running, golf, and skateboarding, as well as static foot exercises such as squats, deadlifts, and standing. The preset time period can be set according to the duration of the exercise. The standard data is compared and analyzed with the user's data.

[0057] S206, obtaining a pressure center drift trend of the user of the insole based on the pressure change data, and constructing a three-dimensional structure of the user's sole;

[0058] Specifically, the pressure change data includes the pressure conditions for each subregion of the user's plantar region at each acquisition moment. The pressure distribution matrices of the left and right feet at the same moment are compared to provide the user with a balance analysis of the same subregion in both plantar regions. The pressure distribution matrices of the same foot at different moments are then analyzed to obtain the real-time pressure of each subregion in the user's plantar region and the ratio of the real-time pressure experienced by each subregion to the total pressure experienced by the plantar region. After obtaining the target pressure distribution matrices corresponding to each acquisition moment within a preset time period, the target pressure distribution matrices are analyzed sequentially in chronological order to obtain the average pressure, peak pressure, pressure ratio, average impulse, pressure duration, and pressure direction for each subregion in the plantar region during the preset time period. The average impulse is used to reflect the cumulative effect of pressure in each subregion. Based on this data, the user's center of pressure drift trend is determined. The center of pressure refers to the weighted average point of pressure distribution when the sole of the foot is in contact with the ground. During static or dynamic exercise, the center of pressure moves with changes in plantar pressure. The pressure center drift trend is the change pattern of the pressure center's movement direction, speed, and amplitude in the time dimension, which is used to reflect the dynamic adjustment process of the sole's force on the ground.

[0059] According to the pressure change data within the continuous acquisition time, the local features of each sub-region in the user's sole area can be determined, and the local features of all sub-regions are combined to obtain the three-dimensional structure of the user's sole. The specific process is to input the pressure change data of each sub-region into the inverse modeling model, analyze the pressure change data through the inverse modeling model, and enhance the local features of the sub-region corresponding to the pressure change data. The inverse modeling model can be a model based on modeling technologies such as Variational Autoencoder (VAE), Generative Adversarial Network (GAN) or Point Cloud Generation Network (PointNet++). Preferably, the user's foot image and foot parameters are input into the inverse modeling model during the modeling process, so that the final output three-dimensional structure of the sole is more accurate, which assists the user in choosing shoes.

[0060] S207, extracting gait spatial features from the target pressure distribution matrix at each acquisition moment using a convolutional neural network, and extracting gait temporal features from the target pressure distribution matrix using a long short-term memory network;

[0061] Specifically, the target pressure distribution matrix obtained at each successive acquisition moment is input into a deep learning model based on a convolutional neural network-long short-term memory network (CNN-LSTM). Within this deep learning model, CNN extracts gait spatial features from the target pressure distribution matrix at each acquisition moment, while LSTM extracts gait temporal features from the target pressure distribution matrix at each successive acquisition moment. Gait spatial features and gait temporal features are two core concepts in gait characterization, describing the laws and characteristics of human motion from the spatial and temporal dimensions, respectively.

[0062] Gait spatial features refer to the geometric distribution and morphological expression of gait in physical space, reflecting static or dynamic spatial parameters such as the position, distance, and angle of limbs and joints during movement. A convolutional neural network receives the target pressure distribution matrix at a single acquisition moment and treats it as a "single-channel image." Multiple convolution kernels are used to capture the target pressure values in different subregions of the plantar region, extracting gait spatial features. These features are then flattened into a one-dimensional vector, which serves as the input to the long-short-term memory network.

[0063] Gait temporal characteristics refer to the dynamic changes in gait over time, reflecting the time distribution, rhythm, and periodicity of each stage of movement. The long short-term memory network receives a time series consisting of one-dimensional vectors of gait spatial characteristics at consecutive acquisition moments and outputs the temporal dependencies of these spatial features through an input gate, a forget gate, and an output gate.

[0064] S208, combining the gait spatial feature and the gait temporal feature to determine a target gait feature of the user of the insole;

[0065] Specifically, the gait spatial features and gait temporal features are spliced together to form a joint feature vector, which is the target gait feature of the user within a preset time period. Gait features include cadence features, stride features, and bilateral symmetry features. The cadence feature is the number of steps taken by the user within a preset period, which is used to reflect the user's walking speed. By detecting the number of touchdowns in any sub-area of the sole area of the same insole, the total number of steps taken by the user within the preset period is obtained, and then the cadence feature is determined by the total number of steps and the preset period. The stride feature is the distance between two consecutive touchdowns of the same foot of the user, which is used to reflect the span of the user's steps. The total walking distance of the user within the preset period is obtained, and the stride feature of the user is determined by the total walking distance and the total number of steps of the user in the total walking distance. The bilateral symmetry feature is used to indicate the consistency of the mechanical characteristics of the left and right feet during walking, including the balance of the pressure distribution of the left and right feet. The left and right symmetry feature of the user is determined by comparing the target pressure distribution matrices of the left and right feet.

[0066] The embodiment of the present application can also obtain the user's age, gender, height, weight, foot size and exercise level, and obtain the gait characteristics of people of the same age, gender, height, weight, foot size and exercise level as the user walking in a standard posture, providing the user with standard data for comparison.

[0067] In a feasible implementation, after obtaining the gait characteristics, the gait characteristics and gait change data can be input into an artificial intelligence model. The artificial intelligence model is trained by pre-collected standard data on gait characteristics of people of various ages, genders, heights, weights, foot sizes, and exercise levels. It assists users in comparing gait characteristics, outputs the differences between the user's gait characteristics and the standard data, and provides data analysis for users.

[0068] S209: Determine the user's gait change data based on the target gait characteristics and the historical gait characteristics.

[0069] Specifically, the target gait features are combined with historical gait features through a time series algorithm to obtain the user's gait change data. Optionally, the gait change data can be daily / weekly / monthly / yearly gait change data. The electronic device can provide the user with a selection of change periods for the gait change data, allowing the user to select daily / weekly / monthly / yearly gait change data as needed.

[0070] In one feasible embodiment, an accelerometer and a gyroscope are also installed inside the insole. The accelerometer is used to measure the linear acceleration of the foot in three-dimensional space, quantifying the motion state by detecting changes in inertial force. Its measurement dimensions are the acceleration values of three axes (X / Y / Z directions), and the output signals are static acceleration and dynamic acceleration. The static acceleration can be the acceleration in the direction of gravity, and the dynamic acceleration can be the vibration of the foot during dynamic movements such as walking and running. The gyroscope is used to measure the angular velocity of the foot. Its measurement dimensions are the angular velocity of three axes (pitch angle, roll angle, yaw angle), and the output signal is the rotational change of the foot during movement, such as the inversion / valgus angle of the foot, turning movement, etc. When a user exercises with the insole, not only is pressure data output by the pressure sensor acquired, but also the three-axis angular velocity values collected by the gyroscope at each acquisition moment and the three-axis acceleration values collected by the acceleration sensor at each acquisition moment are acquired. The three-axis angular velocity values represent the rate at which the user of the insole rotates around the three-dimensional coordinate axes in three-dimensional space, and the three-axis acceleration values represent the acceleration of the user along the three-dimensional coordinate axes in three-dimensional space. Based on the three-axis angular velocity and three-axis acceleration values at each acquisition moment, the user's center of gravity trajectory is acquired. The center of gravity is the location of the center of mass of the human body and is the weighted average point of the mass of all parts of the body. The center of gravity trajectory is the continuous movement path of the center of gravity in three-dimensional space, reflecting the overall balance state and motion control efficiency of the human body. After the user's center of pressure drift trend is acquired based on the pressure change data, the user's plantar force direction is determined based on the user's center of gravity trajectory, the pressure center drift trend, and the pressure change data. The plantar force direction is used to reflect the stability of the user's plantar support mechanism.

[0071] For example, assuming that the pressure change data is complete pressure change data of the user during exercise, taking the squat exercise in fitness as an example, the electronic device pre-stores standard data of people of the same age, gender, height, weight, sole size, and exercise level as the user when performing the squat exercise in a standard posture. The plantar pressure distribution matrix at each acquisition moment when the user performs the squat exercise, the pressure change data of each sub-area of the sole at consecutive acquisition moments, the three-axis angular velocity value at each acquisition moment, the change data of the three-axis angular velocity value at consecutive acquisition moments, the three-axis acceleration value at each acquisition moment, and the change data of the three-axis acceleration value at consecutive acquisition moments are analyzed. The plantar pressure distribution matrix, three-axis angular velocity, and three-axis acceleration at the same moment are matched. Through multimodal data, the center of gravity trajectory, pressure center drift trend, and plantar force direction of the user during the squat exercise are obtained, and the user's target posture when performing the squat exercise is determined. The multimodal data obtained when the user performs squat exercises are compared and analyzed with the standard data to determine the difference between the user's target posture and the standard posture, and a prompt message is output on the mobile terminal based on the difference between the target posture and the standard posture to prompt the user to correct the posture.

[0072] In an embodiment of the present application, a plurality of pressure sensors are evenly distributed in the sole area of the insole. Based on the pressure values collected in real time by the evenly distributed pressure sensors, the pressure distribution of the sole area of the user of the insole can be determined in real time, and then the gait characteristics of the user can be determined. When obtaining the target pressure distribution matrix, the initial pressure distribution matrix composed of the target pressure values is subjected to dimensionality reduction compression, which reduces the data dimension and improves the efficiency of subsequent gait feature extraction. The gait characteristics of the user are determined based on the pressure distribution of each area of the sole at multiple acquisition moments, which improves the real-time and accuracy of gait feature acquisition. The current target pressure distribution matrix is combined with the historical pressure distribution matrix to obtain pressure change data, and the target gait characteristics are combined with the historical gait characteristics to obtain gait change data. The pressure change data can comprehensively obtain the fine distribution, change trend and transfer path of the user's sole pressure. Combining pressure change data, angular velocity data, and acceleration data can restore the force angle and direction of human muscles, as well as the posture characteristics and force characteristics of bones under different load conditions, achieving high-precision quantification and dynamic analysis of human motion posture. It is suitable for human posture and motion control analysis in various sports scenarios, helps users correct their posture, improves the user experience, and ensures the effectiveness of the insole.

[0073] based on Figure 1 The following is a schematic diagram of the scene. Figure 5 , the gait feature acquisition device provided in the embodiment of the present application is introduced in detail. It should be noted that, Figure 5 The gait feature acquisition device in the present application is used to execute Figure 2-Figure 4 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 2-Figure 4 The embodiment shown.

[0074] See Figure 5 , Figure 5 This is a schematic diagram of the structure of a gait feature acquisition device provided in an embodiment of the present application. Figure 5 As shown, the gait feature acquisition device 1 of the embodiment of the present application may include: a pressure acquisition unit 11 , a pressure distribution determination unit 12 and a gait feature determination unit 13 .

[0075] A pressure acquisition unit 11 is configured to acquire a target pressure value acquired by a pressure sensor of the insole at each acquisition moment, where each acquisition moment is a plurality of acquisition moments within a preset period. The insole includes a plurality of pressure sensors, and the plurality of pressure sensors are evenly distributed over the sole area of the insole.

[0076] a pressure distribution determining unit 12 for determining a target pressure distribution matrix of the insole at each acquisition moment based on the target pressure value at each acquisition moment and the distribution positions of the pressure sensors in the sole area;

[0077] The gait feature determination unit 13 is configured to determine a target gait feature of the user of the insole based on the target pressure distribution matrix at each acquisition moment.

[0078] Optionally, the pressure acquisition unit 11 is specifically configured to acquire a target resistance value output by a pressure sensor of the insole at a target acquisition time, where the target acquisition time is any acquisition time within a preset time period;

[0079] Based on the mapping relationship between the resistance value and the pressure value, a target pressure value corresponding to the target resistance value at the target acquisition time is determined.

[0080] Optionally, the pressure distribution determining unit 12 is specifically configured to determine an initial pressure distribution matrix of the insole at each collection moment based on the target pressure value at each collection moment and the distribution positions of the pressure sensors in the sole area;

[0081] Each initial pressure distribution matrix is subjected to dimensionality reduction compression to obtain a target pressure distribution matrix corresponding to each initial pressure distribution matrix.

[0082] Optionally, the gait feature acquisition device 1 is specifically used to determine pressure change data of the plantar pressure exerted on the insole based on the target pressure distribution matrix and the historical pressure distribution matrix;

[0083] Based on the pressure change data, the pressure center drift trend of the user of the insole is obtained, and the three-dimensional structure of the user's sole is constructed.

[0084] Optionally, the insole further includes a gyroscope sensor and an acceleration sensor, and the gait feature acquisition device 1 is specifically used to acquire three-axis angular velocity values acquired by the gyroscope sensor at each acquisition moment, and acquire three-axis acceleration values acquired by the acceleration sensor at each acquisition moment, wherein the three-axis angular velocity values are rotation rates of the user of the insole around the three-dimensional coordinate axes in three-dimensional space, and the three-axis acceleration values are accelerations of the user along the three-dimensional coordinate axes in three-dimensional space;

[0085] The user's center of gravity trajectory is obtained based on the three-axis angular velocity values and three-axis acceleration values at each collection moment.

[0086] Optionally, the gait feature acquisition device 1 is specifically used to determine the force direction of the user's sole based on the user's center of gravity trajectory, pressure center drift trend and pressure change data.

[0087] Optionally, the gait feature determination unit 13 is specifically configured to extract gait spatial features from the target pressure distribution matrix at each acquisition moment through a convolutional neural network, and extract gait temporal features from the target pressure distribution matrix through a long short-term memory network;

[0088] The gait spatial features and the gait temporal features are combined to determine the target gait features of the user of the insole.

[0089] Optionally, the gait feature acquisition device 1 is specifically used to determine the user's gait change data based on the target gait feature and the historical gait feature.

[0090] In an embodiment of the present application, a plurality of pressure sensors are evenly distributed in the sole area of the insole. Based on the pressure values collected in real time by the evenly distributed pressure sensors, the pressure distribution in the sole area of the user of the insole can be determined in real time, thereby determining the gait characteristics of the user. When obtaining the pressure value based on the resistance value output by the pressure sensor, the resistance value is subjected to denoising, static calibration, and dynamic calibration, thereby reducing the offset effect of the pressure sensor during long-term use and improving the accuracy of pressure value acquisition. When obtaining the target pressure distribution matrix, the initial pressure distribution matrix composed of the target pressure values is subjected to dimensionality reduction compression, thereby reducing the data dimension and improving the efficiency of subsequent gait feature extraction. The gait characteristics of the user are determined based on the pressure distribution conditions in each area of the sole at multiple acquisition moments, thereby improving the real-time and accuracy of gait feature acquisition. The current target pressure distribution matrix is combined with the historical pressure distribution matrix to obtain pressure change data, and the target gait characteristics are combined with the historical gait characteristics to obtain gait change data. The pressure change data can comprehensively obtain the fine distribution, change trend and transfer path of the user's plantar pressure. Combining the pressure change data, angular velocity data and acceleration data can restore the force angle and direction of the human lower limb muscles, as well as the posture characteristics and force characteristics of the bones under different load states, realizing high-precision quantification and dynamic analysis of human motion posture. It is suitable for human posture and motion control analysis in various sports scenarios, helps users to correct their posture, improves the user experience, and ensures the use effect of the insole.

[0091] See Figure 6 , Figure 6 This is a structural diagram of an electronic device provided in an embodiment of the present application.

[0092] For example, Figure 6 As shown, the electronic device 600 includes: a processor 601 and a memory 602, wherein the processor 601 is electrically connected to the memory 602.

[0093] The processor 601 is the control center of the electronic device 600 and may include one or more processing cores. The processor 601 utilizes various interfaces and circuits to connect the various parts of the entire electronic device. By running or calling computer programs stored in the memory 602, as well as calling data stored in the memory 602, the processor 601 executes various functions of the electronic device and processes data, thereby providing overall control over the electronic device 600. Optionally, the processor 601 may be implemented in the form of at least one hardware component selected from the group consisting of a digital signal processing (DSP), a field programmable gate array (FPGA), and a programmable logic array (PLA). The processor 601 may integrate one or a combination of a CPU, a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interfaces, and applications; the GPU is responsible for rendering and drawing display content; and the modem is responsible for handling wireless communications. It is understood that the modem may not be integrated into the processor 601 and may be implemented separately via a communication chip.

[0094] The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and data processing by running the computer programs and modules stored in the memory 602. The memory 602 can mainly include a program storage area and a data storage area. The program storage area can store an operating system, a computer program required for at least one function, etc.; the data storage area can store data created based on the use of the electronic device 600.

[0095] In addition, the memory 602 may include a high-speed random access memory and a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.

[0096] In this embodiment, the processor 601 in the electronic device 600 loads instructions corresponding to one or more computer program processes into the memory 602 according to the following steps, and the processor 601 runs the computer program stored in the memory 602 to implement various functions as follows:

[0097] Obtaining target pressure values collected by a pressure sensor of the insole at each collection moment, where each collection moment is a plurality of collection moments within a preset period, and the insole includes a plurality of pressure sensors, and the plurality of pressure sensors are evenly distributed on a sole area of the insole;

[0098] Determine the target pressure distribution matrix of the insole at each acquisition moment based on the target pressure value at each acquisition moment and the distribution position of the pressure sensor in the sole area;

[0099] The target gait characteristics of the user of the insole are determined based on the target pressure distribution matrix at each acquisition moment.

[0100] Optionally, when executing the process of acquiring the target pressure value collected by the pressure sensor of the insole at each collection moment, the processor 601 specifically performs:

[0101] Collecting the target resistance value output by the pressure sensor of the insole at a target collection time, where the target collection time is any collection time within a preset time period;

[0102] Based on the mapping relationship between the resistance value and the pressure value, a target pressure value corresponding to the target resistance value at the target acquisition time is determined.

[0103] Optionally, when determining the target pressure distribution matrix of the insole at each acquisition moment based on the target pressure value at each acquisition moment and the distribution position of the pressure sensor in the sole area, the processor 601 specifically performs:

[0104] Based on the target pressure value at each acquisition moment and the distribution position of the pressure sensor in the sole area, an initial pressure distribution matrix of the insole at each acquisition moment is determined;

[0105] Each initial pressure distribution matrix is subjected to dimensionality reduction compression to obtain a target pressure distribution matrix corresponding to each initial pressure distribution matrix.

[0106] Optionally, after determining the target pressure distribution matrix of the insole at each acquisition moment based on the target pressure value at each acquisition moment and the distribution positions of the pressure sensors in the sole area, the processor 601 further executes:

[0107] Determine pressure change data of plantar pressure on the insole based on the target pressure distribution matrix and the historical pressure distribution matrix;

[0108] Based on the pressure change data, the pressure center drift trend of the user of the insole is obtained, and the three-dimensional structure of the user's sole is constructed.

[0109] Optionally, the insole further includes a gyroscope sensor and an acceleration sensor. Before determining the target pressure distribution matrix of the insole at each acquisition moment based on the target pressure value at each acquisition moment and the distribution position of the pressure sensor in the sole area, the processor 601 further executes:

[0110] Obtaining three-axis angular velocity values collected by the gyroscope sensor at each collection moment, and obtaining three-axis acceleration values collected by the acceleration sensor at each collection moment, wherein the three-axis angular velocity values are the rate at which the user of the insole rotates around the three-dimensional coordinate axes in three-dimensional space, and the three-axis acceleration values are the accelerations of the user along the three-dimensional coordinate axes in three-dimensional space;

[0111] The user's center of gravity trajectory is obtained based on the three-axis angular velocity values and three-axis acceleration values at each collection moment.

[0112] Optionally, after acquiring the pressure center drift trend of the user of the insole based on the pressure change data and constructing the three-dimensional structure of the user's sole, the processor 601 further executes:

[0113] Based on the user's center of gravity trajectory, pressure center drift trend and pressure change data, the user's foot force direction is determined.

[0114] Optionally, when determining the target gait characteristics of the user of the insole based on the target pressure distribution matrix at each acquisition moment, the processor 601 specifically performs:

[0115] The gait spatial features are extracted from the target pressure distribution matrix at each acquisition moment through a convolutional neural network, and the gait temporal features are extracted from the target pressure distribution matrix through a long short-term memory network.

[0116] The gait spatial features and the gait temporal features are combined to determine the target gait features of the user of the insole.

[0117] Optionally, after determining the target gait characteristics of the user of the insole based on the target pressure distribution matrix at each acquisition moment, the processor 601 further executes:

[0118] Based on the target gait characteristics and the historical gait characteristics, the user's gait change data is determined.

[0119] In an embodiment of the present application, a plurality of pressure sensors are evenly distributed in the sole area of the insole. Based on the pressure values collected in real time by the evenly distributed pressure sensors, the pressure distribution in the sole area of the user of the insole can be determined in real time, thereby determining the gait characteristics of the user. When obtaining the pressure value based on the resistance value output by the pressure sensor, the resistance value is subjected to denoising, static calibration, and dynamic calibration, thereby reducing the offset effect of the pressure sensor during long-term use and improving the accuracy of pressure value acquisition. When obtaining the target pressure distribution matrix, the initial pressure distribution matrix composed of the target pressure values is subjected to dimensionality reduction compression, thereby reducing the data dimension and improving the efficiency of subsequent gait feature extraction. The gait characteristics of the user are determined based on the pressure distribution conditions in each area of the sole at multiple acquisition moments, thereby improving the real-time and accuracy of gait feature acquisition. The current target pressure distribution matrix is combined with the historical pressure distribution matrix to obtain pressure change data, and the target gait characteristics are combined with the historical gait characteristics to obtain gait change data. The pressure change data can comprehensively obtain the fine distribution, change trend and transfer path of the user's plantar pressure. Combining the pressure change data, angular velocity data and acceleration data can restore the force angle and direction of the human lower limb muscles, as well as the posture characteristics and force characteristics of the bones under different load states, realizing high-precision quantification and dynamic analysis of human motion posture. It is suitable for human posture and motion control analysis in various sports scenarios, helps users to correct their posture, improves the user experience, and ensures the use effect of the insole.

[0120] It should be understood that the device provided in the embodiment of the present application is used to execute the above-mentioned gait feature acquisition method, and thus can achieve the same effect as the above-mentioned implementation method.

[0121] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to an electronic device, the processing module may be used to control and manage the operation of the electronic device. The storage module may be used to support the electronic device in executing relevant program codes, etc.

[0122] The processing module may be a processor or controller that implements or executes the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processing system (DSP) and a microprocessor, and the storage module may be a memory.

[0123] In addition, the device provided in the embodiment of the present application can specifically be a chip, component or module, and the chip may include a connected processor and memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a gait feature acquisition method provided in the above embodiment.

[0124] An embodiment of the present application also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned related method steps to implement a gait feature acquisition method provided in the above embodiment.

[0125] This embodiment further provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a gait feature acquisition method provided in the above embodiment.

[0126] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0127] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0128] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0129] The above content is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A gait feature acquisition method, characterized in that: The method comprises: Obtaining a target pressure value collected by a pressure sensor of the insole at each collection moment, where each collection moment is a plurality of collection moments within a preset time period, and the insole includes a plurality of pressure sensors, and the plurality of pressure sensors are evenly distributed in a sole area of the insole; Determining a target pressure distribution matrix of the insole at each of the acquisition moments based on the target pressure value at each of the acquisition moments and the distribution positions of the pressure sensors in the sole area; The target gait characteristics of the user of the insole are determined based on the target pressure distribution matrix at each acquisition moment.

2. The method according to claim 1, characterized in that The step of obtaining the target pressure value collected by the pressure sensor of the insole at each collection moment includes: collecting a target resistance value output by a pressure sensor of the insole at a target collection time, wherein the target collection time is any collection time within the preset time period; Based on the mapping relationship between the resistance value and the pressure value, a target pressure value corresponding to the target resistance value at the target acquisition time is determined.

3. The method according to claim 1, characterized in that Determining the target pressure distribution matrix of the insole at each of the acquisition moments based on the target pressure value at each of the acquisition moments and the distribution positions of the pressure sensors in the sole area includes: determining an initial pressure distribution matrix of the insole at each of the acquisition moments based on the target pressure value at each of the acquisition moments and the distribution positions of the pressure sensors in the sole area; Perform dimensionality reduction compression on each of the initial pressure distribution matrices to obtain a target pressure distribution matrix corresponding to each of the initial pressure distribution matrices.

4. The method according to claim 1, wherein After determining the target pressure distribution matrix of the insole at each of the acquisition moments based on the target pressure values at each of the acquisition moments and the distribution positions of the pressure sensors in the sole area, the method further includes: determining pressure change data of the plantar pressure exerted on the insole based on the target pressure distribution matrix and the historical pressure distribution matrix; The pressure center drift trend of the user of the insole is obtained based on the pressure change data, and the three-dimensional structure of the sole of the user is constructed.

5. The method according to claim 4, characterized in that The insole further includes a gyroscope sensor and an acceleration sensor. Before determining the target pressure distribution matrix of the insole at each acquisition moment based on the target pressure value at each acquisition moment and the distribution position of the pressure sensor in the sole area, the method further includes: Obtaining three-axis angular velocity values collected by the gyroscope sensor at each collection moment, and obtaining three-axis acceleration values collected by the acceleration sensor at each collection moment, wherein the three-axis angular velocity values are rotation rates of the user of the insole around the three-dimensional coordinate axes in the three-dimensional space, and the three-axis acceleration values are accelerations of the user along the three-dimensional coordinate axes in the three-dimensional space; The center of gravity trajectory of the user is obtained based on the three-axis angular velocity values and the three-axis acceleration values at each of the acquisition moments.

6. The method according to claim 5, characterized in that After obtaining the pressure center drift trend of the user of the insole based on the pressure change data and constructing the three-dimensional structure of the sole of the user, the method further includes: The force direction of the user's sole is determined based on the user's center of gravity trajectory, the pressure center drift trend, and the pressure change data.

7. The method according to claim 1, characterized in that The determining of the target gait characteristics of the user of the insole based on the target pressure distribution matrix at each acquisition moment includes: Extracting gait spatial features from the target pressure distribution matrix at each acquisition moment through a convolutional neural network, and extracting gait temporal features from the target pressure distribution matrix through a long short-term memory network; The gait spatial feature is combined with the gait temporal feature to determine a target gait feature of the user of the insole.

8. The method according to claim 1, characterized in that After determining the target gait characteristics of the user of the insole based on the target pressure distribution matrix at each acquisition moment, the method further includes: Based on the target gait characteristics and the historical gait characteristics, the user's gait change data is determined.

9. A gait feature acquisition device, characterized in that: The device comprises: a pressure acquisition unit, configured to acquire a target pressure value acquired by a pressure sensor of the insole at each acquisition moment, wherein each acquisition moment is a plurality of acquisition moments within a preset time period, and the insole includes a plurality of pressure sensors, and the plurality of pressure sensors are evenly distributed over a sole area of the insole; a pressure distribution determining unit, configured to determine a target pressure distribution matrix of the insole at each of the acquisition moments based on the target pressure value at each of the acquisition moments and the distribution positions of the pressure sensors in the sole area; A gait feature determination unit is used to determine a target gait feature of the user of the insole based on the target pressure distribution matrix at each acquisition moment.

10. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable program code; A processor is configured to call and run the executable program code from the memory, so that the electronic device executes the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program code, and when the computer program code is executed, the method according to any one of claims 1 to 8 is implemented.

Images