Real-time system parameter automatic tuning method and device based on local intelligence

Abstract

The application discloses a real-time system parameter automatic tuning method and device based on local intelligence, and the method comprises the following steps: acquiring public application interaction data of a server, and training a public AI data model by using the public application interaction data to obtain a trained public AI data model; acquiring real-time interaction information of a user and a smart terminal; inputting the acquired real-time interaction information of the user and the smart terminal into the trained public AI data model, and obtaining current system automatic tuning parameters by predicting and outputting the trained public AI data model; and controlling the smart terminal to automatically adjust system parameters according to the obtained current system automatic tuning parameters. The application realizes the provision of real-time personalized system parameter automatic tuning schemes for users by combining historical data of local user equipment with an AI model, and adds a new function to the smart terminal, i.e., the function of automatically optimizing and adjusting system parameters, thereby providing convenience for the use of users.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent terminals, in particular to a real-time system parameter automatic tuning method and device based on local intelligence, an intelligent terminal and a storage medium. BACKGROUND

[0002] With the development of electronic technology and the continuous improvement of people's living standards, the use of various intelligent terminals is becoming more and more popular, and intelligent terminals have become an indispensable tool in people's lives.

[0003] The intelligent terminal and other intelligent devices of the prior art all provide different system parameter configuration options, such as system volume parameter adjustment, screen brightness parameter adjustment, etc., but these parameters generally need to be manually adjusted by the user. Sometimes the user manually adjusts the process to be too large or too small, and the adjustment scheme of the prior art cannot automatically adjust in real time according to changes in the user's scene, and some parameters are also difficult for the user to understand, resulting in the user being unable to obtain the best effect when using the device.

[0004] Therefore, the prior art still needs to be improved and developed. SUMMARY

[0005] The technical problem to be solved by the present application is to provide a real-time system parameter automatic tuning method and device based on local intelligence, an intelligent terminal and a storage medium, which solves the technical problem that the adjustment scheme of the prior art cannot automatically adjust in real time according to changes in the user's scene, and some parameters are also difficult for the user to understand, resulting in the user being unable to obtain the best effect when using the device.

[0006] The technical scheme adopted by the present application to solve the problem is as follows:

[0007] A real-time system parameter automatic tuning method based on local intelligence, comprising:

[0008] Obtain public application interaction data of a server, and train a public AI data model with the public application interaction data to obtain a trained public AI data model;

[0009] Obtain real-time interaction information between a user and an intelligent terminal;

[0010] Input the obtained real-time interaction information between the user and the intelligent terminal into the trained public AI data model, and predict and output a current system automatic tuning parameter through the trained public AI data model;

[0011] Control the intelligent terminal to automatically adjust the system parameters according to the obtained current system automatic tuning parameter.

[0012] The real-time system parameter automatic tuning method based on local intelligence, wherein the step of inputting the obtained real-time interaction information between the user and the intelligent terminal into the trained public AI data model and obtaining the current system automatic tuning parameter by predicting output of the trained public AI data model further comprises:

[0013] Meanwhile, the trained public AI data model is individually reinforced by using the obtained real-time interaction information between the user and the intelligent terminal and the current device parameter information of the intelligent terminal, so as to obtain a local AI data model after reinforcement training.

[0014] The real-time interaction information between the user and the intelligent terminal is input into the local AI data model after reinforcement training, so as to obtain the optimal numerical value of the system parameter.

[0015] The real-time system parameter automatic tuning method based on local intelligence, wherein the step of obtaining the public application interaction data of the server and training the public AI data model by using the public application interaction data to obtain the trained public AI data model further comprises:

[0016] Obtaining the interaction information and device parameter information generated in the interaction process between each intelligent terminal and the user.

[0017] The obtained interaction information and device parameter information generated in the interaction process between each intelligent terminal and the user are sent to the server for storage.

[0018] The real-time system parameter automatic tuning method based on local intelligence, wherein the step of obtaining the public application interaction data of the server and training the public AI data model by using the public application interaction data to obtain the trained public AI data model further comprises:

[0019] Obtaining the interaction information and device parameter information generated in the interaction process between each intelligent terminal and the user of the server.

[0020] Training the public AI data model by using the interaction information and device parameter information generated in the interaction process between each intelligent terminal and the user to obtain the trained public AI data model.

[0021] The real-time system parameter automatic tuning method based on local intelligence, wherein the step of obtaining the real-time interaction information between the user and the intelligent terminal further comprises:

[0022] The obtained trained public AI data model is pre-set in the intelligent terminal.

[0023] The real-time system parameter automatic tuning method based on local intelligence, wherein the interaction information comprises application information of the intelligent terminal, audio-video playing state, and model information.

[0024] The device parameter information comprises system parameter volume value and brightness value.

[0025] The real-time system parameter automatic tuning method based on local intelligence, wherein the step of automatically adjusting the system parameter by the intelligent terminal according to the obtained current system automatic tuning parameter comprises:

[0026] obtaining the current system automatic tuning parameter predicted and output by the trained public AI data model;

[0027] automatically adjusting the system parameter by the intelligent terminal according to the obtained current system automatic tuning parameter.

[0028] A real-time system parameter automatic tuning device based on local intelligence, wherein the device comprises:

[0029] a public data acquisition module configured to acquire public application interaction data of a server, and train a public AI data model by using the public application interaction data to obtain a trained public AI data model;

[0030] a real-time data acquisition module configured to acquire real-time interaction information of a user and an intelligent terminal;

[0031] a parameter prediction module configured to input the acquired real-time interaction information of the user and the intelligent terminal into the trained public AI data model, and obtain a current system automatic tuning parameter by predicting and outputting the trained public AI data model;

[0032] a reinforcement training module configured to perform individualized reinforcement training on the trained public AI data model by using the acquired real-time interaction information of the user and the intelligent terminal, and device parameter information of the current intelligent terminal, to obtain a local AI data model after reinforcement training;

[0033] an individualized parameter prediction module configured to perform optimal numerical value prediction on system parameters by using the local AI data model after reinforcement training, to obtain the current system automatic tuning parameter;

[0034] a parameter automatic adjustment control module configured to control the intelligent terminal to automatically adjust the system parameter according to the obtained current system automatic tuning parameter.

[0035] An intelligent terminal, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for performing any of the methods.

[0036] A non-transitory computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform any of the methods.

[0037] The present application provides a real-time system parameter automatic tuning method and device based on local intelligence.

[0038] 1) The device terminal can automatically adjust the parameters, without the need for manual adjustment by the user, providing convenience for the user.

[0039] 2) The parameter adjustment is performed locally, without the need for accessing the server each time to make a judgment, saving the server cost and reducing the server occupancy rate.

[0040] 3) The device model is trained using local user data, without the need for uploading to the cloud, ensuring user privacy. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0042] Figure 1 is a flowchart of the real-time system parameter automatic tuning method based on local intelligence provided by the embodiment of the present application.

[0043] Figure 2 is a schematic diagram of the master-slave device connection of the real-time system parameter automatic tuning method based on local intelligence provided by the embodiment of the present application.

[0044] Figure 3 is a principle block diagram of the real-time system parameter automatic tuning device based on local intelligence provided by the embodiment of the present application.

[0045] Figure 4It is an internal structure principle block diagram of the intelligent terminal provided by the embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the objects, technical solutions and advantages of the present application clearer and more explicit, the present application is further described in detail below with reference to the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0047] It should be noted that if the present application embodiments involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directional indications also change accordingly.

[0048] With the development of intelligent screens, the market demand for multi-screen linkage playback is becoming more and more obvious, such as TV stores, large public places, etc. There is a need for synchronous playback of the same video. However, generally, it is realized by using a code stream instrument or other auxiliary equipment, and without the equipment, the multi-screen progress can only be manually adjusted, which is troublesome to use.

[0049] In order to solve the problems of the prior art, the present application provides a real-time system parameter automatic tuning method based on local intelligence. In the intelligent terminal, a general public AI data model is pre-installed or downloaded from the cloud, and information generated in the device and user interaction process and device information are saved locally, such as information of the application of the device at a certain time, audio and video playback state, system parameter value (such as volume value, brightness value), model, etc. The public AI model uses related data to perform reinforcement learning on the device locally and performs optimal value prediction of the system parameters.

[0050] Exemplary method

[0051] As shown in Figure 1 The embodiment of the present application provides a real-time system parameter automatic tuning method based on local intelligence, which can be applied to an intelligent terminal. In the embodiment of the present application, the method comprises the following steps:

[0052] Step S100, obtaining public application interaction data of a server, and training a public AI data model with the public application interaction data to obtain a trained public AI data model;

[0053] In the embodiment of the present application, first, the public AI data model of the public network is acquired. The public AI data model in the embodiment of the present application refers to a deep neural network model. The deep neural network model used in the present application mainly includes a convolutional neural network (CNN), a recurrent neural network (RNN), a deep belief network (DBN), a deep autoencoder (AutoEncoder), and a generative adversarial network (GAN), etc.

[0054] The public application interaction data of the server is historical data of each user using the intelligent terminal device collected by the server using big data, such as the information of the application where the device is located, the audio / video playing state, the system parameter value (such as the volume value, the brightness value), the model, etc. at a certain moment. In the embodiment of the present application, the public application interaction data of the server, i.e. the historical data of each user using the intelligent terminal device collected, is acquired first, and the public AI data model is trained using the public application interaction data, to obtain the trained public AI data model, so as to facilitate predicting the system parameter data through the public AI data model.

[0055] In the specific implementation, first, the interaction information and the device parameter information generated in the interaction process between each intelligent terminal and the user are acquired; such as the information of the application where the device is located, the audio / video playing state, the system parameter value (such as the volume value, the brightness value), the model, etc. at a certain moment. Then, the acquired interaction information and the device parameter information generated in the interaction process between each intelligent terminal and the user are sent to the server for storage.

[0056] Then, the intelligent terminal of the user end acquires the interaction information and the device parameter information generated in the interaction process between each intelligent terminal and the user of the server; such as the information of the application where the device is located, the audio / video playing state, the system parameter value (such as the volume value, the brightness value), the model, etc. Then, the public AI data model is trained using the public interaction information and the device parameter information generated in the interaction process between each intelligent terminal and the user, to obtain the trained public AI data model. This facilitates predicting the appropriate system parameter data through the public AI data model.

[0057] Step S200, acquiring real-time interaction information between the user and the intelligent terminal;

[0058] In the specific implementation of the present application, the trained public AI data model can be pre-set in the intelligent terminal, such as pre-installed or downloaded from the cloud to the intelligent terminal of the user. The intelligent terminal in the embodiment of the present application can be a user's mobile phone, a smart TV at home, etc.

[0059] Then the intelligent terminal acquires real-time interaction information of the user and the intelligent terminal, wherein the interaction information comprises application information of the intelligent terminal, audio / video playing state, and model information.

[0060] In step S300, the acquired real-time interaction information of the user and the intelligent terminal is input into the trained public AI data model, and current system automatic tuning parameters are predicted and output by the trained public AI data model.

[0061] In the embodiment of the application, the acquired real-time interaction information of the user and the intelligent terminal (for example, application information of the intelligent terminal, audio / video playing state, and model information) is input into the trained public AI data model, and current system automatic tuning parameters are predicted and output by the trained public AI data model, for example, system parameter values (such as volume value and brightness value) at this time are output.

[0062] In step S400, the intelligent terminal is controlled to automatically perform system parameter adjustment according to the obtained current system automatic tuning parameters.

[0063] Specifically, the current system automatic tuning parameters predicted and output by the trained public AI data model are acquired, and the intelligent terminal is controlled to automatically perform system parameter adjustment according to the obtained current system automatic tuning parameters.

[0064] In this step, according to the system parameter values (such as volume value and brightness value) at this time output by the trained public AI data model, the intelligent terminal is controlled to automatically perform system parameter adjustment according to the obtained current system automatic tuning parameters, so as to control the intelligent terminal to be adjusted to system parameters suitable for the current application scenario. In this way, the application realizes optimal value prediction of system parameters by using real-time interaction information of the user and the intelligent terminal through the trained public AI data model, and automatically adjusts the system parameters of the intelligent terminal to be suitable for the current application scenario, without the need for manual adjustment by the user, thereby providing convenience for the user.

[0065] In a further embodiment of the application, in order to further improve the accuracy of optimal value prediction of system parameters of each intelligent terminal, the application simultaneously uses the acquired real-time interaction information of the user and the intelligent terminal, and device parameter information of the current intelligent terminal to perform individualized reinforcement training on the trained public AI data model, so as to obtain a local AI data model after reinforcement training.

[0066] That is, the application also pre-provides the intelligent terminal with the trained public AI data model, and uses the historical interaction information data and system parameter data of the intelligent terminal to perform individualized reinforcement training on the trained public AI data model of the intelligent terminal, to obtain a local AI data model after reinforcement training. The real-time interaction information between the user and the intelligent terminal is predicted by using the local AI data model after reinforcement training to obtain the optimal value of the system parameter. The device parameter information includes the volume value and the brightness value of the system parameter.

[0067] The application will be further described below by means of a specific application embodiment:

[0068] As shown in the figure, the real-time system parameter automatic tuning method based on a local intelligent terminal according to the specific application embodiment of the application comprises the following steps: Figure 2

[0069] Step S10, start, and enter step S11.

[0070] Step S11, train the public AI data model by using the server data, and enter step S12.

[0071] Step S12, obtain the public AI data model, and enter step S13.

[0072] Step S13, distribute the public AI data model to the intelligent device APP by pre-provisioning or downloading, and enter step S14.

[0073] Step S14, the intelligent device APP acquires the real-time interaction information between the user and the device, and simultaneously enter step S15 and step S151.

[0074] Step S15, input the interaction information into the AI data model to recommend the result of the system parameter currently desired by the user, and enter step S16.

[0075] Step S151, encrypt and store the information locally, and enter step S152.

[0076] Step S152, periodically input the locally encrypted information into the AI model to perform reinforcement training, and return to step S15.

[0077] In the specific embodiment of the application, preferably, the prediction in step S16 is performed after the reinforcement training. In order to make the prediction result of the system parameter more accurate, two predictions can be performed each time, and the average value of the two predicted system parameters is better.

[0078] Step S16, the intelligent device APP adjusts the corresponding system parameter according to the inference result, and then enters step S17. ​

[0079] Step S17, end.

[0080] From the above, the application can realize, according to the reasoning result of the model, real-time adjustment of the system parameters, so that the system parameters are always optimal for the current user. And the application can also be based on continuous reinforcement learning, the model will gradually realize the learning of the individualization of the user, so that the adjustment of the system parameters can match the individualization needs of the current user, and the various parameters of the intelligent device can be automatically adjusted without manual adjustment by the user, providing convenience for the use of the user.

[0081] The application can realize, according to the reasoning result of the model, real-time adjustment of the system parameters, so that the system parameters are always optimal for the current user. And the application can also be based on continuous reinforcement learning, the model will gradually realize the learning of the individualization of the user, so that the adjustment of the system parameters can match the individualization needs of the current user, and the various parameters of the intelligent device can be automatically adjusted without manual adjustment by the user, providing convenience for the use of the user.

[0082] Exemplary device

[0083] As shown in the Figure 3 The embodiment of the application provides a real-time system parameter automatic tuning device based on local intelligence, which comprises:

[0084] The public data acquisition module 510 is used for acquiring public application interaction data of a server, and training a public AI data model by using the public application interaction data to obtain a trained public AI data model.

[0085] The real-time data acquisition module 520 is used for acquiring real-time interaction information of a user and an intelligent terminal.

[0086] The parameter prediction module 530 is used for inputting the acquired real-time interaction information of the user and the intelligent terminal into the trained public AI data model, and outputting a current system automatic tuning parameter by using the trained public AI data model.

[0087] The reinforcement training module 540 is used for performing individualized reinforcement training on the trained public AI data model by using the acquired real-time interaction information of the user and the intelligent terminal and device parameter information of the current intelligent terminal to obtain a local AI data model after reinforcement training.

[0088] The individualized parameter prediction module 550 is used for performing optimal value prediction of a system parameter on the real-time interaction information of the user and the intelligent terminal by using the local AI data model after reinforcement training to obtain a current system automatic tuning parameter.

[0089] The parameter automatic adjustment control module 560 is configured to control the intelligent terminal to automatically adjust system parameters according to the obtained current system automatic tuning parameters, and the specific process is as described above.

[0090] Based on the above embodiments, the application further provides an intelligent terminal, a principle block diagram of which is shown in FIG. 8. Figure 4 The intelligent terminal can be a smart television, which includes a processor, a memory, a network interface, a display screen, and a camera connected through a system bus. The processor of the intelligent terminal is configured to provide computing and control capabilities. The memory of the intelligent terminal 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 operating system and the computer program in the non-volatile storage medium to run. The network interface of the intelligent terminal is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a real-time system parameter automatic tuning method based on local intelligence. The display screen of the intelligent terminal can be a liquid crystal display screen or an electronic ink display screen. The camera of the intelligent terminal is pre-set in the intelligent terminal and is configured to capture and obtain user gesture images.

[0091] Those skilled in the art can understand that Figure 4 The principle block diagram shown in FIG. 8 is only a block diagram of part of the structure related to the application scheme and does not constitute a limitation on the intelligent terminal to which the application scheme is applied. Specifically, the intelligent terminal can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0092] In one embodiment, an intelligent terminal is provided, which includes a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations:

[0093] Obtaining public application interaction data of a server, and training a public AI data model with the public application interaction data to obtain a trained public AI data model;

[0094] Obtaining real-time interaction information between a user and the intelligent terminal;

[0095] Inputting the obtained real-time interaction information between the user and the intelligent terminal into the trained public AI data model, and predicting and outputting current system automatic tuning parameters through the trained public AI data model;

[0096] Controlling the intelligent terminal to automatically adjust system parameters according to the obtained current system automatic tuning parameters, and the specific process is as described above.

[0097] The step of inputting the obtained real-time interaction information between the user and the intelligent terminal into the trained public AI data model and predicting and outputting a current system automatic tuning parameter through the trained public AI data model further includes:

[0098] Meanwhile, the trained public AI data model is individually reinforced by using the obtained real-time interaction information between the user and the intelligent terminal and the current device parameter information of the intelligent terminal, to obtain a local AI data model after reinforcement.

[0099] The real-time interaction information between the user and the intelligent terminal is subjected to optimal numerical prediction of system parameters by using the local AI data model after reinforcement, to obtain the current system automatic tuning parameter.

[0100] The step of obtaining the public application interaction data of the server and training the public AI data model by using the public application interaction data to obtain the trained public AI data model further includes:

[0101] Interaction information and device parameter information generated in the interaction process between each intelligent terminal and the user are obtained.

[0102] The obtained interaction information and device parameter information generated in the interaction process between each intelligent terminal and the user are sent to the server for storage.

[0103] The step of obtaining the public application interaction data of the server and training the public AI data model by using the public application interaction data to obtain the trained public AI data model includes:

[0104] Interaction information and device parameter information generated in the interaction process between each intelligent terminal and the user of the server are obtained.

[0105] The public AI data model is trained by using the interaction information and device parameter information generated in the interaction process between each intelligent terminal and the user, to obtain the trained public AI data model.

[0106] The step of obtaining the real-time interaction information between the user and the intelligent terminal further includes:

[0107] The obtained trained public AI data model is pre-set in the intelligent terminal.

[0108] The interaction information includes application information of the intelligent terminal, audio and video playing states, and model information.

[0109] The device parameter information includes system parameter volume values and brightness values.

[0110] The step of automatically adjusting the system parameters by the control intelligent terminal according to the obtained current system automatic tuning parameters comprises:

[0111] The current system automatic tuning parameters predicted by the trained public AI data model are obtained.

[0112] The real-time control intelligent terminal automatically adjusts the system parameters according to the obtained current system automatic tuning parameters, and the specific process is as described above.

[0113] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the computer program can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in each embodiment of the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0114] In summary, the application discloses a kind of based on local intelligence real-time system parameter automatic tuning method, device, intelligent terminal and storage medium, the method includes: obtaining the public application interaction data of server, and the public AI data model is trained with the public application interaction data, obtain the public AI data model after training;Real-time interaction information of user and intelligent terminal is obtained;The real-time interaction information of user and intelligent terminal obtained is input into the public AI data model after training, and the current system automatic tuning parameter is obtained by the prediction output of the public AI data model after training;Intelligent terminal is controlled according to the current system automatic tuning parameter obtained, and automatically carries out system parameter adjustment.The application is based on the historical data of local user equipment, combined with AI model, realizes for user provides real-time personalized system parameter automatic tuning scheme, and the intelligent terminal is increased new function: with system parameter automatic optimization adjustment function, greatly provides the convenience for user's use.The application also has the following advantages:

[0115] 1), equipment terminal can automatically adjust parameter, need not user manual adjustment, provides the convenience for user's use;

[0116] 2), parameter adjustment is carried out locally, need not access server to judge each time, saves the expense of server, reduces the occupancy rate of server.

[0117] 3), equipment model is trained using local data of user, need not upload cloud, ensure user privacy.

[0118] It should be understood that the application of the application is not limited to the above examples, and those skilled in the art can improve or change according to the above description, and all these improvements and changes should belong to the protection scope of the claims of the application.

Claims

1. A method for automatic tuning of real-time system parameters based on local intelligence, applied to smart terminals, characterized in that, The method comprises the following steps: acquiring public application interaction data of a server, and training a public AI data model by using the public application interaction data to obtain a trained public AI data model; acquiring real-time interaction information between a user and a smart terminal; inputting the acquired real-time interaction information between the user and the smart terminal into the trained public AI data model, and obtaining current system automatic tuning parameters by predicting and outputting the trained public AI data model; controlling the smart terminal to automatically adjust system parameters according to the obtained current system automatic tuning parameters; the step of inputting the acquired real-time interaction information between the user and the smart terminal into the trained public AI data model, and obtaining current system automatic tuning parameters by predicting and outputting the trained public AI data model further comprises the following steps: simultaneously performing individualized reinforcement training on the trained public AI data model by using the acquired real-time interaction information between the user and the smart terminal, and device parameter information of the current smart terminal to obtain a local AI data model after reinforcement training; performing optimal numerical prediction of system parameters on the real-time interaction information between the user and the smart terminal by using the local AI data model after reinforcement training to obtain current system automatic tuning parameters.

2. The method for automatic tuning of real-time system parameters based on local intelligence as claimed in claim 1, wherein, The step of acquiring public application interaction data of a server, and training a public AI data model by using the public application interaction data to obtain a trained public AI data model further comprises the following steps: acquiring interaction information and device parameter information generated in the interaction process between each smart terminal and a user; sending the acquired interaction information and device parameter information generated in the interaction process between each smart terminal and a user to a server for storage.

3. The method for automatic tuning of real-time system parameters based on local intelligence as claimed in claim 1, wherein, The step of acquiring public application interaction data of a server, and training a public AI data model by using the public application interaction data to obtain a trained public AI data model comprises the following steps: acquiring public interaction information and device parameter information generated in the interaction process between each smart terminal and a user of a server; training a public AI data model by using the public interaction information and device parameter information generated in the interaction process between each smart terminal and a user to obtain a trained public AI data model.

4. The method for automatic tuning of real-time system parameters based on local intelligence as claimed in claim 1, wherein, The step of acquiring real-time interaction information between a user and a smart terminal further comprises the following step: previously setting the obtained trained public AI data model in the smart terminal.

5. The method for automatic tuning of real-time system parameters based on local intelligence as claimed in claim 1, wherein, The interaction information comprises application information of the smart terminal, audio and video playing states, and model information. The device parameter information comprises system parameter volume values and brightness values.

6. The method for automatic tuning of real-time system parameters based on local intelligence as claimed in claim 1, wherein, The step of controlling the smart terminal to automatically adjust system parameters according to the obtained current system automatic tuning parameters comprises the following steps: acquiring current system automatic tuning parameters predicted and output by the trained public AI data model; controlling the smart terminal to automatically adjust system parameters according to the obtained current system automatic tuning parameters in real time.

7. A device for automatically tuning parameters of a real-time system based on local intelligence, for implementing the method for automatically tuning parameters of a real-time system based on local intelligence according to any one of claims 1 to 6, characterized in that, The device comprises: a public data acquisition module, configured to acquire public application interaction data of a server, and train a public AI data model by using the public application interaction data to obtain a trained public AI data model; Real-time data acquisition module, used for acquiring real-time interaction information of the user and the intelligent terminal; Parameter prediction module, used for inputting the acquired real-time interaction information of the user and the intelligent terminal into the trained public AI data model, and outputting current system automatic tuning parameters through the trained public AI data model; Reinforcement training module, used for performing personalized reinforcement training on the trained public AI data model by using the acquired real-time interaction information of the user and the intelligent terminal and the device parameter information of the current intelligent terminal, and obtaining a local AI data model after reinforcement training; Personalized parameter prediction module, used for performing optimal numerical prediction of system parameters on the real-time interaction information of the user and the intelligent terminal by using the local AI data model after reinforcement training, and obtaining current system automatic tuning parameters; Parameter automatic adjustment control module, used for controlling the intelligent terminal to automatically adjust system parameters according to the obtained current system automatic tuning parameters.

8. A smart terminal, characterized by A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform the method of any of claims 1-6.

9. A non-transitory computer-readable storage medium, comprising: When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can perform the method of any of claims 1-6.

Images