Gait information processing method

Abstract

The present invention provides a gait information processing method, which can be applied to the fields of inertial sensing application technologies and intelligent medical technologies for Parkinson's disease. The method comprises: in response to receiving confirmation information used for indicating that it is confirmed that a target subject has taken a target medicine, detecting a motion state of the target subject; when the motion state of the target subject is a walking state, acquiring walking information of straight walking of the target subject; in response to detecting that the target subject has changed from the straight walking to another type of walking, the acquisition frequency of the walking information of the straight walking of the target subject is greater than or equal to a predetermined acquisition frequency threshold, and the single-day acquisition cycle number of the walking information of the straight walking of the target subject is greater than or equal to a predetermined acquisition cycle threshold, using an objective function to process the walking information of the straight walking of the target subject to obtain gait parameters; and sending the gait parameters to a mobile communication terminal, so that the mobile communication terminal performs anomaly detection on the gait parameters.

Description

A gait information processing method

[0001] The present invention relates to the field of inertial sensing application technology and Parkinson's disease intelligent medical technology, and in particular to a gait information processing method. Background Art

[0002] Parkinson's disease (PD) is the second most common chronic neurodegenerative disease after Alzheimer's disease, with bradykinesia, tremor, rigidity and abnormal gait as its main characteristics.

[0003] With the development of medical technology, electronic devices can be used to collect walking information of Parkinson's patients to provide technical support for medical treatment.

[0004] In the process of realizing the concept of the present invention, the inventors discovered that there is a problem of excessive consumption of electronic equipment resources due to a large amount of invalid information collected. Summary of the Invention

[0005] In view of the above problems, the present invention provides a gait information processing method.

[0006] According to a first aspect of the present invention, a gait information processing method is provided, which is applied to a wearable device, comprising: in response to receiving confirmation information used to characterize that a target subject has confirmed that a target drug has been used, detecting a motion state of the target subject; when the motion state of the target subject is a walking state, collecting walking information of the target subject walking in a straight line; in response to detecting that the target subject changes from walking in a straight line to another type of walking, the number of collections of the walking information of the target subject walking in a straight line is greater than or equal to a predetermined collection number threshold, and the number of daily collection cycles of the walking information of the target subject walking in a straight line is greater than or equal to a predetermined collection cycle threshold, processing the walking information of the target subject walking in a straight line using an objective function to obtain gait parameters; and sending the gait parameters to a mobile communication terminal so that the mobile communication terminal can perform abnormality detection on the gait parameters.

[0007] According to an embodiment of the present invention, the walking information includes a first segment of walking information, a second segment of walking information, and a third segment of walking information collected in sequence according to the collection time sequence; the above-mentioned gait information processing method also includes: determining first walking straight condition information of the target object based on the first segment of walking information and the third segment of walking information; in response to the first walking straight condition information indicating that the target object changes from straight walking to turning, determining second walking straight condition information of the target object based on the second segment of walking information; and determining that the target object changes from straight walking to other types of walking based on the second walking straight condition information.

[0008] According to an embodiment of the present invention, the first segment of walking information includes the first walking position coordinates, and the third segment of walking information includes the second walking position coordinates; based on the first segment of walking information and the third segment of walking information, determining the first walking straight condition information of the target object includes: inputting the first walking position coordinates into the straight line function to be fitted, and fitting to obtain a first fitting straight line, wherein the first fitting straight line includes the first predicted position coordinates corresponding to the first walking position coordinates, and the first square sum of errors between the first predicted position coordinates and the first walking position coordinates is minimized; inputting the second walking position coordinates into the straight line function to be fitted, and fitting to obtain a second fitting straight line, wherein the second fitting straight line includes the second predicted position coordinates corresponding to the second walking position coordinates, and the second square sum of errors between the second predicted position coordinates and the second walking position coordinates is minimized; when the first square sum of errors and the second square sum of errors meet a predetermined error condition, determining the first walking straight condition information of the target object based on the first slope of the first fitting straight line and the second slope of the second fitting straight line.

[0009] According to an embodiment of the present invention, the second segment of walking information includes Q yaw angle values, and the Q yaw angle values ​​are arranged in the walking order of the target object, and Q is a positive integer greater than 1; in response to the first walking straight condition information characterizing that the target object changes from walking straight to turning, the second walking straight condition information of the target object is determined according to the second segment of walking information, including: determining the difference between the qth yaw angle value and the q+1th yaw angle value in the Q yaw angle values ​​to obtain Q-1 differences, where q is a positive integer less than 1; in response to the sum of the Q-1 differences being greater than or equal to a predetermined difference threshold, generating the second walking straight condition information characterizing the target object; in response to the sum of the Q-1 differences being less than the predetermined difference threshold, generating the second walking straight condition information characterizing that the target object is walking straight.

[0010] According to an embodiment of the present invention, gait parameters include the duration of the foot swing phase, the duration of the foot support phase, step height, step width, step length, the angular velocity variation coefficient of the pitch angle during the foot landing phase, the angular velocity variation coefficient of the pitch angle during the foot extension phase, the step height variation coefficient, the foot swing width variation coefficient and the step length variation coefficient.

[0011] According to a second aspect of the present invention, a gait information processing method is provided, which is applied to a mobile communication terminal, comprising: receiving gait parameters from a wearable device, wherein the gait parameters are obtained by processing the walking information of the target object's straight walking using an objective function in response to detecting that a target object has changed from straight-line walking to other types of walking, the number of collection times of the target object's walking information of straight-line walking is greater than or equal to a predetermined collection time threshold, and the number of single-day collection cycles of the target object's walking information of straight-line walking is greater than or equal to a predetermined collection cycle threshold, the walking information of the target object's straight-line walking is collected when the target object's motion state is a walking state, and the target object's motion state is detected in response to receiving confirmation information for characterizing that the target object has confirmed that it has used a target drug; and performing abnormality detection on the gait parameters to obtain an abnormality detection result.

[0012] According to an embodiment of the present invention, gait parameters are subjected to abnormality detection to obtain abnormality detection results, including: in response to the number of collection days corresponding to the collected walking information being equal to a predetermined day threshold, the gait parameters are processed using a first gait parameter abnormality detection algorithm to obtain a first abnormality detection result corresponding to a change pattern of the gait parameters; and the gait parameters are processed using a second gait parameter abnormality detection algorithm to obtain a second abnormality detection result corresponding to a deviation of the gait parameters.

[0013] According to an embodiment of the present invention, there are M groups of gait parameters, and the M groups of gait parameters correspond to M medication periods of the target subject in a single day. The M groups of gait parameters are arranged in sequence according to the walking time, and M is a positive integer greater than 1; the gait parameters are processed using the first gait parameter anomaly detection algorithm to obtain a first anomaly detection result corresponding to the change law of the gait parameters, including: according to the m-1th group of gait parameters and the mth group of gait parameters in the M groups of gait parameters, the m-1th group of first-order forward difference values ​​is calculated, where m is greater than 1 and a positive integer less than or equal to M; calculating the m-2th group of second-order forward difference values ​​based on the m-2th group of first-order forward difference values ​​and the m-1th group of first-order forward difference values ​​in the M-1 groups of first-order forward difference values; in response to the M-2th group of second-order forward difference values ​​being greater than a predetermined difference value threshold, generating a first abnormality detection result characterizing that there is no abnormal condition in the gait parameters; in response to the M-2th group of second-order forward difference values ​​being less than or equal to the predetermined difference value threshold, generating a first abnormality detection result characterizing that there is an abnormal condition in the gait parameters.

[0014] According to an embodiment of the present invention, the mth group of gait parameters includes K gait parameters corresponding to K detection cycles; the gait parameters are processed using a second gait parameter anomaly detection algorithm to obtain a first anomaly detection result corresponding to the deviation of the gait parameters, including: determining statistical values ​​of the K gait parameters; determining K differences between the statistical values ​​and the K gait parameters; in response to the K differences being less than or equal to a predetermined difference threshold, generating a second anomaly detection result characterizing that there is no abnormal condition in the gait parameters; in response to the K differences being greater than a predetermined difference threshold, generating a second anomaly detection result characterizing that there is an abnormal condition in the gait parameters.

[0015] According to an embodiment of the present invention, the above-mentioned gait information processing method also includes: in response to the first abnormality detection result and the second abnormality detection result both indicating that the gait parameters do not have an abnormal condition, sending the gait parameters to the server so that the server stores the gait parameters; in response to at least one of the first abnormality detection result and the second abnormality detection result indicating that the gait parameters have an abnormal condition, sending an information acquisition request to the wearable device to obtain the walking information corresponding to the gait parameters with the abnormal condition cached by the wearable device, and sending the walking information corresponding to the gait parameters with the abnormal condition to the server so that the server stores the walking information corresponding to the gait parameters with the abnormal condition.

[0016] The gait information processing method provided by the present invention adaptively determines whether to execute the next step based on the actual condition of the target object, based on confirmation information, the target object's motion state, the target object's walking condition, the number of walking information collection times, and the number of walking information collection cycles per day. This avoids wasting the wearable device's power resources and extends the wearable device's standby time. Furthermore, because unnecessary operations are avoided, the wearable device's computing power can be fully utilized to process the walking information required, avoiding the wearable device from processing invalid walking information and reducing resource consumption.

[0017] Furthermore, since only gait parameters are sent to the mobile communication terminal, the amount of information sent to the mobile communication terminal is reduced, the information processing efficiency of the mobile communication terminal can be improved, and the resources of the mobile communication terminal can be saved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above contents and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0019] FIG1 shows an application scenario diagram of a gait information processing method according to an embodiment of the present invention;

[0020] FIG2 shows a flow chart of a method for processing gait information according to an embodiment of the present invention;

[0021] FIG3 shows a schematic diagram of a portable insole according to an embodiment of the present invention;

[0022] FIG4 shows a state monitoring framework diagram based on an SVM model according to an embodiment of the present invention;

[0023] FIG5 is a schematic diagram showing a straight trajectory and a turning trajectory according to an embodiment of the present invention;

[0024] FIG6 shows a schematic diagram of turn detection according to an embodiment of the present invention;

[0025] FIG7 shows a flow chart of a second method for generating straight-ahead walking condition information according to an embodiment of the present invention;

[0026] FIG8 shows a flowchart of a method for processing gait information according to another embodiment of the present invention;

[0027] FIG9 is a schematic diagram showing a normal change curve of gait parameters after medication according to an embodiment of the present invention;

[0028] FIG10 is a schematic diagram showing a method for processing gait information according to another embodiment of the present invention;

[0029] FIG11 shows a structural block diagram of a wearable device according to an embodiment of the present invention;

[0030] FIG12 shows a structural block diagram of a mobile communication terminal according to an embodiment of the present invention;

[0031] FIG13 shows a block diagram of an electronic device suitable for implementing a gait information processing method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concept of the present invention.

[0033] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the presence of the features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0034] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0035] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0036] In the technical solution of the present invention, the user information involved (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0037] According to an embodiment of the present invention, a health management system applied to Parkinson's disease may include a mobile communication terminal, a wearable device, and a server.

[0038] The inventors have found that for elderly patients suffering from neurodegenerative diseases, it is difficult to flexibly use the application of mobile communication terminals to assist medical staff in collecting disease information. Therefore, the collected information is difficult to meet the needs of medical staff. Among them, neurodegenerative diseases may include Parkinson's disease, etc. For example, for medication management, it is necessary to collect walking information of patients who exercise multiple times after taking the medicine. In addition, because medical staff need to analyze the changes in the patient's gait over time after taking the medicine, the quality requirements for the collected walking information are high. Parkinson's disease can be divided into an "on period" and an "off period" to judge the patient's gait condition and other information during the period when the drug is effective based on the "on period" and "off period". Medical staff not only need to analyze the collected information every day, but also need to analyze the gradual changes in the medication date.

[0039] For wearable devices, such as health smart watches, the collection mode needs to be manually adjusted by the user. Since the collection mode is a fixed paradigm set at the factory, it is difficult for health smart watches to automatically identify which data is qualified and which to upload based on the needs of the disease and the quality of the exercise information. In addition, for home management of Parkinson's disease, wearable devices need to be on standby for a long time and upload the collected information regularly. Based on this, since the uploaded information includes unqualified information, the limited power and communication traffic of the wearable device are consumed. For the information sent to the mobile communication terminal, the unqualified and invalid information will waste the storage space of the mobile communication terminal, and will also bring a lot of noise to the doctor's manual analysis, resulting in a waste of resources.

[0040] In view of this, an embodiment of the present invention provides a gait information processing method, which is applied to a wearable device, comprising: in response to receiving confirmation information used to characterize that the target object has confirmed that the target drug has been used, detecting the motion state of the target object. When the motion state of the target object is a walking state, collecting walking information of the target object walking in a straight line. In response to detecting that the target object changes from walking in a straight line to other types of walking, the number of collections of the walking information of the target object walking in a straight line is greater than or equal to a predetermined collection number threshold, and the number of single-day collection cycles of the walking information of the target object walking in a straight line is greater than or equal to a predetermined collection cycle threshold, processing the walking information of the target object walking in a straight line using an objective function to obtain gait parameters. Sending the gait parameters to a mobile communication terminal so that the mobile communication terminal can perform abnormality detection on the gait parameters.

[0041] FIG1 shows an application scenario diagram of a gait information processing method according to an embodiment of the present invention.

[0042] As shown in Figure 1, an application scenario 100 according to this embodiment may include a wearable device 101, a mobile communication terminal 102, and a server 103. A network is a medium for providing a communication link between the wearable device 101, the mobile communication terminal 102, and the server 103. The network may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0043] A user may use a mobile communication terminal 102 to interact with the server 103 via a network to receive or send messages, etc. Various communication client applications may be installed on the mobile communication terminal 102, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0044] The wearable device can be an insole-type device built with a foot IMU (Inertial Measurement Unit) that uses a 6-axis sensor for the arch position of the foot. Among them, 3 axes of the 6-axis sensor are used to measure acceleration, and the other 3 axes of the 6-axis sensor are used to measure angular velocity.

[0045] The mobile communication terminal 102 may be any electronic device having a display screen and supporting web browsing, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like.

[0046] Server 103 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using mobile communication terminal 102. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the mobile communication terminal.

[0047] It should be noted that the gait information processing method provided in the embodiments of the present invention can generally be executed by the wearable device 101 or the mobile communication terminal 102. It should be understood that the number of wearable devices 101, mobile communication terminals 102, and servers 103 in Figure 1 is only a guide. Any number of wearable devices 101, mobile communication terminals 102, and servers 103 can be used as required.

[0048] The following will describe in detail the gait information processing method of an embodiment of the present invention based on the scenario described in FIG1 through FIG2 to FIG10.

[0049] FIG2 shows a flowchart of a method for processing gait information according to an embodiment of the present invention.

[0050] As shown in FIG2 , the gait information processing method of this embodiment can be applied to a wearable device. The method includes operations S210 to S240.

[0051] In operation S210 , in response to receiving confirmation information indicating that the target object has confirmed the use of the target medicine, a motion state of the target object is detected.

[0052] In operation S220 , when the motion state of the target object is a walking state, walking information of the target object walking straight is collected.

[0053] In operation S230, in response to detecting that the target object changes from straight-line walking to other types of walking, the number of times the walking information of the target object's straight-line walking is collected is greater than or equal to a predetermined collection number threshold, and the number of single-day collection cycles of the walking information of the target object's straight-line walking is greater than or equal to a predetermined collection cycle threshold, the walking information of the target object's straight-line walking is processed using the objective function to obtain gait parameters.

[0054] In operation S240, the gait parameters are transmitted to the mobile communication terminal so that the mobile communication terminal performs abnormality detection on the gait parameters.

[0055] According to an embodiment of the present invention, the target subject may be a subject using a wearable device to collect walking information. The target subject may suffer from Parkinson's disease, etc. The disease targeted by the target drug may be Parkinson's disease, etc.

[0056] According to an embodiment of the present invention, the motion state of the target object can be used to represent the target object's ongoing activity. The motion state of the target object can include a sitting state, a lying state, or a walking state.

[0057] According to an embodiment of the present invention, walking information may include acceleration and angular velocity collected by the IMU during walking, but is not limited thereto. Walking information may also include the position of the target object's feet, and the time when various parts of the feet touch the ground, etc.

[0058] According to an embodiment of the present invention, the target object may take a total of I steps in a single walking detection, where I is a positive integer greater than 3.

[0059] According to an embodiment of the present invention, gait parameters include the duration of the foot swing phase, the duration of the foot support phase, step height, step width, step length, the angular velocity variation coefficient of the pitch angle during the foot landing phase, the angular velocity variation coefficient of the pitch angle during the foot extension phase, the step height variation coefficient, the foot swing width variation coefficient and the step length variation coefficient.

[0060] The objective function may include a function for calculating the duration of a unilateral foot swing period, a function for calculating the duration of a unilateral foot support period, a function for calculating the height of a unilateral footstep, a function for calculating the width of a unilateral footstep, a function for calculating the length of a unilateral footstep, a function for calculating the angular velocity variation coefficient of the pitch angle of a unilateral foot landing period, a function for calculating the angular velocity variation coefficient of the pitch angle of a unilateral foot extension period, a function for calculating the coefficient of variation of the unilateral footstep height, a function for calculating the coefficient of variation of the unilateral foot swing width, and a function for calculating the coefficient of variation of the unilateral footstep length.

[0061] According to an embodiment of the present invention, the unilateral foot swing phase duration calculation function may be as follows:

[0062] (1);

[0063] Among them, swD iIndicates the duration of the unilateral foot swing phase. i0 Indicates the time when the toe leaves the ground at the i-th step in the walking information. i+1 HS Indicates the time when the heel of the i+1th step in the walking information is touched down.

[0064] According to an embodiment of the present invention, the unilateral foot support period duration calculation function may be as follows:

[0065] (2);

[0066] Among them, stD i Indicates the duration of the unilateral foot support period. i HS Indicates the time when the heel of the i-th step in the walking information. i 0 Indicates the time when the toe leaves the ground in the i-th step in the walking information.

[0067] According to an embodiment of the present invention, a single-side footstep height calculation function may be as follows:

[0068] (3);

[0069] Among them, sH i Indicates that one side of the foot is high. z,i max Indicates the highest vertical position of the foot in the i-th step in the walking information. z,i min It represents the lowest vertical position of the foot in the i-th step in the above walking information.

[0070] According to an embodiment of the present invention, a single-side step width calculation function may be as follows:

[0071] (4);

[0072] Among them, sW i Indicates the width of one side of the foot. y,i max Indicates the farthest horizontal position of the foot in the i-th step in the above walking information. y,i min It represents the most recent horizontal position of the foot in the i-th step in the above walking information.

[0073] According to an embodiment of the present invention, the unilateral step length calculation function may be as follows:

[0074] (5);

[0075] Among them, sL i Indicates the length of one side's footstep. x,i max Indicates the farthest position of the foot in the longitudinal direction (front and back) in the i-th step in the walking information above. x,i min Indicates the most recent vertical position of the foot in the i-th step in the walking information.

[0076] According to an embodiment of the present invention, a calculation function for the coefficient of variation of the angular velocity of the pitch angle during the unilateral foot landing period may be as follows:

[0077] (6);

[0078] (7);

[0079] (8);

[0080] Among them, hsPv CV Indicates the coefficient of variation of the angular velocity of the pitch angle during the landing phase of a single foot. hsPv i represents the angular velocity of the pitch angle of one foot during the loading phase (LP) of the i-th gait cycle in the aforementioned walking information. Count represents the total number of gait cycles in the aforementioned walking information. μ(hsPv) represents the mean angular velocity of the pitch angle during the loading phase. σ(hsPv) represents the standard deviation of the angular velocity of the pitch angle during the loading phase.

[0081] According to an embodiment of the present invention, the calculation function of the angular velocity variation coefficient of the unilateral pitch angle during the extension phase can be as follows:

[0082] (9);

[0083] (10);

[0084] (11);

[0085] Among them, toPv CV The coefficient of variation of the angular velocity of the pitch angle during the extension phase of the unilateral pedaling. toPv i Indicates the angular velocity of the unilateral foot pitch angle during the extension phase of the i-th gait cycle in the walking information above. μ(toPv i ) represents the mean angular velocity of the pitch angle during the unilateral extension phase. i ) represents the standard deviation of the angular velocity of the pitch angle during the unilateral extension phase. Count represents the total number of gait cycles in the walking information.

[0086] According to an embodiment of the present invention, the unilateral footstep height variation coefficient calculation function may be as follows:

[0087] (12);

[0088] (13);

[0089] (14);

[0090] Among them, sH CV represents the coefficient of variation of unilateral footstep height. σ(sH) represents the standard deviation of unilateral footstep height. μ(sH) is the mean value of unilateral footstep height. i Indicates the height of the i-th step in the above walking information. Count indicates the total number of steps in the above walking information.

[0091] According to an embodiment of the present invention, the calculation function of the coefficient of variation of the unilateral foot swing width can be as follows:

[0092] (15);

[0093] (16);

[0094] (17);

[0095] Among them, sW CV sW represents the coefficient of variation of the unilateral foot swing width. σ(sW) represents the standard deviation of the unilateral foot swing width. μ(sW) represents the mean value of the unilateral foot swing width. sW i Indicates the foot swing width of the i-th step in the walking information. Count indicates the total number of steps in the walking information.

[0096] According to an embodiment of the present invention, the unilateral step length variation coefficient calculation function can be as follows:

[0097] (18);

[0098] (19);

[0099] (20);

[0100] Among them, sL CV sL represents the coefficient of variation of unilateral step length. irepresents the stride length of the i-th step in the walking information. σ(sL) represents the standard deviation of the unilateral step length. μ(sL) represents the average unilateral step length. Count represents the total number of steps taken in the walking information. σ(sL) represents the standard deviation of the unilateral step length. μ(sL) represents the average unilateral step length.

[0101] FIG3 shows a schematic diagram of a portable insole according to an embodiment of the present invention.

[0102] Figure 3 shows a wearable device in the form of an insole worn by the target subject. A first microsensor 321 and a second microsensor 322, built using a six-axis inertial measurement unit (IMU) sensor for the arch of the foot, can be embedded in the first and second insoles 311, 312 to minimize impact on the target subject's daily movements and allow for long-term wear. The first microsensor 321 for the left foot can be embedded in the first insole 311 of the left foot, while the second microsensor 322 for the right foot can be embedded in the second insole 312 of the right foot.

[0103] The acquisition module in the insole can be used to collect walking information such as three-axis acceleration and three-axis angular velocity output by the plantar IMU in real time.

[0104] The preprocessing module in the insole can be used to perform missing value processing, outlier detection, and denoising on the collected three-axis acceleration and three-axis angular velocity to obtain processed acceleration and processed angular velocity.

[0105] The quality discrimination module in the insole can be used to determine in real time whether the target object's motion state is walking, ensuring that the collected walking information is cached only in the walking state and the gait parameters are calculated for the cached walking information, so as to improve the utilization efficiency of the storage resources and computing resources of the wearable device.

[0106] FIG4 shows a state monitoring framework diagram based on an SVM model according to an embodiment of the present invention.

[0107] The quality determination module can also be used to pass the processed acceleration and angular velocity data through a trained SVM (Support Vector Machine) algorithm 403, as shown in Figure 4, to determine whether the target object is currently walking. Six-axis data 401, consisting of processed acceleration and angular velocity data collected multiple times by the six-axis sensor, can be processed using a PCA (Principal Component Analysis) algorithm 402 to obtain reduced-dimensionality feature information. The trained SVM 403 is then used to process this reduced-dimensionality feature information to determine the target object's current motion state. The target object's current motion state can include walking type 404 or other type 405.

[0108] FIG5 is a schematic diagram showing a straight trajectory and a turning trajectory according to an embodiment of the present invention.

[0109] According to an embodiment of the present invention, the target subject exhibits the motion pattern shown in Figure 5 during free walking. This motion pattern consists of two parts: straight walking and turning. Since the most critical part of characterizing the target subject's gait is the walking information of the straight walking portion, a walking information collection paradigm combining straight walking and turning is adopted, and the turning gait action can be used as the end mark of walking information collection.

[0110] As shown in Figures 4 and 5, PCA algorithm 402 and SVM algorithm 403 can be used to determine whether the target object is currently moving straight or turning. PCA algorithm 402 and SVM algorithm 403 can be used to determine whether the target object is currently moving straight or turning only when the number of straight steps taken by the target object equals a predetermined acquisition threshold.

[0111] According to an embodiment of the present invention, when it is detected that the motion state of the target object is not a walking state, a prompt instruction may be sent to the mobile communication terminal so that the mobile communication terminal reminds the target object to perform gait detection.

[0112] When it is detected that the motion state of the target object is a walking state, the collected walking information may be stored, and the collected walking information may be processed using a peak detection algorithm to calculate the number of collection times.

[0113] According to an embodiment of the present invention, the target subject needs to take medication multiple times a day. The target subject needs to perform multiple walking tests each time he takes medication. The target subject needs to collect walking information multiple times within the detection cycle of each walking test. The number of collection cycles per day can be the number of walking tests performed after the target subject takes medication in a single day. The predetermined collection cycle threshold can be the same as the number of times the target subject needs to take medication in a single day. The number of times the walking information of the target subject walking straight can be collected can be the number of steps the target subject takes straight as collected by the wearable device. The number of collections can be the same as the number of steps the target subject walks. For example, the wearable device will collect walking information once each time the target subject walks. The predetermined collection number threshold can be the number of times the walking information of the target subject needs to be collected for each walking test, which is pre-set by medical staff based on the condition of the target subject.

[0114] Based on this, both the predetermined collection period threshold and the predetermined collection number threshold can be set by the doctor according to the medication needs of the target subject.

[0115] According to an embodiment of the present invention, other types of walking of the target object may include the target object turning, etc.

[0116] According to an embodiment of the present invention, when the target object turns and the number of straight steps of the target object collected before the turn is greater than or equal to a predetermined collection number threshold, it can be determined that the target object has completed a single detection within a single day.

[0117] If the target subject turns and the number of straight-line steps collected before the turn is less than a predetermined collection threshold, it can be determined that a single detection within a single day has not been completed. Based on this, the wearable device can reset the step count and clear the step information cached by the wearable device. When the target subject is detected walking straight, the wearable device can re-collect the target subject's straight-line step information until the number of straight-line steps collected before the target subject turns is greater than or equal to the predetermined collection threshold.

[0118] If the target object fails to walk straight ahead continuously before turning within the detection period until the number of straight-ahead steps is greater than or equal to the predetermined collection number threshold, it is determined that the walking detection has failed.

[0119] According to an embodiment of the present invention, when the number of collection cycles of the target object in a single day is greater than or equal to a predetermined collection cycle threshold, it can be determined that the target object has completed all walking detections in a single day.

[0120] When the number of collection cycles of the target object in a single day is less than the predetermined collection cycle threshold, it can be determined that the target object has not completed all walking detections in a single day.

[0121] Based on this, when the number of walking information collection is greater than or equal to the predetermined collection number threshold, and it is determined that the quality of the collected walking information is sufficient to support subsequent data calculation and analysis, the information collection during the gait detection period is stopped to reduce the power consumption of the wearable device, and the turning and subsequent information is deleted, and only the walking information before the turn is retained to improve the effective utilization of storage space.

[0122] According to an embodiment of the present invention, when the target object completes the last walking detection in a single day, it can be detected that the target object has changed from straight-line walking to other types of walking, the number of times the walking information of the target object's straight-line walking is collected is greater than or equal to a predetermined collection number threshold, and the number of single-day collection cycles of the walking information of the target object's straight-line walking is greater than or equal to a predetermined collection cycle threshold.

[0123] According to an embodiment of the present invention, when the target object completes the last detection task within a single day and the number of single-day collection cycles of the target object's walking information of walking in a straight line is less than a predetermined collection cycle threshold, it can be determined that the target object's walking detection on that day has failed, and all walking information collected within that day can be deleted to avoid invalid walking information consuming resources of the wearable device.

[0124] According to an embodiment of the present invention, by adaptively determining whether to execute the next operation based on the actual condition of the target object based on confirmation information, the target object's motion state, the target object's walking condition, the number of walking information collection times, and the number of walking information collection cycles per day, the wearable device avoids wasting power resources and prolongs its standby time. Furthermore, because the wearable device avoids unnecessary operations, the computing power of the wearable device can be fully utilized to process the walking information required, avoiding the wearable device from processing invalid walking information and reducing resource consumption of the wearable device.

[0125] Furthermore, since only gait parameters are sent to the mobile communication terminal, the amount of information sent to the mobile communication terminal is reduced, the information processing efficiency of the mobile communication terminal can be improved, and the resources of the mobile communication terminal can be saved.

[0126] According to an embodiment of the present invention, the walking information includes first, second, and third segments of walking information collected sequentially in chronological order. The gait information processing method further includes: determining first straight-line walking condition information of the target object based on the first and third segments of walking information. In response to the first straight-line walking condition information indicating that the target object has changed from straight-line walking to turning, determining second straight-line walking condition information of the target object based on the second segment of walking information. Based on the second straight-line walking condition information, determining that the target object has changed from straight-line walking to other types of walking.

[0127] According to an embodiment of the present invention, the first straight-walking condition information may include first straight-walking condition information characterizing that the target object turns and first straight-walking condition information characterizing that the target object walks straight.

[0128] According to an embodiment of the present invention, the second straight-walking condition information may include second straight-walking condition information characterizing that the target object turns and second straight-walking condition information characterizing that the target object walks straight.

[0129] According to an embodiment of the present invention, the first walking segment, the second walking segment, and the third walking segment can be obtained by evenly dividing all the steps taken by the target object in a single detection. For example, the total number of steps taken by the target object in a single detection can be 30 steps. The first walking segment can be the first 10 steps taken by the target object in the 30 steps. The second walking segment can be the middle 10 steps taken by the target object in the 30 steps. The third walking segment can be the last 10 steps taken by the target object in the 30 steps. The first walking segment information may include walking information for each step in the first walking segment. The second walking segment information may include walking information for each step in the second walking segment. The third walking segment information may include walking information for each step in the third walking segment.

[0130] According to an embodiment of the present invention, the first straight-walking condition information obtained from the first and second walking information segments can be used to determine the overall walking trend of the target subject. Based on this, if the first straight-walking condition information indicates that the target subject is walking straight, the operation of determining the second straight-walking condition information can be omitted, thereby saving power consumed by the wearable device.

[0131] According to an embodiment of the present invention, if the second straight-walking condition information indicates that the target object is walking straight, it can be determined that the target object has not changed from walking straight to another type of walking. If the second straight-walking condition information indicates that the target object is turning, it can be determined that the target object has changed from walking straight to another type of walking.

[0132] If the first straight-line status information indicates that the target object has transitioned from straight-line walking to turning, the second straight-line status information can be determined based on the second segment of walking that is located between the first and third segments of the target object's walking. Because the second segment of walking is located between the first and third segments, it can better reflect the target object's turning tendency in detail. Based on this, the target object's straight-line status can be determined from the details based on the second segment of walking information, thereby improving the accuracy of determining the target object's straight-line status.

[0133] According to an embodiment of the present invention, the first segment of walking information includes first walking position coordinates, and the third segment of walking information includes second walking position coordinates. Determining first straight-line walking status information of a target object based on the first and third segments of walking information includes: inputting the first walking position coordinates into a to-be-fitted straight line function to obtain a first fitting straight line, wherein the first fitting straight line includes first predicted position coordinates corresponding to the first walking position coordinates, and the sum of squared first errors between the first predicted position coordinates and the first walking position coordinates is minimized. Inputting the second walking position coordinates into the to-be-fitted straight line function to obtain a second fitting straight line, wherein the second fitting straight line includes second predicted position coordinates corresponding to the second walking position coordinates, and the sum of squared second errors between the second predicted position coordinates and the second walking position coordinates is minimized. If the sum of squared first errors and the sum of squared second errors meet a predetermined error condition, determining the first straight-line walking status information of the target object based on a first slope of the first fitting line and a second slope of the second fitting line.

[0134] According to an embodiment of the present invention, the first walking position coordinate and the second walking position coordinate may both be coordinates in an earth coordinate system. The first walking position coordinate and the second walking position coordinate may both be coordinates in the form of (x, y). The linear function to be fitted may be y = kx + c, where k is the slope of the line and c is the intercept of the line.

[0135] According to an embodiment of the present disclosure, the first predicted position coordinates may be coordinates obtained by fitting the first fitting line, and the second predicted position coordinates may be coordinates obtained by fitting the second fitting line.

[0136] The first walking position coordinate corresponding to the first predicted position coordinate may be the first walking position coordinate that is closest to the first predicted position coordinate.

[0137] The second walking position coordinate corresponding to the second predicted position coordinate may be the first walking position coordinate that is closest to the second predicted position coordinate.

[0138] According to an embodiment of the present invention, the first sum of squared errors may be determined based on the square of the distance between the first predicted position coordinate and the first walking position coordinate. The second sum of squared errors may be determined based on the square of the distance between the second predicted position coordinate and the second walking position coordinate.

[0139] According to an embodiment of the present invention, when the first sum of squared errors and the second sum of squared errors are both less than a predetermined error threshold, it can be determined that the target object is walking in a straight line in the first and third walking segments, and it can be determined that the first sum of squared errors and the second sum of squared errors meet the predetermined error condition.

[0140] According to an embodiment of the present invention, when at least one of the first sum of squared errors and the second sum of squared errors is greater than or equal to a predetermined error threshold, it can be determined that the target object has turned in at least one of the first and third walking segments, and it can be determined that the first sum of squared errors and the second sum of squared errors do not satisfy the predetermined error condition.

[0141] FIG6 shows a schematic diagram of turn detection according to an embodiment of the present invention.

[0142] According to an embodiment of the present invention, the predetermined collection number threshold may be 30, but is not limited thereto. As shown in FIG6 , after the target object's step count reaches 30, the target object's overall walking condition, whether it is straight walking or turning, may be determined based on the walking information of the first 30 steps.

[0143] Two sets of data can be obtained: the foot landing position data from the 30th step to the 21st step before the current position and the foot landing position data from the 10th step to the 1st step before the current position. The 30th step to the 21st step before the current position can correspond to the first walking segment, while the 10th step to the 1st step before the current position corresponds to the third walking segment.

[0144] Based on this, the first and third steps can each have ten walking position coordinates. The first step position coordinate of the first step can be expressed as L 30 ~L 21 The coordinates of the second step position in the third step can be expressed as L 10 ~L1. Among them, the coordinates of the i-th walking position are L i Represented by two-dimensional coordinates (xi,yi).

[0145] According to an embodiment of the present invention, the least square method can be used to perform linear fitting on the first walking position coordinate and the second walking position coordinate. 30 ~L 21 Taking the position point data as an example, the slope-intercept equation of the straight line function to be fitted is: y=kx+c, where k is the slope of the line and c is the intercept of the line.

[0146] Based on this, the function of the first fitting straight line can be set as:

[0147] (twenty one);

[0148] in, is the slope of the first fitted straight line. is the intercept of the first fitted straight line. is x on the first fitting line i The corresponding value. The matrix form of the first fitting straight line can be shown as follows:

[0149] (twenty two);

[0150] in, It can be a real data matrix, wherein the real data can include the first walking position coordinates. It can be the parameter matrix to be determined. Can be a fitting data matrix.

[0151] The objective function can be set to the sum of squares of the errors between the first predicted position coordinates and the first walking position coordinates, that is, the first sum of squares of errors mentioned above. Based on this, the calculation formula for the first sum of squares of errors is:

[0152] (twenty three);

[0153] Wherein, J1 is the first error sum of squares. is the first predicted position coordinate. y is the first walking position coordinate.

[0154] Substituting the first fitted straight line in matrix form into the calculation formula of the first sum of squared errors, we can obtain:

[0155] (twenty four);

[0156] Where J1 is the first square error sum, and y is the first walking position coordinate. It can be a real data matrix, wherein the real data can include the first walking position coordinates. It can be the parameter matrix to be determined.

[0157] To find the value of θ when the first error square sum J1 is minimized, we can find the partial derivative of the first error square sum J1 with respect to θ and set it to 0, that is:

[0158] (25);

[0159] Where J1 is the first square error sum, and y is the first walking position coordinate. It can be a real data matrix, wherein the real data can include the first walking position coordinates. It can be the parameter matrix to be determined.

[0160] The solution is as follows:

[0161] (26);

[0162] Among them, y is the coordinate of the first step position. It can be a real data matrix, wherein the real data can include the first walking position coordinates. It can be the parameter matrix to be determined.

[0163] Based on this, L can be fitted 30 ~L 21 The first fitting straight line , and then, we can find the minimum sum of squares of errors , i.e. the first square error sum. The first square error sum can be compared with the predetermined error threshold J determined by experiment. threshold Compare, in In the case of , it can be determined that the target object walks in a straight line in the first step. Similarly, L 10 The second fitting straight line of ~L1 Minimum sum of squared errors , which is the second square error sum, and the same method can be used to determine whether the target object is walking straight in the third segment. In the case that both the first and third segments are walking in a straight line, the angle α between the first fitting line and the second fitting line can be calculated based on the slope of the first fitting line and the slope of the second fitting line. For example, the direction vector of the first fitting line can be The direction vector of the second fitting straight line can be The angle α can be calculated using the following formula:

[0164] (27);

[0165] When the angle α is greater than 45°, it can be determined that the overall walking trend of the target object is a turning trend, and first straight-walking condition information representing the turning of the target object is generated.

[0166] When the angle α is less than or equal to 45°, it can be determined that the overall walking trend of the target object is a straight-walking trend, and first straight-walking condition information representing that the target object is walking straight-walking can be generated.

[0167] According to an embodiment of the present invention, an accurate first fitting line can be obtained by minimizing the sum of squares of the first error between the first predicted position coordinates and the first walking position coordinates, and an accurate second fitting line can be obtained by minimizing the sum of squares of the second error between the second predicted position coordinates and the second walking position coordinates. Based on this, accurate information about the first straight-line walking condition can be determined based on the first fitting line and the second fitting line.

[0168] Moreover, the first straight-walking condition information is determined only when the first square error sum and the second square error sum meet a predetermined error condition, thereby avoiding the consumption of power of the wearable device and improving the battery life of the wearable device.

[0169] According to an embodiment of the present invention, the second segment of walking information includes Q yaw angle values, where the Q yaw angle values ​​are arranged in the order of the target object's walking, and Q is a positive integer greater than 1. In response to the first straight-line walking condition information indicating that the target object changes from walking straight to turning, second straight-line walking condition information of the target object is determined based on the second segment of walking information, including: determining the difference between the qth yaw angle value and the q+1th yaw angle value in the Q yaw angle values ​​to obtain Q-1 differences, where q is a positive integer less than Q. In response to the sum of the Q-1 differences being greater than or equal to a predetermined difference threshold, the second straight-line walking condition information indicating that the target object is walking straight is generated. In response to the sum of the Q-1 differences being less than the predetermined difference threshold, the second straight-line walking condition information indicating that the target object is walking straight is generated.

[0170] According to an embodiment of the present invention, the second segment of the target object's walking may include Q steps, where Q may be less than 1. The second segment of the target object's walking information may include Q pieces of walking information corresponding to the Q steps. Each piece of walking information may include a yaw angle value. Thus, the Q pieces of walking information may include Q yaw angle values.

[0171] According to an embodiment of the present invention, the yaw angle difference between two adjacent steps can be calculated. , from which we can get the Q-1 difference. Among them, β i is the i-th yaw angle value. q+1 is the q+1th yaw angle value.

[0172] The Q-1 differences can be accumulated as shown in the following formula:

[0173] (28);

[0174] in, represents the sum of the above Q-1 differences, represents the difference between the qth yaw angle value and the q+1th yaw angle value mentioned above.

[0175] exist In the case of the target object turning during the second walking process, it is determined that the target object has turned, and the second walking straight condition information representing the target object turning is generated.

[0176] exist In the case of the target object walking straight in the second walking segment, it is determined that the target object is walking straight, and second straight walking condition information representing the target object walking straight is generated. 45° may be a predetermined difference threshold. It should be noted that the predetermined difference threshold can be set as needed and is not limited to 45°.

[0177] According to an embodiment of the present invention, the straight-walking condition of the target object in the second walking section is determined by calculating the difference in yaw angle values ​​one by one according to the yaw angle values. The straight-walking condition of the target object is determined in detail, thereby improving the accuracy of determining the straight-walking condition of the target object.

[0178] According to an embodiment of the present invention, when the second straight-walking condition information represents a turn of the target object, the third straight-walking condition information of the target object is determined based on the qth step among the Q steps, the first fitting straight line and the second fitting straight line.

[0179] The third straight-walking condition information may include third straight-walking condition information indicating that the target object changes from straight-walking to turning and third straight-walking condition information indicating that the target object does not change from straight-walking to turning.

[0180] If the third straight walking condition information indicates that the target object has turned, it is determined that the target object has changed from straight walking to other types of walking. If the third straight walking condition information indicates that the target object is walking straight, it is determined that the target object has not changed from straight walking to other types of walking.

[0181] According to an embodiment of the present invention, the qth step in the Q steps may include a plurality of qth position coordinates. The q position coordinates may be input into a line function to be fitted, and a fitting line for the qth step may be obtained by fitting.

[0182] A first angle between the first fitting line and the qth step fitting line can be determined, and a second angle between the second fitting line and the qth step fitting line can be determined. The opening of the first angle can be oriented in the direction of the third step of the target object, and the opening of the second angle can be oriented in the direction of the first step of the target object. The first angle can be calculated based on the slope of the first fitting line and the slope of the qth step fitting line. The second angle can be calculated based on the slope of the first fitting line and the slope of the qth step fitting line.

[0183] The qth step may be determined as a target step when the sum of the angle value of the first angle and the angle value of the second angle is greater than or equal to a predetermined angle threshold.

[0184] When the sum of the angle value of the first angle and the angle value of the second angle is less than a predetermined angle threshold, the qth step may be determined to be a non-target step.

[0185] When the ratio of the target walking steps to the Q walking steps is greater than or equal to a predetermined ratio threshold, third walking straight condition information representing the turning of the target object may be generated.

[0186] When the proportion of the target walking steps to the Q walking steps is less than a predetermined proportion threshold, third straight-walking condition information representing that the target object is walking straight can be generated.

[0187] The predetermined angle threshold and the predetermined ratio threshold can be set according to needs, and the present invention does not limit them here.

[0188] Based on this, by using the first angle and the second angle, the straight-walking condition of the target object can be determined for each step in the second walking segment from a more detailed aspect relative to the straight-walking condition information of the second walking segment, thereby improving the accuracy of determining the walking condition of the target object.

[0189] FIG. 7 shows a flowchart of a second method for generating straight-ahead walking condition information according to an embodiment of the present invention.

[0190] As shown in FIG. 7 , the second method for generating straight walking condition information of this embodiment includes operations S701 to S709 .

[0191] In operation S701 , walking information of a target object walking straight ahead is collected.

[0192] In operation S702, is the number of times the walking information of the target object walking straight greater than a predetermined collection number threshold? If so, operations S703 and S704 are executed; if not, the process returns to executing operation S701.

[0193] In operation S703, the first walking position coordinates are input into a line function to be fitted, and a first fitting line is obtained by fitting.

[0194] In operation S704, the second walking position coordinates are input into the to-be-fitted straight line function, and a second fitting straight line is obtained by fitting.

[0195] In operation S705 , when the first square error sum and the second square error sum meet a predetermined error condition, first straight-walking condition information of the target object is determined according to the first slope of the first fitting line and the second slope of the second fitting line.

[0196] In operation S706, in response to the first straight-walking condition information indicating that the target object changes from straight-walking to turning, a difference between an i-th yaw angle value and an i+1-th yaw angle value among the I yaw angle values ​​is determined to obtain an I-1 difference.

[0197] In operation S707, is the I-1 difference greater than or equal to the predetermined difference threshold? If not, then execute operation S708; if yes, then execute operation S709;

[0198] In operation S708 , second straight-walking condition information representing that the target object is walking straight is generated.

[0199] In operation S709 , second walking straight condition information representing that the target object turns is generated.

[0200] FIG8 shows a flowchart of a method for processing gait information according to another embodiment of the present invention.

[0201] As shown in Figure 8, the gait information processing method of this embodiment can be applied to a mobile communication terminal. The method includes operations S810 to S820.

[0202] In operation S810, gait parameters are received from the wearable device, wherein the gait parameters are obtained by processing the walking information of the target object's straight-line walking using an objective function in response to the wearable device detecting that the target object has changed from straight-line walking to other types of walking, the number of collection times of the target object's walking information of the straight-line walking is greater than or equal to a predetermined collection time threshold, and the number of single-day collection cycles of the target object's walking information of the straight-line walking is greater than or equal to a predetermined collection cycle threshold, the walking information of the target object's straight-line walking is collected when the target object's motion state is a walking state, and the target object's motion state is detected in response to receiving confirmation information for characterizing that the target object has confirmed that it has used the target drug.

[0203] In operation S820, abnormality detection is performed on the gait parameters to obtain an abnormality detection result.

[0204] According to an embodiment of the present invention, a doctor may pre-set a fixed walking detection time period, which may be 0 hours, 1 hour, 2 hours, 3 hours, or 4 hours apart.

[0205] For example, at a target time before the detection period, the mobile communication terminal can remind the target subject to take medicine. For example, at 5 minutes before the detection period, the mobile communication terminal can remind the target subject by ringing a bell.

[0206] For example, when the detection period has expired and no instruction for indicating that the medication reminder is effective has been received, the mobile communication terminal may prompt the target object at intervals of a first predetermined time. For example, when the detection period has expired but no confirmation information for indicating that the medication reminder is effective has been received, the mobile communication terminal may ring once every 5 minutes. For example, when the detection period has expired and no instruction for the target object to cancel the ringing has been received, it is determined that no instruction for indicating that the medication reminder is effective has been received. For example, the instruction for indicating that the medication reminder is effective may be an instruction for canceling the ringing. When an instruction for indicating that the target object to cancel the ringing has been received, it can be determined that this reminder is effective.

[0207] For example, if a command indicating that a medication reminder has taken effect is received and no confirmation information indicating that the target subject has taken the target medication is received within a second predetermined time period, the target subject may be prompted to confirm medication use. For example, the second predetermined time period may be 2 minutes, but is not limited thereto. For example, the target subject may be reminded to confirm medication use by ringing a bell.

[0208] According to an embodiment of the present invention, by adaptively determining whether to execute the next operation based on the actual condition of the target object based on confirmation information, the target object's motion state, the target object's walking condition, the number of walking information collection times, and the number of walking information collection cycles per day, the wearable device avoids wasting power resources and prolongs its standby time. Furthermore, by avoiding unnecessary operations on the wearable device, the wearable device's computing power can be fully utilized to process the walking information required.

[0209] Furthermore, since the gait parameters are received from the wearable device, the amount of information received by the mobile communication terminal is reduced, the information processing efficiency of the mobile communication terminal can be improved, and the resources of the mobile communication terminal can be saved.

[0210] According to an embodiment of the present invention, performing abnormality detection on gait parameters to obtain an abnormality detection result includes: in response to the number of collection days corresponding to the collected walking information being equal to a predetermined day threshold, processing the gait parameters using a first gait parameter abnormality detection algorithm to obtain a first abnormality detection result corresponding to a variation pattern of the gait parameters. Processing the gait parameters using a second gait parameter abnormality detection algorithm to obtain a second abnormality detection result corresponding to a deviation of the gait parameters.

[0211] According to an embodiment of the present invention, the variation pattern of the gait parameter may be the variation pattern of the gait parameter between M medication periods within a single day. The deviation of the gait parameter may be the deviation between the gait parameters of K detection cycles within a single medication period.

[0212] According to an embodiment of the present invention, the mobile communication terminal can determine the number of days for which the walking information collected was collected based on the number of received gait parameters. If the number of days for which the walking information was collected is less than a predetermined threshold, it can be determined that the target subject has not collected gait parameters that meet the requirements, and the target subject can continue to be reminded to take medication and undergo testing every day.

[0213] According to an embodiment of the present invention, if the number of days of collection equals a predetermined threshold, it can be determined that the target subject has collected gait parameters that meet the requirements. Thus, the gait parameters can be processed using a first gait parameter anomaly detection algorithm to obtain a first anomaly detection result corresponding to the variation pattern of the gait parameters. Furthermore, the gait parameters can be processed using a second gait parameter anomaly detection algorithm to obtain a second anomaly detection result corresponding to the deviation of the gait parameters.

[0214] According to an embodiment of the present invention, by using the first gait parameter abnormality detection algorithm and the second gait parameter abnormality detection algorithm respectively, a first abnormality detection result corresponding to the changing law of the gait parameters and a second abnormality detection result corresponding to the deviation of the gait parameters can be obtained, thereby realizing the determination of the abnormal conditions of the gait parameters from multiple aspects, thereby improving the accuracy of determining the gait parameters with abnormal conditions.

[0215] According to an embodiment of the present invention, there are M groups of gait parameters, and the M groups of gait parameters correspond to M medication periods of the target subject in a single day. The M groups of gait parameters are arranged in sequence according to the walking time, and M is a positive integer greater than 1. The gait parameters are processed using the first gait parameter abnormality detection algorithm to obtain a first abnormality detection result corresponding to the change pattern of the gait parameters, including: according to the m-1th group of gait parameters and the m-th group of gait parameters in the M groups of gait parameters, the m-1th group of first-order forward difference values ​​is calculated, wherein m is a positive integer greater than 1 and less than or equal to M. According to the m-2th group of first-order forward difference values ​​and the m-1th group of first-order forward difference values ​​in the M-1 group of first-order forward difference values, the m-2th group of second-order forward difference values ​​is calculated. In response to the M-2th group of second-order forward difference values ​​being greater than a predetermined difference value threshold, a first abnormality detection result is generated, indicating that there is no abnormal condition in the gait parameters. In response to the M‑2 groups of second-order forward difference values ​​being less than or equal to a predetermined difference value threshold, a first abnormality detection result is generated, indicating that an abnormal condition exists in the gait parameter.

[0216] According to embodiments of the present invention, clinical observations of Parkinson's disease patients after medication use indicate that the drug's gait-regulating effect gradually increases within two hours after administration, reaches a maximum around two hours, and then gradually weakens. Therefore, there are two types of changing trends in the corresponding gait parameters. These changing trends can be divided into Type 1 and Type 2 based on the onset of the target drug.

[0217] FIG9 is a schematic diagram showing a normal change curve of gait parameters after medication according to an embodiment of the present invention.

[0218] As shown in FIG9 , the horizontal axis represents the time after taking the medicine, the vertical axis represents the numerical value of the gait parameter, and P0 to P4 represent the gait parameters at different times ti.

[0219] For type 1, it is a concave function f1(t), and the first-order forward difference value is , where i takes values ​​of 0, 1, 2, and 3, and the second-order forward difference value is , where i takes values ​​of 0, 1, and 2. If for all gait parameters, , that is, if the second-order forward difference value of the M‑2 group is greater than the predetermined difference value threshold, it means that the definition of the concave upper function is met. Therefore, it can be determined that the effect of the drug on the gait of the target object conforms to the normal law. Otherwise, it is determined that the gait parameters of the target object are abnormal.

[0220] For type 2, the convex function f2(t), the first-order forward difference is , where i takes values ​​of 0, 1, 2, and 3. The second-order forward difference is , where i takes values ​​of 0, 1, and 2. If for all gait data, there are If the M-2 second-order forward difference values ​​are greater than a predetermined difference threshold, the function conforms to the definition of an upward convex function, confirming that the drug's effect on the target subject's gait is normal. Otherwise, the target subject's gait parameters are abnormal. Here, 0 can be the predetermined difference threshold, which can be pre-set by a physician.

[0221] Based on this, through the above-mentioned first gait parameter anomaly detection algorithm, a first anomaly detection result can be generated according to a total of 20 gait parameters of the two feet of the target object.

[0222] According to an embodiment of the present invention, by successively calculating the first-order forward difference values ​​between the gait parameters, and then successively calculating the second-order forward difference values ​​based on the first-order forward difference values, the change pattern of the gait parameters of the target object in the M medication periods can be accurately determined, and an accurate first abnormality detection result can be obtained.

[0223] According to an embodiment of the present invention, the mth group of gait parameters includes K gait parameters corresponding to K detection cycles. Processing the gait parameters using a second gait parameter anomaly detection algorithm to obtain a first anomaly detection result corresponding to a deviation in the gait parameters includes: determining a statistical value of the K gait parameters; determining K differences between the statistical value and the K gait parameters; and generating a second anomaly detection result indicating that no anomaly exists in the gait parameters in response to the K differences being less than or equal to a predetermined difference threshold. Generating a second anomaly detection result indicating that an anomaly exists in the gait parameters in response to the K differences being greater than the predetermined difference threshold.

[0224] According to an embodiment of the present invention, the statistical values ​​of the K gait parameters may include an average value of the K gait parameters, etc.

[0225] According to an embodiment of the present invention, the gait parameter calculated based on the gait information of the j-th walking detection on the i-th day can be expressed as Pi,j. The average value of the gait parameter of the j-th walking detection within a detection period can be calculated as , the calculation formula is as follows:

[0226] (29);

[0227] Here, K may be the number of detection cycles within a single medication period, and K may be 7.

[0228] Based on this, the degree of deviation of the gait parameters from the mean value for the jth time each day can be calculated as , that is, the above difference , as shown below:

[0229] (30);

[0230] Among them, P i,j The gait parameter may be calculated based on the gait information of the j-th walking detection on the i-th day. It can be the average value of the gait parameters of the jth walking test within a test cycle. K can be the number of test cycles within a single medication period.

[0231] When the difference is greater than the predetermined threshold ,Right now In the case of an abnormality, a second abnormality detection result is generated to indicate that the gait parameters have an abnormal condition.

[0232] When Aij is less than or equal to the predetermined difference threshold v, ie, a second abnormality detection result is generated indicating that an abnormal condition exists in the gait parameter.

[0233] According to an embodiment of the present invention, the fluctuation condition of the gait parameters within a single detection cycle can be accurately determined based on the statistical values ​​of the K gait parameters and the differences between the K gait parameters.

[0234] According to an embodiment of the present invention, the gait information processing method further includes: in response to both the first abnormality detection result and the second abnormality detection result indicating that the gait parameter does not have an abnormal condition, sending the gait parameter to a server so that the server can store the gait parameter. In response to at least one of the first abnormality detection result and the second abnormality detection result indicating that the gait parameter has an abnormal condition, sending an information acquisition request to the wearable device to obtain walking information corresponding to the gait parameter with the abnormal condition cached by the wearable device, and sending the walking information corresponding to the gait parameter with the abnormal condition to the server so that the server can store the walking information corresponding to the gait parameter with the abnormal condition.

[0235] According to an embodiment of the present invention, the wearable device can transmit the cached walking information with abnormal conditions to a body area gateway, which is a mobile communication terminal.

[0236] After receiving the walking information with abnormal conditions, the mobile communication terminal may send the walking information with abnormal conditions to the server.

[0237] The server can receive and store abnormal walking information uploaded by mobile communication terminals. The server can then send this abnormal walking information to a doctor's terminal, which can then calculate and analyze the abnormal walking information to facilitate personalized adjustments, such as medication dosage and timing. This can prevent resource consumption for non-abnormal walking information and improve information processing efficiency.

[0238] According to an embodiment of the present invention, wearable devices, mobile communication terminals and servers are adaptively and automatically identified and managed according to the data service requirements of the home medication management system for Parkinson's disease, accurately improving the user experience of the target object, the doctor's judgment accuracy and the system's data service performance.

[0239] FIG10 shows a schematic diagram of a gait information processing method according to another embodiment of the present invention.

[0240] As shown in Figure 10, the gait information processing method of this embodiment includes operations S1001 to S1021. Operations S1001 to S1006, operations S1017 to S1019, and operation S1021 are all performed by a mobile communication terminal. Operations S1007 to S1016 and operation S1020 are all performed by a mobile device.

[0241] In operation S1001 , it is determined that it is time to take medication.

[0242] In operation S1002 , a medication reminder is given to the target subject by ringing a bell.

[0243] In operation S1003 , an instruction indicating that a medication reminder is effective is received.

[0244] In operation S1004 , it is determined that a detection time has arrived.

[0245] In operation S1005 , the target object is prompted to perform gait detection by ringing a bell.

[0246] In operation S1006, a walking information collection instruction is sent to the wearable device.

[0247] In operation S1007 , walking information of the target object walking straight is collected.

[0248] In operation S1008 , the number of steps is calculated.

[0249] In operation S1009 , does the target object turn? If yes, then operation S1010 is executed; if no, then the process returns to operation S1008 .

[0250] In operation S1010 , is the acquisition number greater than or equal to a predetermined acquisition number threshold? If so, operation S1013 is executed; if not, operation S1011 is executed.

[0251] In operation S1011, the walking information collected this time is cleared.

[0252] In operation S1012, the number of steps is reset.

[0253] In operation S1013 , is the number of collection cycles per day greater than or equal to a predetermined collection cycle threshold? If so, operation S1015 is executed; if not, operation S1014 is executed.

[0254] In operation S1014, all walking information collected on that day is deleted.

[0255] In operation S1015 , the walking information is processed using an objective function to obtain gait parameters.

[0256] In operation S1016, the gait parameter is transmitted to the mobile communication terminal.

[0257] In operation S1017 , the gait parameters are processed using the first gait parameter anomaly detection algorithm to obtain a first anomaly detection result.

[0258] In operation S1018, the gait parameters are processed using a second gait parameter abnormality detection algorithm to obtain a second abnormality detection result.

[0259] In operation S1019, in response to at least one of the first abnormality detection result and the second abnormality detection result indicating that an abnormal condition exists in the gait parameter, an information acquisition request is sent to the wearable device.

[0260] In operation S1020, in response to receiving the information acquisition request, walking information with an abnormal condition is transmitted to the mobile communication terminal.

[0261] In operation S1021, walking information corresponding to the gait parameters with the abnormal condition is sent to the server.

[0262] Based on the above gait information processing method, the present invention further provides a wearable device, which will be described in detail below with reference to FIG11 .

[0263] FIG11 shows a structural block diagram of a wearable device according to an embodiment of the present invention.

[0264] As shown in FIG. 11 , the wearable device 1100 of this embodiment includes a first detection module 1110 , a collection module 1120 , a processing module 1130 , and a sending module 1140 .

[0265] The first detection module 1110 is configured to detect the motion state of the target object in response to receiving confirmation information indicating that the target object has used the target drug. In one embodiment, the first detection module 1110 may be configured to perform the operation S210 described above, which will not be described in detail herein.

[0266] The acquisition module 1120 is used to acquire walking information of the target object walking straight when the target object's motion state is walking. In one embodiment, the acquisition module 1120 can be used to perform the operation S220 described above, which will not be repeated here.

[0267] Based on this, by using the first angle and the second angle, the straight-walking condition of the target object can be determined for each step in the second walking segment from a more detailed aspect relative to the straight-walking condition information of the second walking segment, thereby improving the accuracy of determining the walking condition of the target object.

[0268] The processing module 1130 is configured to, in response to detecting that the target subject has transitioned from straight-ahead walking to another type of walking, the number of times walking information of the target subject's straight-ahead walking has been collected is greater than or equal to a predetermined collection number threshold, and the number of daily collection cycles of walking information of the target subject's straight-ahead walking is greater than or equal to a predetermined collection cycle threshold, process the walking information of the target subject's straight-ahead walking using an objective function to obtain gait parameters. In one embodiment, the processing module 1130 can be configured to perform operation S230 described above, which will not be described in detail here. The sending module 1140 is configured to send the gait parameters to a mobile communication terminal so that the mobile communication terminal can perform abnormality detection on the gait parameters. In one embodiment, the sending module 1140 can be configured to perform operation S240 described above, which will not be described in detail here.

[0269] According to an embodiment of the present invention, the wearable device further includes a first determination module, a second determination module, a first generation module, and a second generation module. The first determination module is configured to determine first straight-line walking condition information of the target object based on the first segment of walking information and the third segment of walking information; the second determination module is configured to determine second straight-line walking condition information of the target object based on the second segment of walking information in response to the first straight-line walking condition information indicating that the target object has changed from straight-line walking to turning; and the first generation module is configured to generate, based on the second straight-line walking condition information, information indicating that the target object has changed from straight-line walking to other types of walking. The second generation module is configured to generate second straight-line walking condition information indicating that the target object is walking straight in response to the sum of the I-1 difference values ​​being less than a predetermined difference threshold.

[0270] According to an embodiment of the present invention, the first determination module includes a first fitting submodule, a second fitting submodule, and a first determination submodule. The first fitting submodule is configured to input the first walking position coordinates into a to-be-fitted straight line function to obtain a first fitting straight line, wherein the first fitting straight line includes a first predicted position coordinate corresponding to the first walking position coordinate, and the first squared sum of errors between the first predicted position coordinate and the first walking position coordinate is minimized; the second fitting submodule is configured to input the second walking position coordinates into the to-be-fitted straight line function to obtain a second fitting straight line, wherein the second fitting straight line includes a second predicted position coordinate corresponding to the second walking position coordinate, and the second squared sum of errors between the second predicted position coordinate and the second walking position coordinate is minimized; and the first determination submodule is configured to determine the first walking straight condition information of the target object based on the first slope of the first fitting straight line and the second slope of the second fitting straight line when the first squared sum of errors and the second squared sum of errors meet a predetermined error condition.

[0271] According to an embodiment of the present invention, the second determination module includes a second determination submodule and a third determination submodule. The second determination submodule is configured to determine the difference between the qth yaw angle value and the q+1th yaw angle value among the Q yaw angle values ​​to obtain a Q-1 difference value, where q is a positive integer less than Q. The third determination submodule is configured to determine the second straight-walking condition information of the target object in response to the sum of the Q-1 differences being greater than or equal to a predetermined difference threshold.

[0272] According to embodiments of the present invention, any multiple modules among the first detection module 1110, the acquisition module 1120, the processing module 1130, and the sending module 1140 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present invention, at least one of the first detection module 1110, the acquisition module 1120, the processing module 1130, and the sending module 1140 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or implemented in any one of software, hardware, and firmware, or any suitable combination of these. Alternatively, at least one of the first detection module 1110 , the acquisition module 1120 , the processing module 1130 and the sending module 1140 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0273] FIG12 shows a structural block diagram of a mobile communication terminal according to an embodiment of the present invention.

[0274] As shown in FIG. 12 , the mobile communication terminal 1200 of this embodiment includes a receiving module 1210 and a second detecting module 1220 .

[0275] Receiving module 1210 is configured to receive gait parameters from a wearable device. The gait parameters are obtained by processing the target subject's straight-ahead walking information using an objective function in response to the wearable device detecting a target subject transitioning from straight-ahead walking to another type of walking, the target subject's straight-ahead walking information being collected a number of times greater than or equal to a predetermined collection number threshold, and the target subject's straight-ahead walking information being collected a number of times greater than or equal to a predetermined collection cycle threshold per day. The straight-ahead walking information is collected when the target subject's motion state is walking, and the target subject's motion state is detected in response to receiving confirmation information indicating that the target subject has used a target medication. In one embodiment, receiving module 1210 can be configured to perform operation S810 described above, which will not be further described here.

[0276] The second detection module 1220 is used to perform abnormality detection on the gait parameters to obtain abnormality detection results. In one embodiment, the second detection module 1220 can be used to perform the operation S820 described above, which will not be repeated here.

[0277] According to an embodiment of the present invention, the second detection module 1220 includes a first processing submodule and a second processing submodule. The first processing submodule is configured to, in response to the number of days corresponding to the collected walking information being equal to a predetermined threshold number of days, process the gait parameters using a first gait parameter anomaly detection algorithm to obtain a first anomaly detection result corresponding to a pattern of changes in the gait parameters; and the second processing submodule is configured to process the gait parameters using a second gait parameter anomaly detection algorithm to obtain a second anomaly detection result corresponding to a deviation in the gait parameters.

[0278] According to an embodiment of the present invention, the first processing submodule includes a first calculation unit, a second calculation unit, a first generation unit, and a second generation unit. The first calculation unit is used to calculate the m-1th group of first-order forward difference values ​​based on the m-1th group of gait parameters and the m-th group of gait parameters in the M groups of gait parameters, where m is a positive integer greater than 1 and less than or equal to M; the second calculation unit is used to calculate the m-2th group of second-order forward difference values ​​based on the m-2th group of first-order forward difference values ​​and the m-1th group of first-order forward difference values ​​in the M-1 groups of first-order forward difference values; the first generation unit is used to generate a first abnormality detection result indicating that there is no abnormal condition in the gait parameters in response to the M-2th group of second-order forward difference values ​​being greater than a predetermined differential value threshold; the second generation unit is used to generate a first abnormality detection result indicating that there is an abnormal condition in the gait parameters in response to the M-2th group of second-order forward difference values ​​being less than or equal to the predetermined differential value threshold.

[0279] According to an embodiment of the present invention, the second processing submodule includes a first determining unit, a second determining unit, a third generating unit, and a fourth generating unit. The first determining unit is configured to determine a statistical value of K gait parameters; the second determining unit is configured to determine K differences between the statistical value and the K gait parameters; the third generating unit is configured to generate a second anomaly detection result indicating that no abnormality exists in the gait parameters in response to the K differences being less than or equal to a predetermined difference threshold; and the fourth generating unit is configured to generate a second anomaly detection result indicating that no abnormality exists in the gait parameters in response to the K differences being greater than the predetermined difference threshold.

[0280] According to an embodiment of the present invention, the second detection module 1220 further includes a first sending submodule and a second sending submodule. The first sending submodule is configured to, in response to both the first abnormality detection result and the second abnormality detection result indicating that the gait parameters do not have an abnormal condition, send the gait parameters to the server so that the server can store the gait parameters; and the second sending submodule is configured to, in response to at least one of the first abnormality detection result and the second abnormality detection result indicating that the gait parameters have an abnormal condition, send an information acquisition request to the wearable device to obtain walking information corresponding to the gait parameters with the abnormal condition cached by the wearable device, and send the walking information corresponding to the gait parameters with the abnormal condition to the server so that the server can store the walking information corresponding to the gait parameters with the abnormal condition.

[0281] According to embodiments of the present invention, any multiple modules in the receiving module 1210 and the second detection module 1220 may be combined into a single module, or any one of them may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present invention, at least one of the receiving module 1210 and the second detection module 1220 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or implemented in any one of software, hardware, and firmware, or any suitable combination of these. Alternatively, at least one of the receiving module 1210 and the second detection module 1220 may be at least partially implemented as a computer program module that, when executed, performs the corresponding functionality.

[0282] FIG13 shows a block diagram of an electronic device suitable for implementing a gait information processing method according to an embodiment of the present invention.

[0283] As shown in Figure 13, an electronic device 1300 according to an embodiment of the present invention includes a processor 1301, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1302 or programs loaded from a storage unit 1308 into a random access memory (RAM) 1303. Processor 1301 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or related chipsets and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. Processor 1301 may also include onboard memory for caching purposes. Processor 1301 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0284] Various programs and data required for the operation of the electronic device 1300 are stored in the RAM 1303. The processor 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. The processor 1301 performs various operations according to the method flow of the embodiment of the present invention by executing the programs in the ROM 1302 and / or the RAM 1303. It should be noted that the programs may also be stored in one or more memories other than the ROM 1302 and the RAM 1303. The processor 1301 may also perform various operations according to the method flow of the embodiment of the present invention by executing the programs stored in the one or more memories.

[0285] According to an embodiment of the present invention, electronic device 1300 may further include an input / output (I / O) interface 1305, which is also connected to bus 1304. Electronic device 1300 may also include one or more of the following components connected to I / O interface 1305: an input section 1306 including a keyboard, mouse, etc.; an output section 1307 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 1308 including a hard disk; and a communication section 1309 including a network interface card such as a LAN card or modem. Communication section 1309 performs communication processing via a network such as the Internet. A drive 1310 is also connected to I / O interface 1305 as needed. Removable media 1311, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 1310 as needed, so that computer programs read from the removable media can be installed into storage section 1308 as needed.

[0286] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present invention.

[0287] According to an embodiment of the present invention, a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as, but not limited to, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present invention, a computer-readable storage medium may include the ROM 1302 and / or RAM 1303 described above and / or one or more memories other than ROM 1302 and RAM 1303.

[0288] Embodiments of the present invention also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is executed in a computer system, the program code is used to enable the computer system to implement the gait information processing method provided by the embodiment of the present invention.

[0289] The computer program executes the above functions defined in the system / device of the embodiment of the present invention when executed by the processor 1301. According to the embodiment of the present invention, the above-described system, device, module, unit, etc. can be implemented by a computer program module.

[0290] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal over a network medium, downloaded and installed via the communication portion 1309, and / or installed from removable media 1311. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0291] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1309 and / or installed from the removable medium 1311. When the computer program is executed by the processor 1301, the above-described functions defined in the system of the embodiment of the present invention are performed. According to the embodiment of the present invention, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0292] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiment of the present invention can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0293] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0294] It should be noted that, unless it is clearly stated that there is a sequence of execution between different operations shown in the flowchart in the embodiments of the present invention, or there is a sequence of execution between different operations in technical implementation, otherwise, the execution order of multiple operations may not be prioritized, and multiple operations may also be executed simultaneously.

[0295] Those skilled in the art will appreciate that the features described in the various embodiments of the present invention may be combined and / or coupled in various ways, even if such combinations and / or couplings are not explicitly described in the present invention. In particular, the features described in the various embodiments of the present invention may be combined and / or coupled in various ways without departing from the spirit and teachings of the present invention. All such combinations and / or couplings fall within the scope of the present invention.

[0296] The above describes embodiments of the present invention. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be advantageously used in combination. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A gait information processing method, applied to a wearable device, characterized in that: include: In response to receiving confirmation information indicating that the target subject has used the target drug, detecting the target subject state of motion; When the target object is in a walking state, collecting walking information of the target object walking straight; In response to detecting that the target subject changes from straight-ahead walking to another type of walking, the number of times walking information of the target subject's straight-ahead walking is collected is greater than or equal to a predetermined collection number threshold, and the number of single-day collection cycles of walking information of the target subject's straight-ahead walking is greater than or equal to a predetermined collection cycle threshold, processing the walking information of the target subject's straight-ahead walking using an objective function to obtain gait parameters; and transmitting the gait parameters to a mobile communication terminal so that the mobile communication terminal performs abnormality detection on the gait parameters; The walking information includes first segment walking information, second segment walking information, and third segment walking information collected in sequence according to collection time; the method further includes: determining first straight-walking condition information of the target object according to the first segment of walking information and the third segment of walking information; In response to the first straight-walking condition information indicating that the target object changes from walking straight to turning, determining second straight-walking condition information of the target object based on the second segment of walking information; determining, based on the second straight-walking condition information, that the target object changes from straight-walking to other types of walking; the first segment of walking information includes first walking position coordinates, and the third segment of walking information includes second walking position coordinates; Determine the first straight line of the target object based on the first segment of walking information and the third segment of walking information Status information, including: Inputting the first walking position coordinate into a to-be-fitted straight line function to obtain a first fitting straight line, wherein the first fitting straight line includes a first predicted position coordinate corresponding to the first walking position coordinate, and a first sum of squares of errors between the first predicted position coordinate and the first walking position coordinate is minimized; Inputting the second walking position coordinate into the to-be-fitted straight line function to obtain a second fitting straight line, wherein the second fitting straight line includes a second predicted position coordinate corresponding to the second walking position coordinate, and a second sum of squares of errors between the second predicted position coordinate and the second walking position coordinate is minimized; When the first square error sum and the second square error sum meet a predetermined error condition, first straight-walking condition information of the target object is determined according to a first slope of the first fitting line and a second slope of the second fitting line.

2. The method according to claim 1, characterized in that The second segment of walking information includes Q yaw angle values, where the Q yaw angle values ​​are arranged according to the walking order of the target object, and Q is a positive integer greater than 1; In response to the first straight-walking condition information indicating that the target object changes from walking straight to turning, determining second straight-walking condition information of the target object based on the second segment of walking information includes: Determine a difference between a qth yaw angle value and a q+1th yaw angle value among the Q yaw angle values ​​to obtain a Q-1 difference, where q is a positive integer less than 1; In response to the sum of the Q-1 difference values ​​being greater than or equal to a predetermined difference threshold, generating second walking straight condition information representing a turn of the target object; In response to the sum of the Q-1 difference values ​​being less than a predetermined difference threshold, second straight-walking condition information characterizing that the target object is walking straight is generated.

3. The method according to claim 1, characterized in that The gait parameters include the duration of the foot swing phase, the duration of the foot support phase, the step height, the step width, the step length, the angular velocity variation coefficient of the pitch angle during the foot landing phase, the angular velocity variation coefficient of the pitch angle during the foot extension phase, the step height variation coefficient, the foot swing width variation coefficient and the step length variation coefficient.

4. A gait information processing method, applied to a mobile communication terminal, characterized in that: include: receiving gait parameters from a wearable device, wherein the gait parameters are obtained by processing the target subject's straight-ahead walking information using an objective function in response to the wearable device detecting that the target subject has transitioned from straight-ahead walking to another type of walking, the number of collection times of the target subject's straight-ahead walking information being greater than or equal to a predetermined collection time threshold, and the number of daily collection cycles of the target subject's straight-ahead walking information being greater than or equal to a predetermined collection cycle threshold, the straight-ahead walking information of the target subject being collected when the target subject's motion state is walking, and the motion state of the target subject being detected in response to receiving confirmation information indicating that the target subject has confirmed use of a target medication; Performing abnormality detection on the gait parameters to obtain abnormality detection results includes: In response to the number of collection days corresponding to the collected walking information being equal to a predetermined day threshold, processing the gait parameters using a first gait parameter anomaly detection algorithm to obtain a first anomaly detection result corresponding to a change pattern of the gait parameters; processing the gait parameters using a second gait parameter anomaly detection algorithm to obtain a second anomaly detection result corresponding to a deviation of the gait parameters; There are M groups of gait parameters, and the M groups of gait parameters correspond to the M medication periods of the target subject in a single day. The gait parameters of the group are arranged in order according to the walking time, and M is a positive integer greater than 1; Processing the gait parameters using a first gait parameter anomaly detection algorithm to obtain a first anomaly detection result corresponding to a change pattern of the gait parameters includes: Calculating an m-1th group of first-order forward difference values ​​based on the m-1th group of gait parameters and the m-th group of gait parameters in the M groups of gait parameters, where m is a positive integer greater than 1 and less than or equal to M; According to the m‑2th group of first-order forward difference values ​​and the m‑1th group of first-order forward difference values ​​in the M‑1 groups of first-order forward difference values, Calculate the m‑2th group of second-order forward difference values; In response to the M-2 sets of second-order forward difference values ​​being greater than a predetermined difference value threshold, generating a first abnormality detection result indicating that the gait parameter does not have an abnormal condition; In response to the M‑2 groups of second-order forward difference values ​​being less than or equal to a predetermined difference value threshold, a first abnormality detection result is generated, indicating that the gait parameter has the abnormal condition.

5. The method according to claim 4, characterized in that The mth group of gait parameters includes K gait parameters corresponding to K detection cycles; Processing the gait parameter using a second gait parameter anomaly detection algorithm to obtain a first anomaly detection result corresponding to a deviation of the gait parameter includes: Determining statistical values ​​of the K gait parameters; determining K differences between the statistical value and the K gait parameters; In response to the K differences being less than or equal to a predetermined difference threshold, generating a second abnormality detection result indicating that the gait parameter does not have an abnormal condition; In response to the K differences being greater than a predetermined difference threshold, a second abnormality detection result is generated, indicating that the abnormal condition exists in the gait parameter.

6. The method according to claim 4 or 5, characterized in that Also includes: In response to the first abnormality detection result and the second abnormality detection result both indicating that the gait parameter does not have the abnormal condition, sending the gait parameter to a server so that the server stores the gait parameter; In response to at least one of the first abnormality detection result and the second abnormality detection result indicating that the gait parameter has the abnormal condition, an information acquisition request is sent to the wearable device to obtain walking information corresponding to the gait parameter with the abnormal condition cached by the wearable device, and the walking information corresponding to the gait parameter with the abnormal condition is sent to the server, so that the server can store the walking information corresponding to the gait parameter with the abnormal condition.

Images