Watch wearing tightness detection method and device

Abstract

The invention provides a watch wearing tightness detection method and device, and relates to the field of sports health monitoring. The method comprises the following steps: collecting current motion data of a target watch worn by a user in real time through a six-axis acceleration gyroscope sensor, wherein the current motion data comprises acceleration data and angular velocity data; acquiring motion features corresponding to the current motion data, wherein the motion features are time sequence features corresponding to the acceleration data and the angular velocity data respectively; judging the wearing state of the target watch according to the time sequence characteristics through a motion data dynamic analysis model; if it is confirmed that the wearing state is the loose wearing state, preset prompt information is sent to the user, and the preset prompt information is used for prompting the user to adjust the wearing state from the loose wearing state to the tight wearing state. According to the method and the device, the problem that the heart rate measurement precision is affected due to the fact that an existing watch wearing tightness detection mode often lacks real-time detection capability and cannot feed back the wearing tightness change in time is solved.

Description

Technical Field

[0001] The present application relates to the field of sports health monitoring, and in particular to a method and device for detecting the tightness of a watch. Background Art

[0002] Current methods for determining whether a watch is worn tight or loose rely primarily on the user's subjective judgment or simple physical sensor data.

[0003] Subjective judgment relies on the user's personal feelings and habits, which is prone to errors and cannot accurately reflect the actual wearing situation; traditional methods mostly rely on a single sensor (such as a pressure sensor), which has single data and cannot fully capture the movement state of the watch and the changes in the tightness of wearing. Therefore, the existing watch tightness inspection methods often lack real-time detection capabilities and cannot timely feedback the changes in the tightness of wearing, resulting in the accuracy of heart rate measurement being affected.

[0004] Therefore, there is an urgent need for a method and device for detecting the tightness of a watch. Summary of the invention

[0005] The present application provides a method and device for detecting the tightness of a watch, which solves the problem that the existing method for checking the tightness of a watch often lacks real-time detection capability and cannot promptly feedback changes in the tightness of the watch, thereby affecting the accuracy of heart rate measurement.

[0006] In a first aspect of the present application, a method for detecting the tightness of a watch is provided, the method comprising: collecting current motion data of a user wearing a target watch in real time through a six-axis acceleration-gyroscope sensor, the current motion data including acceleration data and angular velocity data; obtaining motion features corresponding to the current motion data, the motion features being time series features corresponding to the acceleration data and the angular velocity data respectively; judging the wearing state of the target watch according to the time series features through a motion data dynamic analysis model; if it is confirmed that the wearing state is a loose wearing state, sending a preset prompt message to the user, the preset prompt message being used to prompt the user to adjust the wearing state from a loose wearing state to a tight wearing state.

[0007] Optionally, before obtaining the motion features corresponding to the current motion data, a preprocessing operation is performed on the current motion data, specifically including: obtaining first current motion data and second current motion data, the first current motion data and the second current motion data being any two groups of adjacent motion data in the current motion data; obtaining a fluctuation change value between the first current motion data and the second current motion data; determining whether the fluctuation change value is less than a preset fluctuation value; if the fluctuation change value is less than the preset fluctuation value, determining that there is no abnormal data in the current motion data, and completing the preprocessing operation.

[0008] Optionally, before collecting the current motion data of the user wearing the target watch in real time through the six-axis acceleration gyroscope sensor, the method also includes: obtaining static data, the static data includes first static data and second static data, the first static data and the second static data are any two adjacent groups of data in the static data; obtaining the fluctuation change value between the first static data and the second static data; judging whether the fluctuation change value is less than a preset fluctuation value; if the fluctuation change value is less than the preset fluctuation value, confirming that the static data is stable static data, and collecting the current motion data in real time through the six-axis acceleration gyroscope sensor.

[0009] Optionally, the wearing state of the target watch is determined according to the time series characteristics through a dynamic analysis model of motion data, specifically including: calculating a looseness / tightness state threshold according to historical motion data; calculating a looseness / tightness state characteristic value according to the time series characteristics; determining whether the looseness / tightness state threshold is greater than or equal to the looseness / tightness state characteristic value; if the looseness / tightness state threshold is greater than or equal to the looseness / tightness state characteristic value, confirming that the wearing state is a tight wearing state; if the looseness / tightness state threshold is less than the looseness / tightness state characteristic value, confirming that the wearing state is a loose wearing state.

[0010] Optionally, calculating the tightness state threshold according to the historical motion data specifically includes: calculating the tightness state threshold by the following formula:

[0011]

[0012] in, is the tightness threshold, c is the weight factor, and c>1, w is the size of the moving window, X i is the i-th time series feature, X i-w+j is the i-w+jth time series feature, NOC represents the tight wearing state, ζ j represents weighting the product of fixed probability thresholds.

[0013] Optionally, according to the time series characteristics, calculating the looseness and tightness state characteristic value specifically includes: calculating the looseness and tightness state characteristic value by the following formula:

[0014]

[0015] Among them, it means that p(NOC|x i ) is the tightness threshold, xi is the i-th current motion data, p(xi|NOC) represents the conditional probability of observing the i-th current motion data when the wearing state is the tight wearing state, p(NOC) is the prior probability corresponding to the tight wearing state, the prior probability is obtained through historical motion data, and p(xi) is calculated by the following total probability formula:

[0016] p(x i )=p(x i|NOC)p(NOC)+p(x i |F1)p(F1)…+p(x i |F K )p(F K );

[0017] Among them, F1, F2, ..., F K They respectively represent the historical motion data obtained under K different wearing tightnesses, and different wearing tightnesses correspond to different buckle positions of the target watch.

[0018] Optionally, if it is determined that the tightness state characteristic value is less than or equal to the tightness state threshold, then the wearing state is determined to be a tight wearing state, specifically including: judging the wearing state according to the following inequality:

[0019]

[0020] Among them, p(NOC|x i ) is the characteristic value of the loose and tight state, is the tightness threshold. If the above inequality is satisfied, it is confirmed that the wearing state is tight.

[0021] In a second aspect of the present application, a device for detecting the tightness of a watch is provided, the device comprising a motion feature acquisition module and a wearing state analysis and processing module, wherein:

[0022] The motion feature acquisition module is used to collect the current motion data of the user wearing the target watch in real time through a six-axis acceleration and gyroscope sensor, and the current motion data includes acceleration data and angular velocity data; obtain the motion features corresponding to the current motion data, and the motion features are the time series features corresponding to the acceleration data and angular velocity data respectively.

[0023] The wearing status analysis and processing module is used to determine the wearing status of the target watch according to the time series characteristics through the dynamic analysis model of motion data; if the wearing status is confirmed to be a loose wearing state, a preset prompt message is sent to the user, and the preset prompt message is used to prompt the user to adjust the wearing status from a loose wearing state to a tight wearing state.

[0024] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0025] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to perform any of the above methods.

[0026] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0027] 1. The current motion data of the user wearing the target watch is collected in real time through the six-axis acceleration and gyroscope sensor. The current motion data includes acceleration data and angular velocity data, and the time series characteristics corresponding to the acceleration data and angular velocity data are obtained respectively. Then, the wearing state of the target watch is judged according to the time series characteristics through the motion data dynamic analysis model. If the wearing state is confirmed to be loose, a preset prompt message is sent to the user. The preset prompt message is used to prompt the user to adjust the wearing state from a loose wearing state to a tight wearing state. Then, through the real-time feedback mechanism, the user can adjust the wearing method of the target watch in time to avoid affecting the accuracy of the heart rate data due to inappropriate wearing tightness.

[0028] 2. By improving the fixed tightness state threshold to an adaptive tightness state threshold, when the user's violent movement causes a drastic change in the signal, the adaptive tightness state threshold is reduced and is lower than the tightness state threshold before the improvement, so as to prevent false alarms.

[0029] 3. By acquiring historical motion data, the historical motion data includes historical motion data corresponding to the loose wearing state and historical motion data corresponding to the tight wearing state, and constructing the motion data dynamic analysis model based on the historical motion data, so that the model can learn the characteristic change rules under different states, thereby improving the accuracy of real-time wearing state judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a flow chart of a method for detecting the tightness of a watch provided in an embodiment of the present application;

[0031] Figure 2 It is a module schematic diagram of a watch wearing tightness detection device provided in an embodiment of the present application;

[0032] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0033] Explanation of the reference numerals: 21, motion feature acquisition module; 22, wearing state analysis and processing module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0034] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0035] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0036] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0037] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0038] Current methods for determining whether a watch is worn tight or loose rely primarily on the user's subjective judgment or simple physical sensor data.

[0039] Subjective judgment relies on the user's personal feelings and habits, which is prone to errors and cannot accurately reflect the actual wearing situation; traditional methods mostly rely on a single sensor (such as a pressure sensor), which has single data and cannot fully capture the movement state of the watch and the changes in the tightness of wearing. Therefore, the existing watch tightness inspection methods often lack real-time detection capabilities and cannot timely feedback the changes in the tightness of wearing, resulting in the accuracy of heart rate measurement being affected.

[0040] Therefore, there is an urgent need for a method and device for detecting the tightness of a watch.

[0041] Please refer to Figure 1 , which shows a flow chart of a method for detecting the tightness of a watch provided in an embodiment of the present application. The method is applied to a server. The flow chart mainly includes the following steps: S101 to S104.

[0042] Step S101, collecting the current motion data of the user wearing the target watch in real time through a six-axis acceleration gyroscope sensor, where the current motion data includes acceleration data and angular velocity data.

[0043] Specifically, the six-axis acceleration-gyro sensor includes an accelerometer and a gyro sensor. The accelerometer and the gyro sensor have a signal processing path and support digital programmable data rate and filtering functions. The six-axis acceleration-gyro sensor is used to monitor the user's wearing of the target watch in real time, and obtain the current motion data of the user when wearing the target watch. The current motion data includes acceleration data and angular velocity data, wherein the acceleration data is obtained in real time by the accelerometer, the angular velocity data is obtained by the gyro sensor, and the acceleration.

[0044] In a possible implementation, step S101 also includes: performing preprocessing operations on the current motion data, specifically including: obtaining static data, the static data including first static data and second static data, the first static data and the second static data being any two adjacent groups of data in the static data; obtaining a fluctuation change value between the first static data and the second static data; determining whether the fluctuation change value is less than a preset fluctuation value; if the fluctuation change value is less than the preset fluctuation value, confirming that the static data is stable static data, and collecting the current motion data in real time through a six-axis acceleration gyroscope sensor.

[0045] Specifically, before collecting the current motion data of the target watch worn by the user in real time through the six-axis acceleration gyroscope sensor, it is also necessary to collect the static data of the target watch. The static data is the data collected when the target watch is in a stationary state. At this time, the static data is filtered by installing a filter in the target watch. The static data includes first static data and second static data. The first static data and the second static data are any two adjacent groups of data in the static data. The fluctuation change value between the first static data and the second static data is obtained, that is, it is determined whether the fluctuation change value of any two adjacent groups of static data in the static data is less than the preset fluctuation value. If the fluctuation change value is less than the preset fluctuation value, it is determined that the static data of the target watch tends to be stable. After determining that the static data is stable data, the tightness state of the target watch is checked, and the current motion data is collected in real time through the six-axis acceleration gyroscope sensor; if the fluctuation change value is greater than or equal to the preset fluctuation value, it is determined that there is unstable static data in the static data of the target watch. At this time, the first static data and the second static data are eliminated as abnormal data. The fluctuation change value is the absolute value of the difference between the static data collected at adjacent times, and the preset fluctuation value is a pre-set fluctuation judgment value, which can be set according to the actual data screening requirements. By obtaining static data before the inspection, even if the user suddenly stops during exercise, it will not affect the inspection of the wearing status of the target watch.

[0046] Step S102, obtaining motion features corresponding to the current motion data, where the motion features are time series features corresponding to the acceleration data and the angular velocity data respectively.

[0047] Specifically, by performing time series analysis on accelerometer data, the periodicity of movement can be identified, such as the regularity of a person's movements when running or swinging his arms. The time series features include, but are not limited to: periodicity features, increment features, rotation amplitude features, and speed change features. For the time series characteristics of acceleration data: Periodic characteristics: When in motion, the swinging of the human body's arms will bring about periodic changes in acceleration. Therefore, when worn tightly, the periodicity of the acceleration data is strong and stable, reflecting that the watch is close to the wrist without sliding or shaking, while in the loose wearing state, the periodicity of the acceleration data becomes unstable and the amplitude change increases; Incremental characteristics: By calculating the acceleration increments between adjacent time points, the amplitude and stability of the swinging arm movement can be judged. When worn tightly, the incremental distribution is relatively stable, while in the loose wearing state, due to the shaking of the watch, the incremental distribution becomes irregular. For the time series characteristics of angular velocity data: Rotation amplitude characteristics and speed change characteristics: Angular velocity data reflects the rotation amplitude and speed of the watch. When worn tightly, the watch rotates synchronously with the wrist, and the angular velocity data is relatively stable; while in the loose wearing state, the shaking or tipping of the watch will cause the fluctuation of the angular velocity data to increase and irregular changes will occur.

[0048] Step S103, judging the wearing status of the target watch according to the time series characteristics through the motion data dynamic analysis model.

[0049] Specifically, the time series features are input into the dynamic analysis model, and the wearing state of the target watch is judged according to the dynamic analysis model. The dynamic process in the time series features of the dynamic analysis model of motion data is estimated by estimating the time independent components of the motion data to achieve the classification of the tightness of the watch.

[0050] In a possible implementation, step S103 further includes: acquiring historical motion data, the historical motion data including historical motion data corresponding to a loose wearing state and historical motion data corresponding to a tight wearing state; and constructing a motion data dynamic analysis model through the historical motion data.

[0051] Specifically, historical motion data is obtained. Historical motion data needs to be obtained under multiple different wearing conditions. Users can choose the most comfortable wearing state as the tight wearing state according to their personal habits, and collect the data at this time as historical motion data for training. After that, these operations can determine the tightness of the target watch when it is in the loose wearing state. The tightness includes but is not limited to: "loose", "very loose", "extremely loose", etc. The tightness of the target watch when the user wears it needs to be gradually changed. For example, the user gradually changes the hand buckle position of the target watch to change the tightness when wearing the target watch, and the data collected at each hand buckle position is used as the historical motion data for training, and the motion data dynamic analysis model is constructed through the historical motion data corresponding to the tight wearing state and the motion data corresponding to the loose wearing state. The construction process is as follows: In order to realize the detection and classification of the wearing state, the state of the parent node D in the motion data dynamic analysis model is set to the historical motion data corresponding to the tight wearing state and the motion data corresponding to the loose wearing state. Then, according to the given historical motion data, the dynamic structure matrix is ​​estimated by the following formula:

[0052]

[0053] in, is the estimated dynamic structure matrix, which is used to describe the dynamic characteristics of motion data. The incremental matrix represents the motion data. The incremental matrix is ​​constructed by the difference of motion data between adjacent time points, by calculating It can capture the changing trend of motion data over time. for The transpose operation converts rows into columns and columns into rows, and is used in conjunction with matrix multiplication in calculations. is the inverse matrix of the covariance matrix of the incremental matrix. Through the operation of this inverse matrix, the collinearity or correlation problem between the input data can be eliminated, so as to estimate the dynamic structure matrix more accurately. After that, the historical motion data corresponding to the tight wearing state and the motion data corresponding to the loose wearing state are further decomposed to obtain the corresponding time independent components of all categories. The time-independent component replaces the original historical motion data to form a new training set; then, the newly obtained training set and the structural parameters used to train the dynamic analysis model of motion data, including the prior probabilities p(NOC), p(F1), ..., p(F K ), and the mean vector μ of the child nodes corresponding to the normal class and all loose classes NOC , μ1, μ2, …, μ K and the covariance matrix ∑ NOC ,∑1,∑2,…,∑ KThe prior probability of the parent node is determined by empirical knowledge, and the parameters of the child node can be calculated by MLE. After the training process is completed, the trained motion data dynamic analysis model can perform online tightness detection and classification on the test samples. For any current motion data, according to the dynamic structure matrix Estimate its time-independent components and make decisions based on pre-defined discrimination rules.

[0054] In a possible implementation, step S103 further includes: calculating the tightness state threshold according to the historical motion data, that is, calculating the tightness state threshold by the following formula:

[0055]

[0056] in, is the loose / tight state threshold, c is the weight factor, and c>1, w is the time window, X i is the i-th time series feature, X i-w+j is the i-w+jth time series feature, NOC represents the tight wearing state, ζ j Indicates weighting the product of the fixed probability threshold; judging whether the tightness state threshold is greater than or equal to the tightness state characteristic value; if the tightness state threshold is greater than or equal to the tightness state characteristic value, then confirming that the wearing state is the tight wearing state; if the tightness state threshold is less than the tightness state characteristic value, then confirming that the wearing state is the loose wearing state, that is, judging the wearing state according to the following inequality:

[0057]

[0058] Among them, p(NOC|x i ) is the characteristic value of the loose and tight state, is the tightness threshold. If the above inequality is satisfied, it is confirmed that the wearing state is tight.

[0059] Specifically, the application scenario of the present application is a sports scenario. In this scenario, if the wearing state of the target watch is a tight state, the user's sudden intense movement during exercise causes a drastic change in the signal, which may cause the target watch to be misjudged as a loose state. Therefore, the tightness state threshold proposed in this application is an improved tightness state threshold proposed in consideration of this misjudgment. The tightness state threshold can adapt to the user's exercise process. The threshold is obtained in the following way: Different from the consideration based on the fixed tightness state threshold, when determining whether the current exercise data at time point i is in a loose state, the time point i and the previous w-1 secondary statistics are considered, and the fixed tightness state threshold is improved as follows:

[0060]

[0061] Among them, x i is the i-th current motion data, NOC is the tightness state, c represents the weight factor, and c>1, w is the size of the moving window, CL is the baseline probability that the current wearing state is in the tightness state, CL can be calculated from the original motion data, in order to establish an equivalent relationship between the motion data dynamic analysis model and the improved tightness state threshold, and realize state detection and classification, the improved tightness state threshold is derived as follows:

[0062]

[0063] Then we get the following relationship:

[0064]

[0065] After that, multiply both sides of the inequality by the same constant term to get:

[0066]

[0067] Among them, ∑ NOC is the covariance matrix corresponding to the historical motion data corresponding to the tight wearing state. According to the multivariate Gaussian probability density function, the improved tightness state threshold is further derived as follows:

[0068]

[0069] Among them, x * The historical motion data sample represents the tight wearing state, and its statistic is equal to CL. According to the Bayesian formula, multiply both sides of the inequality by the prior probability p(NOC) and divide by p(x i ), so the characteristic value of the loose and tight state is:

[0070]

[0071] Among them, the total probability formula p(x i ) can be expressed as:

[0072] p(x i )=p(x i |NOC)p(NOC)+p(x i |F1)p(F1)…+p(x i |F K )p(F K );

[0073] So far, x i The loose and tight state characteristic value p(NOC|x i ) and the adaptive tightness threshold in the tight state The relationship between can be derived, namely:

[0074]

[0075] Among them, p(NOC|x i ) is the characteristic value of the loose and tight state, is the tightness threshold, and the tightness threshold is calculated by the following formula:

[0076]

[0077] in, is the tightness threshold, c is the weight factor, and c>1, w is the size of the moving window, X i is the i-th time series feature, X i-w+j is the i-w+jth time series feature, NOC represents the tight wearing state, ζ j It means weighting the product of fixed probability thresholds and satisfying:

[0078]

[0079] According to the loose and tight state characteristic value p(NOC|x i ) and the adaptive tightness threshold in the tight state If the tightness state threshold is greater than or equal to the tightness state characteristic value, the wearing state is confirmed to be tight; if the tightness state threshold is less than the tightness state characteristic value, the wearing state is confirmed to be loose. Based on the above method, the improved tightness state threshold can be adjusted adaptively. When the user's strenuous exercise causes a drastic change in the signal, the adaptive tightness state threshold is used. Decreases and falls below the tightness threshold before improvement To prevent false alarms.

[0080] Step S104: If it is confirmed that the wearing state is the loose wearing state, a preset prompt message is sent to the user, and the preset prompt message is used to prompt the user to adjust the wearing state from the loose wearing state to the tight wearing state.

[0081] Specifically, if it is detected that the watch is worn too loosely, the user will be reminded to adjust the tightness through vibration or display. The user can adjust the wearing state from a loose wearing state to a tight wearing state according to the prompt, thereby ensuring the accuracy of heart rate measurement.

[0082] The present application adopts the above method to collect the current motion data of the user wearing the target watch in real time through a six-axis acceleration and gyroscope sensor. The current motion data includes acceleration data and angular velocity data, and the time series characteristics corresponding to the acceleration data and the angular velocity data are obtained respectively. Therefore, the wearing state of the target watch is judged according to the time series characteristics through the motion data dynamic analysis model. If the wearing state is confirmed to be a loose wearing state, a preset prompt message is sent to the user. The preset prompt message is used to prompt the user to adjust the wearing state from a loose wearing state to a tight wearing state. Then, through the real-time feedback mechanism, the user can adjust the wearing method of the target watch in time to avoid affecting the accuracy of the heart rate data due to inappropriate wearing tightness.

[0083] Please refer to Figure 2 , which shows a module schematic diagram of a watch wearing tightness detection device provided in an embodiment of the present application, the device is a server, and the server includes a motion feature acquisition module 21 and a wearing state analysis and processing module 22, wherein,

[0084] The motion feature acquisition module 21 is used to collect the current motion data of the user wearing the target watch in real time through a six-axis acceleration and gyroscope sensor, and the current motion data includes acceleration data and angular velocity data; obtain the motion features corresponding to the current motion data, and the motion features are the time series features corresponding to the acceleration data and the angular velocity data respectively.

[0085] The wearing state analysis and processing module 22 is used to determine the wearing state of the target watch according to the time series characteristics through the dynamic analysis model of motion data; if the wearing state is confirmed to be a loose wearing state, a preset prompt message is sent to the user, and the preset prompt message is used to prompt the user to adjust the wearing state from a loose wearing state to a tight wearing state.

[0086] In a possible implementation, the motion feature acquisition module 21 is used to collect the current motion data of the user wearing the target watch in real time through the six-axis acceleration gyroscope sensor, and the method also includes: obtaining static data, the static data includes first static data and second static data, the first static data and the second static data are any two adjacent groups of data in the static data; obtaining the fluctuation change value between the first static data and the second static data; judging whether the fluctuation change value is less than the preset fluctuation value; if the fluctuation change value is less than the preset fluctuation value, confirming that the static data is stable static data, and collecting the current motion data in real time through the six-axis acceleration gyroscope sensor.

[0087] In a possible implementation, the wearing state analysis processing module 22 is used to construct a motion data dynamic analysis model before judging the wearing state of the target watch according to the time series characteristics through the motion data dynamic analysis model, specifically including: obtaining historical motion data, the historical motion data including historical motion data corresponding to the loose wearing state and historical motion data corresponding to the tight wearing state; and constructing a motion data dynamic analysis model through the historical motion data.

[0088] In a possible implementation, the wearing status analysis processing module 22 is used to determine the wearing status of the target watch according to the time series characteristics through a dynamic analysis model of motion data, specifically including: calculating a looseness / tightness threshold according to historical motion data; calculating a looseness / tightness characteristic value according to the time series characteristics; determining whether the looseness / tightness threshold is greater than or equal to the looseness / tightness characteristic value; if the looseness / tightness threshold is greater than or equal to the looseness / tightness characteristic value, confirming that the wearing status is a tight wearing status; if the looseness / tightness threshold is less than the looseness / tightness characteristic value, confirming that the wearing status is a loose wearing status.

[0089] In a possible implementation, the wearing state analysis and processing module 22 is used to calculate the tightness state threshold according to the historical motion data, specifically including: calculating the tightness state threshold by the following formula:

[0090]

[0091] in, is the tightness threshold, c is the weight factor, and c>1, w is the size of the moving window, X i is the i-th time series feature, X i-w+j is the i-w+jth time series feature, NOC represents the tight wearing state, ζ j represents weighting the product of fixed probability thresholds.

[0092] In a possible implementation, the wearing state analysis and processing module 22 is used to calculate the tightness state characteristic value according to the time series characteristics, specifically including: calculating the tightness state characteristic value by the following formula:

[0093]

[0094] Among them, it means that p(NOC|x i ) is the tightness threshold, xi is the i-th current motion data, p(xi|NOC) represents the conditional probability of observing the i-th current motion data when the wearing state is the tight wearing state, p(NOC) is the prior probability corresponding to the tight wearing state, the prior probability is obtained through historical motion data, and p(xi) is calculated by the following total probability formula:

[0095] p(xi )=p(x i |NOC)p(NOC)+p(x i |F1)p(F1)…+p(x i |F K )p(F K );

[0096] Among them, F1, F2, ..., F K They respectively represent the historical motion data obtained under K different wearing tightnesses, and different wearing tightnesses correspond to different buckle positions of the target watch.

[0097] In a possible implementation manner, the wearing state analysis and processing module 22 is used to determine that the wearing state is a tight wearing state if it is determined that the looseness state characteristic value is less than or equal to the looseness state threshold value, specifically including: determining the wearing state according to the following inequality:

[0098]

[0099] Among them, p(NOC|x i ) is the characteristic value of the loose and tight state, is the tightness threshold. If the above inequality is satisfied, it is confirmed that the wearing state is tight.

[0100] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0101] The present application also provides an electronic device. Figure 3 , Figure 3 30 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include: at least one processor 301, at least one communication bus 302, a user interface 303, at least one network interface 304, and a memory 305.

[0102] The communication bus 302 is used to realize the connection and communication between these components.

[0103] The user interface 303 may include a display screen (Display) and a camera (Camera). The optional user interface 303 may also include a standard wired interface and a wireless interface.

[0104] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0105] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0106] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a watch wearing tightness detection application.

[0107] exist Figure 3 In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the watch wearing tightness detection application stored in the memory 305. When executed by one or more processors 301, the electronic device executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0108] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0109] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0110] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0113] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0114] The above are only exemplary embodiments disclosed in this application, and the scope of the disclosure of this application cannot be limited by this. That is, any equivalent changes and modifications made according to the teachings disclosed in this application are still within the scope of the disclosure of this application. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other implementation schemes disclosed in this application.

[0115] This application is intended to cover any modifications, uses or adaptive changes disclosed in this application, which follow the general principles disclosed in this application and include common knowledge or customary technical means in the technical field not recorded in this application.

Claims

1. A method for detecting the tightness of a watch, characterized in that: The method comprises: The current motion data of the user wearing the target watch is collected in real time through a six-axis acceleration gyroscope sensor, wherein the current motion data includes acceleration data and angular velocity data; Acquire a motion feature corresponding to the current motion data, wherein the motion feature is a time series feature corresponding to the acceleration data and the angular velocity data respectively; Using a motion data dynamic analysis model, judging the wearing state of the target watch according to the time series characteristics; If it is confirmed that the wearing state is a loose wearing state, a preset prompt message is sent to the user, and the preset prompt message is used to prompt the user to adjust the wearing state from the loose wearing state to the tight wearing state.

2. The method according to claim 1, characterized in that Before collecting the current motion data of the user wearing the target watch in real time through the six-axis acceleration gyroscope sensor, the method further includes: Acquire static data, where the static data includes first static data and second static data, where the first static data and the second static data are any two adjacent groups of data in the static data; Acquire a fluctuation change value between the first static data and the second static data; Determining whether the fluctuation change value is less than a preset fluctuation value; If the fluctuation change value is less than the preset fluctuation value, the static data is confirmed to be stable static data, and the current motion data is collected in real time through the six-axis acceleration gyroscope sensor.

3. The method according to claim 1, characterized in that: Before judging the wearing state of the target watch according to the time series characteristics through the motion data dynamic analysis model, it is necessary to construct the motion data dynamic analysis model, which specifically includes: Acquire historical motion data, wherein the historical motion data includes historical motion data corresponding to the loose wearing state and historical motion data corresponding to the tight wearing state; The motion data dynamic analysis model is constructed using the historical motion data.

4. The method according to claim 3, characterized in that The step of determining the wearing state of the target watch according to the time series characteristics through the motion data dynamic analysis model specifically includes: Calculating a looseness / tightness state threshold value based on the historical motion data; calculating a looseness / tightness state characteristic value based on the time series characteristics; Determine whether the tightness state threshold is greater than or equal to the tightness state characteristic value; If the tightness state threshold is greater than or equal to the tightness state characteristic value, confirming that the wearing state is the tight wearing state; If the tightness state threshold is less than the tightness state characteristic value, the wearing state is confirmed to be the loose wearing state.

5. The method according to claim 4, characterized in that The calculating of the looseness / tightness state threshold according to the historical motion data specifically includes: The tightness threshold is calculated by the following formula: Among them, T i A is the tightness threshold, c is the weight factor, and c>1, w is the size of the moving window, X i is the i-th time series feature, X i-w+j is the i-w+jth time series feature, NOC represents the tight wearing state, ζ j represents weighting the product of fixed probability thresholds.

6. The method according to claim 5, characterized in that The calculating of the looseness / tightness state characteristic value according to the time series characteristics specifically includes: The loose / tight state characteristic value is calculated by the following formula: Among them, it means that p(NOC|x i ) is the tightness threshold, xi is the i-th current motion data, p(xi|NOC) represents the conditional probability that the i-th current motion data can be observed when the wearing state is the tight wearing state, p(NOC) is the prior probability corresponding to the tight wearing state, the prior probability is obtained through the historical motion data, and p(xi) is calculated by the following total probability formula: p(x i )=p(x i ∣NOC)p(NOC)+p(x i ∣F1)p(F1)…+p(x i ∣F K )p(F K ); Among them, F1, F2, …, F K They respectively represent the historical motion data obtained under K different wearing tightnesses, and the different wearing tightnesses correspond to different buckle positions of the target watch.

7. The method according to claim 3, characterized in that If the tightness state threshold is greater than or equal to the tightness state characteristic value, then the wearing state is confirmed to be the tight wearing state: The wearing state is determined according to the following inequality: if p(NOC|x i )≥T i A ; Among them, p(NOC|x i ) is the characteristic value of the looseness and tightness state, T i A is the tightness state threshold. If the above inequality is satisfied, it is confirmed that the wearing state is the tight wearing state.

8. A watch wearing tightness detection device, characterized in that: The device includes a motion feature acquisition module and a wearing state analysis and processing module, wherein: The motion feature acquisition module is used to collect the current motion data of the user wearing the target watch in real time through a six-axis acceleration gyroscope sensor, wherein the current motion data includes acceleration data and angular velocity data; and obtain the motion features corresponding to the current motion data, wherein the motion features are time series features corresponding to the acceleration data and the angular velocity data respectively. The wearing state analysis and processing module is used to determine the wearing state of the target watch according to the time series characteristics through a motion data dynamic analysis model; if the wearing state is confirmed to be a loose wearing state, a preset prompt message is sent to the user, and the preset prompt message is used to prompt the user to adjust the wearing state from the loose wearing state to the tight wearing state.

9. An electronic device, characterized in that: It includes a processor, a communication bus, a user interface, a network interface and a memory, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images