Tablet computer fault prediction system based on reinforcement learning

Abstract

The invention relates to a tablet computer fault prediction system based on reinforcement learning, and the system comprises a user terminal which is used for providing state monitoring data when a user uses a tablet computer in daily life; the simulation test terminal is used for providing simulation test parameters; and a server module, the server module further comprising: a storage unit, which is used for storing terminal maintenance data; and the model training and running unit is used for running and training a preset fault model and obtaining a fault prediction result according to the state monitoring data. State monitoring data is used as a sample to be input into a model training and operation unit, preliminary training of a model is completed, simulation test parameters are used as decision objects, a fault prediction result is generated, correctness of the fault prediction result is verified after a simulation test terminal generates an actual result, and a reinforcement learning process is completed. Therefore, sample data resources are reasonably utilized, continuous iteration of the prediction model is completed, and the accuracy of the tablet computer fault prediction system based on reinforcement learning is improved.

Description

Technical Field

[0001] The present application relates to the field of machine learning technology, and in particular to a tablet computer fault prediction system, method, computer device, storage medium, and computer program product based on reinforcement learning. Background Art

[0002] With the rapid development of electronics and communication technologies, tablet computers are becoming more and more popular and are widely used in various scenarios such as education, medical care, business, smart homes, etc.

[0003] A Chinese invention patent with publication number CN116467110B discloses a tablet computer damage detection method and system. Using an appearance inspection program, a tablet computer appearance photo imported into the inspection system is compared with a standard model corresponding to the tablet model. The comparison results determine whether the tablet's appearance is damaged. The tablet's operating system is determined based on the tablet model and updated to the latest version, followed by a functional test of the tablet. The tablet is connected to the internet, and sensor data is received, processed, and stored via a cloud platform. A software diagnostic program is run to perform self-diagnosis on the tablet, and the diagnostic results determine whether the tablet has hardware or software issues. Using a system to detect tablet computer faults can significantly improve efficiency. Manual troubleshooting of a fault requires time and expertise. Using a detection system can quickly locate the fault point and effectively repair it.

[0004] However, this method currently still relies heavily on the direct correspondence between hardware and faults set by the program. It can only detect some faults that have already occurred, and it is difficult to make accurate predictions about the occurrence of faults. Summary of the Invention

[0005] Based on this, it is necessary to provide a tablet computer fault prediction system, method, computer device, computer-readable storage medium and computer program product based on reinforcement learning that can improve the accuracy of fault prediction in response to the above technical problems.

[0006] In a first aspect, the present application provides a tablet computer fault prediction system based on reinforcement learning, the system comprising:

[0007] User terminal, used to provide status monitoring data of users' daily use of tablet computers;

[0008] A simulation test terminal is used to provide simulation test parameters;

[0009] and a server module, the server module also including:

[0010] A storage unit, used for storing terminal maintenance data;

[0011] The model training and operation unit is used to run and train the preset fault model and obtain fault prediction results based on the status monitoring data.

[0012] In one embodiment, the user terminal includes:

[0013] CPU monitoring unit, used to monitor and output CPU temperature, CPU power consumption and CPU occupancy;

[0014] Screen status monitoring unit, used to monitor and output screen temperature and screen brightness;

[0015] Battery management unit, used to monitor and output battery temperature, charging current, charging voltage and charging power;

[0016] A gyroscope unit, used for outputting gyroscope data;

[0017] The data temporary storage unit is used to temporarily store CPU temperature, CPU power consumption, CPU occupancy, screen temperature, screen brightness, battery temperature, charging current, charging voltage, charging power and gyroscope data.

[0018] In a second aspect, the present application also provides a tablet computer fault prediction method based on reinforcement learning, the method comprising:

[0019] The terminal maintenance data pre-stored in the storage space of the server module is used as a first sample and input into a preset fault prediction model to obtain a first fault prediction model;

[0020] Inputting the simulation test parameters into the first fault prediction model to obtain a first fault prediction result;

[0021] Waiting for and obtaining a simulation test result corresponding to the simulation test parameter, and determining whether the first fault prediction result matches the first fault prediction result;

[0022] If not, taking the simulation test parameters and the simulation test results as a second sample, and inputting the second sample into the fault prediction model to obtain a second fault prediction model;

[0023] Obtain status monitoring data of user terminals;

[0024] The second fault prediction model is used as a new preset fault prediction model, and the condition monitoring data is input into the preset fault monitoring model to output a fault prediction result.

[0025] In one embodiment, the specific steps of inputting the simulation test parameters into the first fault prediction model to obtain the first fault prediction result include:

[0026] Determine whether there are any unfinished maintenance work orders;

[0027] If so, the monitoring data of the terminal corresponding to the unfinished work order is input into the first fault prediction model as a simulation test parameter to obtain a first fault prediction result;

[0028] In one embodiment, the specific steps of waiting for and obtaining the simulation test result corresponding to the simulation test parameter and determining whether the first fault prediction result matches the first fault prediction result include:

[0029] Wait for the unfinished work orders to be completed, and re-obtain the actual failure conclusions of the unfinished work orders as simulation test results;

[0030] Determining whether the simulation test result matches the first fault prediction result;

[0031] In one embodiment, the specific steps of inputting the simulation test parameters into the first fault prediction model to obtain the first fault prediction result include:

[0032] If there is no unfinished maintenance work order;

[0033] The monitoring data of the current test terminal is obtained as a simulation test parameter and input into the first fault prediction model to obtain a first fault monitoring result;

[0034] Waiting for and obtaining the test result of the current test terminal as the simulation test result;

[0035] Determine whether the simulation test result matches the first fault prediction result.

[0036] In one embodiment, the specific steps of obtaining the status monitoring data of the user terminal include:

[0037] Send a status monitoring request command to the user terminal, wait for and obtain the status monitoring data sent back by the user terminal;

[0038] The status monitoring data includes changes in preset key parameters of the user terminal within the past preset time period. The key parameters include CPU temperature, CPU power consumption, CPU occupancy, screen temperature, screen brightness, battery temperature, charging current, charging voltage, charging power and gyroscope data.

[0039] 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:

[0040] The terminal maintenance data pre-stored in the storage space of the server module is used as a first sample and input into a preset fault prediction model to obtain a first fault prediction model;

[0041] Inputting the simulation test parameters into the first fault prediction model to obtain a first fault prediction result;

[0042] Waiting for and obtaining a simulation test result corresponding to the simulation test parameter, and determining whether the first fault prediction result matches the first fault prediction result;

[0043] If not, taking the simulation test parameters and the simulation test results as a second sample, and inputting the second sample into the fault prediction model to obtain a second fault prediction model;

[0044] Obtain status monitoring data of user terminals;

[0045] The second fault prediction model is used as a new preset fault prediction model, and the condition monitoring data is input into the preset fault monitoring model to output a fault prediction result.

[0046] 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:

[0047] The terminal maintenance data pre-stored in the storage space of the server module is used as a first sample and input into a preset fault prediction model to obtain a first fault prediction model;

[0048] Inputting the simulation test parameters into the first fault prediction model to obtain a first fault prediction result;

[0049] Waiting for and obtaining a simulation test result corresponding to the simulation test parameter, and determining whether the first fault prediction result matches the first fault prediction result;

[0050] If not, taking the simulation test parameters and the simulation test results as a second sample, and inputting the second sample into the fault prediction model to obtain a second fault prediction model;

[0051] Obtain status monitoring data of user terminals;

[0052] The second fault prediction model is used as a new preset fault prediction model, and the condition monitoring data is input into the preset fault monitoring model to output a fault prediction result.

[0053] 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:

[0054] The terminal maintenance data pre-stored in the storage space of the server module is used as a first sample and input into a preset fault prediction model to obtain a first fault prediction model;

[0055] Inputting the simulation test parameters into the first fault prediction model to obtain a first fault prediction result;

[0056] Waiting for and obtaining a simulation test result corresponding to the simulation test parameter, and determining whether the first fault prediction result matches the first fault prediction result;

[0057] If not, taking the simulation test parameters and the simulation test results as a second sample, and inputting the second sample into the fault prediction model to obtain a second fault prediction model;

[0058] Obtain status monitoring data of user terminals;

[0059] The second fault prediction model is used as a new preset fault prediction model, and the condition monitoring data is input into the preset fault monitoring model to output a fault prediction result.

[0060] The above-mentioned tablet computer fault prediction system, method, computer equipment, storage medium and computer program product based on reinforcement learning completes the initial training of the model by inputting the status monitoring data as samples into the model training and operation unit, and then uses the simulation test parameters as the decision object to produce the fault prediction results. After the simulation test terminal produces the actual results, it is fed back to the model training and operation unit to verify the correctness of the fault prediction results and complete the reinforcement learning process, thereby rationally utilizing the sample data resources and completing the continuous iteration of the prediction model, thereby improving the accuracy of the tablet computer fault prediction system based on reinforcement learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 1 is a structural block diagram of a tablet computer fault prediction system based on reinforcement learning in one embodiment;

[0062] Figure 2 1 is a flow chart of a method for predicting tablet computer failure based on reinforcement learning in one embodiment;

[0063] Figure 3 FIG1 is an application environment diagram of a tablet computer fault prediction method based on reinforcement learning in one embodiment;

[0064] Figure 4 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0065] 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.

[0066] In one embodiment, Figure 1As shown, a tablet computer fault prediction system based on reinforcement learning is provided, including a user terminal, a simulation test terminal and a server module, wherein:

[0067] User terminal, used to provide status monitoring data of users' daily use of tablet computers;

[0068] A simulation test terminal is used to provide simulation test parameters;

[0069] and a server module, the server module also including:

[0070] A storage unit, used for storing terminal maintenance data;

[0071] The model training and operation unit is used to run and train the preset fault model and obtain fault prediction results based on the status monitoring data.

[0072] The user terminal is the tablet computer used by the user. While providing services to the user, the user terminal monitors its own key parameters and summarizes them into status monitoring data and regularly uploads them to the server module. Specifically, the user terminal includes:

[0073] CPU monitoring unit, used to monitor and output CPU temperature, CPU power consumption and CPU occupancy;

[0074] Screen status monitoring unit, used to monitor and output screen temperature and screen brightness;

[0075] Battery management unit, used to monitor and output battery temperature, charging current, charging voltage and charging power;

[0076] A gyroscope unit, used for outputting gyroscope data;

[0077] And a data temporary storage unit for temporarily storing CPU temperature, CPU power consumption, CPU occupancy, screen temperature, screen brightness, battery temperature, charging current, charging voltage, charging power and gyroscope data.

[0078] The server module can periodically send status monitoring request instructions to the user terminal through a preset program. After receiving the status monitoring request instructions from the server module, the user terminal returns the status monitoring data within a preset time interval to the server module. The preset time interval is the time period between the last time the status monitoring request instruction was received and the current time the status monitoring request instruction is received. Since the server module sends the status monitoring request instruction according to a fixed period set by the program, the preset time interval is an interval of fixed time length.

[0079] In an embodiment of the present application, the storage unit of the server module stores terminal maintenance data, which specifically refers to the status monitoring data sent back by the terminal device that is actually under maintenance before the maintenance occurs, and the fault information input by the maintenance personnel after the maintenance of the terminal device is completed. The fault information includes the faulty hardware and its corresponding fault type, such as screen shattering, screen display failure, circuit board poor soldering, circuit board short circuit, battery aging, etc. The specific content can be manually set according to actual conditions when establishing the database.

[0080] In one embodiment, the simulation test terminal is a tablet computer that has experienced a fault but has not yet begun maintenance, and the simulation test parameters are the tablet computer's recently uploaded status monitoring data. For this type of faulty device, the model training and operation unit stored in the server predicts and determines the fault, completing a decision. After maintenance personnel complete subsequent maintenance, the prediction results of the model training and operation unit are compared with the actual fault information obtained by the maintenance personnel and re-entered into the model to complete the verification of the decision. This method achieves reinforcement learning and iteration of the prediction model, thereby improving the accuracy of the prediction results.

[0081] In another embodiment, the simulation test terminal is a tablet computer used for simulation testing. Specifically, the simulation test terminal can be a tablet computer specifically used for testing, or a virtual tablet computer generated by digital twin technology for simulation testing. The simulation test terminal is usually used to perform various tests on tablet computer products. During the test process, the simulation test terminal will also record the various key parameters of the tablet computer and summarize them as simulation test parameters. After the simulation test parameters are input into the model training and operation unit of the server, the result of the tablet computer failure state after a preset time period will be obtained. The result includes all the above-mentioned artificially set failure information, as well as a result indicating that no failure will occur after the preset time period. By using a tablet computer or a virtual tablet computer used for testing, the speed of model reinforcement learning and iteration can be accelerated, thereby further improving the accuracy of the model prediction results.

[0082] Based on the same inventive concept, embodiments of the present application also provide a method for predicting tablet computer faults based on reinforcement learning, which is applied to the aforementioned system for predicting tablet computer faults based on reinforcement learning. The solution provided by this method is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the method for predicting tablet computer faults based on reinforcement learning provided below can be found in the limitations of the aforementioned system for predicting tablet computer faults based on reinforcement learning, and will not be further elaborated here.

[0083] In one embodiment, Figure 2As shown in the figure, a tablet computer fault prediction method based on reinforcement learning is provided. Figure 2 As shown, the following steps are included:

[0084] Step A100: terminal maintenance data pre-stored in the storage space of the server module is used as a first sample and input into a preset fault prediction model to obtain a first fault prediction model.

[0085] Among them, the storage space is provided by the storage unit, and the terminal maintenance data is the data provided by the tablet computer when a fault occurs and the maintenance is completed. The terminal maintenance data includes the status monitoring data of the product under maintenance that was last fed back before the maintenance, and the fault information entered by the maintenance personnel after the maintenance is completed. By inputting the terminal maintenance data into the preset fault prediction model, a mapping relationship between the various parameters in the status monitoring data and the fault information can be established, that is, the first fault prediction model is obtained. The preset fault prediction model is stored in the model training and operation unit, and iteration is completed by inputting samples and reinforcement learning. When the first fault prediction model is first obtained, by setting the weights of the various parameters in the preset fault prediction model to the same weight, after inputting several first samples, the weights of the various parameters of the first fault prediction model obtained are changed compared to the original preset fault prediction model, thereby establishing a more accurate mapping relationship between the various parameters and the fault information.

[0086] Step A200: Inputting simulation test parameters into a first fault prediction model to obtain a first fault prediction result.

[0087] The simulation test parameters are provided by the simulation test terminal and stored in the server storage unit. The simulation test parameters are of the same parameter type as the condition monitoring data. The purpose of obtaining the simulation test parameters is to provide an object for simulation decision-making for the first fault prediction model. That is, by inputting the simulation test parameters into the first fault prediction model, a first fault prediction result is obtained. Whether the fault prediction result is correct can only be determined after the test or detection process of the simulation test terminal is completed and the actual result is output. The simulation test terminal is a tablet computer that has experienced a fault but has not yet started maintenance.

[0088] In the embodiment of the present application, the specific steps of step A200 include:

[0089] Step A210: Determine whether there is any unfinished maintenance work order.

[0090] Among them, the unfinished maintenance work order is a part of the maintenance work order data of the tablet computer product pre-stored in the server storage module. The completed maintenance work order is stored in the storage space as terminal maintenance data, and the unfinished maintenance work order is still treated as an unfinished maintenance work order. The maintenance work order only contains the status monitoring data uploaded for the last time by the tablet computer being repaired before it was sent for repair. When executing this step, the storage space of the server module is accessed to determine whether such data exists.

[0091] Step A220: If yes, the monitoring data of the terminal corresponding to the unfinished work order is input into the first fault prediction model as a simulation test parameter to obtain a first fault prediction result.

[0092] In this embodiment, if there is no unfinished work order, the first fault prediction model is directly used as the second fault prediction model, and step A300 and step A400 are skipped to directly execute step A500.

[0093] Step A300: Wait and obtain the simulation test result corresponding to the simulation test parameter, and determine whether the first fault prediction result matches the first fault prediction result.

[0094] The simulation test result is the maintenance result of the simulation test terminal completed and input by the maintenance personnel. In this embodiment, the steps of step A300 include:

[0095] Step A310: Wait for the unfinished work orders to be completed, and re-obtain the actual fault conclusion of the unfinished work orders as the simulation test result.

[0096] When executing this step, the waiting time for the unfinished work order can be limited. When the predetermined time is exceeded, the first fault prediction model can be used as the second fault model, and the process jumps to step A500.

[0097] Step A320: Determine whether the simulation test result matches the first fault prediction result.

[0098] By determining whether the first fault prediction result matches the second fault prediction result, the first fault prediction result can be verified. However, due to the limited number of faulty devices that need to be repaired, the number of samples used for reinforcement learning is also limited, which will slow down the further iteration of the first fault prediction model to a certain extent.

[0099] Therefore, in another embodiment, the specific steps of step A200 include:

[0100] Step A210: Determine whether there is any unfinished maintenance work order.

[0101] Step A240: If not, obtain the monitoring data of the current test terminal as a simulation test parameter and input it into the first fault prediction model to obtain a first fault monitoring result.

[0102] In this embodiment, if there are no unfinished maintenance work orders, the test data of the terminal currently in the test phase is obtained, that is, the test data of the current test terminal is input as simulation test parameters into the first fault prediction model to perform fault prediction. The test data of the current test terminal is obtained in the same manner as the status monitoring data of the user terminal. The fault monitoring result in this step is the first fault prediction model's prediction of whether the current test terminal will fail before the next monitoring data output, and what kind of failure it will fail. This includes all the aforementioned fault types, as well as the result type of no fault.

[0103] Correspondingly, in this embodiment, the specific steps of step A300 further include:

[0104] Step A330: Wait and obtain the test result of the current test terminal as the simulation test result.

[0105] Step A340: Determine whether the simulation test result matches the first fault prediction result.

[0106] Step A400: If not, the simulation test parameters and the simulation test results are used as a second sample, and the second sample is input into the fault prediction model to obtain a second fault prediction model.

[0107] Through step S400, the first iteration of the first fault prediction model can be completed, thereby achieving the purpose of reinforcement learning.

[0108] Step A500: Acquire status monitoring data of the user terminal.

[0109] Specifically, the specific steps of step A500 include: sending a status monitoring request instruction to the user terminal, waiting for and obtaining status monitoring data sent back by the user terminal.

[0110] The status monitoring data includes changes in preset key parameters of the user terminal within the past preset time period. The key parameters include CPU temperature, CPU power consumption, CPU occupancy, screen temperature, screen brightness, battery temperature, charging current, charging voltage, charging power and gyroscope data.

[0111] Step A600: The second fault prediction model is used as a new preset fault prediction model, and the status monitoring data is input into the preset fault monitoring model to output a fault prediction result.

[0112] The iteration of the preset fault model is completed by taking the iterated second fault prediction model as a new preset fault model, thereby obtaining a more accurate fault prediction result.

[0113] 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.

[0114] The tablet computer fault prediction method based on 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.

[0115] Each module in the aforementioned reinforcement learning-based tablet computer fault prediction system 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 within a computer device as hardware, or stored in a computer device memory as software, allowing the processor to call and execute the corresponding operations of each module.

[0116] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, a memory, and a network interface 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, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store status monitoring data and simulation test parameters. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a tablet computer fault prediction method based on reinforcement learning is implemented.

[0117] 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.

[0118] 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:

[0119] Step A100: using the terminal maintenance data pre-stored in the storage space of the server module as a first sample, and inputting it into a preset fault prediction model to obtain a first fault prediction model;

[0120] Step A200: Inputting simulation test parameters into a first fault prediction model to obtain a first fault prediction result;

[0121] Step A300: Waiting and obtaining a simulation test result corresponding to the simulation test parameter, and determining whether the first fault prediction result matches the first fault prediction result;

[0122] Step A400: If not, taking the simulation test parameters and the simulation test results as a second sample, and inputting the second sample into the fault prediction model to obtain a second fault prediction model;

[0123] Step A500: Acquire status monitoring data of the user terminal;

[0124] Step A600: The second fault prediction model is used as a new preset fault prediction model, and the status monitoring data is input into the preset fault monitoring model to output a fault prediction result.

[0125] 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:

[0126] Step A100: using the terminal maintenance data pre-stored in the storage space of the server module as a first sample, and inputting it into a preset fault prediction model to obtain a first fault prediction model;

[0127] Step A200: Inputting simulation test parameters into a first fault prediction model to obtain a first fault prediction result;

[0128] Step A300: Waiting and obtaining a simulation test result corresponding to the simulation test parameter, and determining whether the first fault prediction result matches the first fault prediction result;

[0129] Step A400: If not, taking the simulation test parameters and the simulation test results as a second sample, and inputting the second sample into the fault prediction model to obtain a second fault prediction model;

[0130] Step A500: Acquire status monitoring data of the user terminal;

[0131] Step A600: The second fault prediction model is used as a new preset fault prediction model, and the status monitoring data is input into the preset fault monitoring model to output a fault prediction result.

[0132] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0133] Step A100: using the terminal maintenance data pre-stored in the storage space of the server module as a first sample, and inputting it into a preset fault prediction model to obtain a first fault prediction model;

[0134] Step A200: Inputting simulation test parameters into a first fault prediction model to obtain a first fault prediction result;

[0135] Step A300: Waiting and obtaining a simulation test result corresponding to the simulation test parameter, and determining whether the first fault prediction result matches the first fault prediction result;

[0136] Step A400: If not, taking the simulation test parameters and the simulation test results as a second sample, and inputting the second sample into the fault prediction model to obtain a second fault prediction model;

[0137] Step A500: Acquire status monitoring data of the user terminal;

[0138] Step A600: The second fault prediction model is used as a new preset fault prediction model, and the status monitoring data is input into the preset fault monitoring model to output a fault prediction result.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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 tablet computer fault prediction system based on reinforcement learning, characterized in that: include User terminal, used to provide status monitoring data of users' daily use of tablet computers; A simulation test terminal is used to provide simulation test parameters; and a server module, wherein the server module further comprises: A storage unit, used for storing terminal maintenance data; The model training and operation unit is used to run and train the preset fault model and obtain fault prediction results based on the status monitoring data.

2. The tablet computer fault prediction system based on reinforcement learning according to claim 1, characterized in that: The user terminal includes: CPU monitoring unit, used to monitor and output CPU temperature, CPU power consumption and CPU occupancy; Screen status monitoring unit, used to monitor and output screen temperature and screen brightness; Battery management unit, used to monitor and output battery temperature, charging current, charging voltage and charging power; A gyroscope unit, used for outputting gyroscope data; The data temporary storage unit is used to temporarily store CPU temperature, CPU power consumption, CPU occupancy, screen temperature, screen brightness, battery temperature, charging current, charging voltage, charging power and gyroscope data.

3. A tablet computer fault prediction method based on reinforcement learning, characterized in that: include: The terminal maintenance data pre-stored in the storage space of the server module is used as a first sample and input into a preset fault prediction model to obtain a first fault prediction model; Inputting the simulation test parameters into the first fault prediction model to obtain a first fault prediction result; Waiting for and obtaining a simulation test result corresponding to the simulation test parameter, and determining whether the first fault prediction result matches the first fault prediction result; If not, taking the simulation test parameters and the simulation test results as a second sample, and inputting the second sample into the fault prediction model to obtain the second fault prediction model; Obtain status monitoring data of user terminals; The second fault prediction model is used as a new preset fault prediction model, and the state monitoring data is input into the preset fault monitoring model to output a fault prediction result.

4. The tablet computer fault prediction method based on reinforcement learning according to claim 3 is characterized in that: The specific steps of inputting the simulation test parameters into the first fault prediction model to obtain the first fault prediction result include: Determine whether there are any unfinished maintenance work orders; If so, the monitoring data of the terminal corresponding to the unfinished work order is input into the first fault prediction model as a simulation test parameter to obtain a first fault prediction result.

5. The tablet computer fault prediction method based on reinforcement learning according to claim 4 is characterized in that: The specific steps of waiting for and obtaining the simulation test result corresponding to the simulation test parameter and determining whether the first fault prediction result matches the first fault prediction result include: Waiting for the unfinished work order to be completed, and re-obtaining the actual failure conclusion of the unfinished work order as the simulation test result; Determine whether the simulation test result matches the first fault prediction result.

6. The tablet computer fault prediction method based on reinforcement learning according to claim 4 or 5, characterized in that: The specific steps of inputting the simulation test parameters into the first fault prediction model to obtain the first fault prediction result include: If there is no unfinished maintenance work order; The monitoring data of the current test terminal is obtained as a simulation test parameter and input into the first fault prediction model to obtain a first fault monitoring result; Waiting for and obtaining the test result of the current test terminal as a simulation test result; Determine whether the simulation test result matches the first fault prediction result.

7. The tablet computer fault prediction method based on reinforcement learning according to claim 6, characterized in that: The specific steps of obtaining the status monitoring data of the user terminal include: Sending a status monitoring request instruction to a user terminal, waiting for and obtaining the status monitoring data returned by the user terminal; The status monitoring data includes changes in preset key parameters of the user terminal within the past preset time period, and the key parameters include CPU temperature, CPU power consumption, CPU occupancy, screen temperature, screen brightness, battery temperature, charging current, charging voltage, charging power and gyroscope data.

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 3 to 7 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 3 to 7 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 3 to 7 are implemented.

Images