Human gait analysis method and system based on big data

Abstract

The application discloses a human gait analysis method and system based on big data, and belongs to the technical field of gait analysis. The system comprises a user information association module, a data acquisition module, a data analysis module, an analysis database, an intelligent evaluation module and a digital display module. The user information association module is used for associating a sensor device for monitoring human gait data with a patient, and determining basic information parameters of the associated patient. The data acquisition module is used for acquiring human gait data of the patient when walking. The data analysis module is used for determining the total center of gravity change of the patient's body when walking. The analysis database is used for integrating human gait data of each patient when walking, determining the risk value of falling down of each total center of gravity change of the patient's body when walking, and the intelligent evaluation module is used for evaluating the movement ability of the patient. The digital display module is used for digitally displaying the movement ability evaluation result of the patient.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gait analysis, in particular to a human gait analysis method and system based on big data. BACKGROUND

[0002] Gait analysis is a systematic observation, measurement and analysis process of the movement characteristics of human walking. It collects and analyzes data related to gait through various sensors, camera equipment and calculation methods to reveal the normality and abnormality of gait, and is often used to study and evaluate the biomechanical characteristics, movement patterns and physiological state of humans during walking. By extracting and selecting features of human movement, the abnormality of gait can be accurately reflected. However, the existing technology has low recognition accuracy when facing complex gait abnormalities, and it is difficult to comprehensively evaluate the movement ability of patients according to their gait data. In addition, most systems only focus on the changes of a single joint or part during feature extraction, and do not fully consider the overall and dynamic nature of gait, resulting in insufficient robustness and generalization ability of the system. SUMMARY

[0003] The present application aims to provide a human gait analysis method and system based on big data to solve the problems raised in the background.

[0004] To solve the above technical problems, the present application provides the following technical solution: a human gait analysis method based on big data, comprising the following steps:

[0005] Step S1, the patient associates a sensor device for monitoring human gait data, and collects human gait data when the patient walks; the human gait data includes the center of mass position information of each body segment when the patient walks;

[0006] Step S2, analyze the collected human gait data, and determine the total center of gravity change of the patient's body when walking according to the center of mass position information of each body segment and the weight of each body segment;

[0007] Step S3, establish an analysis database, integrate the human gait data of each patient when walking in the analysis database; according to the human gait data of the patient when falling and the total center of gravity change of the patient's body when walking, get the risk value of falling of the patient's body under each total center of gravity change when walking;

[0008] Step S4, evaluate the movement ability of the patient according to the risk value of falling of the patient's body under each total center of gravity change when walking; establish an activity log of the movement ability evaluation results of the patient in different periods, and digitally display the movement ability evaluation results of the patient.

[0009] The human gait analysis system based on big data comprises a user information association module, a data acquisition module, a data analysis module, an analysis database, an intelligent evaluation module and a digital display module.

[0010] The user information association module is used for associating a sensor device for monitoring human gait data with a patient, and determining basic information parameters of the patient, which include the height, weight, age, gender of the patient and the length of each body segment of the patient.

[0011] The data acquisition module is used for acquiring human gait data of the patient when walking, wherein the human gait data includes the center of mass position information of each body segment of the patient when walking, and the acquired human gait data is sent to the data analysis module and the analysis database.

[0012] The data analysis module is used for analyzing the human gait data acquired by the data acquisition module, determining the total center of gravity change of the patient's body when walking according to the center of mass position information of each body segment of the patient when walking and the weight of each body segment, and sending the determined total center of gravity change of the patient's body when walking to the intelligent evaluation module.

[0013] The analysis database is used for integrating the human gait data of each patient when walking, obtaining the risk value of falling of each total center of gravity change of the patient's body when walking according to the human gait data of the patient when falling in the analysis database, and sending the risk value of falling of each total center of gravity change of the patient's body when walking to the intelligent evaluation module.

[0014] The intelligent evaluation module is used for evaluating the movement ability of the patient according to the total center of gravity change of the patient's body when walking sent by the data analysis module and the risk value of falling of each total center of gravity change of the patient's body when walking sent by the analysis database, and sending the evaluation result of the movement ability of the patient to the digital display module.

[0015] The digital display module is used for establishing an activity log of the movement ability evaluation result of the patient in different periods, and digitally displaying the movement ability evaluation result of the patient.

[0016] An electronic device comprises a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0017] The processor executes the above-mentioned human gait analysis method based on big data by calling the computer program stored in the memory.

[0018] A computer readable storage medium stores instructions, when the instructions are run on a computer, the computer executes the above-mentioned human gait analysis method based on big data.

[0019] Compared with the prior art, the present application has the beneficial effects that: by determining the center of mass coordinates and weight of each body segment of the patient, calculating the total center of gravity change of the patient's body when walking, analyzing the human gait data from the overall and dynamic nature of the patient's body, the robustness and generalization ability of the analysis system are improved; according to the total center of gravity change, the risk of the patient falling is predicted, and the accuracy of the patient's gait analysis is improved; by calculating the patient's motor ability evaluation value, it is beneficial for medical personnel to more intuitively understand the patient's health status. BRIEF DESCRIPTION OF DRAWINGS

[0020] Fig. 1 is a step schematic diagram of the human gait analysis method based on big data of the present application;

[0021] Fig. 2 is a structure schematic diagram of the human gait analysis system based on big data of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0023] The present application collects the center of mass position information of each body segment of the patient when walking, determines the total center of gravity change of the patient's body according to the collected center of mass position information, evaluates the patient's motor ability according to the risk value of the patient falling under different total center of gravity changes, improves the accuracy of the patient's gait data analysis, helps medical personnel to more intuitively understand the patient's health status, and formulates a more personalized rehabilitation plan.

[0024] Please refer to Figs. 1-2 The present application provides the following technical solutions:

[0025] Please refer to Fig. 1 In the first embodiment, a human gait analysis method based on big data is provided, which comprises the following steps:

[0026] Step S1, the patient associates a sensor device for monitoring human gait data, and collects human gait data when the patient walks; the human gait data contains the center of mass position information of each body segment of the patient when walking.

[0027] Further, the basic information parameters of the associated patient are determined, and the basic information parameters include the height, weight, age, gender of the patient, and the length of each body segment of the patient; wherein the gait data of the human body when the patient walks is collected by a sensor device, and the sensor device includes a high-speed camera for capturing the motion trajectory of each body segment of the patient and a mechanical measuring device for capturing the motion acceleration and direction of each body segment of the patient.

[0028] Further, the method for determining the center of mass position information of each body segment of the patient when walking is as follows: the length of each body segment of the patient is determined, and the joint connection points of each body segment of the patient are determined; a three-dimensional space model about the X-axis, the Y-axis and the Z-axis is established, the motion trajectory of each joint connection point in the three-dimensional space model is determined according to the motion trajectory, the motion acceleration and the direction of each body segment of the patient, the coordinate changes of the proximal segment and the distal segment of each body segment of the patient at different time stamps t are respectively determined according to the motion trajectory of each joint connection point, and the center of mass position information of each body segment of the patient when walking is determined according to the coordinate changes of the proximal segment and the distal segment of each body segment, according to the calculation formula:

[0029]

[0030] wherein, and respectively represent the coordinates of the i-th body segment of the patient on the X-axis, the Y-axis and the Z-axis at different time stamps t; and respectively represent the coordinates of the proximal segment of the i-th body segment of the patient on the X-axis, the Y-axis and the Z-axis at different time stamps t; and respectively represent the coordinates of the distal segment of the i-th body segment of the patient on the X-axis, the Y-axis and the Z-axis at different time stamps t; i∈{1,2,...,n}; n represents the number of body segments of the patient; B i represents the percentage of the length of the proximal segment of the i-th body segment of the patient to the center of mass position to the length of the proximal segment to the distal segment.

[0031] In the present embodiment, the body segments of the patient are divided into head, neck, upper torso, lower torso, upper arm, forearm, thigh, lower leg, hand and foot; when collecting the gait data of the human body when the patient walks, the center point of one of the high-speed cameras is taken as the origin, the three-dimensional space model is established, the video data collected by the high-speed camera is combined with the motion acceleration and direction captured by the mechanical measuring device in the sensor device, the occlusion perception mechanism algorithm is introduced, the 3D posture information of the human body is extracted from the video data, and thus the motion trajectory of each body segment of the patient is captured and the motion change of each body segment of the patient is determined; the mechanical measuring device includes an accelerometer and a gyroscope.

[0032] It should be noted that the segment proximal end represents the end of the patient's body segment closer to the body center; the segment distal end represents the end of the patient's body segment away from the body center; according to the movement trajectory of each body segment of the patient, the position coordinates of the segment proximal end and the segment distal end in each body segment of the patient are determined, and the centroid position coordinates of each body segment of the patient at the corresponding timestamp are obtained in combination with the length of each body segment, so as to calculate and that is, the centroid position information of each body segment of the patient when walking, and the total center of gravity of the patient's body when walking is conveniently determined subsequently; in the embodiment, B i obtained from anthropometric literature or experimental data of anthropometry.

[0033] Step S2, analyzing the collected human gait data, determining the total center of gravity of the patient's body when walking according to the centroid position information of each body segment of the patient when walking and the weight of each body segment.

[0034] Specifically, the method for determining the total center of gravity of the patient's body when walking comprises the following steps: determining the weight of each body segment of the patient according to the basic information parameters of the patient, and calculating the coordinates of the total center of gravity of the patient's body on the X axis, the Y axis and the Z axis at different timestamps t according to the centroid position information of each body segment of the patient when walking

[0035]

[0036] wherein, G represents the weight of the patient; g i represents the weight of the i-th body segment of the patient.

[0037] In the embodiment, in the process of determining the weight of each body segment of the patient, the known relative mass distribution table of each body segment of the human body is used through the basic information parameters of the patient, for example: the upper torso of a male student accounts for 27.23% of the relative mass of the body weight, and the lower torso accounts for 14.19% of the relative mass of the body weight; the torso of a female student accounts for 27.48% of the relative mass of the body weight, and the lower torso accounts for 14.10% of the relative mass of the body weight; wherein the weight of each body segment of the patient can be adjusted according to the specific condition of the patient; since the centroid of an object or system is the weighted average position of all mass elements, according to the principle of moment balance, the total center of gravity coordinates of the patient's body when walking are calculated by determining the centroid coordinates and the weight of each body segment of the patient, and the total center of gravity change of the patient's body when walking is obtained; analyzing the human gait data from the overall and dynamic analysis of the patient's body improves the robustness and generalization ability of the analysis system, and the risk of falling of the patient is predicted according to the total center of gravity change, which improves the accuracy of the analysis of the patient's gait.

[0038] Step S3, an analysis database is established, and human gait data of each patient walking is integrated in the analysis database; according to human gait data of the patient falling in the analysis database and total center of gravity changes of the patient's body when walking, a risk value of falling of each total center of gravity change of the patient's body when walking is obtained;

[0039] Specifically, the method steps are:

[0040] Step S31, an analysis database is established in the cloud, and the collected human gait data of each patient walking is sent to the analysis database in the cloud for storage and continuous updating;

[0041] Step S32, the human gait data stored in the analysis database is analyzed, the center of mass position information of the patient's foot is taken as an analysis origin, the coordinate changes of the analysis origin on the X-axis, Y-axis and Z-axis are determined, and the coordinate changes of the total center of gravity of the patient's body on the X-axis, Y-axis and Z-axis when walking are determined; the analysis origin coordinates and the total center of gravity coordinates are connected to obtain an angle value of the connecting line with the horizontal plane, and the obtained angle value is taken as a total center of gravity angle;

[0042] Step S33, the human gait data of the patient falling in the analysis database is analyzed, according to the corresponding total center of gravity angle when the patient falls, the frequency of each total center of gravity angle appearing in the analysis database when the patient falls is determined, and is taken as a risk value of falling under each total center of gravity change.

[0043] It should be noted that the frequency of each total center of gravity angle of the patient falling in the analysis database, that is, the proportion of the number of times the patient falls at each total center of gravity angle to the amount of human gait data corresponding to the total center of gravity angle in the analysis database, the higher the frequency, the higher the risk value of the patient falling; in this embodiment, according to the accuracy of the high-speed camera and the sensor device data collection, when the total center of gravity coordinates of the patient's body when walking are analyzed, the coordinate point analysis range ε of the total center of gravity coordinate value is determined, for example, the total center of gravity coordinate points in and are taken as human gait data under the same total center of gravity angle for analysis, the higher the accuracy of data collection, the smaller the value of ε, thereby improving the accuracy of human gait analysis; by determining the risk value of falling of each total center of gravity change of the patient's body when walking, the movement ability of the patient is conveniently evaluated; based on the analysis of the human gait data of each patient walking collected in the analysis database, and the analysis database is updated, the autonomous analysis of the falling risk value of the patient under each total center of gravity change is realized.

[0044] Step S4, according to the risk value of falling down of the change of the total center of gravity of the body of the patient when walking, the movement ability of the patient is evaluated; the activity log of the evaluation results of the movement ability of the patient in different periods is established, and the evaluation results of the movement ability of the patient are digitally displayed.

[0045] Specifically, the method steps are:

[0046] Step S41, the coordinates of the total center of gravity of the body of the patient in X axis, Y axis and Z axis when walking at different time stamps t are determined The total center of gravity angle at different time stamps t is determined, and the risk value F of falling down of the patient at different time stamps t is obtained according to step S33 t ;

[0047] Step S42, according to F t , the movement ability of the patient is evaluated, the movement ability evaluation value H of the patient is determined, and the calculation formula is:

[0048]

[0049] Wherein, t1 represents the starting time of the patient walking; t2 represents the ending time of the patient walking;

[0050] Step S43, the movement ability evaluation value of the patient in different periods is determined, and the activity log of the patient is established, and the movement ability evaluation value of the patient in different periods is digitally displayed.

[0051] It should be noted that the human gait data of the patient is analyzed by intelligent calculation, the movement ability evaluation value of the patient is calculated according to the risk value of falling down of the patient, so as to help the medical staff to more intuitively understand the health status of the patient, and assist the medical staff to make decision evaluation; in this embodiment, the medical staff can check the movement ability evaluation value of the patient in different periods through the activity log of the patient, so as to make more personalized rehabilitation plan; at the same time, according to the different movement ability evaluation value, the corresponding rehabilitation scheme is set, the system can push the corresponding rehabilitation scheme according to the current calculation of the movement ability evaluation value of the patient, so as to realize the intelligent level of the system.

[0052] Please refer to Fig. 2 In this embodiment two: a human gait analysis system based on big data is provided, which comprises a user information association module, a data acquisition module, a data analysis module, an analysis database, an intelligent evaluation module and a digital display module;

[0053] The user information association module is used for associating the sensor equipment for monitoring human gait data with the patient, determining the basic information parameters of the associated patient, and the basic information parameters include the height, weight, age, gender of the patient and the length of each body part of the patient;

[0054] The data acquisition module is used to collect human gait data of the patient when walking; the human gait data includes the center of mass position information of each body segment of the patient when walking; and send the collected human gait data to the data analysis module and the analysis database;

[0055] The data analysis module is used to analyze the human gait data collected by the data acquisition module, determine the change in the total center of gravity of the patient's body when walking based on the center of mass position information of each body segment and the weight of each body segment when the patient walks; and send the determined change in the total center of gravity of the patient's body when walking to the intelligent evaluation module;

[0056] The analysis database is used to integrate the human gait data of each patient when walking; based on the human gait data of the patient when falling in the analysis database, the risk value of falling due to each change in the total center of gravity of the patient's body when walking is obtained; and the risk value of falling due to each change in the total center of gravity of the patient's body when walking is sent to the intelligent assessment module;

[0057] The intelligent assessment module is used to assess the patient's exercise capacity based on the changes in the patient's total center of gravity when walking, sent by the data analysis module, and the risk values ​​of falling for each change in the patient's total center of gravity when walking, sent by the analysis database; and send the patient's exercise capacity assessment results to the digital display module;

[0058] The digital display module is used to establish an activity log of the patient's exercise capacity evaluation results at different periods and to digitally display the patient's exercise capacity evaluation results.

[0059] Furthermore, the digital display module includes a human-computer interaction platform, which is used to display basic information parameters related to the patient, the center of mass position information of each body part of the patient when walking, the weight of each body part of the patient, the change of the total center of gravity of the patient's body when walking, and the risk value of falling due to the change of the total center of gravity of the patient's body when walking; wherein, the user can modify the weight of each body part of the patient through the human-computer interaction platform according to the specific situation of the patient.

[0060] In this embodiment:

[0061] The system is a human gait analysis system used to predict the degree of health recovery of patients. Patients associate sensor devices used to monitor human gait data through the user information association module and determine basic information parameters;

[0062] The data acquisition module collects the human gait data of the patient when walking; and sends the collected human gait data to the data analysis module and the analysis database;

[0063] The data analysis module analyzes the human gait data collected by the data collection module to determine the total center of gravity change of the patient's body when walking; and sends the determined total center of gravity change of the patient's body when walking to the intelligent evaluation module.

[0064] The analysis database integrates the human gait data of each patient when walking to obtain the risk value of falling down of each total center of gravity change of the patient's body when walking and sends it to the intelligent evaluation module.

[0065] The intelligent evaluation module evaluates the patient's motor ability and sends the patient's motor ability evaluation result to the digital display module.

[0066] The digital display module establishes the activity log of the patient's motor ability evaluation result in different periods and digitally displays the patient's motor ability evaluation result; wherein, a human-computer interaction platform is provided, when the user modifies the weight of each body segment of the patient through the human-computer interaction platform, the user's modified weight of each body segment of the patient is sent to the data analysis module.

[0067] In this embodiment three: an electronic device is provided, comprising a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0068] The processor executes the steps of the above-mentioned human gait analysis method based on big data by calling the computer program stored in the memory.

[0069] In this embodiment four: a computer readable storage medium is provided, which stores instructions, when the instructions run on the computer, the computer executes the steps of the above-mentioned human gait analysis method based on big data to realize the following functions: associate the sensor device for monitoring human gait data; collect human gait data when the patient walks; determine the total center of gravity change of the patient's body when walking; determine the risk value of falling down of each total center of gravity change of the patient's body when walking; evaluate the patient's motor ability.

[0070] The computer readable storage medium includes: U disk, mobile hard disk, read-only memory, random access memory, magnetic disk or optical disk and various storage program code medium.

[0071] Finally, it should be pointed out that: the above-mentioned only for the preferred embodiments of the present application, and not for limiting the present application, although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for human gait analysis based on big data, characterized in that: The method comprises the following steps: Step S1, the patient associates a sensor device for monitoring human gait data, and collects human gait data when the patient walks; the human gait data includes the center of mass position information of each body segment of the patient when walking; Step S2, analyzing the collected human gait data, determining the total center of gravity change of the patient's body when walking according to the center of mass position information of each body segment and the weight of each body segment; Step S3, establishing an analysis database, integrating the human gait data of each patient when walking in the analysis database; according to the human gait data of the patient when falling and the total center of gravity change of the patient's body when walking, the risk value of falling under each total center of gravity change of the patient's body when walking is obtained; the specific process is: Step S31, an analysis database is established in the cloud, and the collected human gait data of each patient when walking is sent to the analysis database in the cloud for storage and continuous updating; Step S32, analyzing the human gait data stored in the analysis database, taking the center of mass position information of the patient's foot as the analysis origin, determining the coordinate change of the analysis origin on the X axis, Y axis and Z axis, and determining the coordinate change of the total center of gravity of the patient's body on the X axis, Y axis and Z axis; connecting the analysis origin coordinates and the total center of gravity coordinates to obtain the angle value of the connecting line with the horizontal plane, and taking the obtained angle value as the total center of gravity angle; Step S33, analyzing the human gait data of the patient when falling in the analysis database, determining the frequency of each total center of gravity angle appearing in the analysis database according to the corresponding total center of gravity angle when the patient falls, and taking it as the risk value of falling under each total center of gravity change; Step S4, according to the risk value of falling under each total center of gravity change of the patient's body when walking, evaluating the patient's motor ability; establishing an activity log of the patient's motor ability evaluation results in different periods, and digitally displaying the patient's motor ability evaluation results; the specific process is: Step S41, determine the coordinates of the total center of gravity of the patient's body on the X-axis, Y-axis and Z-axis when walking at different timestamps t Determine the total center of gravity angle at different timestamps t, and obtain the risk value F of the patient falling at different timestamps t according to step S33 t ; Step S42, according to F t The patient's exercise capacity is evaluated to determine the patient's exercise capacity evaluation value H according to the calculation formula: Wherein, t1 represents the start time of the patient walking; t2 represents the end time of the patient walking; Step S43, determining the motor ability evaluation value of the patient in different periods, and establishing an activity log about the patient, and digitally displaying the motor ability evaluation value of the patient in different periods.

2. The big data based human gait analysis method according to claim 1, characterized in that: The basic information parameters associated with the patient are determined, including the height, weight, age, gender of the patient and the length of each body segment of the patient; wherein the human gait data is collected by a sensor device, which includes a high-speed camera for capturing the movement trajectory of each body segment of the patient and a mechanical measuring device for capturing the movement acceleration and direction of each body segment of the patient. 3.The big data based human gait analysis method according to claim 2, characterized in that: The method for determining the center of mass position information of each body segment of a patient when walking is as follows: lengths of each body segment of the patient are determined, joint connecting points of each body segment of the patient are determined; a three-dimensional space model about an X axis, a Y axis and a Z axis is established, a movement trajectory of each joint connecting point of the patient in the three-dimensional space model is determined according to a movement trajectory, a movement acceleration and a direction of the patient; coordinate changes of a segment proximal end of each body segment of the patient at different time stamps t are respectively determined according to the movement trajectory of each joint connecting point, and coordinate changes of a segment distal end of each body segment of the patient at different time stamps t are determined; the center of mass position information of each body segment of the patient when walking is determined according to the coordinate changes of the segment proximal end and the segment distal end of each body segment, according to a calculation formula: wherein, and Xi(t), Yi(t), and Zi(t) represent the coordinates of the i th body segment of the patient on the X-axis, Y-axis, and Z-axis at different timestamps t, respectively; and Xi(t), Yi(t), and Zi(t) represent the coordinates of the i th body segment of the patient on the X-axis, Y-axis, and Z-axis at different timestamps t, respectively; and Xi(t), Yi(t), and Zi(t) represent the coordinates of the i th body segment of the patient on the X-axis, Y-axis, and Z-axis at different timestamps t, respectively; i∈{1,2,...,n}; n represents the number of body segments of the patient; i Xi(t), Yi(t), and Zi(t) represent the coordinates of the i th body segment of the patient on the X-axis, Y-axis, and Z-axis at different timestamps t, respectively; i∈{1,2,...,n}; n represents the number of body segments of the patient; 4. The big data based human gait analysis method of claim 3, wherein: The method for determining the total center of gravity of the body of the patient when walking comprises the following steps: determining the weight of each body segment of the patient according to basic information parameters of the patient, and calculating the coordinates of the total center of gravity of the body of the patient on the X axis, the Y axis and the Z axis at different time stamps t according to the center of mass position information of each body segment of the patient when walking wherein, G represents the weight of the patient; g i Wi represents the weight of the i-th body segment of the patient.

5. An analysis system for implementing the big data-based human gait analysis method according to any one of claims 1 to 4, characterized in that: The analysis system comprises a user information association module, a data acquisition module, a data analysis module, an analysis database, an intelligent evaluation module and a digital display module; The user information association module is used for associating a sensor device for monitoring human gait data of a patient, and determining basic information parameters of the associated patient, the basic information parameters comprising a height, a weight, an age, a gender of the patient and lengths of each body segment of the patient; The data acquisition module is used for acquiring human gait data of the patient when walking, the human gait data comprising center of mass position information of each body segment of the patient when walking; and the acquired human gait data is sent to the data analysis module and the analysis database; The data analysis module is used for analyzing the human gait data acquired by the data acquisition module, determining a total center of gravity change of the patient's body when walking according to the center of mass position information of each body segment of the patient when walking and weights of each body segment, and sending the determined total center of gravity change of the patient's body when walking to the intelligent evaluation module; The analysis database is used for integrating human gait data of each patient when walking, obtaining a risk value of falling of each total center of gravity change of the patient's body when walking according to the human gait data of the patient when falling in the analysis database, and sending the risk value of falling of each total center of gravity change of the patient's body when walking to the intelligent evaluation module; The intelligent evaluation module is used for evaluating the movement ability of the patient according to the total center of gravity change of the patient's body when walking sent by the data analysis module and the risk value of falling of each total center of gravity change of the patient's body when walking sent by the analysis database, and sending the evaluation result of the movement ability of the patient to the digital display module; The digital display module is used for establishing an activity log of the evaluation result of the movement ability of the patient at different periods, and digitally displaying the evaluation result of the movement ability of the patient.

6. The big data based human gait analysis system according to claim 5, wherein: The digital display module comprises a human-computer interaction platform, which is used for displaying the basic information parameters of the associated patient, the center of mass position information of each body segment of the patient when walking, the weights of each body segment of the patient, the total center of gravity change of the patient's body when walking, and the risk value of falling of each total center of gravity change of the patient's body when walking; wherein a user can modify the weights of each body segment of the patient through the human-computer interaction platform according to the specific conditions of the patient.

7. An electronic device, comprising: It comprises: A processor and a memory, wherein the memory stores a computer program which can be invoked by the processor; The processor executes the big data-based human gait analysis method of any one of claims 1-4 by invoking the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: The computer stores instructions which, when executed on the computer, cause the computer to execute the big data-based human gait analysis method of any one of claims 1-4.

Images