Multi-source data and reinforcement learning combined intelligent tablet computer user behavior analysis system

Abstract

The invention relates to a multi-source data and reinforcement learning combined intelligent tablet computer user behavior analysis system and method, computer equipment, a storage medium and a computer program product. The method comprises the steps that user face information is acquired, and a preset brightness adjusting model is acquired according to the user face information; acquiring a current brightness value of a tablet computer screen as a first brightness value, acquiring an environment brightness value as a second brightness value, and calculating a brightness difference between the first brightness value and the second brightness value; obtaining a screen brightness value matched with the brightness difference from a preset brightness adjustment model; adjusting the brightness of the tablet computer screen according to the screen brightness value; waiting and judging whether a brightness adjustment instruction input by a user is received within a preset time; if yes, obtaining target brightness according to the brightness adjustment instruction; and feeding back the target brightness to a preset brightness adjustment model to update the brightness adjustment model. By adopting the scheme, different preset brightness adjusting units can be matched according to different users to realize automatic adjustment of the screen brightness, and after automatic adjustment of the screen brightness is completed, reinforcement learning is performed on the preset brightness adjusting model according to the screen brightness adjusting instruction input by the user; therefore, the preset brightness adjustment model can output the screen brightness better meeting the user requirements.

Description

Technical Field

[0001] The present application relates to the field of machine learning technology, and in particular to a system, method, computer device, storage medium, and computer program product for analyzing user behavior of a smart tablet computer that combines multi-source data with reinforcement learning. Background Art

[0002] In today's mobile computing era, tablet computers are widely used in education, entertainment, business, and other fields due to their portability, rich multimedia features, and user-friendly interface. As the audience and usage scenarios of tablet computers continue to expand, how to provide users with a personalized visual experience has become a key issue that cannot be ignored during tablet product design.

[0003] An existing Chinese invention patent, publication number CN116741093A, discloses a mobile terminal extension screen with a light sensor and a brightness adjustment method. The method includes: A. connecting the extension screen to an external mobile terminal; B. the light sensor detects and obtains the light intensity value of the environment in real time when powered on; C. sending the obtained light intensity value to the external mobile terminal; D. the external mobile terminal outputs the required brightness percentage based on a preset mapping relationship between light intensity value and brightness percentage; E. sending the required brightness percentage to the extension screen; F. the extension screen adjusts the current screen brightness according to the required brightness percentage. A light sensor is set on the extension screen, and the light intensity value obtained by the light sensor is sent to the mobile terminal to obtain the required brightness percentage. The mobile terminal's automatic brightness adjustment function is utilized to enable the extended screen in a minimalist state to have automatic brightness adjustment, and the adjustment is simple and convenient.

[0004] However, the solution for adjusting the screen brightness is still a fixed solution set by the program, which is difficult to meet the different brightness requirements of different users in different scenarios. Summary of the Invention

[0005] Based on this, it is necessary to provide a smart tablet computer user behavior analysis system, method, computer device, computer-readable storage medium and computer program product that combines multi-source data and reinforcement learning to provide different brightness adjustment solutions for different users in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for analyzing user behavior of a smart tablet computer by combining multi-source data with reinforcement learning, the method comprising:

[0007] Obtaining user facial information and obtaining a preset brightness adjustment model based on the user facial information;

[0008] Obtain the current brightness value of the tablet screen as a first brightness value, obtain the ambient brightness value as a second brightness value, and calculate the brightness difference between the first brightness value and the second brightness value;

[0009] Obtaining a screen brightness value that matches the brightness difference from a preset brightness adjustment model;

[0010] Adjust the brightness of the tablet screen according to the screen brightness value;

[0011] Waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time;

[0012] If so, the target brightness is obtained according to the brightness adjustment instruction;

[0013] The target brightness is fed back to the preset brightness adjustment model to update the brightness adjustment model.

[0014] In one embodiment, the specific steps of obtaining the ambient brightness value as the second brightness value include:

[0015] Obtain the user's facial brightness value based on the user's facial information;

[0016] Get the brightness value in front of the screen and the brightness value behind the screen;

[0017] Compare the brightness value of the user's face with the brightness value in front of the screen;

[0018] If the user's facial brightness is greater than the screen brightness, the maximum of the screen brightness and the screen brightness is used as the ambient brightness.

[0019] If the user's facial brightness is lower than the screen brightness, the minimum of the screen brightness and the screen brightness is used as the ambient brightness.

[0020] In one embodiment, the specific steps of obtaining a screen brightness value that matches the brightness difference from a preset brightness adjustment model include:

[0021] Substitute the brightness difference value into the preset brightness adjustment model to obtain the ideal brightness value;

[0022] Determining whether a difference between the first brightness value and the ideal brightness value is greater than a preset threshold;

[0023] If so, the ideal brightness value is used as the screen brightness value and output;

[0024] If not, the first brightness value is used as the screen brightness value and output.

[0025] In one embodiment, the specific steps of waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time include:

[0026] Wait for the tablet's brightness to reach the screen brightness value and obtain the corresponding timestamp information;

[0027] The time corresponding to the timestamp information is used as the starting time, and the waiting time corresponds to the preset time;

[0028] It is determined whether a brightness adjustment instruction input by a user for adjusting screen brightness is received during the waiting period.

[0029] In one embodiment, the step of feeding back the target brightness to the preset brightness adjustment model to update the brightness adjustment model includes:

[0030] Waiting for and obtaining the last screen adjustment command, including:

[0031] Get the command timestamp when the user inputs the screen adjustment command;

[0032] Determining whether a new screen adjustment instruction is received within a second preset time after the instruction timestamp time;

[0033] If not, the screen adjustment instruction is taken as the last screen adjustment instruction obtained;

[0034] If so, the command timestamp corresponding to the new screen adjustment command will be reacquired, and it will be determined whether the screen adjustment command is received again within the second preset time after the new command timestamp.

[0035] In one embodiment, the step of feeding back the target brightness to the preset brightness adjustment model to update the brightness adjustment model further includes:

[0036] The target brightness and brightness query are input into the brightness adjustment model as positive samples;

[0037] The screen brightness value and brightness difference are input into the brightness adjustment model as negative samples;

[0038] The preset brightness adjustment model obtained after training the input positive samples and negative samples is used as a new preset brightness adjustment model.

[0039] In a second aspect, the present application also provides a smart tablet user behavior analysis system that combines multi-source data with reinforcement learning, the system comprising:

[0040] The screen module is used to obtain a brightness adjustment instruction and a screen brightness value, adjust the brightness according to the screen brightness value or the brightness adjustment instruction, and output the current brightness value;

[0041] Facial information collection module, used to obtain user facial information;

[0042] Brightness acquisition module, used to detect the ambient brightness and output the ambient brightness value;

[0043] a CPU module, configured to calculate a brightness difference between a first brightness value and a second brightness value, to run a preset brightness adjustment model to obtain a screen brightness value that matches the brightness difference, and to feed back a target brightness corresponding to a brightness adjustment instruction input by a user to the preset brightness adjustment model to update the brightness adjustment model;

[0044] The storage module is used to store the preset brightness adjustment model and user information.

[0045] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0046] Obtaining user facial information and obtaining a preset brightness adjustment model based on the user facial information;

[0047] Obtain the current brightness value of the tablet screen as a first brightness value, obtain the ambient brightness value as a second brightness value, and calculate the brightness difference between the first brightness value and the second brightness value;

[0048] Obtaining a screen brightness value that matches the brightness difference from a preset brightness adjustment model;

[0049] Adjust the brightness of the tablet screen according to the screen brightness value;

[0050] Waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time;

[0051] If so, the target brightness is obtained according to the brightness adjustment instruction;

[0052] The target brightness is fed back to the preset brightness adjustment model to update the brightness adjustment model.

[0053] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0054] Obtaining user facial information and obtaining a preset brightness adjustment model based on the user facial information;

[0055] Obtain the current brightness value of the tablet screen as a first brightness value, obtain the ambient brightness value as a second brightness value, and calculate the brightness difference between the first brightness value and the second brightness value;

[0056] Obtaining a screen brightness value that matches the brightness difference from a preset brightness adjustment model;

[0057] Adjust the brightness of the tablet screen according to the screen brightness value;

[0058] Waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time;

[0059] If so, the target brightness is obtained according to the brightness adjustment instruction;

[0060] The target brightness is fed back to the preset brightness adjustment model to update the brightness adjustment model.

[0061] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which, when executed by a processor, implements the following steps:

[0062] Obtaining user facial information and obtaining a preset brightness adjustment model based on the user facial information;

[0063] Obtain the current brightness value of the tablet screen as a first brightness value, obtain the ambient brightness value as a second brightness value, and calculate the brightness difference between the first brightness value and the second brightness value;

[0064] Obtaining a screen brightness value that matches the brightness difference from a preset brightness adjustment model;

[0065] Adjust the brightness of the tablet screen according to the screen brightness value;

[0066] Waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time;

[0067] If so, the target brightness is obtained according to the brightness adjustment instruction;

[0068] The target brightness is fed back to the preset brightness adjustment model to update the brightness adjustment model.

[0069] The above-mentioned smart tablet computer user behavior analysis system, method, computer device, storage medium and computer program product that combine multi-source data with reinforcement learning can achieve automatic adjustment of screen brightness by matching different preset brightness adjustment units according to different users. After the automatic adjustment of the screen brightness is completed, the preset brightness adjustment model is reinforced learned according to the screen brightness adjustment instruction input by the user, so that the preset brightness adjustment model can output a screen brightness that better meets user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 This is a structural block diagram of a smart tablet computer user behavior analysis system that combines multi-source data with reinforcement learning in one embodiment;

[0071] Figure 2 1 is a flow chart of a method for analyzing user behavior of a smart tablet computer by combining multi-source data with reinforcement learning in one embodiment;

[0072] Figure 3This is a diagram illustrating an application environment of a method for analyzing user behavior of a smart tablet computer that combines multi-source data with reinforcement learning in one embodiment;

[0073] Figure 4 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0075] In one embodiment, Figure 1 As shown, a smart tablet user behavior analysis system combining multi-source data with reinforcement learning is provided, including:

[0076] The screen module is used to obtain a brightness adjustment instruction and a screen brightness value, adjust the brightness according to the screen brightness value or the brightness adjustment instruction, and output the current brightness value;

[0077] Facial information collection module, used to obtain user facial information;

[0078] Brightness acquisition module, used to detect the ambient brightness and output the ambient brightness value;

[0079] a CPU module, configured to calculate a brightness difference between a first brightness value and a second brightness value, to run a preset brightness adjustment model to obtain a screen brightness value that matches the brightness difference, and to feed back a target brightness corresponding to a brightness adjustment instruction input by a user to the preset brightness adjustment model to update the brightness adjustment model;

[0080] The storage module is used to store the preset brightness adjustment model and user information.

[0081] Specifically, in the embodiment of the present application, the screen module is a touch screen installed on a tablet computer. In addition to basic display functions and brightness adjustment functions, it also has the function of receiving various touch signals. The facial acquisition module is a front-facing camera installed on one side of the tablet computer screen module, which can be used to collect the user's facial information. The brightness acquisition module is a light sensor installed on the side of the tablet computer screen and / or the rear camera module of the screen computer, which is used to measure the brightness of different directions in the scene where the tablet computer is located, thereby facilitating the adjustment of the tablet computer screen brightness to a value suitable for the user to view.

[0082] In an embodiment of the present application, the brightness acquisition module includes a front-screen brightness detection unit and a behind-screen brightness detection unit, wherein the front-screen brightness detection unit is a light sensor integrated in the front camera module on the screen side of the tablet computer, and is used to output the front-screen brightness value; the behind-screen brightness detection unit is a light sensor integrated in the rear camera module of the tablet computer, and is used to output the behind-screen brightness value.

[0083] Based on the same inventive concept, the embodiments of the present application also provide a method for analyzing user behavior of a smart tablet computer that combines multi-source data and reinforcement learning, which is applied to the aforementioned system for analyzing user behavior of a smart tablet computer that combines multi-source data and reinforcement learning. The implementation solution provided by this method is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations in one or more embodiments of the method for analyzing user behavior of a smart tablet computer that combines multi-source data and reinforcement learning provided below can be found in the above-mentioned limitations on the system for analyzing user behavior of a smart tablet computer that combines multi-source data and reinforcement learning, and will not be repeated here.

[0084] In one embodiment, Figure 2 As shown, a method for analyzing user behavior of a smart tablet computer that combines multi-source data with reinforcement learning is provided. This method is described by taking the CPU module in the behavior analysis system of the smart tablet computer that combines multi-source data with reinforcement learning as an example. The method includes the following steps:

[0085] Step A100: Obtain user facial information, and obtain a preset brightness adjustment model based on the user facial information.

[0086] Among them, the user facial information is the user facial image obtained through the facial information acquisition module. After obtaining the user facial information, the CPU module will match the user facial information with the user identity information pre-stored in the storage module, thereby obtaining the user identity information corresponding to the user facial information, and then obtain the preset brightness adjustment model pre-stored in the storage module based on the user identity information. In the embodiment of the present application, there is at least one preset brightness adjustment model, and the preset brightness adjustment model corresponds to the user identity information one-to-one, thereby realizing different screen brightness adjustment strategies for different users, so that the tablet computer is more in line with the usage habits of specific users.

[0087] Step A200: obtaining the current brightness value of the tablet screen as a first brightness value, obtaining the ambient brightness value as a second brightness value, and calculating the brightness difference between the first brightness value and the second brightness value.

[0088] Among them, the current brightness value is the brightness value obtained by the CPU after reading the current brightness of the tablet computer screen, and the ambient brightness value is a value with the same dimension as the current brightness value obtained by converting the ambient brightness obtained by the front-screen brightness detection unit and / or the back-screen brightness detection unit; the brightness difference is the difference between the first brightness value and the second brightness value.

[0089] Specifically, the specific steps of step A200 include:

[0090] Step A210: Obtain the user's facial brightness value based on the user's facial information.

[0091] The user's facial brightness value is a brightness value calculated by performing image processing on the user's facial information and has the same dimension as the current brightness value.

[0092] Step A220: Obtain the brightness value in front of the screen and the brightness value behind the screen.

[0093] The behind-the-screen brightness value is a brightness value detected by a behind-the-screen brightness acquisition unit.

[0094] Step A230: Compare the brightness value of the user's face with the brightness value in front of the screen.

[0095] Step A231: If the user's facial brightness is greater than the screen brightness, the maximum of the screen brightness and the screen brightness is used as the ambient brightness.

[0096] Step A232: If the user's facial brightness value is less than the screen brightness value, the minimum value between the screen brightness value and the screen brightness value is used as the ambient brightness value.

[0097] Through steps A230-A232, the relationship between the brightness of the user's face and the brightness in front of the screen is first determined. If the facial brightness is greater than the ambient brightness in front of the screen, it means that the current ambient light is weak (for example, after dark, the user's environment has no light or the light is weak), and the screen brightness is too high. The screen brightness should be lowered. The minimum value of the brightness value in front of the screen and the brightness value behind the screen is then used as the ambient brightness value. The purpose is that the brightness behind the screen is less affected by the diffuse reflected light from the user's face than the brightness in front of the screen, and its detection value is closer to the actual brightness in the user's environment.

[0098] If the facial brightness is lower than the ambient brightness in front of the screen, it means that the current ambient light is strong (such as at daybreak, or in a scene with strong lighting in the user's environment), and the screen brightness is too low. The screen brightness should be increased. The purpose of using the maximum value of the brightness value in front of the screen and the brightness value behind the screen as the ambient brightness value is that, generally in this type of scene, the darker side is usually the shadow side. For example, a tablet computer is tilted and set on a horizontal plane, and the brightness detection unit behind the screen collects the brightness of the backlight side of the tablet computer, and its value is quite different from the brightness of the actual scene.

[0099] Step A300: Obtaining a screen brightness value that matches the brightness difference from a preset brightness adjustment model.

[0100] The preset brightness adjustment model is stored in the storage space and is called and executed by the CPU module. In the embodiment of the present application, the preset brightness adjustment model is a mapping curve between a brightness difference and a screen brightness value, where one brightness difference corresponds to one screen brightness value. Specifically, the specific steps of step A300 include:

[0101] Step A310: Substitute the brightness difference into a preset brightness adjustment model to obtain an ideal brightness value.

[0102] The ideal brightness value is the screen brightness value corresponding to the brightness difference obtained through a preset brightness adjustment model.

[0103] Step A320: Determine whether the difference between the first brightness value and the ideal brightness value is greater than a preset threshold.

[0104] Step A331: If yes, the ideal brightness value is used as the screen brightness value and output.

[0105] Step A332: If not, the first brightness value is used as the screen brightness value and outputted.

[0106] By setting steps A310 to A332, the screen brightness can be kept stable, preventing the tablet screen from changing when the external screen brightness changes slightly, thereby reducing the damage to the user's eyes caused by rapid changes in screen brightness.

[0107] Step A400: Adjust the brightness of the tablet screen according to the screen brightness value.

[0108] Step A500: Wait and determine whether a brightness adjustment instruction input by the user is received within a preset time.

[0109] Specifically, step A500 includes:

[0110] Step A510: Wait for the brightness of the tablet computer to reach the screen brightness value, and obtain corresponding timestamp information.

[0111] Step A520: starting from the time corresponding to the timestamp information and waiting for a time duration corresponding to a preset time.

[0112] Step A530: Determine whether a brightness adjustment instruction input by the user for adjusting the screen brightness is received during the waiting period.

[0113] Through steps A410 to A430, feedback on the user's autonomous screen adjustment can be obtained after the automatic adjustment of the screen brightness is completed. If the user does not autonomously adjust the screen brightness within the preset time, it means that the screen brightness obtained by the preset brightness adjustment model is the brightness that the current user can adapt to, and therefore there is no need to readjust the model or enhance learning. If the user still autonomously adjusts the screen brightness after the automatic adjustment is completed, it means that the screen brightness value after the automatic adjustment is completed is not suitable for the user, and further training of the preset brightness adjustment model is required.

[0114] Step A600: If yes, obtain the target brightness according to the brightness adjustment instruction.

[0115] Step A700: Feedback the target brightness to the preset brightness adjustment model to update the brightness adjustment model.

[0116] Specifically, the steps of step A700 include:

[0117] Step A710: Waiting for and obtaining the last screen adjustment instruction. Specifically including:

[0118] Step A711: Obtain the instruction timestamp when the user inputs the screen adjustment instruction.

[0119] Step A712: Determine whether a new screen adjustment instruction is received within a second preset time after the instruction timestamp time.

[0120] Step A713: If not, the screen adjustment instruction is taken as the last screen adjustment instruction obtained.

[0121] Step A714: If yes, then the command timestamp corresponding to the new screen adjustment command is acquired again, and it is determined whether another screen adjustment command is received within a second preset time after the new command timestamp.

[0122] Through steps A711 to A714, it is possible to determine whether the screen adjustment instruction input by the user is completed. After the completion, the screen brightness at the end is used as the screen brightness adapted by the user, and is input into the preset brightness adjustment model, thereby completing reinforcement learning.

[0123] Step A700 also includes:

[0124] Step A750: Input the target brightness and the brightness query as positive samples into the brightness adjustment model.

[0125] Step A760: Input the screen brightness value and brightness difference as negative samples into the brightness adjustment model.

[0126] Step A770: The preset brightness adjustment model obtained after training the input positive samples and negative samples is used as a new preset brightness adjustment model.

[0127] Through steps A750 to A770, the reinforcement learning of the preset brightness adjustment model can be completed, so that the preset brightness adjustment model can output a screen brightness that is more suitable for the user after the next automatic brightness adjustment.

[0128] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0129] Each module in the aforementioned smart tablet user behavior analysis system combining multi-source data with reinforcement learning can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device's memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0130] The user behavior analysis method for smart tablet computers that combines multi-source data with reinforcement learning provided in the embodiment of the present application can also be applied to Figure 3 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated on server 104 or placed on a cloud or other network server. Terminal 102 can be, but is not limited to, various tablet computers or IoT devices based on tablet computers. IoT devices can be smart home central control terminals, smart car devices, etc. Server 104 can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0131] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, memory, communication interface, display screen and input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for analyzing user behavior of a smart tablet computer that combines multi-source data with reinforcement learning is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0132] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0133] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0134] Step A100: Obtaining user facial information, and obtaining a preset brightness adjustment model based on the user facial information;

[0135] Step A200: obtaining a current brightness value of the tablet screen as a first brightness value, obtaining an ambient brightness value as a second brightness value, and calculating a brightness difference between the first brightness value and the second brightness value;

[0136] Step A300: obtaining a screen brightness value that matches the brightness difference from a preset brightness adjustment model;

[0137] Step A400: adjusting the brightness of the tablet screen according to the screen brightness value;

[0138] Step A500: Waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time;

[0139] Step A600: If yes, obtain the target brightness according to the brightness adjustment instruction;

[0140] Step A700: Feedback the target brightness to the preset brightness adjustment model to update the brightness adjustment model.

[0141] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0142] Step A100: Obtaining user facial information, and obtaining a preset brightness adjustment model based on the user facial information;

[0143] Step A200: obtaining a current brightness value of the tablet screen as a first brightness value, obtaining an ambient brightness value as a second brightness value, and calculating a brightness difference between the first brightness value and the second brightness value;

[0144] Step A300: obtaining a screen brightness value that matches the brightness difference from a preset brightness adjustment model;

[0145] Step A400: adjusting the brightness of the tablet screen according to the screen brightness value;

[0146] Step A500: Waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time;

[0147] Step A600: If yes, obtain the target brightness according to the brightness adjustment instruction;

[0148] Step A700: Feedback the target brightness to the preset brightness adjustment model to update the brightness adjustment model.

[0149] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0150] Step A100: Obtaining user facial information, and obtaining a preset brightness adjustment model based on the user facial information;

[0151] Step A200: obtaining a current brightness value of the tablet screen as a first brightness value, obtaining an ambient brightness value as a second brightness value, and calculating a brightness difference between the first brightness value and the second brightness value;

[0152] Step A300: obtaining a screen brightness value that matches the brightness difference from a preset brightness adjustment model;

[0153] Step A400: adjusting the brightness of the tablet screen according to the screen brightness value;

[0154] Step A500: Waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time;

[0155] Step A600: If yes, obtain the target brightness according to the brightness adjustment instruction;

[0156] Step A700: Feedback the target brightness to the preset brightness adjustment model to update the brightness adjustment model.

[0157] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0158] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but are not limited to these.

[0159] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0160] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A smart tablet user behavior analysis system combining multi-source data with reinforcement learning, characterized by: include: Acquiring user facial information, and acquiring a preset brightness adjustment model based on the user facial information; Obtain the current brightness value of the tablet screen as a first brightness value, obtain the ambient brightness value as a second brightness value, and calculate the brightness difference between the first brightness value and the second brightness value; Acquire a screen brightness value matching the brightness difference from the preset brightness adjustment model; adjusting the brightness of the tablet computer screen according to the screen brightness value; Waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time; If yes, obtaining the target brightness according to the brightness adjustment instruction; The target brightness is fed back to the preset brightness adjustment model to update the brightness adjustment model.

2. According to the multi-source data and reinforcement learning combined smart tablet computer user behavior analysis system of claim 1, the specific step of obtaining the ambient brightness value as the second brightness value comprises: Acquire a user's facial brightness value based on the user's facial information; Obtaining the brightness value in front of the screen and the brightness value behind the screen; Comparing the brightness value of the user's face with the brightness value in front of the screen; If the user's facial brightness value is greater than the screen-front brightness value, the maximum value of the screen-front brightness value and the screen-back brightness value is used as the ambient brightness value; If the user's facial brightness value is less than the screen front brightness value, the minimum value between the screen front brightness value and the screen back brightness value is used as the ambient brightness value.

3. The smart tablet computer user behavior analysis system combining multi-source data and reinforcement learning according to claim 1 or 2, characterized in that: The specific step of obtaining a screen brightness value matching the brightness difference from the preset brightness adjustment model includes: Substituting the brightness difference value into the preset brightness adjustment model to obtain an ideal brightness value; Determining whether a difference between the first brightness value and the ideal brightness value is greater than a preset threshold; If yes, the ideal brightness value is used as the screen brightness value and outputted; If not, the first brightness value is used as the screen brightness value and outputted.

4. The smart tablet computer user behavior analysis system combining multi-source data and reinforcement learning according to claim 3 is characterized in that: The specific steps of waiting and determining whether a brightness adjustment instruction input by the user is received within a preset time include: Waiting for the brightness of the tablet computer to reach the screen brightness value and obtaining corresponding timestamp information; The time corresponding to the timestamp information is used as the starting time, and the waiting time corresponds to the preset time; It is determined whether a brightness adjustment instruction input by a user for adjusting screen brightness is received during the waiting period.

5. The smart tablet computer user behavior analysis system combining multi-source data and reinforcement learning according to claim 4 is characterized in that: The step of feeding back the target brightness to the preset brightness adjustment model to update the brightness adjustment model includes: Waiting for and obtaining the last screen adjustment command, including: Get the command timestamp when the user inputs the screen adjustment command; Determining whether a new screen adjustment instruction is received within a second preset time after the instruction timestamp time; If not, the screen adjustment instruction is taken as the last screen adjustment instruction obtained; If so, the command timestamp corresponding to the new screen adjustment command will be reacquired, and it will be determined whether the screen adjustment command is received again within the second preset time after the new command timestamp.

6. The smart tablet computer user behavior analysis system combining multi-source data and reinforcement learning according to claim 5 is characterized in that: The step of feeding back the target brightness to the preset brightness adjustment model to update the brightness adjustment model further includes: Input the target brightness and the brightness query as positive samples into the brightness adjustment model; Input the screen brightness value and brightness difference as negative samples into the brightness adjustment model; The preset brightness adjustment model obtained by training the positive sample and the negative sample is used as a new preset brightness adjustment model.

7. A smart tablet user behavior analysis system combining multi-source data with reinforcement learning, characterized by: The system comprises: The screen module is used to obtain a brightness adjustment instruction and a screen brightness value, adjust the brightness according to the screen brightness value or the brightness adjustment instruction, and output the current brightness value; Facial information collection module, used to obtain user facial information; Brightness acquisition module, used to detect the ambient brightness and output the ambient brightness value; a CPU module, configured to calculate a brightness difference between a first brightness value and a second brightness value, to run a preset brightness adjustment model to obtain a screen brightness value that matches the brightness difference, and to feed back a target brightness corresponding to a brightness adjustment instruction input by a user to the preset brightness adjustment model to update the brightness adjustment model; The storage module is used to store the preset brightness adjustment model and user information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images