Walking posture detection method and system based on walking posture correction wearable equipment

Abstract

The invention discloses a walking posture detection method and system based on a walking posture correction wearable device, and belongs to the technical field of data detection.The walking posture detection method comprises the steps that a plurality of pressure sensors are arranged in the walking posture correction wearable device used by a target object based on fixed-point layout, and pressure signals are transmitted to a microprocessor MCU; if the pressure signal difference is greater than a first threshold value, converting the pressure signal into pressure data, setting a wireless transmission mode, and transmitting the pressure data to an APP terminal based on the wireless transmission mode; classifying and marking all the pressure data as a left pressure data set and a right pressure data set, and storing the left pressure data set and the right pressure data set into a database; and the analysis model outputs a first change trend and a second change trend corresponding to the standard left data and the standard right data in a preset time length, generates a data report, and sends the data report to the target object to complete walking posture detection reminding. According to the invention, the timeliness and accuracy of walking posture detection can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data detection, and in particular relates to a walking posture detection method and system based on a walking posture correction wearable device. Background Art

[0002] Flat feet are common in life and are quite harmful. Patients are prone to foot pain and local swelling after long-term walking, and may even cause dislocation of the talohumeral joint or calcaneal valgus. In addition, due to abnormal foot structure, the force pattern and mechanical structure during the load-bearing process will also change, which may accelerate the degeneration of the ankle, knee, hip and spinal joints, causing osteoarthritis and joint pain. The prevention and correction of acquired flat feet can start from childhood. The arch of the foot is not fully formed in infancy, and this problem can be avoided by cultivating good foot habits. Therefore, a shoe solution will be provided for walking posture detection and cultivating good foot habits.

[0003] Similar prior art includes a Chinese patent application with publication number CN104887372A, which provides a walking and standing posture correction device, shoes, insoles and correction method. The walking posture correction device includes: a signal transmitter for transmitting a signal; a signal receiver, wirelessly connected to the signal transmitter, for receiving the signal transmitted by the signal transmitter; a processor, connected to the signal receiver, for determining whether the intensity of the signal received by the signal receiver is within a preset intensity range, if not, generating a prompt signal; a prompter, connected to the processor, for prompting the user that the walking posture is incorrect after receiving the prompt signal. This invention can detect whether the user's walking and standing posture is correct and give a prompt. There is also a Chinese patent application with publication number CN106889691A, which provides a smart shoe and a gait monitoring method, wherein the smart shoe includes: a shoe body and a monitoring device arranged in the shoe body, wherein the monitoring device includes: a first detection module, which includes at least one first detection module for detecting the pressure of the sole of the foot on the shoe body, and each first detection module is arranged in the shoe body; a reminder module, which is configured to perform a reminder operation when the pressure value detected by the first detection module is greater than the corresponding preset pressure. The invention can remind the user in real time of irregular gait and ensure the standardization of the user's gait.

[0004] However, in the above-mentioned prior art, prompting the user's walking posture by emitting a prompt signal may result in problems such as interruption of the prompt signal or untimely prompting; using the pressure value corresponding to the first detection module to remind the user of irregular gait in real time may result in randomness, which reduces the accuracy of the reminder operation. In actual situations, it is necessary to reduce the transmission power consumption of the pressure sensor, improve the stability of data collection, and improve the accuracy of the target object's walking posture detection by the analysis model. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a walking posture detection method and system based on a walking posture correction wearable device to solve the problems in the prior art.

[0006] In order to achieve the above-mentioned purpose of the invention, the present invention proposes a walking posture detection method based on a walking posture correction wearable device, comprising:

[0007] A plurality of pressure sensors are arranged in a fixed-point layout in the walking posture correction wearable device used by the target object, and the pressure sensors collect pressure signals and transmit the pressure signals to a microprocessor MCU;

[0008] The microprocessor MCU analyzes and processes the pressure signal based on a preset built-in algorithm, sets a first threshold, converts the pressure signal into pressure data if the pressure signal difference is greater than the first threshold, sets a wireless transmission mode, and transmits the pressure data to an APP terminal based on the wireless transmission mode;

[0009] The APP terminal classifies and marks all the pressure data into a left pressure data set and a right pressure data set based on the label information of the pressure sensor, and stores them in a database;

[0010] An analysis model is constructed, and all data sets contained in the database are screened based on time features to generate standard left data and standard right data. The analysis model outputs a first change trend and a second change trend corresponding to a preset time length based on the standard left data and the standard right data, respectively. A data report is generated based on the first change trend and the second change trend. The APP terminal sends the data report to the target object to complete the walking posture detection reminder.

[0011] Furthermore, the walking posture correction wearable device includes two symmetrical sole devices, three point positions are located in the sole devices, the three point positions constitute the arch area, and the arch area is set to the fixed point layout, and the pressure sensor is installed based on the point positions, wherein the point positions include a large foot pillow, a small foot pillow and a heel.

[0012] Further, calculating the pressure signal difference corresponding to the walking posture correction wearable device includes:

[0013] Calculate the pressure signal difference F corresponding to the sole device at the same collection point based on the first formula r , the first formula is: Wherein, F1 is the intensity value of the pressure signal corresponding to the pressure sensor at the small footrest, F2 is the intensity value of the pressure signal corresponding to the pressure sensor at the large footrest, and || is an absolute value operation symbol;

[0014] The pressure signal differences corresponding to all the sole devices are set as the pressure signal differences corresponding to the walking posture correction wearable device.

[0015] Further, the wireless transmission mode is set based on the following steps:

[0016] All the pressure sensors are set as sub-nodes, multiple transfer devices are set, the signal strength between the sub-nodes and any transfer device is compared, the transfer device with the largest signal strength is set as the transfer node, the sub-nodes are connected to the APP terminal based on the transfer node, a transmission path is generated, and the transmission path is set to the wireless transmission mode.

[0017] Furthermore, transmitting the pressure data to the APP terminal based on the wireless transmission mode includes the following steps:

[0018] Obtain the communication duration between the child node and the transit node, obtain the collection interval of the pressure sensor corresponding to the child node, set a second threshold based on the collection interval, if the communication duration is greater than the second threshold, extract a pressure sensor from the remaining child nodes and set it as a replacement node, transmit the pressure data corresponding to the child node to the replacement node, and then the transit node corresponding to the replacement node transmits all the pressure data contained therein to the APP terminal; otherwise, transmit the pressure data to the APP terminal based on the transmission path corresponding to the child node, wherein the pressure data includes the converted value of the pressure signal and the label information of the pressure sensor.

[0019] Furthermore, after receiving the pressure data, the transfer device sends a receiving signal to the corresponding child node based on the tag information, obtains the time difference between the sending time of the pressure data sent by the child node and the expected time of receiving the receiving signal, and sets the time difference as the communication duration.

[0020] Further, outputting the first change trend and the second change trend comprises the following steps:

[0021] The data set includes the left pressure data set and the right pressure data set, and the timestamp of any pressure data in the data set is obtained respectively. If the number of pressure data greater than 0 contained in any timestamp is equal to the total number of the pressure sensors, all the pressure data contained in any timestamp is removed, and the remaining pressure data in the left pressure data set is set as the standard left data, and the remaining pressure data in the right pressure data set is set as the standard right data;

[0022] Connecting the standard left data and the standard right data in sequence based on the time feature and the label information to generate a corresponding first curve and a second curve;

[0023] Extracting first curves corresponding to two pressure sensors from all first curves based on the tag information and setting them as comparison curves, setting the tag information corresponding to the two comparison curves as comparison tags, obtaining a difference between the two comparison curves at the same timestamp, sequentially connecting all the differences to generate a first difference curve, and intercepting the first difference curve into a plurality of first sub-curves based on the preset time length;

[0024] Inputting all the first sub-curves corresponding to the comparison labels into the analysis model for training and learning, and outputting the prediction analysis results corresponding to the future preset time length, and setting the prediction analysis results as the first change trend;

[0025] Repeat this step to generate the second variation trend corresponding to the second curve based on the analysis model.

[0026] Furthermore, the completion of the walking posture detection reminder includes the following steps:

[0027] Set a third threshold, obtain data points in the first change trend and the second change trend that are greater than the third threshold respectively, aggregate all the data points and the corresponding comparison labels to generate the data report, and complete the walking posture detection reminder based on the data report, wherein the data points include numerical information and time information.

[0028] Furthermore, the point positions corresponding to the pressure sensors of the two comparison tags are obtained based on the fixed-point layout, the individual parameters of the target object are obtained, and the third threshold is set based on the individual parameters and the point positions.

[0029] The present invention also provides a walking posture detection system based on a walking posture correction wearable device, which is used to implement the above-mentioned walking posture detection method based on a walking posture correction wearable device. The system mainly includes:

[0030] The device acquisition module includes a plurality of pressure sensors arranged in a fixed-point layout in the walking posture correction wearable device used by the target object, and the pressure sensors collect pressure signals and transmit the pressure signals to the microprocessor MCU;

[0031] The data transmission module, the microprocessor MCU analyzes and processes the pressure signal based on a preset built-in algorithm, sets a first threshold, converts the pressure signal into pressure data if the pressure signal difference is greater than the first threshold, sets a wireless transmission mode, and transmits the pressure data to the APP terminal based on the wireless transmission mode;

[0032] A data processing module, wherein the APP terminal classifies and marks all the pressure data into a left pressure data set and a right pressure data set based on the label information of the pressure sensor, and stores the data in a database;

[0033] A detection generation module is provided, which constructs an analysis model, and screens all data sets contained in the database based on time features to generate standard left data and standard right data. The analysis model outputs a first change trend and a second change trend corresponding to a preset time length based on the standard left data and the standard right data, respectively. A data report is generated based on the first change trend and the second change trend. The APP terminal sends the data report to the target object to complete the walking posture detection reminder.

[0034] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0035] The present invention firstly arranges the pressure sensors of the walking posture correction wearable device through a fixed-point layout, so as to improve the accuracy of the force analysis on the sole of the target object; then, by setting the wireless transmission mode, the pressure data is transmitted to the APP terminal, and the stability of the data transmission can be achieved through a low-power communication transmission method; finally, by constructing an analysis model, the first change trend and the second change trend corresponding to the target object when using the walking posture correction wearable device are predicted and generated, so as to improve the accuracy and predictability of the data report and realize the timeliness and avoidability of the walking posture detection reminder. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of the steps of a walking posture detection method based on a walking posture correction wearable device of the present invention;

[0037] Figure 2 is a schematic diagram of a wearable device for correcting walking posture in the present invention;

[0038] Figure 3 It is a schematic diagram of the fixed-point layout in the present invention;

[0039] Figure 4 It is a schematic diagram of force analysis based on numerical information in the present invention;

[0040] Figure 5 This is a structural diagram of a walking posture detection system based on a walking posture correction wearable device of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0042] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0043] like Figure 1 As shown, a walking posture detection method based on a walking posture correction wearable device includes:

[0044] S1: The walking posture correction wearable device used by the target object is equipped with multiple pressure sensors based on a fixed-point layout. The pressure sensors collect pressure signals and transmit the pressure signals to the microprocessor MCU.

[0045] Specifically, in this embodiment, the target object refers to the user, including but not limited to teenagers. The walking posture correction wearable device refers to a shoe device provided for teenagers to detect walking posture and cultivate good foot habits. The fixed-point layout refers to the location layout for placing pressure sensors, wherein the pressure sensor is a device that detects and responds to pressure changes, converts the pressure signal into a usable electrical signal, including but not limited to capacitive pressure sensors and strain pressure sensors. The microprocessor MCU (Microcontroller Unit) is a processor composed of an integrated circuit chip that can control and handle major tasks in an electronic system. The pressure signal is the electrical signal collected by the pressure sensor when the pressure changes, and the microprocessor MCU is used to receive and process the electrical signal. Figure 2 As shown, the walking posture correction wearable device is equipped with a microprocessor MCU, a group of pressure sensors (responsible for collecting pressure signals from the test points on the soles of the feet when walking), a battery and a power management chip. Among them, the microprocessor MCU includes a Bluetooth SOC (System on Chip), and the entire module will be installed on the bottom of the shoe or in the insole.

[0046] S2: The microprocessor MCU analyzes and processes the pressure signal based on a preset built-in algorithm, sets a first threshold, and if the pressure signal difference is greater than the first threshold, converts the pressure signal into pressure data, sets a wireless transmission mode, and transmits the pressure data to the APP terminal based on the wireless transmission mode.

[0047] Specifically, in this embodiment, the built-in algorithm is a function formula that is calculated inside the microprocessor MCU, and the pressure signal can be analyzed and processed. The pressure signal difference refers to the difference in signal strength obtained by fixed-point layout between all pressure signals contained in the walking posture correction wearable device, and the specific calculation method is described later. The first threshold is a pre-set value. If the pressure signal difference is greater than the first threshold, it means that each group of pressure signals corresponding to the pressure signal difference is comparable, and the group of pressure signals needs to be converted into pressure data, wherein an analog-to-digital converter can be used to convert the electrical signal corresponding to the pressure signal into a digital value corresponding to the pressure data. The usability of pressure data can be improved and unnecessary pressure data can be reduced. The wireless transmission mode refers to the way and method in which pressure data is transmitted from one device to another through a wireless channel in a wireless communication system. The APP terminal refers to a device that installs and runs an application (Application, APP), which can receive pressure data and analyze and process the pressure data.

[0048] S3: The APP terminal classifies and marks all pressure data into a left pressure data set and a right pressure data set based on the label information of the pressure sensor, and stores them in the database.

[0049] Specifically, in this embodiment, the label information refers to the label of the pressure sensor corresponding to the collected pressure data. Usually, the walking posture correction wearable device is a group of left and right devices, so all pressure data need to be labeled and classified based on the label information to generate corresponding left pressure data sets and right pressure data sets, wherein the left pressure data set refers to the pressure data collected by the left device in the walking posture correction wearable device, and the right pressure data set refers to the pressure data collected by the right device in the walking posture correction wearable device. The database refers to a data management system for storing pressure data.

[0050] S4: Construct an analysis model, filter all data sets contained in the database based on time features, generate standard left data and standard right data, the analysis model outputs the first change trend and the second change trend corresponding to the preset time length based on the standard left data and the standard right data respectively, generate a data report based on the first change trend and the second change trend, the APP terminal sends the data report to the target object, and completes the walking posture detection reminder.

[0051] Specifically, in this embodiment, the analysis model refers to a model used to analyze and process all data sets in the database, and the standard left data and the standard right data are respectively the pressure data retained after all data sets are screened, wherein the data sets include a left pressure data set and a right pressure data set. The standard left data and the standard right data are respectively input into the analysis model, and the analysis model outputs the corresponding first change trend and second change trend, wherein the preset time length refers to a preset time period, for example, 24 hours. The data report refers to the text information generated by combining the first change trend and the second change trend, and the target object is reminded of the potential walking posture correctness coefficient according to the data report. If there is a data reminder of the wrong walking posture in the data report, the APP terminal displays the data reminder and sends it to the target object to complete the walking posture detection reminder.

[0052] As a preferred technical solution of the present invention, a wearable device for correcting walking posture includes two symmetrical sole devices, three point positions are located in the sole devices, the arch area is composed of the three point positions, and the arch area is set to a fixed-point layout, and a pressure sensor is installed based on the point position, wherein the point position includes a large foot pillow, a small foot pillow and a heel.

[0053] Specifically, in this embodiment, the mutually symmetrical sole devices are the left device and the right device in the walking posture correction wearable device. Figure 3 As shown in the figure, the fixed-point layout is described, taking the sole device corresponding to the right device in the walking posture correction wearable device as an example. The three points are the big foot pillow, the small foot pillow and the heel, and pressure sensors are placed at the three points. The arch area is composed of three connecting lines: the medial longitudinal arch, the lateral longitudinal arch and the transverse arch.

[0054] As a preferred technical solution of the present invention, calculating the pressure signal difference corresponding to the walking posture correction wearable device includes:

[0055] Based on the first formula, the pressure signal difference F corresponding to the sole device at the same collection point is calculated r , the first formula is: Among them, F1 is the intensity value of the pressure signal corresponding to the pressure sensor at the small footrest, F2 is the intensity value of the pressure signal corresponding to the pressure sensor at the large footrest, and || is the absolute value operation symbol.

[0056] The pressure signal differences corresponding to all sole devices are set as the pressure signal differences corresponding to the walking posture correction wearable device.

[0057] Specifically, in this embodiment, the pressure signal difference corresponding to the sole device is first calculated by the first formula. The same acquisition point refers to the pressure signal corresponding to the pressure sensor at the same timestamp. The intensity value of the pressure signal refers to the amplitude value of the signal. For example, in the first formula, the intensity value F1 of the pressure signal at the small foot pillow is 2, and the intensity value F2 of the pressure signal at the large foot pillow is 5. Then the pressure signal difference F corresponding to the sole device is r for:

[0058] The pressure signal difference corresponding to the posture correction wearable device includes the pressure signal difference corresponding to all sole devices. For example, the pressure signal difference corresponding to the sole device in the left device is 50%, and the pressure signal difference corresponding to the sole device in the right device is 150%. Then the pressure signal difference corresponding to the posture correction wearable device is 50% and 150%. If any pressure signal difference corresponding to the posture correction wearable device is greater than the first threshold, all pressure signals corresponding to the collection point are converted into pressure data. Otherwise, no conversion is required, which can reduce unnecessary pressure data and improve the usability of pressure data.

[0059] As a preferred technical solution of the present invention, the wireless transmission mode is set based on the following steps:

[0060] Set all pressure sensors as sub-nodes, set up multiple relay devices, compare the signal strength between the sub-nodes and any relay device, set the relay device with the largest signal strength as the relay node, connect the sub-nodes to the APP terminal based on the relay node, generate a transmission path, and set the transmission path to wireless transmission mode.

[0061] Specifically, in this embodiment, the subnode is the transmission starting point in the wireless transmission mode, the transfer node corresponding to the transfer device refers to the transmission connection point of the wireless transmission mode, and the APP terminal is the transmission end point in the wireless transmission mode. The transfer device refers to a device used to expand the signal coverage and enhance the signal strength in network communication. The signal strength refers to the power level of the wireless signal. Each subnode first selects a transfer device as a transfer node, and then forms a transmission path from the subnode → transfer node → APP terminal. The stability of data transmission can be improved to avoid channel interference when the same transfer device is used to transmit data.

[0062] As a preferred technical solution of the present invention, transmitting pressure data to the APP terminal based on the wireless transmission mode includes the following steps:

[0063] Obtain the communication duration between the child node and the transit node, obtain the collection interval of the pressure sensor corresponding to the child node, set a second threshold based on the collection interval, if the communication duration is greater than the second threshold, extract a pressure sensor from the remaining child nodes and set it as a replacement node, transmit the pressure data corresponding to the child node to the replacement node, and then the transit node corresponding to the replacement node transmits all the contained pressure data to the APP terminal, otherwise, transmit the pressure data to the APP terminal based on the transmission path corresponding to the child node, wherein the pressure data includes the converted value of the pressure signal and the label information of the pressure sensor.

[0064] Specifically, in this embodiment, the communication duration refers to the transmission time, and the collection interval refers to the time interval between the current collection point and the previous collection point in the pressure sensor. Since the collection interval may change, the second threshold is also set after the pressure data of the current sub-node is received. If the communication duration is greater than the preset second threshold, it means that there is an obstruction or signal interference between the sub-node and the corresponding transfer node. Therefore, a pressure sensor corresponding to a sub-node can be extracted from the remaining sub-nodes as a replacement node, that is, there can also be a data transmission function between each sub-node. The sub-node is first transmitted to the replacement node, and then transmitted by the transmission path corresponding to the replacement node. This step can improve the stability of the wireless transmission mode.

[0065] As a preferred technical solution of the present invention, after receiving the pressure data, the transfer device sends a receiving signal to the corresponding child node based on the tag information, obtains the time difference between the sending time of the pressure data sent by the child node and the expected time of receiving the receiving signal, and sets the time difference as the communication duration.

[0066] Specifically, in this embodiment, after receiving the pressure data, the transfer device sends a receiving signal to the corresponding child node, and the communication duration of the child node is set by the time difference between the sending time and the receiving time.

[0067] As a preferred technical solution of the present invention, outputting the first change trend and the second change trend includes the following steps:

[0068] The data set includes a left pressure data set and a right pressure data set. The timestamp of any pressure data in the data set is obtained respectively. If the number of pressure data greater than 0 contained in any timestamp is equal to the total number of pressure sensors, all pressure data contained in any timestamp is eliminated, and the remaining pressure data in the left pressure data set is set as the standard left data, and the remaining pressure data in the right pressure data set is set as the standard right data.

[0069] Based on the time feature and the label information, the standard left data and the standard right data are sequentially connected to generate the corresponding first curve and second curve.

[0070] Based on the label information, the first curves corresponding to the two pressure sensors are extracted from all the first curves and set as comparison curves. The label information corresponding to the two comparison curves is set as the comparison label. The difference between the two comparison curves at the same timestamp is obtained, all the differences are connected in sequence to generate a first difference curve, and the first difference curve is intercepted into multiple first sub-curves based on a preset time length.

[0071] All first sub-curves corresponding to the comparison labels are input into the analysis model for training and learning, and the prediction analysis results corresponding to the future preset time length are output, and the prediction analysis results are set as the first change trend.

[0072] Repeat this step to generate a second variation trend corresponding to the second curve based on the analysis model.

[0073] Specifically, in this embodiment, the data set includes pressure data corresponding to all pressure sensors, and the timestamp refers to the time point when the pressure sensor collects pressure data. If the number of pressure data greater than 0 at the same timestamp is equal to the total number of pressure sensors, it means that the target object is not walking. For example, the total number of pressure sensors is 6, and at timestamp t1, there are 6 pressure data greater than 0, which means that the target object may be standing at timestamp t1. Therefore, all pressure data corresponding to any timestamp are deleted, thereby generating standard left data and standard right data.

[0074] The time feature refers to the information corresponding to the timestamp of the pressure data. The standard left data and the standard right data corresponding to the same label information are sequentially connected by the time feature to generate the first curve and the second curve. That is, the first curve is the curve corresponding to the standard left data, and the second curve is the curve corresponding to the standard right data. Therefore, in the standard left data, any label information has a corresponding first curve, and in the standard right data, any label information has a corresponding second curve.

[0075] In this embodiment, the two extracted pressure sensors are pressure sensors at the big footrest and the small footrest, respectively. The extraction can be performed through the tag information, and the first curves corresponding to the two pressure sensors are set as the comparison curve. The first difference curve is used to describe the fluctuation change of the difference between the two comparison curves. The first difference curve can be cut according to the preset time length to generate multiple continuous first sub-curves.

[0076] The analysis model refers to an LSTM (Long Short-Term Memory) neural network model, which can be trained and learned through all the first sub-curves input, adjust the model parameters, and output the prediction analysis results corresponding to the future step length with a preset time length as the step length. Among them, the prediction analysis results are also fluctuating change curves. Therefore, the prediction analysis results are set as the first change trend.

[0077] Through the same steps, all second curves are analyzed, and the corresponding second variation trends are generated by the analysis model.

[0078] As a preferred technical solution of the present invention, completing the walking posture detection reminder includes the following steps:

[0079] Set a third threshold, obtain data points in the first change trend and the second change trend that are greater than the third threshold respectively, summarize all data points and corresponding comparison labels to generate a data report, and complete walking posture detection reminder based on the data report, wherein the data points include numerical information and time information.

[0080] Specifically, in the present embodiment, the walking posture detection reminder includes a reminder of the point position of incorrect walking posture and a reminder of the time of incorrect walking posture. If there are data points greater than the third threshold value in the first change trend and the second change trend, it means that the target object will still have incorrect walking behavior at the data point in the future. Therefore, all data points and corresponding comparison labels are summarized to generate a data report. For example, there is a data point (Tx, Fy) in the second change trend, where T is a future time point, i.e., time information, and F is the difference in pressure data corresponding to the two comparison labels, i.e., numerical information, and x and y are specific numerical values, respectively. Then, the generated data report is: It is predicted that the difference in pressure data of the right foot of the target object at the future time point Tx is Fy, and attention should be paid to correcting the walking posture of the left foot. Fy can be used to determine the size of the difference between the two comparison labels, and to determine the stress condition of the arch of the foot. Figure 4 As shown, during normal walking, the stress conditions of the medial and lateral longitudinal arches are similar, and the arch of the foot is in normal condition. The occurrence of acquired high arches or low arches (flat feet) is usually due to the fact that the stress on the lateral or medial longitudinal arch is greater than that on the other side during walking. This bad habit of using the foot is formed over a long period of time. The position of the point with greater stress in the two comparison labels can be determined by the positive and negative values ​​of Fy.

[0081] As a preferred technical solution of the present invention, the point positions corresponding to the pressure sensors of the two comparison tags are obtained based on the fixed-point layout, the individual parameters of the target object are obtained, and the third threshold is set based on the individual parameters and the point position.

[0082] Specifically, in this embodiment, individual parameters refer to data information such as weight, height and shoe size of the target object. The point positions of the two comparison labels can be obtained by the fixed-point layout, and the third threshold can be set by the individual parameters and the point positions. For example, the third threshold will decrease with the increase of the weight value in the individual parameters, because target objects with heavier weight will have greater force on the soles of their feet when walking. By reducing the third threshold, it can be more accurately determined whether the pressure data corresponding to the two comparison labels meet the force conditions of the correct walking posture.

[0083] like Figure 5 As shown, the present invention also provides a walking posture detection system based on a walking posture correction wearable device, which is used to implement the above-mentioned walking posture detection method based on a walking posture correction wearable device, and the system mainly includes:

[0084] The device acquisition module includes a plurality of pressure sensors arranged based on a fixed-point layout in the walking posture correction wearable device used by the target object. The pressure sensors collect pressure signals and transmit the pressure signals to the microprocessor MCU.

[0085] The data transmission module, the microprocessor MCU analyzes and processes the pressure signal based on a preset built-in algorithm, sets a first threshold, and if the pressure signal difference is greater than the first threshold, converts the pressure signal into pressure data, sets the wireless transmission mode, and transmits the pressure data to the APP terminal based on the wireless transmission mode.

[0086] Data processing module, the APP terminal classifies and marks all pressure data into left pressure data set and right pressure data set based on the label information of the pressure sensor, and stores them in the database.

[0087] The detection generation module builds an analysis model, screens all data sets contained in the database based on time features, generates standard left data and standard right data, and the analysis model outputs the first change trend and the second change trend corresponding to the preset time length based on the standard left data and the standard right data respectively, generates a data report based on the first change trend and the second change trend, and the APP terminal sends the data report to the target object to complete the walking posture detection reminder.

[0088] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0089] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The above-mentioned program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0090] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0092] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A walking posture detection method based on a walking posture correction wearable device, characterized in that: The method comprises the following steps: A plurality of pressure sensors are arranged in a fixed-point layout in the walking posture correction wearable device used by the target object, and the pressure sensors collect pressure signals and transmit the pressure signals to a microprocessor MCU; The microprocessor MCU analyzes and processes the pressure signal based on a preset built-in algorithm, sets a first threshold, converts the pressure signal into pressure data if the pressure signal difference is greater than the first threshold, sets a wireless transmission mode, and transmits the pressure data to an APP terminal based on the wireless transmission mode; The APP terminal classifies and marks all the pressure data into a left pressure data set and a right pressure data set based on the label information of the pressure sensor, and stores them in a database; An analysis model is constructed, and all data sets contained in the database are screened based on time features to generate standard left data and standard right data. The analysis model outputs a first change trend and a second change trend corresponding to a preset time length based on the standard left data and the standard right data, respectively. A data report is generated based on the first change trend and the second change trend. The APP terminal sends the data report to the target object to complete the walking posture detection reminder.

2. The method according to claim 1, characterized in that The walking posture correction wearable device includes two symmetrical sole devices, three point positions are located in the sole devices, the three point positions constitute the arch area, and the arch area is set to the fixed point layout, and the pressure sensor is installed based on the point positions, wherein the point positions include a large foot pillow, a small foot pillow and a heel.

3. The method according to claim 2, characterized in that Calculating the pressure signal difference corresponding to the walking posture correction wearable device includes: Calculate the pressure signal difference F corresponding to the sole device at the same collection point based on the first formula r , the first formula is: Wherein, F1 is the intensity value of the pressure signal corresponding to the pressure sensor at the small footrest, F2 is the intensity value of the pressure signal corresponding to the pressure sensor at the large footrest, and || is an absolute value operation symbol; The pressure signal differences corresponding to all the sole devices are set as the pressure signal differences corresponding to the walking posture correction wearable device.

4. The method according to claim 1, characterized in that: The wireless transmission mode is set based on the following steps: All the pressure sensors are set as sub-nodes, multiple transfer devices are set, the signal strength between the sub-nodes and any transfer device is compared, the transfer device with the largest signal strength is set as the transfer node, the sub-nodes are connected to the APP terminal based on the transfer node, a transmission path is generated, and the transmission path is set to the wireless transmission mode.

5. The method according to claim 4, characterized in that The transmitting the pressure data to the APP terminal based on the wireless transmission mode comprises the following steps: Obtain the communication duration between the child node and the transit node, obtain the collection interval of the pressure sensor corresponding to the child node, set a second threshold based on the collection interval, if the communication duration is greater than the second threshold, extract a pressure sensor from the remaining child nodes and set it as a replacement node, transmit the pressure data corresponding to the child node to the replacement node, and then the transit node corresponding to the replacement node transmits all the pressure data contained therein to the APP terminal; otherwise, transmit the pressure data to the APP terminal based on the transmission path corresponding to the child node, wherein the pressure data includes the converted value of the pressure signal and the label information of the pressure sensor.

6. The method according to claim 5, characterized in that After receiving the pressure data, the transfer device sends a receiving signal to the corresponding child node based on the tag information, obtains the time difference between the sending time of the pressure data by the child node and the receiving time of the receiving signal, and sets the time difference as the communication duration.

7. The method according to claim 1, characterized in that Outputting the first change trend and the second change trend comprises the following steps: The data set includes the left pressure data set and the right pressure data set, and the timestamp of any pressure data in the data set is obtained respectively. If the number of pressure data greater than 0 contained in any timestamp is equal to the total number of the pressure sensors, all the pressure data contained in any timestamp is removed, and the remaining pressure data in the left pressure data set is set as the standard left data, and the remaining pressure data in the right pressure data set is set as the standard right data; Connecting the standard left data and the standard right data in sequence based on the time feature and the label information to generate a corresponding first curve and a second curve; Extracting first curves corresponding to two pressure sensors from all first curves based on the tag information and setting them as comparison curves, setting the tag information corresponding to the two comparison curves as comparison tags, obtaining a difference between the two comparison curves at the same timestamp, sequentially connecting all the differences to generate a first difference curve, and intercepting the first difference curve into a plurality of first sub-curves based on the preset time length; Inputting all the first sub-curves corresponding to the comparison labels into the analysis model for training and learning, and outputting the prediction analysis results corresponding to the future preset time length, and setting the prediction analysis results as the first change trend; Repeat this step to generate the second variation trend corresponding to the second curve based on the analysis model.

8. The method according to claim 7, characterized in that The completion of the walking posture detection reminder comprises the following steps: Set a third threshold, obtain data points in the first change trend and the second change trend that are greater than the third threshold respectively, aggregate all the data points and the corresponding comparison labels to generate the data report, and complete the walking posture detection reminder based on the data report, wherein the data points include numerical information and time information.

9. The method according to claim 8, characterized in that Based on the fixed-point layout, the point positions corresponding to the pressure sensors of the two comparison tags are obtained, the individual parameters of the target object are obtained, and the third threshold is set based on the individual parameters and the point positions.

10. A walking posture detection system based on a walking posture correction wearable device, used to implement the method according to any one of claims 1 to 9, characterized in that: The system includes the following modules: The device acquisition module includes a plurality of pressure sensors arranged in a fixed-point layout in the walking posture correction wearable device used by the target object. The pressure sensors collect pressure signals and transmit the pressure signals to the microprocessor MCU. The data transmission module, the microprocessor MCU analyzes and processes the pressure signal based on a preset built-in algorithm, sets a first threshold, converts the pressure signal into pressure data if the pressure signal difference is greater than the first threshold, sets a wireless transmission mode, and transmits the pressure data to the APP terminal based on the wireless transmission mode; A data processing module, wherein the APP terminal classifies and marks all the pressure data into a left pressure data set and a right pressure data set based on the label information of the pressure sensor, and stores the data in a database; A detection generation module is provided, which constructs an analysis model, and screens all data sets contained in the database based on time features to generate standard left data and standard right data. The analysis model outputs a first change trend and a second change trend corresponding to a preset time length based on the standard left data and the standard right data, respectively. A data report is generated based on the first change trend and the second change trend. The APP terminal sends the data report to the target object to complete the walking posture detection reminder.

Images