Gait state recognition method and device, equipment, storage medium

Abstract

The present invention discloses a gait state recognition method and device, equipment, and storage medium; the method includes: collecting first acceleration data of a target object in a current period; determining a target gait cycle of the target object in the current period and a target acceleration extreme value in each target gait cycle according to the first acceleration data; identifying the gait state of the target object in the current period according to the target gait cycle and a preset cycle threshold interval under different gait states, a target acceleration extreme value, and a preset acceleration threshold interval under different gait states; the preset cycle threshold interval and the preset acceleration threshold interval are predetermined based on the second acceleration data collected by the target object in a specific gait state. In this way, the gait state of the target object can be accurately identified, and the same device can be applied to different target objects, with a wider range of adaptability.

Description

Technical Field

[0001] The embodiments of the present application relate to information processing technologies, including but not limited to a gait state recognition method, device, equipment, and storage medium. Background Art

[0002] With the increasing maturity of communication technologies, intelligent terminals and other technologies, various types of sensors are increasingly used in terminal devices to meet different requirements. For example, by integrating an acceleration sensor, a Global Positioning System (GPS), a gyroscope, a magnetic sensor, etc. into a terminal device, the usability of the terminal device can be improved. For example, the target object can be located indoors by judging its running trajectory; and the inertial sensor can be used to navigate the target object outdoors, reducing the huge energy consumption caused by over-reliance on GPS; or an acceleration sensor can be integrated into a health earphone to monitor the motion state of the target object, provide health protection for the target object, and also give a corresponding correction plan according to the monitoring results.

[0003] In these applications that provide various services for the target object, it is crucial to accurately identify the gait state of the target object. Moreover, if the same device uses the same discrimination parameters for different target objects, it cannot be well applied to the gait state recognition of different groups of objects. Therefore, how to accurately judge the gait state of the target object and make the same device applicable to different groups is a relatively important issue. Summary of the Invention

[0004] In view of this, the gait state recognition method, device, equipment, and storage medium provided by the embodiments of the present application can accurately identify the gait state of the target object, and make the same device applicable to different target objects, with a wider adaptation range. The gait state recognition method, device, equipment, and storage medium provided by the embodiments of the present application are implemented as follows:

[0005] The gait state recognition method provided by the embodiments of the present application includes: collecting first acceleration data of the target object in the current period; determining the gait cycle of the target object in the current period and the acceleration extreme value in each gait cycle according to the first acceleration data; identifying the gait state of the target object in the current period according to the gait cycle and the preset period threshold interval in different gait states, the acceleration extreme value, and the preset acceleration threshold interval in different gait states; the preset period threshold interval and the preset acceleration threshold interval are pre-determined based on the second acceleration data collected by the target object in a specific gait state.

[0006] In the embodiments of the present application, by analyzing the gait cycle and acceleration extreme values of the target object in the current period, and comparing them with the preset cycle threshold intervals and acceleration threshold intervals in different gait states, the gait state of the target object in the current period can be accurately determined; and the preset cycle threshold intervals and preset acceleration threshold intervals corresponding to different target objects are different, enabling the same device to be applicable to different target objects and having a wider adaptation range.

[0007] In some embodiments, the first acceleration data includes multiple gait cycles. According to the first acceleration data, determining the gait cycle of the target object in the current period and the acceleration extreme values in each gait cycle includes: determining a standard acceleration extreme value in the first acceleration data of the current period, where the standard acceleration extreme value is the maximum or minimum value of the acceleration in the first acceleration data; in the first acceleration data, filtering out the data other than the standard acceleration extreme value within the first time period centered on the moment where the standard acceleration extreme value is located, to obtain first target acceleration data; determining an acceleration extreme value set in the first target acceleration data; the acceleration extreme value set includes the standard acceleration extreme value; based on the acceleration extreme value set, determining the gait cycle of the target object in the current period and the acceleration extreme values in each gait cycle.

[0008] In some embodiments, the method further includes: determining a target acceleration threshold based on the standard acceleration extreme value; where, when the standard acceleration extreme value is the maximum value of the acceleration in the first acceleration, the data that is continuously sequential in time series and whose acceleration data within the first time period is greater than the target acceleration threshold; when the standard acceleration extreme value is the minimum value of the acceleration in the first acceleration, the data that is continuously sequential in time series and whose acceleration data within the first time period is less than the target acceleration threshold.

[0009] In some embodiments, determining the acceleration extreme value set in the first target acceleration data includes: determining the first acceleration extreme value that is closest to the moment where the standard acceleration extreme value is located in the first target acceleration data. When the standard acceleration extreme value is the maximum value of the acceleration in the first acceleration data, the first acceleration extreme value is the data greater than the target acceleration threshold. When the standard acceleration extreme value is the minimum value of the acceleration in the first acceleration data, the first acceleration extreme value is the data less than the target acceleration threshold; in the first target acceleration data, filtering out the data other than the first acceleration extreme value within the first time period centered on the moment where the first acceleration extreme value is located, to obtain second target acceleration data; determining the second acceleration extreme value that is closest to the moment where the first acceleration extreme value is located in the second target acceleration data; continuing to execute the step of determining the third acceleration extreme value that is closest to the moment where the second acceleration extreme value is located based on the second acceleration extreme value, until the first target acceleration data is traversed, to obtain an acceleration extreme value set including multiple acceleration extreme values.

[0010] In some embodiments, based on the set of acceleration extreme values, determining the gait cycle of the target object in the current period and the acceleration extreme values in each gait cycle includes: determining a plurality of gait cycles of the target object in the current period according to the time differences between two adjacent acceleration extreme values in time sequence in the set of acceleration extreme values, and determining two adjacent acceleration extreme values in time sequence as the acceleration extreme values in each corresponding gait cycle.

[0011] In some embodiments, the gait state at least includes running or walking; identifying the gait state of the target object in the current period according to the gait cycle, the preset period threshold interval in different gait states, the acceleration extreme values, and the preset acceleration threshold interval in different gait states includes: based on each gait cycle, determining the target gait cycle of the target object in the current period; and based on each acceleration extreme value, determining the target acceleration extreme value of the target object in the current period; if the target gait cycle is within the preset period threshold interval in the running state and the target acceleration extreme value is within the preset acceleration threshold interval in the running state, determining that the gait state of the target object in the current period is running; if the target gait cycle is within the preset period threshold interval in the walking state and the target acceleration extreme value is within the preset acceleration threshold interval in the walking state, determining that the gait state of the target object in the current period is walking; if the target gait cycle is within the overlapping interval of the preset period threshold interval in the running state and the preset period threshold interval in the walking state, and / or the target acceleration extreme value is within the overlapping interval of the preset acceleration threshold interval in the running state and the preset acceleration threshold interval in the walking state, determining that the gait state of the target object in the current period is the gait state before the current period.

[0012] In some embodiments, the preset period threshold interval and the preset acceleration threshold interval are obtained in advance by the following method: collecting second acceleration data of the target object in the historical period; the gait state of the target object in the historical period at least includes running or walking; according to the second acceleration data, determining the historical gait cycle of the target object in the historical period and the historical acceleration extreme values in each historical gait cycle; according to each historical gait cycle, determining the candidate gait cycle of the target object in the corresponding gait state, and based on each historical acceleration extreme value, determining the candidate acceleration extreme value of the target object in the corresponding gait state; according to the candidate gait cycles, determining the preset period threshold interval in each gait state, and according to the candidate acceleration extreme values, determining the preset acceleration threshold interval in each gait state.

[0013] The gait state recognition device provided by the embodiment of the present application includes: an acquisition module, configured to acquire first acceleration data of a target object within a current period; a determination module, configured to determine a target gait cycle of the target object within the current period and target acceleration extreme values within each target gait cycle according to the first acceleration data; an identification module, configured to identify the gait state of the target object within the current period according to the target gait cycle and a preset period threshold interval in different gait states, the target acceleration extreme values, and a preset acceleration threshold interval in different gait states; the preset period threshold interval and the preset acceleration threshold interval are pre-determined based on second acceleration data acquired by the target object in a specific gait state.

[0014] The computer device provided by the embodiment of the present application includes a memory and a processor. The memory stores a computer program that can run on the processor, and when the processor executes the program, it implements the method described in the embodiment of the present application.

[0015] The computer-readable storage medium provided by the embodiment of the present application stores a computer program thereon, and when the computer program is executed by a processor, it implements the method provided by the embodiment of the present application.

[0016] The gait state recognition method, device, computer device, and computer-readable storage medium provided by the embodiments of the present application can accurately identify the gait state of a target object, and enable the same device to be applicable to different target objects, with a wider adaptation range, thereby solving the technical problems proposed in the background art. Description of the Drawings

[0017] The drawings here are incorporated into the specification and constitute a part of this specification. These drawings show embodiments that conform to the present application and are used together with the specification to explain the technical solutions of the present application.

[0018] Figure 1 It is a schematic flowchart of the implementation of a gait state recognition method provided by the embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of an acceleration curve of a target object in a walking state provided by the embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of an acceleration curve of a target object in a running state provided by the embodiment of the present application;

[0021] Figure 4 It is a schematic flowchart of the implementation of another gait state recognition method provided by the embodiment of the present application;

[0022] Figure 5 It is a schematic diagram of an acceleration curve of a target object in a walking or running state provided by the embodiment of the present application;

[0023] Figure 6 It is a schematic structural diagram of the gait state recognition device provided by the embodiment of the present application;

[0024] Figure 7 It is a schematic structural diagram of the computer device provided by the embodiment of the present application. Detailed implementation manners

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will further describe the specific technical solutions of the present application in detail with reference to the accompanying drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application but are not intended to limit the scope of the present application.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0027] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0028] It should be noted that the terms "first / second / third" involved in the embodiments of the present application are used to distinguish similar or different objects and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0029] Before further elaborating on the embodiments of the present application, the nouns and terms involved in the embodiments of the present application are described. The nouns and terms involved in the embodiments of the present application are applicable to the following explanations.

[0030] Accelerometer: An instrument that can output acceleration values along the three axes of up / down, left / right, and front / back.

[0031] Gait cycle (GC): The process from when one heel touches the ground to when the same heel touches the ground again during walking is called a gait cycle, usually expressed in seconds (s). In each gait cycle, each lower limb experiences a process of coming into contact with the ground, bearing weight, and then leaving the ground and moving forward. Generally, the gait cycle of an adult is about 1 - 1.32 s.

[0032] An embodiment of the present application provides a gait state recognition method, which is applied to an electronic device. During implementation, the electronic device can be various types of devices with data acquisition capabilities. For example, the electronic device can be a sensor configured in a terminal device (such as a personal computer, laptop, handheld computer, server, wearable device, etc.) carried by a target object (such as a person, animal, or robot, etc.), or it can be an independent sensor device, and no limitation is made thereto. Among them, a wearable device refers to a portable device that is directly worn on the body or integrated into the user's clothes or accessories. Optionally, the wearable device can be a motion capture device, a smart bracelet, a smart watch, a head-mounted display device, and other portable electronic devices. The function implemented by this method can be realized by a processor in the electronic device calling program code. Of course, the program code can be stored in a computer storage medium. It can be seen that the electronic device at least includes a processor and a storage medium.

[0033] Figure 1 FIG. is a schematic flowchart of the implementation of the gait state recognition method provided by the embodiment of the present application, which can accurately identify the gait state of the target object and enable the same device to be applicable to different target objects, with a wider adaptation range. As Figure 1 shown, the method may include the following steps 101 to 103:

[0034] Step 101, collect first acceleration data of the target object during the current period.

[0035] In the embodiment of the present application, no limitation is made on the type of the device for collecting acceleration data. For example, acceleration data can be collected by a gyroscope or an accelerometer. Among them, if the collection is carried out in a short period of time, a gyroscope can be used for data collection. However, the characteristic of gyroscope collection is that the collected value is relatively accurate in a short period of time, but there will be errors due to data drift during long-term collection; if the collection is carried out in a long period of time, an accelerometer can be used for data collection. The characteristic of accelerometer collection is that the collected value is relatively accurate in a long period of time, but there will be errors in the collected data due to the existence of signal noise during short-term collection. In practical applications, based on the characteristics of the two collection methods, they can be selected according to different needs, or a combined collection method using both of them can be used for the collection of acceleration data.

[0036] In the embodiment of the present application, no limitation is made on the duration of the current period. For example, the first acceleration data of the target object can be collected within 10 s, or the first acceleration data of the target object can be collected within 20 s, etc. The specific collection duration can be set according to actual needs.

[0037] Step 102: Determine the gait cycle of the target object in the current period and the acceleration extreme value in each gait cycle according to the first acceleration data.

[0038] Understandably, when the target object is in motion, the acceleration data output by the accelerometer generally approximately presents a sine wave waveform. Since the sine wave has strong periodicity, in practical applications, either the minimum value (wave trough) or the maximum value (wave peak) of the acceleration data can be used as the acceleration extreme value. In a preferred embodiment, the maximum value in each period can be used as the acceleration extreme value for gait state detection.

[0039] As Figure 2 shown, a schematic diagram of the acceleration curve of the target object in the walking state is given; as Figure 3 shown, a schematic diagram of the acceleration curve of the target object in the running state is given. According to Figure 2 and Figure 3 it can be analyzed that during the movement of the target object, the acceleration generated by vertical and forward movement is approximately a sine curve with time, and there is a peak at a certain point. Among them, the acceleration change in the vertical direction is the largest. By detecting and calculating the peak value of the trajectory and making an acceleration threshold decision, the number of steps of the target object's movement can be calculated in real time, and the movement distance of the target object can be further estimated accordingly. Of course, if the acceleration data collected within a certain period of time is less than a certain value, it can be determined that the target object is not moving currently.

[0040] Based on this, in some embodiments, the multiple gait cycles of the target object in the current period and the acceleration extreme value in each gait cycle can be determined by the first acceleration data obtained in the current period.

[0041] In a feasible embodiment, the gait cycle of the target object and the target acceleration extreme value can be determined in the following way: after obtaining the first acceleration data of the current period, multiple local maximum or minimum points can be determined in the first acceleration data, and these maximum or minimum points are used as the starting or ending points of a gait cycle; the maximum or minimum value in each gait cycle is used as the acceleration extreme value in the current gait cycle.

[0042] Furthermore, in another feasible embodiment, the gait cycle of the target object and the acceleration extreme value in each gait cycle can be determined by performing steps 402 to 405 in the following embodiment.

[0043] Step 103: Identify the gait state of the target object in the current period based on the gait cycle, the preset period threshold intervals in different gait states, the acceleration extreme values, and the preset acceleration threshold intervals in different gait states. The preset period threshold intervals and the preset acceleration threshold intervals are determined in advance based on the second acceleration data collected for the target object in a specific gait state.

[0044] In the embodiments of the present application, the preset period threshold intervals and the preset acceleration threshold intervals corresponding to different target objects are different. That is to say, when different target objects use the same device for gait state recognition, the device uses the preset period threshold intervals and the preset acceleration threshold intervals applicable to the current target object to identify the gait state of the current target object. In this way, the same device can be applicable to different target objects, and the applicable range is wider.

[0045] Based on Figure 2 and Figure 3 the data analysis in, it can be seen that the acceleration data of the target object is periodic in different gait states (such as running or walking). The difference between different gait states lies in the magnitude and period of the acceleration value (if the foot frequency is different, the period is different). Taking the acceleration extreme value as the maximum value as an example, the gait cycle in the running state is shorter and the acceleration extreme value is larger; while the gait cycle in the walking state is longer and the acceleration extreme value is smaller.

[0046] Based on the above principle, in the embodiments of the present application, after determining the target gait cycle and the target acceleration extreme value of the target object based on the first acceleration data obtained in the current period, compare them with the preset period threshold intervals and the preset acceleration threshold intervals of the target object set in advance to determine which gait state the target object is in during the current period.

[0047] It should be noted that the method for determining the preset period threshold intervals and the preset acceleration threshold intervals for the same target object can be the same as the method for determining the gait cycle and the acceleration extreme value of the target object. For example, the method in steps 402 to 405 in the following embodiments can be used to determine the preset period and the preset acceleration extreme value, and then the preset period threshold intervals and the preset acceleration threshold intervals are determined based on the preset period and the preset acceleration extreme value; it can also be determined in any combination manner, and the embodiments of the present application do not limit this.

[0048] For example, if the acquisition device does not have the function of automatically correcting parameters, the target object can estimate them by itself. Specifically: when the target object is in motion, it generally alternates between different gait states. For example, after running for a period of time, it walks for a period of time. Based on this, when the target object initially uses the acquisition device, it can analyze the second acceleration data in the historical period collected by the acquisition device by itself, and classify a segment of the second acceleration data whose difference between the differences of multiple gait cycles and acceleration extreme values is less than a specific range into one category. In this way, at least two categories of second acceleration data can be obtained. The data with a larger acceleration extreme value and a smaller gait cycle is determined as the running state, and the data with a smaller acceleration extreme value and a larger gait cycle is determined as the walking state; then, the data of each category is analyzed subsequently to obtain a preset period threshold interval and a preset acceleration threshold interval, and they are applied to the subsequent motion of the target object.

[0049] For another example, in some embodiments, the preset period threshold interval and the preset acceleration threshold interval of the target object can be determined by performing the following steps 1031 to 1034:

[0050] Step 1031: Collect the second acceleration data of the target object in the historical period; the gait state of the target object in the historical period includes at least running or walking.

[0051] It can be understood that if, for different target objects, the corresponding gait states are determined based on the same preset period threshold interval and preset acceleration threshold interval, there may be a situation where the movement paces and movement frequencies of different target objects are different, thus causing inaccurate recognition. For example, if an adult and a child use the same device together, their gait cycles and acceleration extreme values during motion are generally different. Therefore, if the same threshold is still used for recognition, it is easy to cause misrecognition, such as recognizing the running posture of a child as a walking posture, or recognizing the walking posture of an adult as a running posture, etc.

[0052] In the embodiments of the present application, the manner of triggering the collection of the second acceleration data of the target object in the historical period is not limited. For example, in some embodiments, it can be actively triggered by the target object for collection; in other embodiments, if the device detects that the user has been changed, when the target object initially uses the device, the device can actively remind the target object to correct each threshold interval.

[0053] For example, a calibration reminder "Do you want to start calibration?" is displayed on the device. If the target object clicks "Yes", then exercise prompts such as "Get ready to run" or "Get ready to walk" are displayed again to remind the target object to start exercising in a running gait or a walking gait, and the second acceleration data of the target object within a historical period is recorded. Herein, the duration of the historical period is not limited. For example, it can be 10 s, and it only needs to ensure that multiple cycles are included within the historical period to make it predictively representative.

[0054] Step 1032: Determine the historical gait cycles of the target object within the historical period and the historical acceleration extreme values within each historical gait cycle according to the second acceleration data.

[0055] After the obtained second acceleration data, the historical gait cycles of the target object within the historical period and the historical acceleration extreme values within each historical gait cycle can be determined according to the method of determining each gait cycle and the acceleration extreme value within each gait cycle based on the first acceleration data provided in step 102.

[0056] Step 1033: Determine the candidate gait cycles of the target object in the corresponding gait states according to each historical gait cycle, and determine the candidate acceleration extreme values of the target object in the corresponding gait states based on each historical acceleration extreme value.

[0057] Step 1034: Determine the preset cycle threshold intervals in each gait state according to the candidate gait cycles, and determine the preset acceleration threshold intervals in each gait state according to the candidate acceleration extreme values.

[0058] In the embodiments of the present application, the methods for determining the candidate gait cycles according to each historical gait cycle and determining the candidate acceleration extreme values according to each historical acceleration extreme value are not limited. For example, the mean value of each historical gait cycle can be taken to obtain the candidate gait cycle; the intermediate value of each historical gait cycle can be taken and used as the candidate gait cycle; the mode of each historical gait cycle can be taken and used as the candidate gait cycle, and so on.

[0059] In the embodiments of the present application, the gait states are not limited, such as running, walking, cycling mode, etc.

[0060] Specifically, taking the current gait as running as an example, after determining each historical gait cycle of the target object in the running gait, the average value can be taken for multiple historical gait cycles to obtain a candidate gait cycle in the running gait; subsequently, based on the candidate gait cycle, the upper and lower threshold intervals are determined, so as to obtain the preset cycle threshold interval of the target object in the running gait. For example, if the determined candidate gait cycle is RefTime1, accordingly, the upper limit of the preset acceleration threshold interval is set to 0.8RefTime1, and the lower limit of the preset acceleration threshold interval is set to 1.2RefTime1, then the preset cycle threshold interval is [0.8RefTime1, 1.2RefTime1].

[0061] Similarly, after determining the historical acceleration extreme values in each historical gait cycle of the target object in the running gait, the average value can be taken for multiple historical acceleration extreme values to obtain a candidate acceleration extreme value in the running gait; subsequently, based on the candidate acceleration extreme value, the upper and lower threshold intervals are determined, so as to obtain the preset acceleration threshold interval of the target object in the running gait. For example, if the determined candidate acceleration extreme value is RefMax1, accordingly, the upper limit of the preset cycle threshold interval is set to 0.8RefMax1, and the lower limit of the preset acceleration threshold interval is set to 1.2RefMax1, then the preset acceleration threshold interval is [0.8RefMax1, 1.2RefMax1].

[0062] Similarly, if the device reminds the target object that it is currently moving in the walking gait, the corresponding preset cycle threshold interval and preset acceleration threshold interval of the target object in the walking gait can also be determined based on the above method. That is, the determined preset cycle threshold interval in the walking gait is [0.8RefTime2, 1.2RefTime2], and the preset acceleration threshold interval is [0.8RefMax2, 1.2RefMax2].

[0063] It can be seen that the preset cycle threshold interval and the preset acceleration threshold interval in the above embodiments are determined before the target object actually uses the device for collecting acceleration data.

[0064] Based on this, in some other embodiments, when the target object actually uses the device for collecting acceleration data, the cycle threshold interval and the acceleration threshold interval suitable for the current target object can be adaptively adjusted based on the second acceleration data obtained by the target object within a period of time during the use process by using the computing unit in the device.

[0065] In some embodiments, the gait state at least includes running or walking; after determining the gait cycle of the target object in the current period and the acceleration extreme value in each gait cycle, the gait state of the target object in the current period can be determined based on the following method:

[0066] Based on each gait cycle, determine the target gait cycle of the target object in the current period; and based on each acceleration extreme value, determine the target acceleration extreme value of the target object in the current period.

[0067] Here, there is no limitation on the method for determining the target gait cycle and the target acceleration extreme value. For example, the average value of each gait cycle or acceleration extreme value can be taken to obtain the corresponding target gait cycle and target acceleration extreme value; the median value of each gait cycle or acceleration extreme value can also be taken and used as the corresponding target gait cycle and target acceleration extreme value; the mode of each gait cycle or acceleration extreme value can also be taken and used as the corresponding target gait cycle and target acceleration extreme value.

[0068] If the target gait cycle is within the preset cycle threshold interval in the running state, and the target acceleration extreme value is within the preset acceleration threshold interval in the running state, determine that the gait state of the target object in the current period is running.

[0069] For example, if the target gait cycle of the target object in the current period is between [0.8RefTime1, 1.2RefTime1], and the target acceleration extreme value of the target object in the current period is between [0.8RefMax1, 1.2RefMax1], then determine that the gait state of the target object in the current period is running.

[0070] If the target gait cycle is within the preset cycle threshold interval in the walking state, and the target acceleration extreme value is within the preset acceleration threshold interval in the walking state, determine that the gait state of the target object in the current period is walking.

[0071] For example, if the target gait cycle of the target object in the current period is between [0.8RefTime2, 1.2RefTime2], and the target acceleration extreme value of the target object in the current period is between [0.8RefMax2, 1.2RefMax2], then determine that the gait state of the target object in the current period is running.

[0072] If the target gait cycle is within the overlapping interval of the preset cycle threshold intervals in the running state and the walking state, and / or the target acceleration extreme value is within the overlapping interval of the preset acceleration threshold intervals in the running state and the walking state, determine that the gait state of the target object in the current period is the gait state before the current period.

[0073] For example, if the target gait cycle of the target object within the current period is within the overlapping region of [0.8RefTime1, 1.2RefTime1] and [0.8RefTime2, 1.2RefTime2], or the target acceleration extreme value of the target object within the current period is within the overlapping region of [0.8RefMax1, 1.2RefMax1] and [0.8RefMax2, 1.2RefMax2], then maintain the judgment result before the current period, that is, if it is determined that the gait of the target object is running before the current period, continue to determine that the target object is also running in the current period; if it is determined that the gait of the target object is walking before the current period, continue to determine that the target object is also walking in the current period.

[0074] In the embodiments of the present application, by analyzing the gait cycle and acceleration extreme value of the target object within the current period and comparing them with the preset cycle threshold intervals and acceleration threshold intervals under different gait states, the gait state of the target object within the current period can be accurately determined; and the preset cycle threshold intervals and preset acceleration threshold intervals corresponding to different target objects are different, enabling the same device to be applicable to different target objects and having a wider adaptation range.

[0075] The embodiments of the present application further provide a gait state recognition method. Figure 4 It is a schematic flowchart of the implementation process of the gait state recognition method in the embodiments of the present application, as Figure 4 shown, the method may include the following steps 401 to step 406:

[0076] Step 401, collect the first acceleration data of the target object within the current period.

[0077] Step 402, determine the standard acceleration extreme value in the first acceleration data of the current period.

[0078] In the embodiments of the present application, the method for determining the standard acceleration extreme value in the first acceleration data is not limited. For example, the maximum value in the first acceleration data may be determined as the standard acceleration extreme value, or the minimum value in the first acceleration data may be determined as the standard acceleration extreme value; it is also possible to determine the maximum value or minimum value within a selected period of time as the standard acceleration extreme value, etc.

[0079] Among them, the so-called maximum or minimum value refers to the maximum or minimum value in a whole piece of data; the so-called extreme value refers to the maximum or minimum value within a local range, that is, from the perspective of the overall data, there may be other values greater than or less than this extreme value point.

[0080] Step 403: In the first acceleration data, filter out the data other than the standard acceleration extreme value within the first time period centered on the time when the standard acceleration extreme value is located, to obtain the first target acceleration data.

[0081] It can be understood that both running and walking are periodic. As Figure 5 shown, the period between points A and B is a gait cycle. It is necessary to accurately find points A and B in each cycle in the collected first acceleration data, that is, to find the local extreme points. However, when collecting the first acceleration data, it will be affected by various interferences, resulting in the collected first acceleration data not being smooth. It may be serrated, so that a gait cycle may include multiple extreme points, which will lead to errors in determining each gait cycle.

[0082] In view of this, in the embodiment of the present application, after the first acceleration data in the current time period is collected, first find the maximum value or the minimum value from the first acceleration data as the standard acceleration extreme value; then, with the time when the standard acceleration extreme value is located as the center, set the first time period range, and filter out other data in the first time period range that is relatively close to the standard acceleration extreme value, to obtain the first target acceleration data.

[0083] In some embodiments, the method for determining the first time period is as follows: based on the standard acceleration extreme value, determine the target acceleration threshold; wherein, when the standard acceleration extreme value is the maximum acceleration value in the first acceleration data, the acceleration data within the first time period range is the time-sequential continuous data that is all greater than the target acceleration threshold; when the standard acceleration extreme value is the minimum acceleration value in the first acceleration data, the acceleration data within the first time period range is the time-sequential continuous data that is all less than the target acceleration threshold.

[0084] When determining the target acceleration threshold based on the standard acceleration extreme value, it can be determined by setting the proportionality coefficient ScaleFactor0 corresponding to the standard acceleration extreme value. For example, the proportionality coefficient is set to 0.8, or the proportionality coefficient is set to 0.9. The setting of the proportionality coefficient can be determined based on multiple experiments.

[0085] In a specific embodiment, taking the extreme point as the maximum value as an example, a maximum value point can be determined in the current time period TimeTry, and it is used as the standard acceleration extreme value P0. The time when P0 is located is T0, and the corresponding acceleration value is V0; P0 is used as an acceleration extreme value point in the acceleration extreme value set. To avoid misidentifying the data relatively similar to this point around P0 as the local maximum value and further misidentifying it as the next acceleration extreme value, the range parameter of the first time period can be set to TimeDrop, such as 200 ms, and filter out the similar data within the range of TimeDrop before and after the P0 point, so as to obtain the first target acceleration data.

[0086] In some embodiments, before finding the standard acceleration extreme value, the first acceleration data may also be compared with a preset minimum threshold. If all the first acceleration data are less than the minimum threshold, it indicates that the target object is not moving during the current period, and thus the first acceleration data collected during the current period does not need to be processed. In this way, only processing the data with acceleration values greater than the minimum threshold can improve the processing efficiency and reduce misjudgment.

[0087] Step 404, determine an acceleration extreme value set in the first target acceleration data; the acceleration extreme value set includes the standard acceleration extreme value.

[0088] In the embodiments of the present application, there is no limitation on the method for determining the acceleration extreme value set.

[0089] For example, in some embodiments, the acceleration extreme value set can be determined by performing the following steps 4041 to 4044:

[0090] Step 4041, in the first target acceleration data, determine the first acceleration extreme value that is closest to the moment when the standard acceleration extreme value is located. When the standard acceleration extreme value is the maximum acceleration value in the first acceleration data, the first acceleration extreme value is the data greater than the target acceleration threshold. When the standard acceleration extreme value is the minimum acceleration value in the first acceleration data, the first acceleration extreme value is the data less than the target acceleration threshold.

[0091] After determining the standard acceleration extreme value, based on the moment when the standard acceleration extreme value is located, forward search and backward search can be performed in the first target acceleration data to determine the numerical point that meets the requirements and is closest to the moment when the standard acceleration extreme value is located as the first acceleration extreme value.

[0092] Step 4042, in the first target acceleration data, filter out the data other than the first acceleration extreme value within the first time period centered on the moment when the first acceleration extreme value is located to obtain the second target acceleration data.

[0093] After obtaining at least one first acceleration extreme value, then centered on the moment when the first acceleration extreme value is located, based on the same processing method as the standard acceleration extreme value, filter out the data other than the first acceleration extreme value within the first time period centered on the moment when the first acceleration extreme value is located, so as to obtain the second target acceleration data. In this way, the interference of the data points with similar values around each extreme value point can be avoided, and the determination accuracy of the gait cycle can be improved.

[0094] Step 4043, in the second target acceleration data, determine the second acceleration extreme value that is closest to the moment when the first acceleration extreme value is located.

[0095] Based on the same processing method as in step 4041, find the second acceleration extreme value in the second target acceleration data.

[0096] Step 4044. Continue to execute the step of determining the third acceleration extreme value that is closest to the moment when the second acceleration extreme value is located based on the second acceleration extreme value until the first acceleration data is traversed completely, and an acceleration extreme value set including multiple acceleration extreme values is obtained.

[0097] After the traversal of the first acceleration data is completed, the obtained acceleration extreme value set is the respective maximum extreme points or minimum extreme points. For example, Figure 5 points A and B shown in. These extreme points can be used as the basis for gait cycle division. The number of extreme points is the number of gait cycles, and the time difference between each extreme point is the corresponding gait cycle.

[0098] Also, in some other embodiments, after the first acceleration data of the current period is collected, the acceleration extreme value set can be obtained in the following manner: First, find the standard acceleration extreme value in the first acceleration data of the current period; then, based on the standard acceleration extreme value, determine the target acceleration threshold; based on the target acceleration threshold, find the numerical points in the first acceleration data that are greater than the target acceleration threshold and the time difference is within the first range, and obtain multiple subsets each including multiple numerical points with values greater than the target acceleration threshold; then, determine the unique extreme point in each subset from each subset respectively, and obtain an acceleration extreme value set including multiple acceleration extreme values. Among them, the method for determining the unique extreme point in each subset is not limited. For example, the point with the earliest time sequence can be determined as the extreme point, or the point with the latest time sequence can be determined as the extreme point, or the point with the middle time sequence can be determined as the extreme point, etc.

[0099] In some embodiments, if no valid next acceleration extreme point is found when searching for the next acceleration extreme point based on the previous acceleration extreme point and the target acceleration threshold, it indicates that the current motion state of the target object may have changed, that is, the first acceleration data includes at least two motion states. At this time, the judgment is no longer based on the foregoing rules, but a new gait cycle can be established again from the last acceleration extreme point according to the above method.

[0100] Step 405. Based on the acceleration extreme value set, determine the gait cycle of the target object in the current period and the acceleration extreme value in each gait cycle.

[0101] In some embodiments, the gait cycle and the acceleration extreme values can be determined in the following manner: based on the time differences between two adjacent acceleration extreme values in the set of acceleration extreme values in time sequence, multiple gait cycles of the target object in the current period are determined, and two adjacent acceleration extreme values in time sequence are determined as the acceleration extreme values within each corresponding gait cycle.

[0102] Step 406: Based on the gait cycle, the preset cycle threshold intervals in different gait states, the acceleration extreme values, and the preset acceleration threshold intervals in different gait states, identify the gait state of the target object in the current period.

[0103] After obtaining multiple gait cycles and the acceleration extreme values within each gait cycle, the target gait cycle of the target object in the current period can be determined based on each gait cycle; and the target acceleration extreme value of the target object in the current period can be determined based on each acceleration extreme value. Herein, there is no limitation on the manner of determining the target gait cycle and the target acceleration extreme value. For example, the average value of each gait cycle or acceleration extreme value can be taken to obtain the corresponding target gait cycle and target acceleration extreme value; the median value of each gait cycle or acceleration extreme value can also be taken and used as the corresponding target gait cycle and target acceleration extreme value; or the mode of each gait cycle or acceleration extreme value can be taken and used as the corresponding target gait cycle and target acceleration extreme value.

[0104] After obtaining the target gait cycle and the target acceleration threshold of the target object in the current period, it can be determined which preset cycle threshold interval and preset acceleration threshold interval corresponding to which gait state the target gait cycle and the target acceleration threshold respectively conform to, and then the gait state of the target object in the current period can be determined.

[0105] Here, the manner of determining the gait state of the target object in the current period is the same as that in step 103 and will not be elaborated herein.

[0106] It should be understood that although Figure 1 and Figure 4 the steps in the flowcharts of Figure 1 and Figure 4 are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover,

[0107] Based on the foregoing embodiments, an embodiment of the present application provides a gait state recognition device, which includes each module included therein, as well as each unit included in each module, and can be implemented by a processor; of course, it can also be implemented by specific logic circuits; during implementation, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0108] Figure 6 It is a schematic structural diagram of the gait state recognition device provided by the embodiment of the present application, as Figure 6 shown, the device 600 includes an acquisition module 601, a determination module 602, and an identification module 603, where: the acquisition module is used to acquire first acceleration data of a target object during a current period; the determination module is used to determine a target gait cycle of the target object during the current period and target acceleration extreme values in each target gait cycle according to the first acceleration data; the identification module is used to identify the gait state of the target object during the current period according to the target gait cycle and a preset period threshold interval in different gait states, the target acceleration extreme values, and a preset acceleration threshold interval in different gait states; the preset period threshold interval and the preset acceleration threshold interval are pre-determined based on second acceleration data collected by the target object in a specific gait state.

[0109] In some embodiments, the device further includes a filtering module, and the determination module is further used to determine a standard acceleration extreme value in the first acceleration data of the current period, where the standard acceleration extreme value is the maximum or minimum value of the acceleration in the first acceleration data; the filtering module is used to filter data other than the standard acceleration extreme value within a first time period range centered on the moment when the standard acceleration extreme value is located in the first acceleration data to obtain first target acceleration data; the determination module is further used to determine an acceleration extreme value set in the first target acceleration data; the acceleration extreme value set includes the standard acceleration extreme value; based on the acceleration extreme value set, the gait cycle of the target object during the current period and the acceleration extreme values in each gait cycle are determined.

[0110] In some embodiments, the determination module is further used to determine a target acceleration threshold based on the standard acceleration extreme value; where, when the standard acceleration extreme value is the maximum value of the acceleration in the first acceleration data, the acceleration data within the first time period range is time-sequentially continuous data that is all greater than the target acceleration threshold; when the standard acceleration extreme value is the minimum value of the acceleration in the first acceleration data, the acceleration data within the first time period range is time-sequentially continuous data that is all less than the target acceleration threshold.

[0111] In some embodiments, the determining module is further configured to determine, in the first target acceleration data, a first acceleration extreme value that is closest in time to the time at which the standard acceleration extreme value occurs. When the standard acceleration extreme value is the maximum acceleration value in the first acceleration data, the first acceleration extreme value is a data greater than the target acceleration threshold. When the standard acceleration extreme value is the minimum acceleration value in the first acceleration data, the first acceleration extreme value is a data less than the target acceleration threshold. In the first target acceleration data, filter out the data other than the first acceleration extreme value within the first time period centered on the time at which the first acceleration extreme value occurs, to obtain second target acceleration data. In the second target acceleration data, determine a second acceleration extreme value that is closest in time to the time at which the first acceleration extreme value occurs. Continue to perform the step of determining a third acceleration extreme value that is closest in time to the time at which the second acceleration extreme value occurs based on the second acceleration extreme value, until the first target acceleration data is traversed, to obtain an acceleration extreme value set including a plurality of acceleration extreme values.

[0112] In some embodiments, the determining module is further configured to determine, according to the time differences between two adjacent acceleration extreme values in time sequence in the acceleration extreme value set, a plurality of gait cycles of the target object within the current time period, and determine two adjacent acceleration extreme values in time sequence as the acceleration extreme values within each corresponding gait cycle.

[0113] In some embodiments, the apparatus further includes a judging module. The determining module is further configured to determine, based on each gait cycle, the target gait cycle of the target object within the current time period; and determine, based on each acceleration extreme value, the target acceleration extreme value of the target object within the current time period. The judging module is configured to determine that the gait state of the target object within the current time period is running if the target gait cycle is within the preset cycle threshold interval in the running state and the target acceleration extreme value is within the preset acceleration threshold interval in the running state; determine that the gait state of the target object within the current time period is walking if the target gait cycle is within the preset cycle threshold interval in the walking state and the target acceleration extreme value is within the preset acceleration threshold interval in the walking state; and determine that the gait state of the target object within the current time period is the gait state before the current time period if the target gait cycle is within the overlapping interval of the preset cycle threshold interval in the running state and the preset cycle threshold interval in the walking state, and / or the target acceleration extreme value is within the overlapping interval of the preset acceleration threshold interval in the running state and the preset acceleration threshold interval in the walking state.

[0114] In some embodiments, the acquisition module is further configured to acquire second acceleration data of the target object within a historical period; the gait state of the target object within the historical period includes at least running or walking; the determination module is further configured to determine, according to the second acceleration data, the historical gait cycle of the target object within the historical period and the historical acceleration extreme value within each historical gait cycle; determine, according to each historical gait cycle, the candidate gait cycle of the target object in the corresponding gait state, and determine, based on each historical acceleration extreme value, the candidate acceleration extreme value of the target object in the corresponding gait state; determine the preset cycle threshold interval in each gait state according to the candidate gait cycle, and determine the preset acceleration threshold interval in each gait state according to the candidate acceleration extreme value.

[0115] In the embodiments of the present application, by analyzing the gait cycle and acceleration extreme value of the target object within the current period and comparing them with the preset cycle threshold interval and acceleration threshold interval under different gait states, the gait state of the target object within the current period can be accurately determined; and the preset cycle threshold interval and preset acceleration threshold interval corresponding to different target objects are different, enabling the same device to be applicable to different target objects and having a wider adaptation range.

[0116] The description of the above device embodiments is similar to that of the above method embodiments and has similar beneficial effects to those of the method embodiments. For the technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0117] It should be noted that in the embodiments of the present application Figure 6 The division of the gait state recognition device into modules shown is illustrative, merely a logical function division, and there may be other division methods in actual implementation. In addition, each functional unit in the various embodiments of the present application may be integrated in a processing unit, may exist physically alone, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware, or in the form of a software functional unit, or in the form of a combination of software and hardware.

[0118] It should be noted that in the embodiments of the present application, if the above method is implemented in the form of software function modules and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present application, in essence or the part that contributes to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), magnetic disks, or optical discs that can store program codes. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0119] The embodiments of the present application provide a computer device, which may be a server, and its internal structural diagram may be as Figure 7 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a gait state recognition method.

[0120] The embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in the method provided in the above embodiments.

[0121] The embodiments of the present application provide a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the steps in the method provided in the above method embodiments.

[0122] Those skilled in the art can understand that Figure 7 the structure shown in

[0123] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. Figure 7It runs on the computer device shown. In the memory of the computer device, each program module that makes up the sampling device can be stored. For example, Figure 6 the acquisition module, the determination module, and the recognition module shown. The computer program composed of each program module enables the processor to execute the steps in the gait state recognition method of each embodiment of the present application described in this specification.

[0124] It should be noted here that the descriptions of the above storage medium and device embodiments are similar to the descriptions of the above method embodiments and have beneficial effects similar to those of the method embodiments. For the technical details not disclosed in the storage medium, storage medium, and device embodiments of the present application, please refer to the descriptions of the method embodiments of the present application for understanding.

[0125] It should be understood that the "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures, or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the "in one embodiment" or "in an embodiment" or "in some embodiments" that appear throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The sequence numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments. The above descriptions of each embodiment tend to emphasize the differences between the embodiments, and their similarities can be referred to each other. For the sake of brevity, they will not be elaborated here.

[0126] The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, object A and / or object B can represent: object A exists alone, object A and object B exist simultaneously, and object B exists alone.

[0127] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the element.

[0128] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0129] The modules described above as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules. They can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0130] In addition, in each embodiment of the present application, all the functional modules can be integrated in a processing unit, or each module can be separately used as a unit, or two or more modules can be integrated in a unit. The above integrated modules can be implemented in the form of hardware or in the form of a combination of hardware and software functional units.

[0131] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), magnetic disks, or optical discs.

[0132] Alternatively, if the above integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the related technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable an electronic device to execute all or part of the methods described in various embodiments of the present application. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, ROM, magnetic disks, or optical discs.

[0133] The methods disclosed in several method embodiments provided by the present application can be arbitrarily combined without conflict to obtain new method embodiments.

[0134] The features disclosed in several product embodiments provided by this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0135] The features disclosed in several method or device embodiments provided by this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0136] As mentioned above, it is only the implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A gait state recognition method, characterized in that, the method includes: collecting first acceleration data of a target object within a current period; determining, according to the first acceleration data, a gait cycle of the target object within the current period and acceleration extreme values within each gait cycle, wherein the first acceleration data includes a plurality of gait cycles; recognizing a gait state of the target object within the current period according to the gait cycle and a preset period threshold interval in different gait states, the acceleration extreme values, and a preset acceleration threshold interval in different gait states; the preset period threshold interval and the preset acceleration threshold interval are pre-determined based on second acceleration data collected by the target object in a specific gait state; wherein, the determining, according to the first acceleration data, a gait cycle of the target object within the current period and acceleration extreme values within each gait cycle includes: determining a standard acceleration extreme value in the first acceleration data of the current period, the standard acceleration extreme value being the maximum or minimum value of the acceleration in the first acceleration data; filtering data other than the standard acceleration extreme value within a first period range centered on the moment where the standard acceleration extreme value is located in the first acceleration data to obtain first target acceleration data; determining an acceleration extreme value set in the first target acceleration data; the acceleration extreme value set includes the standard acceleration extreme value; the acceleration extreme value set includes a plurality of acceleration extreme values, the plurality of acceleration extreme values are obtained by traversing the first acceleration data, the plurality of acceleration extreme values include a first acceleration extreme value; the first acceleration extreme value is the acceleration extreme value closest to the moment where the standard acceleration extreme value is located in the first target acceleration data, when the standard acceleration extreme value is the maximum value of the acceleration in the first acceleration data, the first acceleration extreme value is data greater than a target acceleration threshold, when the standard acceleration extreme value is the minimum value of the acceleration in the first acceleration data, the first acceleration extreme value is data less than the target acceleration threshold; the target acceleration threshold is determined according to the standard acceleration extreme value; determining, based on the acceleration extreme value set, a gait cycle of the target object within the current period and acceleration extreme values within each gait cycle.

2. The method according to claim 1, characterized in that, the method further includes: determining a target acceleration threshold based on the standard acceleration extreme value; wherein, when the standard acceleration extreme value is the maximum value of the acceleration in the first acceleration data, the acceleration data within the first period range is sequentially continuous data all greater than the target acceleration threshold; when the standard acceleration extreme value is the minimum value of the acceleration in the first acceleration data, the acceleration data within the first period range is sequentially continuous data all less than the target acceleration threshold.

3. The method according to claim 2, characterized in that, the determining an acceleration extreme value set in the first target acceleration data includes: In the first target acceleration data, filter out the data other than the first acceleration extreme value within the first time period centered on the moment when the first acceleration extreme value is located, to obtain second target acceleration data; In the second target acceleration data, determine a second acceleration extreme value that is closest in time to the moment when the first acceleration extreme value is located; Continue to execute the step of determining a third acceleration extreme value that is closest in time to the moment when the second acceleration extreme value is located based on the second acceleration extreme value, until the first acceleration data is traversed, to obtain the acceleration extreme value set including multiple acceleration extreme values.

4. The method according to claim 3, wherein, the determining the gait cycle of the target object within the current time period and the acceleration extreme value within each gait cycle based on the acceleration extreme value set includes: Determine multiple gait cycles of the target object within the current time period according to the time difference between two adjacent acceleration extreme values in time sequence in the acceleration extreme value set, and determine two adjacent acceleration extreme values in time sequence as the acceleration extreme values within each corresponding gait cycle.

5. The method according to claim 1, wherein, the gait state at least includes running or walking; the identifying the gait state of the target object within the current time period according to the gait cycle and the preset cycle threshold interval in different gait states, the acceleration extreme value and the preset acceleration threshold interval in different gait states includes: Based on each gait cycle, determine the target gait cycle of the target object within the current time period; and based on each acceleration extreme value, determine the target acceleration extreme value of the target object within the current time period; If the target gait cycle is within the preset cycle threshold interval in the running state, and the target acceleration extreme value is within the preset acceleration threshold interval in the running state, determine that the gait state of the target object within the current time period is running; If the target gait cycle is within the preset cycle threshold interval in the walking state, and the target acceleration extreme value is within the preset acceleration threshold interval in the walking state, determine that the gait state of the target object within the current time period is walking; If the target gait cycle is within the overlapping interval of the preset cycle threshold interval in the running state and the preset cycle threshold interval in the walking state, and / or the target acceleration extreme value is within the overlapping interval of the preset acceleration threshold interval in the running state and the preset acceleration threshold interval in the walking state, determine that the gait state of the target object within the current time period is the gait state before the current time period.

6. The method according to any one of claims 1 to 5, wherein, the preset cycle threshold interval and the preset acceleration threshold interval are obtained in advance by the following method: Collect second acceleration data of the target object within a historical time period; the gait state of the target object within the historical time period at least includes running or walking; Determine the historical gait cycle of the target object within the historical period and the historical acceleration extreme value within each historical gait cycle according to the second acceleration data; Determine the candidate gait cycle of the target object in the corresponding gait state according to each historical gait cycle, and determine the candidate acceleration extreme value of the target object in the corresponding gait state based on each historical acceleration extreme value; Determine the preset cycle threshold interval in each gait state according to the candidate gait cycle, and determine the preset acceleration threshold interval in each gait state according to the candidate acceleration extreme value.

7. A gait state recognition device, characterized in that, it includes: An acquisition module for acquiring first acceleration data of a target object within a current period; A determination module for determining the target gait cycle of the target object within the current period and the target acceleration extreme value within each target gait cycle according to the first acceleration data, where the first acceleration data includes multiple gait cycles; An identification module for identifying the gait state of the target object in the current period according to the target gait cycle and the preset cycle threshold interval in different gait states, the target acceleration extreme value and the preset acceleration threshold interval in different gait states; the preset cycle threshold interval and the preset acceleration threshold interval are pre-determined based on second acceleration data collected by the target object in a specific gait state; wherein, the determination module is specifically used for: Determine the standard acceleration extreme value in the first acceleration data of the current period, and the standard acceleration extreme value is the maximum or minimum value of the acceleration in the first acceleration data; In the first acceleration data, filter out the data other than the standard acceleration extreme value within the first time period centered on the moment where the standard acceleration extreme value is located, to obtain first target acceleration data; Determine an acceleration extreme value set in the first target acceleration data; the acceleration extreme value set includes the standard acceleration extreme value; the acceleration extreme value set includes multiple acceleration extreme values, and the multiple acceleration extreme values are obtained by traversing the first acceleration data, and the multiple acceleration extreme values include a first acceleration extreme value; the first acceleration extreme value is the acceleration extreme value closest to the moment where the standard acceleration extreme value is located in the first target acceleration data. When the standard acceleration extreme value is the maximum value of the acceleration in the first acceleration data, the first acceleration extreme value is data greater than the target acceleration threshold. When the standard acceleration extreme value is the minimum value of the acceleration in the first acceleration data, the first acceleration extreme value is data less than the target acceleration threshold; the target acceleration threshold is determined according to the standard acceleration extreme value; Based on the acceleration extreme value set, determine the gait cycle of the target object within the current period and the acceleration extreme value within each gait cycle.

8. A computer device, including a memory and a processor, where the memory stores a computer program that can run on the processor, characterized in that, When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images