Operation behavior prediction method and device and storage medium

Abstract

The invention discloses an operation behavior prediction method and device and a storage medium, and belongs to the field of operation behavior prediction. The method comprises the following steps: acquiring current posture data corresponding to a mobile terminal in a unit time length, wherein a client runs in the mobile terminal; by classifying the current posture data and the multiple pieces of historical posture data, a behavior state label corresponding to a user account of the client is determined, the behavior state label is related to a motion state corresponding to the user account, and the multiple pieces of historical posture data comprise posture data corresponding to the mobile terminal in multiple unit durations in the past; and predicting a target operation behavior of the user account in the client according to the behavior state tag. As the behavior state tag has an accurate corresponding relationship with different types of motion states, the operation behavior of the user account in the client can be predicted through the accurate behavior state tag, and the accuracy of predicting the operation behavior can be improved.

Description

Technical Field

[0001] The present application relates to the field of operation behavior prediction, and in particular to an operation behavior prediction method, device and storage medium. Background Art

[0002] The motion data collected by the motion sensor inside the mobile terminal can be used to analyze the user's motion state during the use of the mobile terminal client, such as walking, running, sitting, etc. Based on the analyzed motion state, the operation behavior that the user may currently perform in the client can be predicted.

[0003] In the related art, by acquiring the motion data collected by the motion sensor and inputting the collected motion data into the neural network model, the motion state corresponding to the motion data predicted by the neural network model can be obtained, that is, the motion state of the user during the use of the client. Then, based on the motion state predicted by the neural network model, the user's operation behavior in the client can be predicted.

[0004] When predicting operational behaviors in the above manner, since the neural network model can only predict the motion state corresponding to the motion data among the motion states that it supports prediction, and there is diversity in motion states, if the motion state exceeds the support of the prediction model, it will lead to the inability to accurately predict the motion state, which in turn leads to a decrease in the accuracy of predicting operational behaviors. Summary of the invention

[0005] The present application provides a method, device and storage medium for predicting operation behavior, which can improve the accuracy of predicting operation behavior. The technical solution is as follows:

[0006] According to one aspect of the present application, a method for predicting an operation behavior is provided, the method being executed by a client, and the method comprising:

[0007] Acquire current posture data corresponding to a mobile terminal within a unit time, wherein the client runs in the mobile terminal;

[0008] Determine a behavior state label corresponding to the user account of the client by classifying the current posture data and a plurality of historical posture data, wherein the behavior state label is related to the motion state corresponding to the user account, and the plurality of historical posture data include posture data corresponding to the mobile terminal in a plurality of unit time periods in the past;

[0009] A target operation behavior of the user account in the client is predicted according to the behavior state tag.

[0010] According to another aspect of the present application, a device for predicting operation behavior is provided, the device comprising:

[0011] An acquisition module, used for acquiring current posture data corresponding to a mobile terminal within a unit time length, wherein the device runs in the mobile terminal;

[0012] a determination module, configured to determine a behavior state label corresponding to a user account of the device by classifying the current posture data and a plurality of historical posture data, wherein the behavior state label is related to a motion state corresponding to the user account, and the plurality of historical posture data include posture data corresponding to the mobile terminal in a plurality of unit time periods in the past;

[0013] A prediction module is used to predict the target operation behavior of the user account in the device according to the behavior state label.

[0014] In an optional design, the determining module is used to:

[0015] The behavior state label corresponding to the user account is determined by clustering the current posture data and the multiple historical posture data.

[0016] In an optional design, the determining module is used to:

[0017] Inputting the current posture data into a clustering model to obtain a clustering label corresponding to the current posture data output by the clustering model;

[0018] Determining the cluster label as the behavior status label corresponding to the user account;

[0019] Wherein, the clustering model is trained by the multiple historical posture data, and the clustering model is a model constructed based on a clustering algorithm.

[0020] In an optional design, the current posture data includes at least one of first sensor data, second sensor data, third sensor data, and fourth sensor data;

[0021] Among them, the first sensor data is collected by the gravity sensor of the mobile terminal, the second sensor data is collected by the acceleration sensor of the mobile terminal, the third sensor data is collected by the azimuth sensor of the mobile terminal, and the fourth sensor data is collected by the gyroscope sensor of the mobile terminal.

[0022] In an optional design, the first sensor data includes at least one of a coordinate axis with a maximum gravity mean value and a coordinate axis with a maximum gravity change.

[0023] In an optional design, the second sensor data includes at least one of the number of acceleration peaks, the average interval of the acceleration peaks, the standard deviation of the interval of the acceleration peaks, the average value of the Euclidean distance of acceleration, and the standard deviation of the Euclidean distance of acceleration.

[0024] In an optional design, the third sensor data includes at least one of a coefficient of variation of an azimuth angle, an average azimuth angle, a coefficient of variation of a horizontal angle, an average horizontal angle, a coefficient of variation of an elevation angle, and an average elevation angle.

[0025] In an optional design, the fourth sensor data includes a coefficient of variation of the gyroscope data.

[0026] In an optional design, the prediction module is used to:

[0027] Acquire a plurality of historical operation behaviors according to the behavior state tag, wherein the plurality of historical operation behaviors include operation behaviors performed in the device when the user account was in the behavior state tag in the past;

[0028] According to the multiple historical operation behaviors, a target operation behavior of the user account in the device is determined.

[0029] In an optional design, the device is used for song playback; the prediction module is used to:

[0030] In a case where song playing operations account for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the song playing operation;

[0031] In a case where the pause playback operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the pause playback operation;

[0032] In the case where the song library viewing operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the song library viewing operation;

[0033] In the case where the singer library viewing operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the singer library viewing operation;

[0034] In a case where the playback volume adjustment operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the playback volume adjustment operation;

[0035] In a case where the sound effect switching operation accounts for the largest proportion among the multiple historical operation behaviors, the target operation behavior is determined to be the sound effect switching operation.

[0036] In an optional design, the device further includes a processing module, and the processing module is used for at least one of the following:

[0037] In the case where the target operation behavior is the song playing operation, displaying recommended songs recommended to the user account;

[0038] When the target operation behavior is the pause play operation, pausing the song playing for the user account;

[0039] When the target operation behavior is the song library viewing operation, displaying the song library interface in the device;

[0040] When the target operation behavior is the singer library viewing operation, displaying the singer library interface in the device;

[0041] When the target operation behavior is the operation of adjusting the playback volume, adjusting the volume of the song played by the user account according to the operation of adjusting the playback volume;

[0042] When the target operation behavior is the sound effect switching operation, the sound effect of the song played by the user account is adjusted according to the sound effect switching operation.

[0043] In an optional design, the acquisition module is used to:

[0044] Acquire device characteristics corresponding to the mobile terminal;

[0045] The prediction module is used to:

[0046] According to the behavior state tag and the device feature, a target operation behavior of the user account in the device is predicted.

[0047] In an optional design, the device feature includes at least one of the first feature, the second feature, the third feature, the fourth feature and the fifth feature;

[0048] Among them, the first feature is used to reflect the signal strength of the mobile terminal, the second feature is used to reflect the remaining power of the mobile terminal, the third feature is used to reflect the charging status of the mobile terminal, the fourth feature is used to reflect the song playing status of the mobile terminal, and the fifth feature is used to reflect the Bluetooth device connected to the mobile terminal.

[0049] According to another aspect of the present application, a computer device is provided, comprising a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the method for predicting operational behavior as described above.

[0050] According to another aspect of the present application, a computer-readable storage medium is provided, in which at least one program is stored. The at least one program is loaded and executed by a processor to implement the method for predicting operational behavior as described above.

[0051] According to another aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for predicting the operation behavior provided in various optional implementations of the above aspects.

[0052] The beneficial effects of the technical solution provided by this application include at least:

[0053] By acquiring the current posture data related to the posture of the mobile terminal and classifying the current posture data with the historical posture data collected in the past, the behavior state label corresponding to the user account is obtained, and the operation behavior of the user account in the client can be predicted based on the behavior state label. Since the behavior state label is obtained by classifying the data related to the posture of the mobile terminal, it is not only associated with the user's motion state, but also not affected by the diversity of the motion state. Therefore, there is an accurate correspondence between the determined behavior state label and different types of motion states. Predicting the operation behavior of the user account in the client through accurate behavior state labels can improve the accuracy of predicting the operation behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 is a structural block diagram of a computer system provided by an exemplary embodiment of the present application;

[0056] Figure 2 is a schematic diagram of a process of predicting an operation behavior provided by an exemplary embodiment of the present application;

[0057] Figure 3 is a flowchart of a method for predicting an operation behavior provided by an exemplary embodiment of the present application;

[0058] Figure 4is a flowchart of a method for predicting an operation behavior provided by an exemplary embodiment of the present application;

[0059] Figure 5 is a schematic diagram of a clustering process of current posture data and historical posture data provided by an exemplary embodiment of the present application;

[0060] Figure 6 is a schematic diagram of a cluster provided by an exemplary embodiment of the present application;

[0061] Figure 7 is a schematic diagram of clustering labels provided by an exemplary embodiment of the present application;

[0062] Figure 8 is a schematic diagram of the structure of an operation behavior prediction device provided by an exemplary embodiment of the present application;

[0063] Fig. 9 is a schematic diagram of the structure of an operation behavior prediction device provided by an exemplary embodiment of the present application;

[0064] Fig.10 It is a schematic diagram of the structure of a terminal provided by an exemplary embodiment of the present application.

[0065] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application. DETAILED DESCRIPTION

[0066] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0067] Figure 1 The computer system 100 includes a terminal 110 and a server 120 .

[0068] The terminal 110 is installed and runs an application 111 that supports song playback. The application 111 includes any one of a listening application, a song application, a singing application, a live broadcast application, a short video application, a video on demand application, a social application, an office application, a game application, a takeaway application, an online shopping application, a financial application, a life service application, a navigation application, a medical application, a learning application, and a mini program. In some embodiments, the application 111 is a client. When the terminal 110 runs the application 111, the user interface of the application 111 is displayed on the screen of the terminal 110. The terminal 110 is a terminal used by the user 112, and the user account of the user 112 can be logged in to the application 111. The terminal 110 can generally refer to one of a plurality of terminals. Optionally, the device type of the terminal 110 includes at least one of a smart phone, a tablet computer, a smart watch, an e-book reader, an MP3 player, an MP4 player, and a laptop computer.

[0069] The terminal 110 is connected to the server 120 via a wireless network or a wired network.

[0070] The server 120 includes at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. The server 120 is used to provide background services for the application 111 that supports song playback. Optionally, the server 120 undertakes the main computing work and the terminal 110 undertakes the secondary computing work; or, the server 120 undertakes the secondary computing work and the terminal 110 undertakes the main computing work; or, the server 120 and the terminal 110 adopt a distributed computing architecture for collaborative computing.

[0071] In an illustrative example, the server 120 includes a processor 121, a user account database 122, a song providing module 123, and a user-oriented input / output interface (I / O interface) 124. The processor 121 is used to load instructions stored in the server 120 and process data in the user account database 122 and the song providing module 123; the user account database 122 is used to store data of user accounts used by the terminal 110 and other terminals, such as the user account's avatar, the user account's nickname, and the virtual currency owned by the user account; the song providing module 123 is used to provide audio files of songs; and the user-oriented I / O interface 124 is used to establish communication and exchange data with the terminal 110 through a wireless network or a wired network.

[0072] In combination with the above introduction to the implementation environment involved in the present application, the method provided in the embodiment of the present application will be described below.

[0073] Figure 2 FIG. 1 is a schematic diagram of a process of predicting an operation behavior provided by an exemplary embodiment of the present application. Figure 2 As shown, the client obtains the current posture data 201 corresponding to the mobile terminal where it is located within a unit time length, and the current posture data 201 includes data affected by the posture of the mobile terminal, that is, the current posture data 201 includes data related to the posture of the mobile terminal. Optionally, the current posture data 201 includes at least one of the first sensor data, the second sensor data, the third sensor data and the fourth sensor data. The first sensor data is collected by the gravity sensor of the mobile terminal, the second sensor data is collected by the acceleration sensor of the mobile terminal, the third sensor data is collected by the azimuth sensor of the mobile terminal, and the fourth sensor data is collected by the gyroscope sensor of the mobile terminal.

[0074] The client can determine the clustering label corresponding to the current posture data 201 by clustering the current posture data 201 and the multiple historical posture data 202, thereby determining the clustering label as the behavior state label 203 corresponding to the user account. Among them, the behavior state label 203 is related to the motion state of the user corresponding to the user account in the unit time used to obtain the current posture data. If the motion state of the user corresponding to the user account in the unit time is different, the corresponding behavior state label 203 is also different. The multiple historical posture data 202 include posture data corresponding to the mobile terminal in multiple unit time periods in the past. Optionally, the historical posture data 202 is of the same type as the data in the current posture data 201.

[0075] After obtaining the behavior status tag 203 corresponding to the user account, the client predicts the target operation behavior 204 of the user account in the client according to the behavior status tag 203. Optionally, the client obtains multiple historical operation behaviors according to the behavior status tag 203, and thereby determines the target operation behavior 204 of the user account in the client according to the multiple historical operation behaviors. The multiple historical operation behaviors include operation behaviors performed in the client when the user account was in the behavior status tag 203 in the past. For example, the behavior status tag 203 is a tag corresponding to the user corresponding to the user account when running, and the historical operation behavior reflects that when the user account was in the behavior status tag 203 in the past, the operation of playing songs was frequently performed. In this case, the client predicts that the target operation behavior 204 of the user account in the client is to play songs. Optionally, in this case, the client will also trigger the recommendation of songs to the user account to enhance the user's experience of using the client.

[0076] By acquiring the current posture data related to the posture of the mobile terminal and classifying the current posture data with the historical posture data collected in the past, the behavior state label corresponding to the user account is obtained, and the operation behavior of the user account in the client can be predicted based on the behavior state label. Since the behavior state label is obtained by classifying the data related to the posture of the mobile terminal, it is not only associated with the user's motion state, but also not affected by the diversity of the motion state. Therefore, there is an accurate correspondence between the determined behavior state label and different types of motion states. Predicting the operation behavior of the user account in the client through accurate behavior state labels can improve the accuracy of predicting the operation behavior.

[0077] Figure 3 FIG. 1 is a flow chart of a method for predicting an operation behavior provided by an exemplary embodiment of the present application. The method can be used in a computer device or a client on a computer device, for example, Figure 1 As shown in the client Figure 3 As shown, the method includes:

[0078] Step 302: Obtain current posture data corresponding to the mobile terminal within a unit time length.

[0079] The client runs in a mobile terminal, and the mobile terminal includes a computer device that can be used during movement. In some embodiments, the client in this application includes a listening client, a song client, a singing client, a live broadcast client, a short video client, a video on demand client, a social client, an office client, a game client, a takeaway client, an online shopping client, a financial client, a life service client, a navigation client, a medical client, a learning client, and any one of a mini program. In some embodiments, the mobile terminal in this application includes at least one of a smart phone, a tablet computer, a smart watch, an e-book reader, an MP3 player, an MP4 player, and a laptop computer.

[0080] The current posture data is related to the posture of the mobile terminal within the unit time. The current posture data corresponding to the mobile terminal within the unit time includes the posture data corresponding to the mobile terminal collected by the client within the first time period, and the duration of the first time period is the unit time period. Optionally, the end time of the first time period is the current time. Optionally, the unit time period is pre-set in the client, for example, it is set by the developer of the client. In some embodiments, the client obtains the current posture data corresponding to the mobile terminal within the unit time period by sampling the posture data corresponding to the mobile terminal within the first time period. The posture data corresponding to the mobile terminal includes data affected by the posture of the mobile terminal in the relevant data of the mobile terminal, and the relevant data of the mobile terminal includes data collected by the mobile terminal, and the current posture data includes data related to the posture of the mobile terminal within the first time period. The posture of the mobile terminal will be affected by the motion state corresponding to the user account of the client, and the motion state corresponding to the user account is the state of the user motion corresponding to the user account, and the user corresponding to the user account includes the object of logging in the user account in the client to use the client. For example, the motion state corresponding to the user account includes at least one of walking, running, standing, sitting, lying flat, lying down, and squatting.

[0081] In some embodiments, the current posture data is obtained by the client through a motion sensor in the mobile terminal. Optionally, the motion sensor in the mobile terminal includes at least one of a gravity sensor, an acceleration sensor, an azimuth sensor, and a gyroscope sensor in the mobile terminal. The gravity sensor, the acceleration sensor, the azimuth sensor, and the gyroscope sensor are exemplarily introduced below.

[0082] A gravity sensor is a sensor that can measure the gravitational acceleration of an object (mobile terminal). The working principle of a gravity sensor is based on Newton's second law, that is, the acceleration of an object is proportional to the force it receives. A gravity sensor usually contains a mass block and some sensitive elements. When the mobile terminal is subjected to gravity, the mass block will be displaced. The sensitive elements will convert this displacement into an electrical signal, which is then processed by circuits and calculated by algorithms to obtain the magnitude and direction of the gravitational acceleration.

[0083] An accelerometer is a sensor that can measure the acceleration components of an object (mobile terminal) in three directions (x-axis, y-axis, and z-axis), and is usually integrated with a three-axis accelerometer. The accelerometer can sense the acceleration or deceleration of linear motion, as well as the static acceleration caused by gravity, so as to determine the movement state, posture change, or vibration of the mobile terminal. In some embodiments, the accelerometer in the present application is a linear accelerometer.

[0084] The azimuth sensor can be called an electronic compass or magnetometer. It is a sensor that can detect and measure the angle of an object (mobile terminal) relative to the direction of the geomagnetic field. The azimuth sensor is a sensor that determines the direction based on the geomagnetic field. Since the earth itself is a huge magnet, it will generate an almost horizontally distributed geomagnetic field. The azimuth sensor contains magnetic sensitive elements, such as magnetic reluctance (MR) elements or fluxgate sensors, which can detect the direction and strength of the magnetic field. When the magnetic field acts on the magnetoresistive element, the resistance value of the magnetoresistive element will change, and this change is related to the direction and magnitude of the magnetic field. By measuring the change in resistance value, the direction of the magnetic field can be calculated, and then the azimuth of the mobile terminal can be obtained. The fluxgate sensor uses the fluxgate effect. When the external AC magnetic field interacts with the static magnetic field to be measured, a secondary induction signal will be generated in the detection coil. By analyzing this signal, the direction of the magnetic field can be determined, and then the azimuth of the mobile terminal can be obtained.

[0085] Gyroscope sensors can be called angular velocity sensors, which are sensors implemented based on the theory of conservation of angular momentum. Gyroscope sensors are usually composed of a rotatable rotor located at the center of the axis. When the rotor rotates, its axis of rotation always points in one direction. When an external force causes it to tilt, the axis of rotation will resist this tilt in an attempt to maintain its original direction. By measuring the angular velocity of rotation in this case, the gyroscope sensor can sense the change in the direction of the mobile terminal.

[0086] Optionally, the current posture data includes at least one of first sensor data, second sensor data, third sensor data and fourth sensor data, wherein the first sensor data is collected by a gravity sensor of the mobile terminal, the second sensor data is collected by an acceleration sensor of the mobile terminal, the third sensor data is collected by an azimuth sensor of the mobile terminal, and the fourth sensor data is collected by a gyroscope sensor of the mobile terminal.

[0087] Step 304: Determine the behavior state label corresponding to the user account of the client by classifying the current posture data and a plurality of historical posture data.

[0088] Multiple historical posture data include posture data corresponding to the mobile terminal in multiple unit time periods in the past, and the historical posture data are related to the posture of the mobile terminal in the unit time period in the past. Multiple historical posture data include posture data corresponding to the mobile terminal collected by the client in multiple second time periods in the past, each second time period is a unit time period, and the second time period is before the first time period. In some embodiments, the client obtains the historical posture data corresponding to the mobile terminal in multiple unit time periods in the past by sampling the posture data corresponding to the mobile terminal in each second time period, thereby obtaining multiple historical posture data. In some embodiments, when the client obtains the historical posture data, it will store the obtained historical posture data. For the introduction of the posture data corresponding to the mobile terminal, refer to the relevant content in step 302, and the embodiments of the present application will not be repeated here. In some embodiments, the type of data in the current posture data is the same as the historical posture data.

[0089] In some embodiments, the client classifies each of the current posture data and the multiple historical posture data to obtain multiple data types, each of which includes one or more posture data in the current posture data and the historical posture data. Optionally, the client classifies the current posture data and the multiple historical posture data according to the similarity between the current posture data and the multiple historical posture data. Since the posture data is associated with the motion state, the posture data under different data types are generated under different motion states, that is, each data type obtained by classification corresponds to a unique motion state, so different data types will correspond to different motion states. The behavior state label corresponding to the user account of the client is the label corresponding to the data type to which the current posture data belongs, and the behavior state label is related to the motion state of the user corresponding to the user account in the unit time length used to obtain the current posture data, that is, the behavior state label is related to the motion state of the user corresponding to the user account in the first time period. If the motion state of the user corresponding to the user account in the first time period is different, the behavior state label corresponding to the current posture data is also different.

[0090] It should be noted that different behavior state labels can only determine that the corresponding motion states are different, but it is impossible to know which motion state a certain behavior state label corresponds to. For example, behavior state label 1, behavior state label 2, and behavior state label 3 are different behavior state labels, and behavior state label 1, behavior state label 2, and behavior state label 3 can be used to distinguish different motion states, but cannot indicate which motion state a certain behavior state label corresponds to.

[0091] In some embodiments, the client obtains a type label corresponding to the historical posture data, and the type label is used to reflect the type of motion state corresponding to the historical posture data. The type label is set manually, for example, type label 1 is manually set for historical posture data 1, and type label 1 can indicate that historical posture data 1 corresponds to a motion state of the type of running. After classifying the current posture data and multiple historical posture data, the client can determine the type of motion state corresponding to the current posture data based on the type label of the target historical posture data corresponding to the current posture data. The target historical posture data includes historical posture data that belongs to the same data type as the current posture data after classification.

[0092] Step 306: predicting the target operation behavior of the user account in the client according to the behavior state tag.

[0093] The target operation behavior is used to predict the operation behavior that the user corresponding to the user account may perform in the motion state corresponding to the behavior state label. The operation behavior is the operation performed by the user account in the client. Optionally, the operation behavior is used to indicate the function used by the user account in the client.

[0094] In some embodiments, the client predicts the target operation behavior of the user account in the client based on the operation behaviors performed when the user account was in the behavior status tag in the past. Optionally, the client obtains multiple historical operation behaviors based on the behavior status tag, and the multiple historical operation behaviors include the operation behaviors performed in the client when the user account was in the behavior status tag in the past. Thereafter, the client determines the target operation behavior of the user account in the client based on the multiple historical operation behaviors to predict the target operation behavior. Optionally, the client determines the target operation behavior of the user account in the client based on the triggering frequency of different operation behaviors in the multiple historical operation behaviors, for example, determining the historical operation behavior with the highest triggering frequency as the target operation behavior.

[0095] In summary, the method provided in this embodiment obtains the current posture data related to the posture of the mobile terminal, and classifies the current posture data with the historical posture data collected in the past to obtain the behavior state label corresponding to the user account, and the operation behavior of the user account in the client can be predicted according to the behavior state label. Since the behavior state label is obtained by classifying the data related to the posture of the mobile terminal, it not only has a correlation with the user's motion state, but also is not affected by the diversity of the motion state. Therefore, there is an accurate correspondence between the determined behavior state label and different types of motion states. Predicting the operation behavior of the user account in the client through accurate behavior state labels can improve the accuracy of predicting the operation behavior.

[0096] Figure 4FIG. 1 is a flow chart of a method for predicting an operation behavior provided by an exemplary embodiment of the present application. The method can be used in a computer device or a client on a computer device, for example, Figure 1 As shown in the client Figure 4 As shown, the method includes:

[0097] Step 402: Acquire current posture data corresponding to the mobile terminal within a unit time length.

[0098] The client runs in a mobile terminal, and the mobile terminal includes a computer device that can be used during movement. In some embodiments, the client in this application includes a listening client, a song client, a singing client, a live broadcast client, a short video client, a video on demand client, a social client, an office client, a game client, a takeaway client, an online shopping client, a financial client, a life service client, a navigation client, a medical client, a learning client, and any one of a mini program. In some embodiments, the mobile terminal in this application includes at least one of a smart phone, a tablet computer, a smart watch, an e-book reader, an MP3 player, an MP4 player, and a laptop computer.

[0099] The current posture data is related to the posture of the mobile terminal within the unit time. The current posture data corresponding to the mobile terminal within the unit time includes the posture data corresponding to the mobile terminal collected by the client within the first time period, and the duration of the first time period is the unit time period. Optionally, the end time of the first time period is the current time. Optionally, the unit time period is pre-set in the client, for example, it is set by the developer of the client. In some embodiments, the client obtains the current posture data corresponding to the mobile terminal within the unit time period by sampling the posture data corresponding to the mobile terminal within the first time period. The posture data corresponding to the mobile terminal includes data affected by the posture of the mobile terminal in the relevant data of the mobile terminal, and the relevant data of the mobile terminal includes data collected by the mobile terminal, and the current posture data includes data related to the posture of the mobile terminal within the first time period. The posture of the mobile terminal will be affected by the motion state corresponding to the user account of the client, and the motion state corresponding to the user account is the state of the user motion corresponding to the user account, and the user corresponding to the user account includes the object of logging in the user account in the client to use the client. For example, the motion state corresponding to the user account includes at least one of walking, running, standing, sitting, lying flat, lying down, and squatting.

[0100] In some embodiments, the current posture data is obtained by the client through a motion sensor in the mobile terminal. Optionally, the motion sensor in the mobile terminal includes at least one of a gravity sensor, an acceleration sensor, an azimuth sensor, and a gyroscope sensor in the mobile terminal.

[0101] Optionally, the current posture data includes at least one of first sensor data, second sensor data, third sensor data and fourth sensor data, wherein the first sensor data is collected by a gravity sensor of the mobile terminal, the second sensor data is collected by an acceleration sensor of the mobile terminal, the third sensor data is collected by an azimuth sensor of the mobile terminal, and the fourth sensor data is collected by a gyroscope sensor of the mobile terminal.

[0102] Optionally, the client obtains first raw data collected by the gravity sensor and processes the first raw data, thereby obtaining first sensor data. The client obtains second raw data collected by the acceleration sensor and processes the second raw data, thereby obtaining second sensor data. The client obtains third raw data collected by the azimuth sensor and processes the third raw data, thereby obtaining third sensor data. The client obtains fourth raw data collected by the gyroscope sensor and processes the fourth raw data, thereby obtaining fourth sensor data.

[0103] In some embodiments, the current posture data is collected by the client according to the sampling frequency in the first time period, and the current posture data includes the posture data corresponding to the mobile terminal at multiple sampling moments in the first time period. Optionally, the first sensor data includes at least one of the coordinate axis with the largest gravity mean and the coordinate axis with the largest gravity change. The coordinate axis includes the x-axis, the y-axis and the z-axis. The gravity mean of a certain coordinate axis is determined according to the average value of the gravity acceleration component collected by the gravity sensor on the coordinate axis at each sampling moment, and the gravity change of a certain coordinate axis is determined by accumulating the difference of the gravity acceleration component collected by the gravity sensor on the coordinate axis at adjacent sampling moments. Optionally, the second sensor data includes at least one of the number of acceleration peaks, the average interval of acceleration peaks, the standard deviation of the interval of acceleration peaks, the average value of the Euclidean distance of acceleration, and the standard deviation of the Euclidean distance of acceleration. The acceleration peak includes the acceleration collected at the target sampling moment, and the acceleration collected at the sampling moment before and after the target sampling moment is lower than the acceleration collected at the target sampling moment. The average interval of the acceleration peaks is determined based on the average value of the time intervals of the sampling moments of two adjacent acceleration peaks. The standard deviation of the interval of the acceleration peaks is determined based on the standard deviation of the time intervals of the sampling moments of two adjacent acceleration peaks. The average value of the Euclidean distance of the acceleration is determined based on the average value of the Euclidean distances corresponding to the accelerations collected at different sampling moments. The standard deviation of the Euclidean distance of the acceleration is determined based on the standard deviation of the Euclidean distances corresponding to the accelerations collected at different sampling moments. Optionally, the third sensor data includes at least one of the coefficient of variation of the azimuth, the average azimuth, the coefficient of variation of the horizontal angle, the average horizontal angle, the coefficient of variation of the pitch angle, and the average pitch angle. The coefficient of variation of the azimuth is determined based on the coefficient of variation corresponding to the azimuth collected at different sampling moments. The average azimuth is determined based on the average value of the azimuth collected at different sampling moments. The coefficient of variation of the horizontal angle is determined based on the coefficient of variation corresponding to the horizontal angle in the azimuth collected at different sampling moments. The average horizontal angle is determined based on the average value of the horizontal angle in the azimuth collected at different sampling moments. The coefficient of variation of the pitch angle is determined based on the coefficient of variation corresponding to the pitch angle in the azimuth angle collected at different sampling moments. The average pitch angle is determined based on the average value of the pitch angle in the azimuth angle collected at different sampling moments. Optionally, the fourth sensor data includes the coefficient of variation of the gyroscope data. The coefficient of variation of the gyroscope data is determined based on the coefficient of variation corresponding to the gyroscope data collected at different sampling moments.

[0104] Step 404: Determine the behavior state label corresponding to the user account of the client by clustering the current posture data and a plurality of historical posture data.

[0105] A plurality of historical posture data include posture data corresponding to the mobile terminal in a plurality of unit durations in the past, and the historical posture data are related to the posture of the mobile terminal in the unit duration in the past. A plurality of historical posture data include posture data corresponding to the mobile terminal collected by the client in a plurality of second time periods in the past, each second time period having a unit duration, and the second time period being before the first time period. In some embodiments, the client obtains historical posture data corresponding to the mobile terminal in a plurality of unit durations in the past by sampling the posture data corresponding to the mobile terminal in each second time period, thereby obtaining a plurality of historical posture data. In some embodiments, when the client obtains the historical posture data, it will store the obtained historical posture data. For the introduction of the posture data corresponding to the mobile terminal, reference may be made to the relevant contents in step 402, and the embodiments of the present application will not be repeated here. In some embodiments, the type of data in the current posture data is the same as the historical posture data.

[0106] In some embodiments, the client obtains multiple clusters by clustering the current posture data and each posture data in the multiple historical posture data, each cluster having a cluster center, and each cluster including one or more posture data in the current posture data and the historical posture data. Clustering is the process of classifying similar data in a data set into the same class or the same cluster. The purpose of clustering is to make the data in the same cluster have a higher similarity, while the data between different clusters have a greater difference. Since the posture data is associated with the motion state, the posture data under different clusters are generated under different motion states, that is, each cluster obtained by clustering corresponds to a unique motion state, so different clusters will correspond to different motion states. The behavior state label corresponding to the user account of the client is the label corresponding to the cluster to which the current posture data belongs, and the behavior state label is related to the motion state of the user corresponding to the user account in the unit time length used to obtain the current posture data, that is, the behavior state label is related to the motion state of the user corresponding to the user account in the first time period. If the motion state of the user corresponding to the user account in the first time period is different, the behavior state label corresponding to the current posture data is also different.

[0107] In some embodiments, the client inputs the current posture data into the clustering model, thereby obtaining the clustering label corresponding to the current posture data output by the clustering model, and determines the clustering label as the behavior state label corresponding to the user account. The clustering label is used to reflect the cluster cluster where the current posture data is located, and the clustering model is trained by multiple historical posture data. The clustering model is a model built based on a clustering algorithm, and the clustering model can be a machine learning model. In some embodiments, the clustering algorithm is a density-based clustering algorithm, such as a density-based clustering algorithm with noise (Density-BasedSpatial Clustering of Applications with Noise, DBSCAN). DBSCAN implements clustering based on the density of data points. If the density of data points in an area exceeds a certain threshold, DBSCAN will divide these data points into a cluster. At the same time, DBSCAN can also identify noise points in the data set (i.e., data points that do not belong to any cluster). For example, when analyzing the distribution of cities on a map, high-density urban areas can be clustered, while single cities isolated in large open areas may be regarded as noise points. It should be noted that in addition to using DBSCAN, you can also use a hierarchical density-based spatial clustering algorithm with noise (Hierarchical Density-Based Spatial Clustering of Applications with Noise, HDBSCAN) or a clustering algorithm based on ordering points to identify the clustering structure (Ordering Points To Identify the Clustering Structure, OPTICS) to achieve clustering of current posture data and historical posture data. The embodiments of the present application do not limit the clustering algorithm used.

[0108] For example, Figure 5 FIG. 1 is a schematic diagram of a clustering process of current posture data and historical posture data provided by an exemplary embodiment of the present application. Figure 5As shown, the posture data corresponding to the mobile terminal is determined based on the data collected by the acceleration sensor as an example. In the process of determining the behavior status label corresponding to the user account, the client obtains the original data 501 collected by the acceleration sensor, and then converts the original data 501 according to the preset index, determines the data feature 502 corresponding to the original data 501, and obtains the current posture data. The current posture data includes the number of acceleration peaks, the average interval of the acceleration peaks, the standard deviation of the interval of the acceleration peaks, the average value of the Euclidean distance of the acceleration, and the standard deviation of the Euclidean distance of the acceleration. After that, the client will normalize the current posture data to obtain the normalized feature 503, and construct a data set 504 with the normalized feature 503 corresponding to the current posture data and the normalized feature corresponding to the historical posture data. After that, the client will cluster the data in the data set 504, so as to determine the behavior status label corresponding to the user account according to the clustering result.

[0109] For example, Figure 6 FIG. 1 is a schematic diagram of a cluster provided by an exemplary embodiment of the present application. Figure 6 As shown in the figure, the client clusters the current posture data and historical posture data through DBSCAN. The parameter Epsilon (eps) of DBSCAN is set to 0.5. The parameter Epsilon is used to determine the neighborhood radius of a point, that is, all points within the ε range of a point are considered to be neighbors of the point. The parameter MinPts (minimum number of points) of DBSCAN is set to 20. The parameter MinPts indicates the minimum number of points that must be included in the ε neighborhood of a point in order for the point to become a core point. The current posture data and historical posture data include 717 data. Through DBSCAN clustering, 6 types of labels are obtained, corresponding to Figure 6 Cluster 601, cluster 602, cluster 603, cluster 604, cluster 605, and cluster 606 are shown in FIG. For example, Figure 7 FIG. 1 is a schematic diagram of cluster labels provided by an exemplary embodiment of the present application. Figure 7 As shown in the figure, by clustering the current posture data and the historical posture data, 6 types of labels can be obtained, namely 0, 1, 2, 3, 4, and 5. The label -1 represents noise data. The proportion of posture data under different labels is Figure 7 as shown in the pie chart.

[0110] Step 406: Acquire multiple historical operation behaviors according to the behavior state tags.

[0111] The multiple historical operation behaviors include the operation behaviors performed in the client when the user account was in the behavior status tag in the past. The operation behaviors performed in the client each time the user account was in the behavior status tag in the past include one or more operations. The multiple historical operation behaviors can be determined based on the operation behaviors performed in the client when the user account was in the behavior status tag once in the past, or can be determined based on the operation behaviors performed in the client when the user account was in the behavior status tag multiple times in the past, and the embodiments of the present application are not limited to this.

[0112] For example, the behavior state label determined by the client according to the current posture data is label 1. The user account was in label 1 in the past time period 1, and the operation behaviors performed by the user account in time period 1 include operation 1 and operation 2. The user account was in label 2 in the past time period 2, and the operation behaviors performed by the user account in time period 2 include operation 3 and operation 4. The user account was in label 1 in the past time period 3, and the operation behaviors performed by the user account in time period 3 include operation 1. In this case, the client obtains the operation behaviors performed by the user account in the past time periods 1 and 3 as multiple historical operation behaviors, and the multiple historical operation behaviors include operation 1, operation 2, and operation 1.

[0113] Step 408: Determine a target operation behavior of the user account in the client according to the multiple historical operation behaviors.

[0114] The target operation behavior is used to predict the operation behavior that the user corresponding to the user account may perform in the motion state corresponding to the behavior state label. The operation behavior is the operation performed by the user account in the client. Optionally, the operation behavior is used to indicate the function used by the user account in the client.

[0115] Optionally, the client determines a target operation behavior of the user account in the client according to the triggering frequency of different operation behaviors in multiple historical operation behaviors, for example, determining the historical operation behavior with the highest triggering frequency as the target operation behavior.

[0116] In some embodiments, the client in the present application is used for song playback. In the case where the song playback operation accounts for the largest proportion among multiple historical operation behaviors, the client determines the target operation behavior to be the song playback operation. The song playback operation is an operation behavior used to play songs in the client. In the case where the pause playback operation accounts for the largest proportion among multiple historical operation behaviors, the client determines the target operation behavior to be the pause playback operation. The pause playback operation is an operation behavior used to pause the song currently being played in the client. In the case where the song library viewing operation accounts for the largest proportion among multiple historical operation behaviors, the client determines the target operation behavior to be the song library viewing operation. The song library viewing operation is an operation behavior used to view the song library in the client. In the case where the singer library viewing operation accounts for the largest proportion among multiple historical operation behaviors, the target operation behavior is determined to be the singer library viewing operation. The singer library viewing operation is an operation behavior used to view the singer library in the client. In the case where the adjustment of the playback volume operation accounts for the largest proportion among multiple historical operation behaviors, the client determines the target operation behavior to be the adjustment of the playback volume operation. The adjustment of the playback volume operation is an operation used to adjust the volume of the song playback in the client. In the case where the sound effect switching operation accounts for the largest proportion among multiple historical operation behaviors, the client determines the target operation behavior to be the sound effect switching operation. The sound effect switching operation is an operation behavior in the client used to switch the sound effects when playing songs.

[0117] Optionally, after the client predicts the target operation behavior of the user account in the client, the client will also trigger an automated process corresponding to the target operation behavior in the client based on the target operation behavior to improve the user experience of the client. The automated process is a process that is automatically executed by the client.

[0118] In some embodiments, when the target operation behavior is a song playing operation, the client will display the recommended songs recommended to the user account, and the client can display the recommended songs in the currently displayed user interface. Optionally, the recommended songs are determined by the client based on the historical songs played by the user account in the past, and the historical songs include the songs played by the user account in the past when it was in the behavior state label. Optionally, in the process of determining the recommended songs based on the historical songs, the client obtains the type label corresponding to the historical posture data, and the type label is used to reflect the type of motion state corresponding to the historical posture data, and the type label is set manually. After that, the client can determine the type of motion state corresponding to the current posture data based on the type label of the target historical posture data corresponding to the current posture data. The target historical posture data includes historical posture data that belongs to the same cluster cluster as the current posture data after clustering. The client calculates the similarity between the lyrics of each song in the historical songs and the type of motion state corresponding to the current posture data, and determines the historical song with the highest similarity as the recommended song.

[0119] In some embodiments, when the target operation behavior is a pause play operation, the client will pause playing songs for the user account. Optionally, the client will pause playing songs for the user account only when the cumulative number of plays of the song currently played by the user account is less than a number threshold. The number threshold can be set by the user account in the client.

[0120] In some embodiments, when the target operation behavior is a song library viewing operation, the client will display the song library interface in the client. In some embodiments, when the target operation behavior is a singer library viewing operation, the singer library interface in the client is displayed. The song library interface is a user interface in the client for displaying the song library of the client, and the singer library interface is a user interface in the client for displaying the singer library of the client.

[0121] In some embodiments, when the target operation behavior is to adjust the playback volume, the client will adjust the volume of the song played by the user account according to the playback volume adjustment operation. Optionally, the client will obtain the playback volume of each song played during the user account's past multiple times in the behavior state label, and calculate the average of all playback volumes to obtain the volume average. When adjusting the volume of the song played by the user account, the client will adjust the volume of the song played to the volume average.

[0122] In some embodiments, when the target operation behavior is a sound effect switching operation, the sound effect of the song played by the user account is adjusted according to the sound effect switching operation. Optionally, the client obtains the sound effect used each time the user account played a song during the past multiple times when the user account was in the behavior state label, and determines the sound effect with the highest proportion among all the sound effects obtained to obtain the target sound effect. When adjusting the sound effect of the song played by the user account, the client adjusts the sound effect of the song played to the target sound effect.

[0123] In some embodiments, in the process of determining the target operation behavior, the client also obtains the device features corresponding to the mobile terminal, and the device features include the features obtained for the mobile terminal during the client obtaining the current posture data. Optionally, the device features include at least one of the first feature, the second feature, the third feature, the fourth feature, and the fifth feature. Among them, the first feature is used to reflect the signal strength of the mobile terminal, for example, the wireless local area network (Wireless Local Area Network, WLAN) signal strength of the mobile terminal. For example, the value of the first feature is 0-4, and the larger the number, the stronger the signal strength of the mobile terminal. The second feature is used to reflect the remaining power of the mobile terminal. For example, the value of the second feature is 1-5, and the larger the number, the more remaining power the mobile terminal has. The third feature is used to reflect the charging status of the mobile terminal. For example, the value of the third feature is 1-5, 1 indicates that the mobile terminal is performing fast wired charging, 2 indicates that the mobile terminal is performing slow wired charging, 3 indicates that the mobile terminal is performing fast wireless charging, 4 indicates that the mobile terminal is performing slow wireless charging, and 5 indicates that the mobile terminal is not charging. The fourth feature is used to reflect the song playing status of the mobile terminal, and is used to indicate whether the mobile terminal is currently playing a song. The fifth feature is used to reflect the Bluetooth device connected to the mobile terminal, such as the index of the Bluetooth device connected to the mobile terminal. The client predicts the target operation behavior of the user account in the client based on the behavior status label and the device characteristics. Optionally, the client obtains multiple historical operation behaviors based on the behavior status label and the device characteristics. In this case, the multiple historical operation behaviors include the operation behaviors performed in the client when the user account was in the behavior status label and had the acquired device characteristics in the past. The client will then determine the target operation behavior based on the multiple historical operation behaviors. The process of determining the target operation behavior can refer to the relevant content in the previous text, and the embodiments of the present application will not be repeated in detail.

[0124] In some embodiments, when the Bluetooth device connected to the mobile terminal indicated by the fifth feature is a vehicle-mounted device, such as a vehicle-mounted central control, the client will also obtain vehicle-related information of the vehicle where the vehicle-mounted central control is located through the vehicle-mounted central control. Vehicle-related information includes at least one of seat sensor information, in-vehicle camera information, seat massage information, air conditioning information, and aromatherapy information. Among them, the seat sensor information is used to indicate the seat occupied by the passenger in the vehicle, the in-vehicle camera information includes the image taken by the in-vehicle camera of the vehicle, the seat massage information is used to reflect whether the massage function of the vehicle seat is turned on, the air conditioning information is used to reflect the operating status of the vehicle's air conditioning, and the aromatherapy information is used to reflect whether the vehicle's aromatherapy is turned on. After obtaining the vehicle-related information, the client will predict the target operation behavior of the user account in the client according to the behavior state tag and the vehicle-related information. Optionally, the client obtains multiple historical operation behaviors according to the behavior state tag and the vehicle-related information. In this case, the multiple historical operation behaviors include the operation behaviors performed in the client when the user account was in the behavior state tag in the past and corresponding to the vehicle-related information. After that, the client will determine the target operation behavior according to the multiple historical operation behaviors. Optionally, when the target operation behavior determined by the client is a song playing operation, the client will also obtain the target songs played by the song playing operations in multiple historical operation behaviors, and recommend the target songs to the user account, or automatically switch the song currently playing on the client to the target song when the song currently playing on the client is inconsistent with the target song.

[0125] In some embodiments, the client will obtain the device features corresponding to the current posture data and the device features corresponding to each historical posture data during the process of clustering the current posture data and multiple historical posture data to determine the behavior status label corresponding to the client's user account. The device features corresponding to the current posture data include the features obtained for the mobile terminal during the period when the client obtains the current posture data, and the device features corresponding to the historical posture data include the features obtained for the mobile terminal during the period when the client obtains the historical posture data. Afterwards, the client will splice the current posture data and the device features corresponding to the current posture data into the current features, and splice the historical posture data and the device features corresponding to the historical posture data into the historical features, and then cluster the current features and multiple historical features to determine the behavior status label corresponding to the client's user account. The process of clustering the current features and multiple historical features can refer to the process of clustering the current posture data and multiple historical posture data in the previous text, and the embodiments of the present application will not be repeated in detail.

[0126] In summary, the method provided in this embodiment obtains the current posture data related to the posture of the mobile terminal, and classifies the current posture data with the historical posture data collected in the past to obtain the behavior state label corresponding to the user account, and the operation behavior of the user account in the client can be predicted according to the behavior state label. Since the behavior state label is obtained by classifying the data related to the posture of the mobile terminal, it is not only associated with the user's motion state, but also will not be affected by the diversity of the motion state. Therefore, there is an accurate correspondence between the determined behavior state label and different types of motion states. Predicting the operation behavior of the user account in the client through accurate behavior state labels can improve the accuracy of predicting the operation behavior. In addition, since the determined behavior state label is related to the motion state, and the process of determining the behavior state label does not need to continuously obtain the posture data corresponding to the mobile terminal, and the method of predicting the motion state according to the neural network model requires continuous collection of the motion data of the mobile terminal. Therefore, compared with the method of predicting the motion state by the neural network model, it can avoid continuously turning on the motion sensor of the mobile terminal, thereby achieving the effect of saving power.

[0127] The method provided in this embodiment also determines the behavior state label by clustering the current posture data and multiple historical posture data. Since the clustering result will not be affected by the diversity of motion states, the accuracy of the determined behavior state label can be improved. By determining the behavior state label based on multiple sensor data, it is possible to determine the behavior state label by referring to data of multiple dimensions, thereby improving the accuracy of the determined behavior state label. By predicting the target operation behavior based on historical operation behavior, since the prediction process refers to the operation behavior of the same user in the past under the same motion state, it helps to improve the accuracy of the predicted operation behavior. By predicting the target operation behavior of the user account based on the device characteristics corresponding to the mobile terminal, it is possible to refer to more dimensions of information compared to only referring to the behavior state label, thereby improving the accuracy of the predicted operation behavior.

[0128] It should be noted that before collecting relevant data of users and during the process of collecting relevant data of users, this application can display a prompt interface, pop-up window or output voice prompt information, and the prompt interface, pop-up window or voice prompt information is used to prompt the user that its relevant data is currently being collected, so that this application only starts to execute the relevant steps of obtaining relevant data of users after obtaining the confirmation operation issued by the user to the prompt interface or pop-up window, otherwise (that is, when the confirmation operation issued by the user to the prompt interface or pop-up window is not obtained), the relevant steps of obtaining relevant data of users are terminated, that is, the relevant data of users are not obtained. In other words, all user data collected by this application are collected with the consent and authorization of the user, and the collection, use and processing of relevant user data need to comply with the relevant laws, regulations and standards of relevant countries and regions.

[0129] It should be noted that the sequence of the method steps provided in the embodiments of the present application can be appropriately adjusted, and the steps can be increased or decreased accordingly according to the circumstances. Any technician familiar with the technical field can easily think of the changed methods within the technical scope disclosed in the present application, and they should be included in the protection scope of the present application, so they will not be repeated here.

[0130] Figure 8 FIG. 1 is a schematic diagram of a structure of an operation behavior prediction device provided by an exemplary embodiment of the present application. Figure 8 As shown, the device comprises:

[0131] An acquisition module 801 is used to acquire current posture data corresponding to a mobile terminal within a unit time length, and the device runs in the mobile terminal;

[0132] A determination module 802 is used to determine a behavior state label corresponding to a user account of the device by classifying the current posture data and a plurality of historical posture data, wherein the behavior state label is related to a motion state corresponding to the user account, and the plurality of historical posture data include posture data corresponding to the mobile terminal in a plurality of unit time periods in the past;

[0133] The prediction module 803 is used to predict the target operation behavior of the user account in the device according to the behavior state label.

[0134] In an optional design, the determining module 802 is used to:

[0135] The behavior state label corresponding to the user account is determined by clustering the current posture data and the multiple historical posture data.

[0136] In an optional design, the determining module 802 is used to:

[0137] Inputting the current posture data into a clustering model to obtain a clustering label corresponding to the current posture data output by the clustering model;

[0138] Determining the cluster label as the behavior status label corresponding to the user account;

[0139] Wherein, the clustering model is trained by the multiple historical posture data, and the clustering model is a model constructed based on a clustering algorithm.

[0140] In an optional design, the current posture data includes at least one of first sensor data, second sensor data, third sensor data, and fourth sensor data;

[0141] Among them, the first sensor data is collected by the gravity sensor of the mobile terminal, the second sensor data is collected by the acceleration sensor of the mobile terminal, the third sensor data is collected by the azimuth sensor of the mobile terminal, and the fourth sensor data is collected by the gyroscope sensor of the mobile terminal.

[0142] In an optional design, the first sensor data includes at least one of a coordinate axis with a maximum gravity mean value and a coordinate axis with a maximum gravity change.

[0143] In an optional design, the second sensor data includes at least one of the number of acceleration peaks, the average interval of the acceleration peaks, the standard deviation of the interval of the acceleration peaks, the average value of the Euclidean distance of acceleration, and the standard deviation of the Euclidean distance of acceleration.

[0144] In an optional design, the third sensor data includes at least one of a coefficient of variation of an azimuth angle, an average azimuth angle, a coefficient of variation of a horizontal angle, an average horizontal angle, a coefficient of variation of an elevation angle, and an average elevation angle.

[0145] In an optional design, the fourth sensor data includes a coefficient of variation of the gyroscope data.

[0146] In an optional design, the prediction module 803 is used to:

[0147] Acquire a plurality of historical operation behaviors according to the behavior state tag, wherein the plurality of historical operation behaviors include operation behaviors performed in the device when the user account was in the behavior state tag in the past;

[0148] According to the multiple historical operation behaviors, a target operation behavior of the user account in the device is determined.

[0149] In an optional design, the device is used for song playback; the prediction module 803 is used to:

[0150] In a case where song playing operations account for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the song playing operation;

[0151] In a case where the pause playback operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the pause playback operation;

[0152] In the case where the song library viewing operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the song library viewing operation;

[0153] In the case where the singer library viewing operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the singer library viewing operation;

[0154] In a case where the playback volume adjustment operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the playback volume adjustment operation;

[0155] In a case where the sound effect switching operation accounts for the largest proportion among the multiple historical operation behaviors, the target operation behavior is determined to be the sound effect switching operation.

[0156] In an alternative design, such as Fig. 9 As shown, the apparatus further includes a processing module 804, and the processing module 804 is used for at least one of the following:

[0157] In the case where the target operation behavior is the song playing operation, displaying recommended songs recommended to the user account;

[0158] When the target operation behavior is the pause play operation, pausing the song playing for the user account;

[0159] When the target operation behavior is the song library viewing operation, displaying the song library interface in the device;

[0160] When the target operation behavior is the singer library viewing operation, displaying the singer library interface in the device;

[0161] When the target operation behavior is the operation of adjusting the playback volume, adjusting the volume of the song played by the user account according to the operation of adjusting the playback volume;

[0162] When the target operation behavior is the sound effect switching operation, the sound effect of the song played by the user account is adjusted according to the sound effect switching operation.

[0163] In an optional design, the acquisition module 801 is used to:

[0164] Acquire device characteristics corresponding to the mobile terminal;

[0165] The prediction module 803 is used to:

[0166] According to the behavior state tag and the device feature, a target operation behavior of the user account in the device is predicted.

[0167] In an optional design, the device feature includes at least one of the first feature, the second feature, the third feature, the fourth feature and the fifth feature;

[0168] Among them, the first feature is used to reflect the signal strength of the mobile terminal, the second feature is used to reflect the remaining power of the mobile terminal, the third feature is used to reflect the charging status of the mobile terminal, the fourth feature is used to reflect the song playing status of the mobile terminal, and the fifth feature is used to reflect the Bluetooth device connected to the mobile terminal.

[0169] It should be noted that the prediction device for operation behavior provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, 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 prediction device for operation behavior provided in the above embodiment and the prediction method embodiment of operation behavior belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0170] An embodiment of the present application also provides a computer device, which includes: a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the prediction method of the operating behavior provided by the above-mentioned method embodiments.

[0171] In some embodiments, the computer device is a terminal. Fig.10 It is a schematic diagram of the structure of a terminal provided by an exemplary embodiment of the present application.

[0172] Typically, the terminal 1000 includes a processor 1001 and a memory 1002 .

[0173] The processor 1001 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1001 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1001 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1001 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1001 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0174] The memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1002 is used to store at least one instruction, which is used to be executed by the processor 1001 to implement the prediction method of the operation behavior provided in the method embodiment of the present application.

[0175] In some embodiments, the terminal 1000 may further optionally include: a peripheral device interface 1003 and at least one peripheral device. The processor 1001, the memory 1002 and the peripheral device interface 1003 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 1003 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 1004, a display screen 1005, a camera assembly 1006, an audio circuit 1007 and a power supply 1008.

[0176] The peripheral device interface 1003 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 1001 and the memory 1002. In some embodiments, the processor 1001, the memory 1002, and the peripheral device interface 1003 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1001, the memory 1002, and the peripheral device interface 1003 may be implemented on a separate chip or circuit board, which is not limited in the embodiments of the present application.

[0177] The radio frequency circuit 1004 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1004 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 1004 converts the electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 1004 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The radio frequency circuit 1004 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1004 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0178] The display screen 1005 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1005 is a touch display screen, the display screen 1005 also has the ability to collect touch signals on the surface or above the surface of the display screen 1005. The touch signal can be input to the processor 1001 as a control signal for processing. At this time, the display screen 1005 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 1005 can be one, and the front panel of the terminal 1000 is set; in other embodiments, the display screen 1005 can be at least two, which are respectively set on different surfaces of the terminal 1000 or are folded; in some other embodiments, the display screen 1005 can be a flexible display screen, which is set on the curved surface or folded surface of the terminal 1000. Even, the display screen 1005 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 1005 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0179] The camera assembly 1006 is used to capture images or videos. Optionally, the camera assembly 1006 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal 1000, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize the panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1006 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0180] The audio circuit 1007 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 1001 for processing, or input them into the radio frequency circuit 1004 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 1000. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 1001 or the radio frequency circuit 1004 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 1007 may also include a headphone jack.

[0181] The power supply 1008 is used to power various components in the terminal 1000. The power supply 1008 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 1008 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0182] In some embodiments, the terminal 1000 further includes one or more sensors 1009 . The one or more sensors 1009 include, but are not limited to: an acceleration sensor 1010 , a gyroscope sensor 1011 , a pressure sensor 1012 , an optical sensor 1013 , and a proximity sensor 1014 .

[0183] The acceleration sensor 1010 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal 1000. For example, the acceleration sensor 1010 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 1001 can control the touch display screen 1005 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 1010. The acceleration sensor 1010 can also be used for collecting game or user motion data.

[0184] The gyro sensor 1011 can detect the body direction and rotation angle of the terminal 1000, and the gyro sensor 1011 can cooperate with the acceleration sensor 1010 to collect the user's 3D actions on the terminal 1000. The processor 1001 can implement the following functions based on the data collected by the gyro sensor 1011: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0185] The pressure sensor 1012 can be set on the side frame of the terminal 1000 and / or the lower layer of the touch display screen 1005. When the pressure sensor 1012 is set on the side frame of the terminal 1000, it can detect the user's holding signal of the terminal 1000, and the processor 1001 performs left and right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 1012. When the pressure sensor 1012 is set on the lower layer of the touch display screen 1005, the processor 1001 controls the operability controls on the UI interface according to the user's pressure operation on the touch display screen 1005. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0186] The optical sensor 1013 is used to collect the ambient light intensity. In one embodiment, the processor 1001 can control the display brightness of the touch display screen 1005 according to the ambient light intensity collected by the optical sensor 1013. Specifically, when the ambient light intensity is high, the display brightness of the touch display screen 1005 is increased; when the ambient light intensity is low, the display brightness of the touch display screen 1005 is reduced. In another embodiment, the processor 1001 can also dynamically adjust the shooting parameters of the camera assembly 1006 according to the ambient light intensity collected by the optical sensor 1013.

[0187] The proximity sensor 1014, also called a distance sensor, is usually arranged on the front panel of the terminal 1000. The proximity sensor 1014 is used to collect the distance between the user and the front of the terminal 1000. In one embodiment, when the proximity sensor 1014 detects that the distance between the user and the front of the terminal 1000 is gradually decreasing, the processor 1001 controls the touch display screen 1005 to switch from the screen-on state to the screen-off state; when the proximity sensor 1014 detects that the distance between the user and the front of the terminal 1000 is gradually increasing, the processor 1001 controls the touch display screen 1005 to switch from the screen-off state to the screen-on state.

[0188] Those skilled in the art will understand that Fig.10 The structure shown in the figure does not constitute a limitation on the terminal 1000, and the terminal 1000 may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.

[0189] A computer-readable storage medium is also provided in an embodiment of the present application, in which at least one instruction, at least one program, code set or instruction set is stored. When the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor of a computer device, the prediction method of the operation behavior provided by the above-mentioned method embodiments is implemented.

[0190] The present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the operation behavior prediction method provided by the above-mentioned method embodiments.

[0191] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned readable storage medium may be a read-only memory, a disk or an optical disk, etc.

[0192] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent switching, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting an operation behavior, characterized in that: The method is executed by a client, and includes: Acquire current posture data corresponding to a mobile terminal within a unit time, wherein the client runs in the mobile terminal; Determine a behavior state label corresponding to the user account of the client by classifying the current posture data and a plurality of historical posture data, wherein the behavior state label is related to the motion state corresponding to the user account, and the plurality of historical posture data include posture data corresponding to the mobile terminal in a plurality of unit time periods in the past; A target operation behavior of the user account in the client is predicted according to the behavior state tag.

2. The method according to claim 1, characterized in that The determining the behavior state label corresponding to the user account of the client by classifying the current posture data and the plurality of historical posture data includes: The behavior state label corresponding to the user account is determined by clustering the current posture data and the multiple historical posture data.

3. The method according to claim 2, characterized in that The step of determining the behavior state label corresponding to the user account by clustering the current posture data and the plurality of historical posture data includes: Inputting the current posture data into a clustering model to obtain a clustering label corresponding to the current posture data output by the clustering model; Determining the cluster label as the behavior status label corresponding to the user account; Wherein, the clustering model is trained by the multiple historical posture data, and the clustering model is a model constructed based on a clustering algorithm.

4. The method according to any one of claims 1 to 3, characterized in that: The current posture data includes at least one of first sensor data, second sensor data, third sensor data, and fourth sensor data; Among them, the first sensor data is collected by the gravity sensor of the mobile terminal, the second sensor data is collected by the acceleration sensor of the mobile terminal, the third sensor data is collected by the azimuth sensor of the mobile terminal, and the fourth sensor data is collected by the gyroscope sensor of the mobile terminal.

5. The method according to any one of claims 1 to 3, characterized in that: The predicting the target operation behavior of the user account in the client according to the behavior status tag includes: Acquire a plurality of historical operation behaviors according to the behavior status tag, wherein the plurality of historical operation behaviors include operation behaviors performed in the client when the user account was in the behavior status tag in the past; According to the multiple historical operation behaviors, a target operation behavior of the user account in the client is determined.

6. The method according to claim 5, characterized in that The client is used for playing songs; and determining the target operation behavior of the user account in the client according to the multiple historical operation behaviors includes: In a case where song playing operations account for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the song playing operation; In a case where the pause playback operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the pause playback operation; In the case where the song library viewing operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the song library viewing operation; In the case where the singer library viewing operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the singer library viewing operation; In a case where the playback volume adjustment operation accounts for the largest proportion among the multiple historical operation behaviors, determining the target operation behavior to be the playback volume adjustment operation; In a case where the sound effect switching operation accounts for the largest proportion among the multiple historical operation behaviors, the target operation behavior is determined to be the sound effect switching operation.

7. The method according to claim 6, characterized in that The method further comprises at least one of the following: In the case where the target operation behavior is the song playing operation, displaying recommended songs recommended to the user account; When the target operation behavior is the pause play operation, pausing the song playing for the user account; When the target operation behavior is the song library viewing operation, displaying the song library interface in the client; When the target operation behavior is the singer library viewing operation, displaying the singer library interface in the client; When the target operation behavior is the operation of adjusting the playback volume, adjusting the volume of the song played by the user account according to the operation of adjusting the playback volume; When the target operation behavior is the sound effect switching operation, the sound effect of the song played by the user account is adjusted according to the sound effect switching operation.

8. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Acquire device characteristics corresponding to the mobile terminal; The predicting the target operation behavior of the user account in the client according to the behavior status tag includes: According to the behavior state tag and the device feature, a target operation behavior of the user account in the client is predicted.

9. The method according to claim 8, characterized in that The device feature includes at least one of the first feature, the second feature, the third feature, the fourth feature and the fifth feature; Among them, the first feature is used to reflect the signal strength of the mobile terminal, the second feature is used to reflect the remaining power of the mobile terminal, the third feature is used to reflect the charging status of the mobile terminal, the fourth feature is used to reflect the song playing status of the mobile terminal, and the fifth feature is used to reflect the Bluetooth device connected to the mobile terminal.

10. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the method for predicting operation behavior as described in any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that: The readable storage medium stores at least one program, and the at least one program is loaded and executed by a processor to implement the method for predicting operation behavior as described in any one of claims 1 to 9.

12. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the method for predicting operational behavior as described in any one of claims 1 to 9.

Images