Webpage object motion identification method and related device

Abstract

The invention discloses a webpage object motion recognition method and a related device, and relates to the technical field of artificial intelligence, a webpage end responds to a motion recognition instruction of a to-be-recognized webpage object, and real-time pose data of a mobile terminal is obtained through a client which pre-constructs a communication link with the webpage end; and performing preset data processing on the real-time pose data to obtain feature data of the real-time pose data. And inputting the feature data of the real-time pose data into a pre-trained motion recognition model to obtain a motion recognition result of the to-be-recognized webpage object output by the motion recognition model. The client and the webpage end run on the mobile terminal, the webpage end obtains the real-time pose data of the mobile terminal through the client, the accuracy and the real-time performance of the real-time pose data are improved, and the motion recognition model is the pre-trained neural network model constructed based on the deep learning algorithm, so that the motion recognition efficiency is improved. And the accuracy of the motion identification result obtained by identifying the feature data of the real-time pose data is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and related device for identifying motion of web page objects. Background Art

[0002] In the traditional method, the web page side controls the movement of the web page object by analyzing the user's touch screen operation on the web page object. For example, the web page object is a moving character object on the web page. The web page side controls the translation direction and speed of the character object by analyzing the user's drag operation data. This method can only realize the recognition and control of the translation movement of the web page object, but cannot realize the recognition and control of the spatial movement (for example, rotation or multi-directional shaking) of the web page object.

[0003] With the development of sensing technology, web pages can detect the posture changes of mobile terminals by monitoring web interface events between the web page and the terminal device, thereby controlling web page objects to achieve highly complex spatial motion. However, currently the accuracy of the motion recognition results of web page objects based on the posture changes of mobile terminals detected by the web page interface events is low, making it impossible to accurately control the motion of web page objects. Summary of the invention

[0004] In view of the above problems, the present application provides a method and a related device for motion recognition of web page objects, aiming to improve the accuracy of the motion recognition results of web page objects by the web page end. The specific scheme is as follows:

[0005] The first aspect of the present application provides a method for identifying the motion of a web page object, which is applied to a web page, and includes:

[0006] In response to a motion recognition instruction of a web page object to be recognized, obtaining real-time position data of the mobile terminal through a client that has a communication link pre-established with the web page, wherein the client and the web page are running on the mobile terminal;

[0007] Performing preset data processing on the real-time posture data to obtain feature data of the real-time posture data;

[0008] The feature data of the real-time posture data is input into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, wherein the motion recognition model is a neural network model constructed based on a deep learning algorithm.

[0009] In a possible implementation, in response to a motion recognition instruction of a webpage object to be recognized, obtaining real-time position and posture data of a mobile terminal through a client that pre-establishes a communication link with the webpage terminal includes:

[0010] A posture data request instruction is sent to the client through a pre-configured bridge interface, so that the client obtains at least one type of sensor data indicated by the posture data request instruction through a preset acquisition interface, and transmits the collected sensor data as real-time posture data back to the web page through the bridge interface.

[0011] In a possible implementation, performing preset data processing on the real-time posture data to obtain feature data of the real-time posture data includes:

[0012] Performing preset data preprocessing on the real-time posture data to obtain standard data of the real-time posture data, wherein the data preprocessing includes normalization, filtering, and data cleaning;

[0013] Dividing the standard data of the real-time posture data according to a time window of a preset size to obtain data segments of the real-time posture data;

[0014] Feature extraction is performed on the data segment of the real-time posture data to obtain feature data of the real-time posture data.

[0015] In a possible implementation, performing feature extraction on a data segment of the real-time posture data to obtain feature data of the real-time posture data includes:

[0016] Using a statistical algorithm to obtain time domain features of a data segment of the real-time posture data;

[0017] Using Fourier transform to obtain frequency domain features of the data segment of the real-time posture data;

[0018] Using wavelet transform to obtain time-frequency domain features of a data segment of the real-time posture data;

[0019] The time domain features, frequency domain features and time-frequency domain features of the data segments of the real-time posture data are combined to obtain feature data of the real-time posture data.

[0020] In a possible implementation, before inputting the feature data of the real-time posture data into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, the web page object motion recognition method further includes:

[0021] Sending a configuration request to a web page server, the configuration request including the performance status of the mobile terminal, the configuration request being used to request the web page server to configure the motion recognition model for the web page;

[0022] In response to receiving the configuration information of the first motion recognition model sent by the web page server, the motion recognition model is configured based on the configuration information of the first motion recognition model; the first motion recognition model is trained by the web page server based on first training data, and the first training data includes feature data of sample posture data generated by a sample mobile terminal with the same performance state as the mobile terminal and a corresponding motion mode label, and the motion mode label corresponding to the feature data of the sample posture data is used to identify the motion mode of the sample mobile terminal when generating the sample posture data.

[0023] In a possible implementation, the method for identifying the motion of a webpage object further includes:

[0024] When a preset model optimization timing is reached, the web page sends an optimization request to the web page server, the optimization request includes the behavior state of the mobile terminal, and the optimization request is used to request optimization of the motion recognition model;

[0025] In response to receiving the configuration information of the second motion recognition model sent by the web server, the motion recognition model is optimized based on the configuration information of the second motion recognition model; the second motion recognition model is trained by the web server based on second training data, and the second training data includes feature data of sample posture data generated by a sample mobile terminal with the same performance state and behavior state as the mobile terminal, and a corresponding motion mode label.

[0026] In a possible implementation, after inputting the feature data of the real-time posture data into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, the motion recognition method of the web page object further includes:

[0027] According to the motion recognition result of the webpage object to be recognized, the webpage object to be recognized is controlled, and the motion recognition result includes one of the preset motion modes.

[0028] A second aspect of the present application provides a motion recognition device for a web page object, comprising:

[0029] A posture data acquisition unit, configured to respond to a motion recognition instruction of a webpage object to be recognized, and acquire real-time posture data of a mobile terminal through a client that has a communication link pre-established with the webpage end, wherein the client and the webpage end are running on the mobile terminal;

[0030] A feature extraction unit, used to perform preset data processing on the real-time posture data to obtain feature data of the real-time posture data;

[0031] The model recognition unit is used to input the feature data of the real-time posture data into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, wherein the motion recognition model is a neural network model constructed based on a deep learning algorithm.

[0032] A third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the motion recognition method for a web page object according to the first aspect or any implementation of the first aspect.

[0033] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0034] The memory is used to store computer programs;

[0035] The processor is used to execute the computer program so that the electronic device can implement the motion recognition method of the web page object of the first aspect or any implementation manner of the first aspect.

[0036] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the motion recognition method of a web page object according to the first aspect or any implementation of the first aspect.

[0037] By means of the above technical scheme, the present application provides a method and related device for motion recognition of web page objects. The web page side responds to the motion recognition instruction of the web page object to be recognized, obtains the real-time posture data of the mobile terminal through the client that pre-builds a communication link with the web page side, performs preset data processing on the real-time posture data, and obtains the feature data of the real-time posture data. The feature data of the real-time posture data is input into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model. Since the client and the web page side are running on the mobile terminal, the web page side obtains the real-time posture data of the mobile terminal through the client, thereby improving the accuracy and real-time performance of the real-time posture data. Since the motion recognition model is a pre-trained neural network model built based on a deep learning algorithm, the accuracy of the motion recognition result obtained by recognizing the feature data of the real-time posture data is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0039] Figure 1 A schematic diagram of a system architecture provided for this application;

[0040] Figure 2 An optional hardware structure diagram of the mobile terminal 100 is shown;

[0041] Figure 3 An optional hardware structure diagram of the server 200 is shown;

[0042] Figure 4 A schematic diagram of a flow chart of a method for identifying motion of a web page object provided in an embodiment of the present application;

[0043] Figure 5 A structural schematic diagram of a motion recognition system for a web page object is provided for an embodiment of the present application;

[0044] Figure 6 A schematic diagram of a flow chart of a method for identifying motion of a web page object provided in an embodiment of the present application;

[0045] Figure 7 A schematic diagram of a spatial coordinate system of a mobile terminal is shown;

[0046] Figure 8 A schematic diagram of the structure of another web page object motion recognition system provided in an embodiment of the present application;

[0047] Fig. 9 A method for training a motion recognition model provided in an embodiment of the present application;

[0048] Fig.10 A schematic diagram of the structure of a motion recognition device for a web page object provided in an embodiment of the present application;

[0049] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0051] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0052] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0053] The present application can be applied to the H5 web page technology and artificial intelligence technology fields, and is specifically applied to the scene of identifying the motion mode of the web page object on the H5 web page of the web page end, and controlling the web page object to perform corresponding motion. Among them, the web page end runs on the mobile terminal, and the mobile terminal also runs a client and is equipped with a sensor device for collecting the posture data of the mobile terminal.

[0054] See also Figure 1 , Figure 1 1 shows a schematic diagram of a system architecture. The system may include a mobile terminal 100 and a server 200. The server 200 may include one or more servers ( Figure 1 In the example, a server is included, and the server 200 can provide the method provided in the embodiment of the present application for one or more terminals.

[0055] Among them, a web page can be installed on the mobile terminal 100, and the web page of the above-mentioned web page can provide an interface. The mobile terminal 100 can receive relevant parameters entered by the user on the interface and send the above-mentioned parameters to the server 200. The server 200 can obtain processing results based on the received parameters and return the processing results to the mobile terminal 100.

[0056] It should be understood that in some optional implementations, the mobile terminal 100 can also complete the action of obtaining the processing result based on the received parameters by itself without the cooperation of the server, and the embodiments of the present application are not limited to this.

[0057] Next describe Figure 1 The product form of the mobile terminal 100;

[0058] The mobile terminal 100 in the embodiment of the present application may be a mobile terminal device such as a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, and the embodiment of the present application does not impose any limitation on this.

[0059] Figure 2 An optional hardware structure diagram of the mobile terminal 100 is shown.

[0060] refer to Figure 2 As shown, the mobile terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), an earphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190 and other components. Those skilled in the art will appreciate that Figure 2 These are merely examples of terminals or multi-function devices and do not constitute limitations on the terminals or multi-function devices, which may include more or fewer components than those shown in the figures, or combinations of certain components, or different components.

[0061] The input unit 130 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the portable multifunctional device. Specifically, the input unit 130 may include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can collect the user's touch operations on or near it (such as the user's operation on or near the touch screen using any suitable object such as fingers, joints, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute the command sent by the processor 170; the touch signal at least includes the touch point coordinate information. The touch screen 131 can provide an input interface and an output interface between the mobile terminal 100 and the user. In addition, the touch screen can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch screen 131, the input unit 130 can also include other input devices. Specifically, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0062] Among them, the input device 132 can receive input data and the like.

[0063] The display unit 140 may be used to display information input by the user or provided to the user, various menus of the mobile terminal 100, interactive interfaces, file display and / or playback of any multimedia file. In the embodiment of the present application, the display unit 140 may be used to display an interface of a motion recognition result of a web page object, a processing result, etc.

[0064] The memory 120 can be used to store instructions and data. The memory 120 can mainly include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files, texts, etc.; the instruction storage area can store software units such as operating systems, applications, instructions required for at least one function, or their subsets and extensions. It can also include a non-volatile random access memory; provide the processor 170 with hardware, software and data resources including management of computing and processing equipment, and support control software and applications. It is also used for the storage of multimedia files, and the storage of running programs and applications.

[0065] The processor 170 is the control center of the mobile terminal 100. It uses various interfaces and lines to connect various parts of the entire mobile terminal 100. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it executes various functions of the mobile terminal 100 and processes data, thereby controlling the terminal device as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 170. In some embodiments, the processor and the memory may be implemented on a single chip, and in some embodiments, they may also be implemented separately on separate chips. The processor 170 may also be used to generate corresponding operation control signals, send them to corresponding components of the computing and processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that each functional module therein performs corresponding functions, thereby controlling the corresponding components to act according to the requirements of the instructions.

[0066] Among them, the memory 120 can be used to store software codes related to the motion recognition method of web page objects, the processor 170 can execute the steps of the motion recognition method of web page objects, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to realize corresponding functions.

[0067] The radio frequency unit 110 (optional) can be used for receiving and sending information or receiving and sending signals during a call, for example, after receiving the downlink information of the base station, it is sent to the processor 170 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, etc. In addition, the radio frequency unit 110 can also communicate with network devices and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile communication (Global System of Mobile communication, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (SMS), etc.

[0068] In this embodiment of the present application, the RF unit 110 can send data to the server 200 and receive processing results sent by the server 200.

[0069] It should be understood that the radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.

[0070] The mobile terminal 100 also includes a power supply 190 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0071] The mobile terminal 100 further includes an external interface 180 , which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the mobile terminal 100 to communicate with other devices, or to connect a charger to charge the mobile terminal 100 .

[0072] Although not shown, the mobile terminal 100 may also include a flashlight, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which are not described in detail here. Some or all of the methods described below may be applied to Figure 2 In the mobile terminal 100 shown.

[0073] Next describe Figure 1 The product form of the server 200;

[0074] Figure 3 A structural diagram of a server 200 is provided, such as Figure 3 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0075] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0076] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0077] The memory 204 may include a volatile memory, such as a random access memory (RAM). The memory 204 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard drive (HDD), or a solid state drive (SSD).

[0078] The memory 204 may be used to store software codes related to the method for identifying the motion of a web page object, and the processor 202 may execute the steps of the method for identifying the motion of a web page object of the chip, and may also schedule other units to implement corresponding functions.

[0079] It should be understood that the above-mentioned mobile terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned mobile terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application specific integrated circuit (ASIC), field-programmable gate array (FPGA), general-purpose processor, digital signal processor (DSP), microprocessor or microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0080] The web page can realize different types of H5 web pages, such as risk control web pages and special web pages. Since the traditional touch screen operation method for controlling the movement of web page objects can realize a relatively single movement mode, it leads to poor user experience. For example, in the slider unlocking scenario of the risk control web page, only simple controls such as manual clicking and dragging can be realized through touch screen operation. The low complexity of the movement leads to low unlocking security. At present, in order to realize the high-complexity movement mode control of web page objects by the web page end, the web page end interface is usually used to monitor the web page end interface event to obtain device information, and the detection algorithm is implemented on the device information to obtain the movement recognition result. For example, in the prior art, the web page end can pre-construct a DeviceOrientation interface, and the DeviceOrientation interface encapsulates the event of the direction sensor data, and can obtain the direction data of the mobile device in the static state, such as the angle, orientation, and direction of the device. Therefore, the web page end listens to the DeviceOrientation event through the DeviceOrientation interface to obtain device information such as device posture information, thereby implementing a detection algorithm on the device information to obtain the movement mode of the current device.

[0081] However, the data accuracy of the device data acquisition method through interface monitoring events is low. This is because the performance of this method on different operating systems is inconsistent, and the device information only includes limited coarse-grained information items, which cannot accurately obtain the device posture data collected by various sensors. In addition, due to the high complexity of device posture changes, the accuracy of motion recognition results obtained by traditional detection algorithms is low.

[0082] In order to solve the above problems, the embodiment of the present application provides a method for motion recognition of web page objects, which is specifically applied to a web page running on a mobile terminal device, and the real-time acquisition of the posture data of the mobile terminal is realized through a client running on the mobile terminal, and the feature data of the real-time posture data is recognized by using a pre-trained motion recognition model through a deep learning algorithm to obtain the motion recognition result of the web page object. The motion recognition method of the web page object in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0083] Reference Figure 4 , Figure 4 A schematic diagram of a flow chart of a method for identifying a motion of a web page object provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, an embodiment of the present application provides a data processing method, which may include S401 to S403, and these steps are described in detail below.

[0084] S401. In response to a motion recognition instruction of a web page object to be recognized, real-time position and posture data of a mobile terminal is obtained through a client that has pre-established a communication link with a web page.

[0085] In this embodiment, the client and the web page are running on a mobile terminal, and the specific structure of the mobile terminal can refer to the above embodiment. The real-time posture data of the mobile terminal is composed of sensor data collected in real time by a variety of sensors.

[0086] In a possible implementation, the H5 webpage of the webpage is embedded into the client, and the H5 webpage of the webpage can be opened through the client, so that the webpage and the client can achieve real-time communication through a pre-built bridge structure. When the webpage obtains the real-time posture data of the mobile terminal through the client that pre-builds a communication link with the webpage, it sends a posture data request instruction to the client, so that the client can obtain at least one type of posture data indicated by the posture data request instruction through a preset acquisition interface. Among them, the posture data is composed of sensor data collected by sensors configured on the mobile terminal. For example, the posture data includes gyroscope data collected by a gyroscope, gravity change data collected by a gravity sensor, and acceleration data collected by an acceleration sensor.

[0087] S402: Perform preset data processing on the real-time posture data to obtain feature data of the real-time posture data.

[0088] In this embodiment, the feature data of the real-time posture data is used to describe the features of the real-time posture data, wherein the feature data includes feature values ​​of multiple features. Data processing includes data preprocessing, data partitioning, and feature extraction, wherein the data preprocessing may include data cleaning, normalization, and filtering.

[0089] S403: Input feature data of the real-time posture data into a pre-trained motion recognition model to obtain a motion recognition result of the web page object to be recognized output by the motion recognition model.

[0090] In this embodiment, the motion recognition model is based on a neural network model constructed based on a deep learning algorithm, for example, a LSTM (Long Short-Term Memory) model, a CNN (Convolutional Neural Network) model, or a Transformer model.

[0091] In this embodiment, the motion recognition model is trained based on training data, wherein the training data includes feature data of a large amount of sample posture data and corresponding motion mode labels, and the motion mode labels of the sample posture data are used to identify the motion mode of the mobile terminal when the sample posture data is generated. The training data is obtained based on historical data or test data.

[0092] In a possible implementation, the feature data of the sample pose data is sequentially input into the neural network model to be trained, and the various model parameters of the training neural network model are output with the motion mode label as the target, indicating that the preset training completion condition is met, and the neural network model is obtained. It should be noted that the training of the model can be completed by the client of the web page, that is, the web client.

[0093] It can be seen from the above technical solution that an embodiment of the present application provides a method for motion recognition of a web page object. The web page side responds to the motion recognition instruction of the web page object to be recognized, obtains the real-time posture data of the mobile terminal through the client that pre-builds a communication link with the web page side, performs preset data processing on the real-time posture data, and obtains the feature data of the real-time posture data. The feature data of the real-time posture data is input into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model. Since the client and the web page side are running on the mobile terminal, the web page side obtains the real-time posture data of the mobile terminal through the client, thereby improving the accuracy and real-time performance of the real-time posture data. Since the motion recognition model is a pre-trained neural network model built based on a deep learning algorithm, the accuracy of the motion recognition result obtained by recognizing the feature data of the real-time posture data is improved.

[0094] Figure 5The present invention provides a schematic diagram of a motion recognition system for a web page object. The motion recognition system includes a web page terminal, a client terminal, and a data acquisition device running on a terminal device. The web page terminal is configured with an H5 web page and a motion recognition model. The H5 web page is used to display the H5 page. The motion recognition model is used to recognize motion patterns. The client terminal is configured with a communication module for realizing data communication with the web page terminal and the data acquisition module. The data acquisition device realizes the collection of sensor data through a variety of sensors, such as Figure 6 As shown, the data acquisition module is used to collect gyroscope data through a gyroscope, to collect gravity sensing data through a gravity sensor, and to collect acceleration data through an accelerometer.

[0095] See also Figure 6 , Figure 6 A method for identifying a motion of a web page object provided in an embodiment of the present application is applied to Figure 5 The web page end in the motion recognition system of the web page object shown in FIG. Figure 6 As shown, this method specifically includes:

[0096] S601. In response to a motion recognition instruction of a web page object to be recognized, real-time position and posture data of a mobile terminal is obtained through a client that has pre-established a communication link with a web page.

[0097] In this embodiment, the web page object to be identified is an active web page object on H5 of the web page end. The motion recognition instruction of the web page object to be identified is triggered based on the successful rendering of the web page or based on the user operation. The web page end and the client can achieve real-time communication through a pre-built bridging structure.

[0098] In this embodiment, the web page sends a posture data request instruction to the client through a pre-configured bridge interface, so that the client can obtain at least one type of sensor data indicated by the posture data request instruction through a preset acquisition interface. The data acquisition device transmits the sensor data requested by the client back to the client through the interface. The client transmits the sensor data as real-time posture data back to the web page through the bridge interface.

[0099] In this embodiment, the posture data request instruction is used to request gyroscope data collected by the gyroscope, gravity change data collected by the gravity sensor, and acceleration data collected by the acceleration sensor.

[0100] In a possible implementation, the process in which the web page side pre-builds a communication link with the web page side and obtains the real-time position and posture data of the mobile terminal through the client side by using the pre-built communication link includes:

[0101] 1. Configure the web page:

[0102] Write HTML and JavaScript code: Write JavaScript code in the H5 web page on the web end to obtain real-time posture data, including methods for starting and stopping the monitoring of sensor data such as gyroscopes. Call the JS communication interface provided by the App.

[0103] Example: Write a button that calls the JS bridge interface to obtain device information and displays the result on the page.

[0104] 2. Configure the client:

[0105] Create WebView: Create a WebView in the client to load the H5 page.

[0106] Enable JavaScript: Configure WebView to enable JavaScript support, allowing JavaScript code in H5 pages to run.

[0107] 3. Establish JS interface communication:

[0108] Add JS interface: Implement a JS interface on the App side, through which the H5 page can call the methods provided by the App.

[0109] Example: In Android, you can use the addJavascriptInterface method to add a JS interface; in iOS, you can use WKScriptMessageHandler to process JS messages.

[0110] 4. Get device information:

[0111] Implement the method for obtaining device information: Implement the method for obtaining device information on the App side and return it to the H5 page through the JS interface. Specifically, the device information includes real-time posture information.

[0112] Example: In Android, you can use the Build class to get the device model and system version; in iOS, you can use the UIDevice class to get device information.

[0113] 5. Return device information to the H5 page:

[0114] Call JavaScript function: After obtaining the real-time posture data on the App side, call the JavaScript function in the H5 page through WebView to pass the real-time posture data to the H5 page for display.

[0115] It should be noted that the real-time posture data returned by the client is continuous sensor data, and the sensor data is real-time data that changes as the posture of the mobile terminal changes.

[0116] S602: Perform preset data preprocessing on the real-time posture data to obtain standard data of the real-time posture data.

[0117] In this embodiment, data preprocessing includes normalization, filtering, and data cleaning.

[0118] It should be noted that the real-time pose data is normalized to eliminate the measurement deviation between different devices, and the real-time pose data is filtered using a low-pass filter to remove high-frequency noise in the real-time pose data and retain the low-frequency components corresponding to the motion mode. The real-time pose data is cleaned by removing outliers and default values. It can be seen that this solution improves the quality of real-time pose data through data preprocessing.

[0119] It should be noted that different types of sensor data are referenced to the pre-constructed spatial rectangular coordinate system. Figure 7 A schematic diagram of the spatial coordinate system of a mobile terminal is shown in FIG. Figure 7 As shown, the spatial coordinate system constructed based on the mobile terminal takes the center of the mobile terminal as the origin, the x-axis is along the horizontal direction of the device screen, and the right is the positive direction of the x-axis. The y-axis is along the vertical direction of the device screen, and the upward direction is the positive direction of the y-axis. The z-axis is perpendicular to the device screen (perpendicular to the x and y planes), and the positive direction of the z-axis is pointing out of the screen.

[0120] S603 , dividing the standard data of the real-time posture data according to a time window of a preset size to obtain data segments of the real-time posture data.

[0121] In this embodiment, the real-time posture data is composed of a variety of sensor data collected in real time. Specifically, a time window of a preset size is pre-constructed, and the real-time posture data is divided based on the timestamp of the real-time posture data through the time window to obtain data segments of equal length. A data segment includes the real-time posture data within a time window. The preset size of the time window (that is, the length of the data segment) represents the collection time period to which the timestamp of the real-time posture data belonging to the data segment belongs.

[0122] S604: extract features from data segments of the real-time posture data to obtain feature data of the real-time posture data.

[0123] In this embodiment, the feature data of the real-time posture data includes time domain features, frequency domain features, and time-frequency domain features. The time domain features include statistical features, such as basic statistical features such as mean, variance, maximum value, and minimum value, as well as rate of change and acceleration. The frequency domain features include main frequency and frequency band energy.

[0124] In this embodiment, a statistical algorithm is used to obtain the time domain characteristics of the data segments of the real-time posture data, Fourier transform is used to obtain the frequency domain characteristics of the data segments of the real-time posture data, and wavelet transform is used to obtain the time-frequency domain characteristics of the data segments of the real-time posture data. The time domain characteristics, frequency domain characteristics, and time-frequency domain characteristics of the data segments of the real-time posture data are combined to obtain the feature data of the real-time posture data.

[0125] S605: Input feature data of the real-time posture data into a pre-trained motion recognition model to obtain a motion recognition result of the web page object to be recognized output by the motion recognition model.

[0126] In this embodiment, the motion recognition result is one of the preset motion modes, wherein each motion mode is used to characterize the current posture change state of the mobile terminal. The motion recognition model is a neural network model constructed based on a deep learning algorithm, for example, a long short-term memory network LSTM model, a convolutional neural network CNN model or a transformer Transformer.

[0127] In this embodiment, the motion recognition model is trained based on training data, wherein the training data includes feature data of a large amount of sample posture data and corresponding motion mode labels, and the motion mode labels of the sample posture data are used to identify the motion mode of the mobile terminal when the sample posture data is generated. The training data is obtained based on historical data or test data.

[0128] In a possible implementation, a cross-validation method is used to train the motion recognition model, and the test data is divided into a training set and a test set. The training set is used to estimate model parameters, and the test set is used to evaluate model accuracy. Specifically, the training method of the motion recognition model includes:

[0129] 1) Data annotation:

[0130] According to the predefined motion patterns, the data segments are labeled to form training sets and test sets.

[0131] The marked motion modes include: rotate left, rotate right, flip, and shake up and down.

[0132] 2) Model training:

[0133] The training set is input into the neural network model built based on the deep learning algorithm to train the neural network model. During the training process, if the loss function value remains stable for multiple consecutive iterations and no longer decreases significantly, the neural network model is determined to have converged.

[0134] 3) Model Evaluation:

[0135] The performance of the neural network model is evaluated using the test set. The performance indicators include accuracy, recall, F1-score, etc. The accuracy of the model is evaluated based on the performance indicators. If the accuracy does not meet the preset accuracy conditions, the structure and parameters of the neural network model are further adjusted to improve the recognition effect of the motion recognition model.

[0136] S606: Control the web page object to be identified according to the motion pattern of the web page object to be identified.

[0137] In this embodiment, based on the page interaction logic pre-corresponding to each motion mode, a control instruction for the web page object to be identified is issued, wherein the page interaction logic includes the motion mode of each web page object under each motion mode.

[0138] It can be seen from the above technical solution that a motion recognition method for web page objects provided in an embodiment of the present application, since the client has higher device information acquisition authority than the web page, real-time communication between the web page and the client is achieved through the client calling the device interface to realize real-time collection of various sensor data, so that the web page can monitor the changes in posture data in a timely and accurate manner.

[0139] For example, the natural posture changes of the device are used to realize page interaction, and the user can complete the operation without touching the screen, which improves the intuitiveness and fun of the user experience. It is widely used in scenes such as picture browsing and game interaction to enhance the interactivity and user stickiness of the application. For example, the present invention can be applied to various business scenarios such as the company's web topics, activities, risk control sliding unlocking, etc. All web pages can realize the perception of the user's handheld device posture through this set of methods, and then realize various interactive forms of the page. Such as: shaking the phone left and right to realize the shake and draw function, turning the phone left and right to realize the special effects of changing the status of the characters in the page, etc. These can greatly improve the interactivity, playability, and security of each product. And then improve the overall product experience.

[0140] Figure 8 A schematic diagram of the structure of another web page object motion recognition system provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the motion recognition system also includes a web server running on the web terminal of the terminal device, and the web server runs on the server. The structure of the server and the mobile terminal can be seen in Figures 1 to 3 The system architecture is shown.

[0141] See also Fig. 9 , Fig. 9 A method for training a motion recognition model is provided in an embodiment of the present application. The method is applied to Figure 8 The motion recognition system of the web page object shown in FIG. Fig. 9 As shown, the method includes:

[0142] S901. The web page obtains the performance status of the mobile terminal.

[0143] In this embodiment, the performance status of the mobile terminal is used to indicate the performance of the mobile terminal. Optionally, the performance status is determined based on performance parameters. Specifically, the performance parameters include hardware parameters and operating parameters. The hardware parameters include fixed parameters such as production date, operating system level and usage time, and the operating parameters include dynamic parameters such as CPU occupancy and memory occupancy.

[0144] Optionally, the performance of the mobile terminal is evaluated according to the performance parameters to obtain the performance status of the mobile terminal. It should be noted that the performance status can be divided into multiple levels in advance, and the performance of the mobile terminal is divided according to the performance parameters, and the obtained performance status is one of the multiple levels.

[0145] S902: The web page sends a configuration request to the web page server.

[0146] In this embodiment, the configuration request includes a performance status, and the configuration request is used to request the web page server to configure a motion recognition model for the web page.

[0147] S903: The web page server obtains first training data based on the performance status of the mobile terminal.

[0148] In this embodiment, the first training data is feature data of sample posture data generated by a sample mobile terminal with the same performance state as the mobile terminal and a corresponding motion mode label. The motion mode label of the sample posture data is used to identify the motion mode of the mobile terminal when the sample posture data is generated. The first training data is obtained based on historical data or test data.

[0149] S904: The web page server obtains a first motion recognition model through training based on the first training data, and configures the first motion recognition model to the web page.

[0150] In this embodiment, the web page server sends the configuration information of the first motion recognition model to the web page, and the web page configures the motion recognition model based on the configuration information of the first motion recognition model, wherein the configuration information includes model parameters.

[0151] S905: When the preset model optimization timing is reached, the web page obtains the behavior status of the mobile terminal.

[0152] S906: The web page sends an optimization request to the web page server.

[0153] In this embodiment, the optimization request is used to request the second motion recognition model, and the optimization request includes the behavior state of the mobile terminal. The behavior state of the mobile terminal is determined based on the behavior characteristics, and the behavior characteristics include the behavior characteristics when the current user operates the mobile terminal, such as behavior sensitivity, etc. The behavior state of the mobile terminal can be one of the preset multiple behavior state categories.

[0154] In this embodiment, the optimization timing includes at least one of the following: reaching the optimization time of a preset optimization cycle, the frequency of model result error reporting being greater than a preset frequency threshold, or the number of model result error reporting reaching a preset number threshold. The model result error reporting refers to an error reporting instruction triggered by an error in the motion recognition result of the web page object to be recognized output by the motion recognition model.

[0155] S907: The web page server obtains second training data based on the behavior state and performance state of the mobile terminal.

[0156] In this embodiment, the second training data is feature data and corresponding motion mode labels of sample posture data generated by a sample mobile terminal having the same performance state and behavior state as the mobile terminal. The motion mode label of the sample posture data is used to identify the motion mode of the mobile terminal when the sample posture data is generated. The second training data is obtained based on historical data or test data.

[0157] S908: The web page server obtains a second motion recognition model through training based on the second training data, and configures the second motion recognition model to the web page.

[0158] In this embodiment, the web page server sends the configuration information of the second motion recognition model to the web page, and the web page configures the motion recognition model based on the configuration information of the second motion recognition model, wherein the configuration information includes model parameters.

[0159] It can be seen from the above technical solutions that a method for training a motion recognition model provided in an embodiment of the present application includes an initial configuration stage and an optimization configuration stage of the motion recognition model.

[0160] In the initial configuration phase, the web page sends a configuration request to the web page server. Since the configuration request includes the performance status of the mobile terminal, the configuration request is used to request the web page server to configure the motion recognition model for the web page. Therefore, the web page server obtains the feature data of the sample posture data generated by the sample mobile terminal with the same performance status as the mobile terminal and the corresponding motion mode label as the first training data, and obtains the first motion recognition model based on the first training data. The configuration information of the first motion recognition model is sent to the web page, and the web page configures the motion recognition model based on the configuration information of the first motion recognition model. Thus, the initial configuration of the motion recognition model is completed.

[0161] It can be seen that the motion recognition model configured in the initial configuration stage of the motion recognition model is trained based on the performance status of the mobile terminal. Therefore, the motion recognition model is more accurate in identifying the motion pattern of the motion object running on the web page of the current mobile terminal.

[0162] In the optimization configuration stage, when the preset model optimization timing is reached, the web page sends an optimization request to the web page server. Since the optimization request includes the behavior state of the mobile terminal, the optimization request is used to request the optimization of the motion recognition model, so that the web page server obtains the feature data of the sample posture data generated by the sample mobile terminal with the same performance state and behavior state as the mobile terminal and the corresponding motion mode label as the second training data, and trains the second motion recognition model based on the second training data. The configuration information of the second motion recognition model is sent to the web page, and the web page configures the motion recognition model based on the configuration information of the second motion recognition model. In this way, the optimization configuration of the motion recognition model is completed.

[0163] It can be seen that the motion recognition model configured in the optimization configuration stage of the motion recognition model is trained based on the performance status and behavior status of the mobile terminal. Therefore, the motion recognition model is more accurate in identifying the motion pattern of the motion object running on the web page of the current mobile terminal.

[0164] It should be noted that due to the large number of web users and the different performance of the mobile terminals running on them, the sensor data’s representation of motion patterns may not be the same. For example, due to the different years of use of mobile terminal devices, the performance of the devices varies greatly, resulting in discontinuous, stuck, and unstable sensor data returned, which will lead to low model recognition accuracy.

[0165] Therefore, this method uses device performance and user operations as the basis for obtaining training data, considers the differences in users and devices running on the web page during the initial configuration and optimization configuration stages, configures the motion recognition model in a targeted manner, and improves the accuracy of the motion recognition model.

[0166] The above describes a flow chart of a method for identifying a motion of a web page object provided by an embodiment of the present application. The following describes a device for executing the method for identifying a motion of a web page object.

[0167] See also Fig.10 , Fig.10 This is a schematic diagram of a motion recognition device for a web page object provided in an embodiment of the present application. Fig.10 As shown, the webpage object motion recognition device 1000 includes:

[0168] A posture data acquisition unit 1001 is used to respond to a motion recognition instruction of a webpage object to be recognized, and to acquire real-time posture data of a mobile terminal through a client that has a communication link pre-established with the webpage, wherein the client and the webpage are running on the mobile terminal;

[0169] A feature extraction unit 1002 is used to perform preset data processing on the real-time posture data to obtain feature data of the real-time posture data;

[0170] The model recognition unit 1003 is used to input the feature data of the real-time posture data into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, wherein the motion recognition model is a neural network model constructed based on a deep learning algorithm.

[0171] In one possible implementation, the posture data acquisition unit is used to respond to the motion recognition instruction of the web page object to be identified, and to obtain the real-time posture data of the mobile terminal through a client that has pre-established a communication link with the web page. It is specifically used to: send a posture data request instruction to the client through a pre-configured bridging interface, so that the client obtains at least one type of sensor data indicated by the posture data request instruction through a preset acquisition interface, and transmits the collected sensor data as real-time posture data back to the web page through the bridging interface.

[0172] In one possible implementation, the feature extraction unit is used to perform preset data processing on the real-time posture data to obtain feature data of the real-time posture data, and is specifically used to: perform preset data preprocessing on the real-time posture data to obtain standard data of the real-time posture data, wherein the data preprocessing includes normalization, filtering, and data cleaning; divide the standard data of the real-time posture data according to a time window of a preset size to obtain data segments of the real-time posture data; and perform feature extraction on the data segments of the real-time posture data to obtain feature data of the real-time posture data.

[0173] In one possible implementation, the feature extraction unit is used to perform feature extraction on the data segment of the real-time posture data, and when obtaining the feature data of the real-time posture data, it is specifically used to: use a statistical algorithm to obtain the time domain features of the data segment of the real-time posture data; use Fourier transform to obtain the frequency domain features of the data segment of the real-time posture data; use wavelet transform to obtain the time and frequency domain features of the data segment of the real-time posture data; combine the time domain features, frequency domain features and time and frequency domain features of the data segment of the real-time posture data to obtain the feature data of the real-time posture data.

[0174] In a possible implementation, the webpage object motion recognition device further includes a model initial configuration unit, which is used to:

[0175] Before inputting the feature data of the real-time posture data into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be identified output by the motion recognition model, a configuration request is sent to the web page server, the configuration request includes the performance status of the mobile terminal, and the configuration request is used to request the web page server to configure the motion recognition model for the web page; in response to receiving the configuration information of the first motion recognition model sent by the web page server, the motion recognition model is configured based on the configuration information of the first motion recognition model; the first motion recognition model is trained by the web page server based on first training data, the first training data includes feature data of sample posture data generated by a sample mobile terminal with the same performance status as the mobile terminal and a corresponding motion mode label, the motion mode label corresponding to the feature data of the sample posture data is used to identify the motion mode of the sample mobile terminal when generating the sample posture data.

[0176] In a possible implementation, the webpage object motion recognition device further includes a model optimization configuration unit, which is used to:

[0177] When a preset model optimization timing is reached, the web page sends an optimization request to the web page server, the optimization request includes the behavior state of the mobile terminal, and the optimization request is used to request optimization of the motion recognition model; in response to receiving the configuration information of the second motion recognition model sent by the web page server, the motion recognition model is optimized based on the configuration information of the second motion recognition model; the second motion recognition model is trained by the web page server based on second training data, and the second training data includes feature data of sample posture data generated by a sample mobile terminal with the same performance state and behavior state as the mobile terminal, and a corresponding motion mode label.

[0178] In a possible implementation, the motion recognition device for a web page object also includes a motion control unit, which is used to control the web page object to be recognized based on the motion recognition result of the web page object to be recognized after inputting the feature data of the real-time posture data into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, and the motion recognition result includes one of the preset motion modes.

[0179] The present application also provides an electronic device in an embodiment. Fig.11 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones and PADs (tablet computers). Fig.11The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0180] like Fig.11 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage device 1108 to a random access memory (RAM) 1103. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 1103. The processing device 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0181] Typically, the following devices may be connected to the I / O interface 1105: an input device 1106 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1107 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1108 including, for example, a memory card, a hard disk, etc.; and a communication device 1109. The communication device 1109 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Fig.11 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0182] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any of the methods for identifying motion of a web page object provided in the embodiments of the present application.

[0183] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the motion recognition methods for web page objects provided in the embodiments of the present application.

[0184] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0185] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0186] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0187] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A method for identifying motion of a web page object, characterized in that: Applied to web pages, including: In response to a motion recognition instruction of a web page object to be recognized, obtaining real-time position data of the mobile terminal through a client that has a communication link pre-established with the web page, wherein the client and the web page are running on the mobile terminal; Performing preset data processing on the real-time posture data to obtain feature data of the real-time posture data; The feature data of the real-time posture data is input into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, wherein the motion recognition model is a neural network model constructed based on a deep learning algorithm.

2. The method for identifying the motion of a web page object according to claim 1, characterized in that: In response to a motion recognition instruction of a web page object to be recognized, obtaining real-time position and posture data of a mobile terminal through a client that pre-establishes a communication link with the web page terminal includes: A posture data request instruction is sent to the client through a pre-configured bridge interface, so that the client obtains at least one type of sensor data indicated by the posture data request instruction through a preset acquisition interface, and transmits the collected sensor data as real-time posture data back to the web page through the bridge interface.

3. The method for identifying the motion of a web page object according to claim 1, characterized in that: Performing preset data processing on the real-time posture data to obtain feature data of the real-time posture data includes: Performing preset data preprocessing on the real-time posture data to obtain standard data of the real-time posture data, wherein the data preprocessing includes normalization, filtering, and data cleaning; Dividing the standard data of the real-time posture data according to a time window of a preset size to obtain data segments of the real-time posture data; Feature extraction is performed on the data segment of the real-time posture data to obtain feature data of the real-time posture data.

4. The method for identifying the motion of a web page object according to claim 3, characterized in that: Performing feature extraction on the data segment of the real-time posture data to obtain feature data of the real-time posture data includes: Using a statistical algorithm to obtain time domain features of a data segment of the real-time posture data; Using Fourier transform to obtain frequency domain features of the data segment of the real-time posture data; Using wavelet transform to obtain time-frequency domain features of a data segment of the real-time posture data; The time domain features, frequency domain features and time-frequency domain features of the data segments of the real-time posture data are combined to obtain feature data of the real-time posture data.

5. The method for identifying the motion of a web page object according to claim 1, characterized in that: Before inputting the feature data of the real-time posture data into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, the web page object motion recognition method further includes: Sending a configuration request to a web page server, the configuration request including the performance status of the mobile terminal, the configuration request being used to request the web page server to configure the motion recognition model for the web page; In response to receiving the configuration information of the first motion recognition model sent by the web page server, the motion recognition model is configured based on the configuration information of the first motion recognition model; the first motion recognition model is trained by the web page server based on first training data, and the first training data includes feature data of sample posture data generated by a sample mobile terminal with the same performance state as the mobile terminal and a corresponding motion mode label, and the motion mode label corresponding to the feature data of the sample posture data is used to identify the motion mode of the sample mobile terminal when generating the sample posture data.

6. The method for identifying the motion of a web page object according to claim 5, characterized in that: Also includes: When a preset model optimization timing is reached, the web page sends an optimization request to the web page server, the optimization request includes the behavior state of the mobile terminal, and the optimization request is used to request optimization of the motion recognition model; In response to receiving the configuration information of the second motion recognition model sent by the web server, the motion recognition model is optimized based on the configuration information of the second motion recognition model; the second motion recognition model is trained by the web server based on second training data, and the second training data includes feature data of sample posture data generated by a sample mobile terminal with the same performance state and behavior state as the mobile terminal, and a corresponding motion mode label.

7. The method for identifying the motion of a web page object according to any one of claims 1 to 6, characterized in that: After inputting the feature data of the real-time posture data into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, the web page object motion recognition method further includes: According to the motion recognition result of the webpage object to be recognized, the webpage object to be recognized is controlled, and the motion recognition result includes one of the preset motion modes.

8. A motion recognition device for a web page object, characterized in that: include: A posture data acquisition unit, configured to respond to a motion recognition instruction of a webpage object to be recognized, and acquire real-time posture data of a mobile terminal through a client that has a communication link pre-established with the webpage end, wherein the client and the webpage end are running on the mobile terminal; A feature extraction unit, used to perform preset data processing on the real-time posture data to obtain feature data of the real-time posture data; A model recognition unit is used to input the feature data of the real-time posture data into a pre-trained motion recognition model to obtain the motion recognition result of the web page object to be recognized output by the motion recognition model, wherein the motion recognition model is a neural network model constructed based on a deep learning algorithm.

9. A computer program product, characterized in that It comprises computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the motion recognition method for a web page object as claimed in any one of claims 1 to 7.

10. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the motion recognition method for a web page object as described in any one of claims 1 to 7.

11. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the motion recognition method for a web page object as described in any one of claims 1 to 7.

Images