Performance parameter adjustment method, device, electronic device, storage medium and product

Abstract

The present application provides a performance parameter adjustment method, device, electronic device, storage medium and product, which belongs to the field of artificial intelligence technology. The method includes: obtaining application status information of a terminal, the application status information is status information when the terminal runs a target application based on a first performance parameter; obtaining feedback information of a target object, the feedback information is feedback information of the target object to the terminal when the terminal runs the target application under the application status information; determining parameter adjustment information of the target application based on the application status information and the feedback information; adjusting the first performance parameter based on the parameter adjustment information. The method improves the accuracy of performance parameter adjustment.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a performance parameter adjustment method, device, electronic device, storage medium and product. Background Art

[0002] In order to bring fun to the user's life, the user will install game applications on the terminal. However, during the operation of the game application, problems such as freezing and heating may occur, thus affecting the user experience; and by adjusting the performance parameters of the terminal running the game application, the above problems can be improved.

[0003] In the related art, the game application is run in a test terminal, and the performance parameters of the game application are determined based on the status information (such as frame rate, temperature, etc.) of the game application running in the test terminal, and the performance parameters of the terminal where the game application is installed are uniformly adjusted based on the performance parameters.

[0004] Since the performance parameter is determined based on the state information of the test terminal running the game application, the performance parameter may not be suitable for the current terminal, thereby reducing the accuracy of the performance parameter adjustment. Summary of the invention

[0005] The embodiments of the present application provide a performance parameter adjustment method, device, electronic device, storage medium and product, which can improve the accuracy of performance parameter adjustment. The technical solution is as follows:

[0006] In one aspect, a performance parameter adjustment method is provided, the method comprising:

[0007] Acquire application status information of the terminal, where the application status information is status information when the terminal runs a target application based on a first performance parameter;

[0008] Acquire feedback information of a target object, where the feedback information is feedback information of the target object to the terminal when the terminal runs the target application under the application state information;

[0009] Determining parameter adjustment information of the target application based on the application state information and the feedback information;

[0010] Based on the parameter adjustment information, the first performance parameter is adjusted.

[0011] In another aspect, a performance parameter adjustment device is provided, the device comprising:

[0012] A first acquisition module, configured to acquire application status information of a terminal, wherein the application status information is status information when the terminal runs a target application based on a first performance parameter;

[0013] A second acquisition module is used to acquire feedback information of a target object, where the feedback information is feedback information of the target object to the terminal when the terminal runs the target application under the application state information;

[0014] A first determination module, configured to determine parameter adjustment information of the target application based on the application state information and the feedback information;

[0015] An adjustment module is used to adjust the first performance parameter based on the parameter adjustment information.

[0016] On the other hand, an electronic device is provided, comprising one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement the performance parameter adjustment method described in any of the above-mentioned implementation methods.

[0017] On the other hand, a computer-readable storage medium is provided, in which at least one program code is stored. The at least one program code is loaded and executed by a processor to implement the performance parameter adjustment method described in any of the above implementation modes.

[0018] On the other hand, a computer program product is provided, wherein the computer program product stores at least one program code, and the at least one program code is used to be executed by a processor to implement the performance parameter adjustment method as described in any of the above implementations.

[0019] In an embodiment of the present application, since the parameter adjustment information is determined based on the application status information of the terminal and the feedback information of the target object, the parameter adjustment information can better reflect the subjective performance requirements of the target object, and then the performance parameters of the terminal are adjusted based on the parameter adjustment information, so that the adjusted performance parameters are more in line with the performance requirements of the target object, thereby improving the accuracy of the performance parameter adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram showing an implementation environment provided by an exemplary embodiment of the present application is shown;

[0021] Figure 2 A flow chart of a performance parameter adjustment method shown in an exemplary embodiment of the present application is shown;

[0022] Figure 3 A flowchart of a method for training a demand forecasting model shown in an exemplary embodiment of the present application is shown;

[0023] Figure 4A schematic diagram of obtaining performance training samples according to an exemplary embodiment of the present application is shown;

[0024] Figure 5 A schematic diagram showing the association of application state information and feedback information shown in an exemplary embodiment of the present application is shown;

[0025] Figure 6 A schematic diagram of clustering performance training samples shown in an exemplary embodiment of the present application is shown;

[0026] Figure 7 A flow chart of a performance parameter adjustment method shown in an exemplary embodiment of the present application is shown;

[0027] Figure 8 A schematic diagram showing a pop-up window displayed on a terminal according to an exemplary embodiment of the present application is shown;

[0028] Fig. 9 A flowchart of predicting performance requirement tags is shown in an exemplary embodiment of the present application;

[0029] Fig.10 A flow chart of a performance parameter adjustment method shown in an exemplary embodiment of the present application is shown;

[0030] Fig.11 A structural block diagram of a performance parameter adjustment device shown in an exemplary embodiment of the present application is shown;

[0031] Fig.12 A structural block diagram of an electronic device according to an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0032] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0033] The term "multiple" as used herein refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0034] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions. For example, the application status information and feedback information involved in this application are obtained with full authorization.

[0035] The performance parameter adjustment method provided in the embodiment of the present application can be executed by an electronic device. In some embodiments, the electronic device is a terminal or a server. The following first takes the electronic device as an example to introduce some implementation environment diagrams of the performance parameter adjustment method provided in the embodiment of the present application. Please refer to Figure 1 , which shows a schematic diagram of an implementation environment provided by an exemplary embodiment of the present application. The implementation environment includes a terminal 100 and a server 200. The terminal 100 and the server 200 can be directly or indirectly connected via wired or wireless communication, which is not limited in the present application.

[0036] In some embodiments, the terminal 100 is a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. In some embodiments, the server 200 is an independent server or a server cluster or a distributed system of multiple physical server projects, and can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0037] In some embodiments, the target application is run on the terminal 100, and the terminal 100 obtains application status information when it runs the target application based on performance parameters and feedback information of the target object using the terminal on the application status information. The terminal sends the application status information and feedback information to the server 200, and the server 200 determines parameter adjustment information of the target application based on the application status information and the feedback information, and sends the parameter adjustment information to the terminal 100, and the terminal 100 adjusts the performance parameters of running the target application based on the parameter adjustment information.

[0038] In some embodiments, the electronic device is a terminal 100, and a target application is run on the terminal 100. The terminal 100 obtains application status information when it runs the target application based on performance parameters and feedback information of the target object using the terminal on the application status information, and determines parameter adjustment information of the target application based on the application status information and feedback information, and then the terminal 100 adjusts the performance parameters of running the target application based on the parameter adjustment information.

[0039] Please refer to Figure 2 , which shows a flow chart of a performance parameter adjustment method shown in an exemplary embodiment of the present application. The execution subject in the embodiment of the present application is an electronic device, and the method includes:

[0040] 201. Obtain application status information of a terminal, where the application status information is status information when the terminal runs a target application based on a first performance parameter.

[0041] 202. Obtain feedback information of the target object, where the feedback information is feedback information of the target object to the terminal when the terminal runs the target application under the application state information.

[0042] 203. Determine parameter adjustment information of the target application based on the application state information and the feedback information.

[0043] 204. Adjust the first performance parameter based on the parameter adjustment information.

[0044] In some embodiments, determining parameter adjustment information of a target application based on application status information and feedback information includes: determining a performance requirement tag of a target object based on application status information and feedback information; and obtaining parameter adjustment information matching the performance requirement tag.

[0045] In some embodiments, based on application status information and feedback information, a performance requirement label of a target object is determined, including: inputting the application status information and feedback information into a demand prediction model to obtain a performance requirement label of the target object, the demand prediction model is trained based on application status information of a sample terminal, feedback information of the sample object, and performance requirement labels, and the demand prediction model is used to predict the performance requirement label of the object.

[0046] In some embodiments, the method also includes: obtaining multiple performance training samples, each performance training sample includes application status information of a sample terminal and feedback information of a sample object, the application status information of the sample terminal is status information when the sample terminal runs the target application based on a second performance parameter, and the feedback information of the sample object is feedback information of the sample object to the sample terminal when running the target application under the application status information; based on the multiple performance training samples, determining multiple performance requirement labels, each performance requirement label corresponds to at least one performance training sample; based on the multiple performance training samples and the multiple performance requirement labels, performing model training to obtain a demand prediction model.

[0047] In some embodiments, based on multiple performance training samples, multiple performance requirement labels are determined, including: clustering the multiple performance training samples to obtain multiple label clusters, each label cluster including at least one performance training sample, and the sample objects corresponding to the performance training samples in the same label cluster have the same performance requirements for the sample terminal running the target application; determining the performance requirement labels corresponding to the multiple label clusters respectively, to obtain multiple performance requirement labels.

[0048] In some embodiments, the performance requirement tag includes at least one of a heat-sensitive tag, a jam-sensitive tag, a heat-tolerant tag, and a jam-tolerant tag.

[0049] In some embodiments, obtaining feedback information from a target object includes: displaying a pop-up window on a terminal, the pop-up window including a plurality of performance feedback options, and in response to a triggering operation of the target object on at least one of the plurality of performance feedback options, obtaining the triggered performance feedback option to obtain feedback information from the target object; or, sending questionnaire survey information to the terminal, obtaining information fed back by the target object based on the questionnaire survey information, to obtain feedback information from the target object.

[0050] In some embodiments, obtaining feedback information of the target object includes at least one of the following implementation methods: obtaining feedback information of the target object in response to an exit operation, the exit operation being used to indicate that the target application has been exited; obtaining feedback information of the target object in response to a switch operation, the switch operation being used to indicate that the target application enters the next level from the current level or re-enters the current level.

[0051] In some embodiments, adjusting the first performance parameter based on the parameter adjustment information includes: the parameter adjustment information includes a third performance parameter, and the first performance parameter is adjusted to the third performance parameter; or, the parameter adjustment information includes an adjustment direction and an adjustment amplitude, and the first performance parameter is adjusted based on the adjustment direction and the adjustment amplitude.

[0052] In some embodiments, before determining parameter adjustment information of the target application based on the application status information and feedback information, the method also includes: determining status requirement information of the target object based on the feedback information, the status requirement information being used to indicate whether the application status information meets the status requirement of the target object; if the status requirement information indicates that the application status information does not meet the status requirement of the target object, then executing the step of determining parameter adjustment information of the target application based on the application status information and feedback information.

[0053] In some embodiments, the application status information includes multiple status data, and the parameter adjustment information of the target application is determined based on the application status information and feedback information, including: determining at least one target status data among the multiple status data, the target status data being the status data that the target object is concerned about; determining the parameter adjustment information of the target application based on at least one target status data and feedback information.

[0054] In an embodiment of the present application, since the parameter adjustment information is determined based on the application status information of the terminal and the feedback information of the target object, the parameter adjustment information can better reflect the subjective performance requirements of the target object, and then the performance parameters of the terminal are adjusted based on the parameter adjustment information, so that the adjusted performance parameters are more in line with the performance requirements of the target object, thereby improving the accuracy of the performance parameter adjustment.

[0055] Please refer to Figure 3 , which shows a flowchart of a method for training a demand prediction model shown in an exemplary embodiment of the present application, and the embodiment is described by taking a server as an execution subject. The method includes:

[0056] 301. The server obtains multiple performance training samples.

[0057] Among them, each performance training sample includes application status information of a sample terminal and feedback information of a sample object, the application status information of the sample terminal is the status information when the sample terminal runs the target application based on the second performance parameter, and the feedback information of the sample object is the feedback information of the sample object to the sample terminal when it runs the target application under the application status information.

[0058] The target application may be any application that needs to adjust performance parameters, such as a game application, a video application, an audio application, etc., without limitation. The application status information includes at least one of temperature data, frame rate data, network delay data, current data, brightness data, whether charging data, and image quality data, without limitation. The feedback information includes at least one of a bit stuck, a bit hot, not bad, etc., without limitation.

[0059] In one implementation, the server conducts scenario-based research to obtain performance training samples, that is, to obtain performance training samples when the sample objects actually run the target application. Figure 4 , which shows a schematic diagram of an exemplary embodiment of the present application showing the acquisition of performance training samples; the server obtains application status information and feedback information during and after the target application is running to obtain the performance training samples.

[0060] Before obtaining the application status information of the sample terminal, the server obtains the performance mode information of the sample terminal; the performance mode information includes one of the high power consumption mode, balanced mode and low power consumption mode. The performance parameters corresponding to the high power consumption mode, balanced mode and low power consumption mode respectively decrease in sequence, and accordingly, the power consumption corresponding to the high power consumption mode, balanced mode and low power consumption mode respectively also decreases in sequence. When the performance mode information is the balanced mode, the server obtains the application status information of the sample terminal. When the performance mode information is the balanced mode, it indicates that the performance parameters of the sample terminal are allowed to be adjusted. When the performance mode information is the high power consumption mode or the low power consumption mode, the server ends the process and no longer obtains the application status information of the sample terminal. When the performance mode information is the high power consumption mode or the low power consumption mode, it indicates that the performance parameters of the sample terminal are not allowed to be adjusted.

[0061] Wherein, when the performance mode information is a balanced mode, the server further obtains a second performance parameter of the sample terminal running the target application, and the second performance parameter is obtained based on the configuration information of the sample terminal. The second performance parameter includes at least one of a plurality of performance data such as the frequency of a central processing unit (CPU), a frame rate of a graphics processing unit (GPU), and the number of threads, and is not specifically limited here.

[0062] Optionally, the performance mode information, application state information and the second performance parameter of the sample terminal are all obtained from a behavior log table of the sample terminal running the target application.

[0063] After the target application runs, the server obtains feedback information from the sample object. Figure 4In one implementation, the server develops access and pushes a survey short message to the sample terminal through a browser or application center within a preset time, such as 10 minutes, after the sample object exits the target application. The sample terminal responds to the sample object's triggering of the survey short message by displaying the questionnaire survey information on the sample terminal, and the server obtains information fed back by the sample object based on the questionnaire survey information to obtain the feedback information of the sample object. The questionnaire survey information refers to a survey questionnaire, which includes multiple questions, and the multiple questions are refined questions set around the heating and lag issues that the sample object is concerned about. Based on these questions, the performance information that the sample object is most concerned about can be obtained, and the disturbance to the sample object is reduced; optionally, the survey questionnaire can also be used to reflect the subjective feelings of the sample object, which is not specifically limited here.

[0064] In some embodiments, the server directly obtains the application status information of the sample terminal and the feedback information of the sample object in pairs to obtain the performance training sample. In other embodiments, the server obtains the application status information of multiple sample terminals and the feedback information of multiple sample objects respectively. Optionally, the application status information and the feedback information respectively carry corresponding association fields. The server associates the application status information of the sample terminal and the feedback information of the sample object using the sample terminal based on the association field to obtain the performance training sample. Optionally, the association field is the device identification number (OpenUser ID, ouid) of the sample terminal. See Figure 5 , which shows a schematic diagram of associating application status information and feedback information shown in an exemplary embodiment of the present application; the server obtains application status information of multiple sample terminals and feedback information of multiple sample objects, and based on the ouid association field, associates the application status information and feedback information corresponding to the multiple sample objects respectively to obtain multiple performance training samples.

[0065] 302. The server determines multiple performance requirement labels based on multiple performance training samples.

[0066] Among them, each performance requirement label corresponds to at least one performance training sample.

[0067] In some embodiments, the server determines multiple performance requirement labels based on multiple performance training samples, including the following steps (1)-(2):

[0068] (1) The server clusters multiple performance training samples to obtain multiple label clusters.

[0069] Each label cluster includes at least one performance training sample, and the sample objects corresponding to the performance training samples in the same label cluster have the same performance requirements for the sample terminal to run the target application.

[0070] Optionally, the server uses at least one of the clustering algorithms such as k-means clustering algorithm, representative density-based clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) and hierarchical agglomerative clustering algorithm (Hierarchical Agglomerative Clustering, HAC) to cluster multiple performance training samples to obtain multiple label clusters, which is not specifically limited here.

[0071] The application status information includes at least one of multiple status data such as temperature data, frame rate data, network delay data, current data, brightness data, whether to charge and image quality data, which is not specifically limited here. Optionally, the application status information includes multiple status data, and the multiple status data and feedback information correspond to a clustering dimension respectively, and the server clusters multiple performance training samples based on the multiple clustering dimensions. See Figure 6 , which shows a schematic diagram of clustering performance training samples shown in an exemplary embodiment of the present application; wherein each dimension corresponds to a state data or feedback information, and the server continuously performs clustering adjustment based on the state data or feedback information corresponding to each dimension to obtain multiple label clusters. Figure 6 The horizontal axis dimension and the vertical axis dimension in can correspond to temperature data and frame rate data respectively, which is not specifically limited here.

[0072] In some embodiments, the application state information includes temperature data and frame rate data, and the feedback information includes one of a little hot, a little stuck and not bad. It should be noted that if the feedback information is not bad, it means that the application state information meets the state requirements of the sample object, and there is no need to adjust the performance parameters of the sample terminal. Therefore, the server determines the label cluster only based on the feedback information of a little hot and a little stuck. Optionally, after the server clusters multiple performance training samples, the performance training samples with a temperature lower than a preset temperature, a frame rate lower than a preset frame rate and feedback information of a little hot are clustered into a first label cluster, the performance training samples with a temperature lower than a preset temperature, a frame rate lower than a preset frame rate and feedback information of a little stuck are clustered into a second label cluster, the performance training samples with a temperature higher than a preset temperature, a frame rate greater than a preset frame rate and feedback information of a little stuck are clustered into a third label cluster, and the performance training samples with a temperature higher than a preset temperature, a frame rate greater than a preset frame rate and feedback information of a little hot are clustered into a fourth label cluster. It should be noted that multiple label clusters can be clustered as needed, and are not limited to this.

[0073] (2) The server determines the performance requirement labels corresponding to the multiple label clusters, and obtains multiple performance requirement labels.

[0074] Optionally, the performance requirement tag includes at least one of a heat-sensitive tag, a jam-sensitive tag, a heat-tolerant tag, and a jam-tolerant tag.

[0075] In some embodiments, the application state information includes temperature data and frame rate data, and the feedback information includes a little hot, a little stuck and not bad. Accordingly, the multiple label clusters are respectively a first label cluster, a second label cluster, a third label cluster and a fourth label cluster. Optionally, the server determines that the performance requirement label corresponding to the first label cluster is a heat sensitivity label, which is used to indicate that the sample object is more sensitive to the temperature of the sample terminal; or, the server determines that the performance requirement label corresponding to the first label cluster is a jam tolerance label, which is used to indicate that the sample object is more tolerant to the frame rate of the sample terminal. The server determines that the performance requirement label corresponding to the second label cluster is a jam sensitivity label, which is used to indicate that the sample object is more sensitive to the frame rate of the sample terminal. The server determines that the performance requirement label corresponding to the third label cluster is a jam sensitivity label, which is used to indicate that the sample object is more sensitive to the frame rate of the sample terminal; or, the server determines that the performance requirement label corresponding to the third label cluster is a heat tolerance label, which is used to indicate that the sample object is more tolerant to the temperature of the sample terminal. The server determines that the performance requirement label corresponding to the fourth label cluster is a heat sensitivity label, which is used to indicate that the sample object is more sensitive to temperature. It should be noted that the performance requirement label corresponding to each label cluster can be set and changed as needed, and is not limited to this.

[0076] In this implementation, the terminal clusters multiple performance training samples to obtain multiple label clusters, thereby realizing the division of objects with different performance requirements, and then assigning different performance requirement labels to objects with different performance requirements, so as to facilitate the subsequent matching of different performance adjustment information for objects with different performance requirements, so that the adjustment of performance parameters based on the performance adjustment information is more in line with the performance requirements of the object, and the adjusted performance parameters are more accurate.

[0077] 303. The server performs model training based on multiple performance training samples and multiple performance demand labels to obtain a demand prediction model.

[0078] Optionally, the server performs iterative training of the model based on multiple performance training samples and multiple performance requirement labels, and adjusts the model parameters of the initial demand forecasting model based on the loss value of each iterative training, where the initial demand forecasting model is a model with initial model parameters. In response to the loss value reaching a preset value or no longer decreasing, the server uses the model parameters corresponding to the loss value as the model parameters of the demand forecasting model to obtain the demand forecasting model.

[0079] An embodiment of the present application provides a method for training a demand prediction model, by training the demand prediction model based on application status information, feedback information and performance requirement labels, so that the demand prediction model can learn the correspondence between application status information, feedback information and performance requirement labels, so that the performance requirement labels of the target objects can be predicted based on the demand prediction model, with high computational efficiency, and the efficiency of adjusting performance parameters can be significantly improved subsequently.

[0080] Please refer to Figure 7 , which shows a flowchart of a performance parameter adjustment method shown in an exemplary embodiment of the present application, and the embodiment is described by taking a terminal as an execution subject. The method includes:

[0081] 701. The terminal obtains application status information of the terminal.

[0082] The terminal obtains application status information during the operation of the target application. The application status information is the status information when the terminal runs the target application based on the first performance parameter. The first performance parameter includes at least one of multiple performance data such as the frequency of the CPU, the frame rate and the number of threads of the GPU. The application status information includes at least one of temperature data, frame rate data, network delay data, current data, brightness data, whether charging data and image quality data, etc., which are not specifically limited here.

[0083] 702. The terminal obtains feedback information of the target object.

[0084] The feedback information is the feedback information of the target object to the terminal when the terminal runs the target application under the application state information. The feedback information includes at least one of "a little stuck", "a little hot", "not bad", etc., which is not specifically limited here.

[0085] In some embodiments, the terminal obtains feedback information of the target object, including the following implementation methods:

[0086] In one implementation, a terminal displays a pop-up window on the terminal, and the pop-up window includes multiple performance feedback options. The terminal responds to the triggering operation of the target object on at least one performance feedback option among the multiple performance feedback options, obtains the triggered performance feedback option, and obtains the feedback information of the target object. In this implementation, by displaying a pop-up window on the terminal and displaying the performance feedback option in the pop-up window, the target object can obtain feedback information after triggering the performance feedback option, thereby improving the efficiency of obtaining the feedback information of the target object.

[0087] In another implementation, the terminal sends questionnaire survey information to the terminal, and the terminal obtains information fed back by the target object based on the questionnaire survey information to obtain feedback information from the target object. In this implementation, by sending questionnaire survey information to the terminal, the target object can directly provide feedback based on the questionnaire survey information displayed on the terminal, which not only facilitates the target object to provide feedback, but also improves the efficiency of the terminal in obtaining feedback information from the target object.

[0088] In some embodiments, when the target application is exited, the target application enters the next level from the current level, or re-enters the current level, the terminal obtains the feedback information of the target object; accordingly, the terminal obtains the feedback information of the target object, including at least one of the following implementation methods:

[0089] In one implementation, the terminal obtains feedback information of the target object in response to the exit operation, and the exit operation is used to indicate that the target application is exited. Optionally, the terminal exits the target application after obtaining the feedback information of the target object, that is, the terminal obtains feedback information on the interface of the target application.

[0090] In this implementation, by obtaining feedback information when the target application exits execution, not only is it possible to avoid disturbing the target object during the operation of the target application, but also the feedback information of the target object is obtained immediately when the target application exits the application. Because the target object has the deepest feelings about the target application that has just been executed when the target application has just exited execution, the feedback information obtained at this moment can more effectively feed back the subjective feelings of the target object, thereby improving the accuracy of the feedback information.

[0091] In another implementation, the terminal obtains feedback information of the target object in response to a switching operation, and the switching operation is used to instruct the target application to enter the next level from the current level or re-enter the current level. Optionally, after the terminal obtains the feedback information of the target object, it enters the next level from the current level or re-enters the current level, that is, the terminal obtains feedback information on the interface of the current level.

[0092] In this implementation, by obtaining feedback information when the target object enters the next level from the current level or re-enters the current level, the target object's subjective feeling about the current level can be obtained in time, making the feedback information more accurate.

[0093] Optionally, the above implementations may be combined arbitrarily to obtain the following implementations:

[0094] (1) The terminal displays a pop-up window in response to the exit operation. The terminal obtains the triggered performance feedback option in response to the triggering operation of the target object on at least one of the multiple performance feedback options, and obtains feedback information corresponding to the target.

[0095] (2) The terminal displays a pop-up window in response to the switching operation. The terminal obtains the triggered performance feedback option in response to the triggering operation of the target object on at least one of the multiple performance feedback options, and obtains feedback information corresponding to the target.

[0096] See also Figure 8 , which shows a schematic diagram of a pop-up window displayed on a terminal according to an exemplary embodiment of the present application. Optionally, the target application is a game application, and the terminal displays a pop-up window after the current level ends. The pop-up window includes multiple performance feedback options, and the multiple performance feedback options are respectively not bad, a little stuck, and a little hot, which respectively correspond to the benchmark question "How was the game experience just now?"

[0097] (3) In response to the exit operation, the terminal sends questionnaire survey information to the terminal, and the terminal obtains information fed back by the target object based on the questionnaire survey information, thereby obtaining feedback information from the target object.

[0098] (4) In response to the switching operation, the terminal sends questionnaire survey information to the terminal, and the terminal obtains information fed back by the target object based on the questionnaire survey information, thereby obtaining feedback information from the target object.

[0099] In some embodiments, before the terminal executes step 703, the terminal also determines the state requirement information of the target object based on the feedback information, and the state requirement information is used to indicate whether the application state information meets the state requirement of the target object. If the state requirement information indicates that the application state information does not meet the state requirement of the target object, the terminal executes step 703. If the state requirement information indicates that the application state information meets the state requirement of the target object, the terminal directly ends the process and no longer adjusts the first performance parameter.

[0100] Optionally, the feedback information includes one of "not bad", "a little hot" and "a little stuck", and the state requirement information includes first state requirement information and second state requirement information, the first state requirement information is used to indicate that the application state information meets the state requirement of the target object, and the second state requirement information is used to indicate that the application state information does not meet the state requirement of the target object. The terminal determines the state requirement information of the target object based on the feedback information, including the following implementation method: if the feedback information is "not bad", the terminal determines that the state requirement information is the first state requirement information, that is, it indicates that the application state information meets the state requirement corresponding to the target. If the feedback information is not "not bad", the terminal determines that the state requirement information is the second state requirement information, that is, it indicates that the application state information does not meet the state requirement of the target object.

[0101] In this embodiment, before executing step 703, it is determined whether the application status information meets the status requirements of the target object based on the feedback information of the target object. Step 703 is executed only when it does not meet the requirements to make subsequent adjustments to the performance parameters. This avoids the waste of resources caused by adjusting the performance parameters when the application status information meets the status requirements of the target object, and avoids the situation where the target object does not meet the application status information corresponding to the adjusted performance parameters after the performance parameters are adjusted.

[0102] 703. The terminal determines the performance requirement label of the target object through a demand prediction model based on the application status information and feedback information.

[0103] In some embodiments, the demand prediction model is deployed in a terminal; the terminal inputs the application status information and feedback information into the demand prediction model to obtain the performance requirement label of the target object; the demand prediction model is trained based on the application status information of the sample terminal, the feedback information of the sample object, and the performance requirement label, and the demand prediction model is used to predict the performance requirement label of the object. When the demand prediction model is deployed in the terminal, the terminal performs data conversion on the demand prediction model so that the demand prediction model matches the terminal, ensuring that the demand prediction model can be normally called on the terminal to predict the performance requirement label.

[0104] In some embodiments, the demand prediction model is deployed in the background server of the target application. After the terminal obtains the application status information and feedback information, it sends it to the server. The application status information and feedback information are input into the demand prediction model through the server to obtain the performance requirement label of the target object; the server sends the performance requirement label to the terminal, so that the terminal obtains the performance requirement label of the target object.

[0105] In this embodiment, the performance requirement label is obtained through the demand prediction model. Since the demand prediction model is pre-trained based on the application status information of the sample terminal, the feedback information of the sample object and the performance requirement label, the performance requirement label of the target object can be quickly obtained based on the demand prediction model, thereby improving the efficiency of determining the performance requirement label of the target object.

[0106] In some embodiments, the terminal obtains application state information and feedback information of the target application that it runs multiple times based on the first performance parameter. Accordingly, the terminal inputs the multiple application state information and multiple feedback information into the demand prediction model to obtain a performance demand label of the target object. In this embodiment, the terminal obtains the performance demand label based on the application state information and feedback information of the target application that it runs multiple times, so that the performance demand label is more accurate, avoiding the situation where the performance demand label is inaccurate due to the inaccurate application state information and feedback information of the target application that the terminal runs once, thereby improving the accuracy of the obtained performance demand label.

[0107] See also Fig. 9 , which shows a flowchart of predicting a performance requirement label shown in an exemplary embodiment of the present application. Among them, the terminal predicts the performance requirement label of the target object based on the application state information and feedback information and the demand prediction model. The performance requirement label is used to represent the performance requirement of the target object.

[0108] 704. The terminal obtains parameter adjustment information matching the performance requirement tag.

[0109] In some embodiments, the terminal obtains the parameter adjustment information from the requirement correspondence based on the performance requirement tag; the requirement correspondence is used to store the correspondence between the performance requirement tag and the parameter adjustment information.

[0110] In some embodiments, the parameter adjustment information includes a third performance parameter, which refers to a performance parameter that directly matches the performance requirement tag, and the terminal can directly adjust the first performance parameter to the third performance parameter. The first performance parameter includes at least one of multiple performance data such as the frequency of the CPU, the frame rate of the GPU, and the number of threads. If the first performance parameter includes multiple performance data, the third performance parameter includes target performance data corresponding to the multiple performance data, and the target performance data is the performance data to be adjusted by the terminal.

[0111] Optionally, the third performance parameter corresponding to each performance requirement label can be set and changed as needed, and is not specifically limited here. For example, for a jamming sensitivity label, if the first performance parameter includes the CPU frequency, the CPU frequency included in the third performance parameter is larger and greater than the CPU frequency included in the first performance parameter.

[0112] In some embodiments, the parameter adjustment information includes an adjustment direction and an adjustment range, wherein the adjustment direction refers to whether to adjust the first performance parameter upward or downward, and the adjustment range refers to the amount of adjustment of the first performance parameter. If the first performance parameter includes multiple performance data, the adjustment direction and adjustment range include the adjustment directions and adjustment ranges corresponding to the multiple performance data respectively.

[0113] Optionally, the adjustment direction and adjustment range corresponding to each performance requirement label can be set and changed as needed, and are not specifically limited here. For example, for the jamming sensitivity label, if the first performance parameter includes the CPU frequency, then correspondingly, the adjustment direction is to increase, and the adjustment range can be set and changed as needed.

[0114] It should be noted that steps 703-704 are an implementation method for the terminal to determine the parameter adjustment information of the target application based on the application status information and feedback information. In another implementation method, the terminal determines the parameter adjustment information of the target application based on the application status information and feedback information, including the following steps: the terminal determines at least one target status data among multiple status data, and the target status data is the status data that the target object is concerned about; the terminal determines the parameter adjustment information of the target application based on the at least one target status data and feedback information. Among them, the target status data is temperature data, frame rate data, etc., which are not specifically limited here. Optionally, the terminal inputs at least one target status data and feedback data into the demand prediction model to obtain the performance requirement label of the target object; the terminal determines the parameter adjustment information that matches the performance requirement label to obtain the parameter adjustment information of the target application.

[0115] In this implementation method, the parameter adjustment information of the target application is determined by the target status data that the target object is concerned about, so that the determined parameter adjustment information is more in line with the subjective performance requirements of the target object, and then the performance parameters of the terminal are subsequently adjusted based on the parameter adjustment information, so that the adjusted performance parameters are more in line with the performance requirements of the target object, which can further improve the accuracy of the performance parameter adjustment.

[0116] 705. The terminal adjusts the first performance parameter based on the parameter adjustment information.

[0117] In some embodiments, the parameter adjustment information includes a third performance parameter, and the terminal adjusts the first performance parameter based on the parameter adjustment information, including the following implementation: the terminal adjusts the first performance parameter to the third performance parameter. In this embodiment, the terminal directly determines the third performance parameter to be adjusted, and then the terminal can directly adjust the first performance parameter to the third performance parameter, that is, the adjustment of the first performance parameter can be achieved through one-step adjustment, thereby improving the efficiency of adjusting the first performance parameter.

[0118] In some embodiments, the parameter adjustment information includes an adjustment direction and an adjustment range, and the terminal adjusts the first performance parameter based on the parameter adjustment information, including the following implementation method: the terminal adjusts the adjustment range of the first performance parameter based on the adjustment direction. In this embodiment, the terminal adjusts the first performance parameter based on the adjustment direction and the adjustment range, so that even if the terminal obtains the same performance requirement label based on different first performance parameters, it can adjust different first performance parameters based on the adjustment direction and the adjustment range; it avoids the situation where the terminal obtains the same performance requirement label based on different first performance parameters, and any first performance parameter is adjusted based on the third performance parameter corresponding to the performance requirement label, causing unreasonable adjustment, thereby improving the flexibility of adjusting the first performance parameter.

[0119] join Fig.10 , which shows a flowchart of performance parameter adjustment shown in an exemplary embodiment of the present application. The terminal repeatedly obtains application state information when it runs the target application based on the first performance parameter and feedback information of the target object based on the feedback of the terminal. Among them, the application state information includes multiple state data, and the terminal uses the multiple state data and feedback information as a feature of the terminal running the target application, and obtains multiple features of the terminal running the target application, and then inputs the multiple features of the terminal running the target application multiple times into the demand prediction model to predict the performance requirement label of the target object. Optionally, the performance requirement label is a fever sensitivity label, and accordingly, the terminal determines the performance adjustment information corresponding to the fever sensitivity label. Optionally, the performance adjustment information includes an adjustment direction and an adjustment amplitude, and the first performance parameter is lowered by a preset amount based on the adjustment direction and the adjustment amplitude, that is, the power consumption is reduced by reducing the first performance parameter to meet the performance requirements of the target object.

[0120] In some embodiments, before the terminal executes the above steps 701-705, the terminal also determines the mode in which the target application is running; when the terminal is in a balanced mode, the terminal executes the above steps 701-705. The balanced mode is a mode that allows adjustment of the first performance parameter. When the terminal is in a high power consumption mode or a low power consumption mode, the process is terminated directly without executing the above steps 701-705. The high power consumption mode and the low power consumption mode are modes that do not allow adjustment of the first performance parameter.

[0121] It should be noted that the method provided in the embodiment of the present application can be applied to any game application that requires a balance between performance and power consumption, and is used to provide objects with personalized performance and power consumption experience; it solves the long-standing problem that terminals cannot meet the needs of personalized configuration of game objects in terms of performance parameters, and truly realizes that performance and power consumption configuration varies from person to person.

[0122] In an embodiment of the present application, the terminal obtains a performance requirement label of the target object through application status information and feedback information, and then adjusts the first performance parameter based on the parameter adjustment information corresponding to the performance requirement label. Since the performance requirement label is obtained based on the application status information and feedback information, the performance requirement label can better reflect the subjective performance requirement of the target object, and then the performance adjustment reference is determined based on the performance requirement label, and then the performance parameters of the terminal are adjusted based on the performance adjustment information, so that the adjusted performance parameters are more in line with the performance requirements of the target object, thereby improving the accuracy of the performance parameter adjustment.

[0123] Please refer to Fig.11 , which shows a structural block diagram of a performance parameter adjustment device shown in an exemplary embodiment of the present application. The device includes:

[0124] A first acquisition module 1101 is used to acquire application status information of a terminal, where the application status information is status information when the terminal runs a target application based on a first performance parameter;

[0125] The second acquisition module 1102 is used to acquire feedback information of the target object, where the feedback information is feedback information of the target object to the terminal when the terminal runs the target application under the application state information;

[0126] A first determination module 1103, configured to determine parameter adjustment information of a target application based on the application state information and the feedback information;

[0127] The adjustment module 1104 is configured to adjust the first performance parameter based on the parameter adjustment information.

[0128] Acquire application status information of the terminal, where the application status information is status information when the terminal runs the target application based on the first performance parameter;

[0129] Acquire feedback information of the target object, where the feedback information is feedback information of the target object to the terminal when the terminal runs the target application under the application state information;

[0130] Determine parameter adjustment information of the target application based on the application status information and the feedback information;

[0131] Based on the parameter adjustment information, the first performance parameter is adjusted.

[0132] In some embodiments, the first determining module 1103 is configured to:

[0133] Determine the performance requirement label of the target object based on the application status information and feedback information;

[0134] Get parameter adjustment information that matches the performance requirement tag.

[0135] In some embodiments, the first determining module 1103 is configured to:

[0136] The application status information and feedback information are input into the demand prediction model to obtain the performance requirement label of the target object. The demand prediction model is trained based on the application status information of the sample terminal, the feedback information of the sample object and the performance requirement label, and the demand prediction model is used to predict the performance requirement label of the object.

[0137] In some embodiments, the apparatus further comprises:

[0138] A third acquisition module is used to acquire multiple performance training samples, each performance training sample includes application state information of a sample terminal and feedback information of a sample object, the application state information of the sample terminal is state information when the sample terminal runs the target application based on the second performance parameter, and the feedback information of the sample object is feedback information of the sample object to the sample terminal when running the target application under the application state information;

[0139] A second determination module is used to determine a plurality of performance requirement labels based on a plurality of performance training samples, each performance requirement label corresponding to at least one performance training sample;

[0140] The training module is used to perform model training based on multiple performance training samples and multiple performance demand labels to obtain a demand prediction model.

[0141] In some embodiments, the second determination module is used to cluster multiple performance training samples to obtain multiple label clusters, each label cluster includes at least one performance training sample, and the sample objects corresponding to the performance training samples in the same label cluster have the same performance requirements for the sample terminal running the target application; determine the performance requirement labels corresponding to the multiple label clusters respectively, and obtain multiple performance requirement labels.

[0142] In some embodiments, the performance requirement tag includes at least one of a heat-sensitive tag, a jam-sensitive tag, a heat-tolerant tag, and a jam-tolerant tag.

[0143] In some embodiments, the second acquisition module 1102 is used to display a pop-up window on the terminal, which includes multiple performance feedback options. In response to the target object's triggering operation on at least one of the multiple performance feedback options, the triggered performance feedback option is acquired to obtain feedback information from the target object; or, questionnaire survey information is sent to the terminal, information feedback from the target object based on the questionnaire survey information is acquired to obtain feedback information from the target object.

[0144] In some embodiments, the second acquisition module 1102 is used to obtain feedback information of the target object in response to an exit operation, where the exit operation is used to indicate that the target application has been exited; and to obtain feedback information of the target object in response to a switch operation, where the switch operation is used to indicate that the target application enters the next level from the current level or re-enters the current level.

[0145] In some embodiments, the adjustment module 1104 is used to adjust the first performance parameter to the third performance parameter when the parameter adjustment information includes a third performance parameter; or, when the parameter adjustment information includes an adjustment direction and an adjustment amplitude, the first performance parameter is adjusted based on the adjustment direction and the adjustment amplitude.

[0146] In some embodiments, the apparatus further comprises:

[0147] A third determination module is used to determine the state requirement information of the target object based on the feedback information, where the state requirement information is used to indicate whether the application state information meets the state requirement of the target object;

[0148] The execution module is used to execute the step of determining parameter adjustment information of the target application based on the application state information and the feedback information if the state requirement information indicates that the application state information does not meet the state requirement of the target object.

[0149] In some embodiments, the application status information includes multiple status data, and the first determination module 1103 is used to determine at least one target status data among the multiple status data, where the target status data is the status data that the target object is concerned about; based on the at least one target status data and feedback information, determine the parameter adjustment information of the target application.

[0150] Please refer to Fig.12 , which shows a structural block diagram of an electronic device 1200 provided by an exemplary embodiment of the present application. The electronic device 1200 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc. The electronic device 1200 in the present application may include one or more of the following components: a processor 1210, a memory 1220, and a display screen 1230.

[0151] The processor 1210 may include one or more processing cores. The processor 1210 uses various interfaces and lines to connect the various parts of the entire electronic device 1200, and executes various functions and processes data of the electronic device 1200 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1220, and calling data stored in the memory 1220. Optionally, the processor 1210 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 1210 can integrate one or more combinations of a central processing unit (CPU), a graphics processing unit (GPU), a neural network processor (NPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content that needs to be displayed on the display screen 1230; the NPU is used to implement artificial intelligence (AI) functions; and the modem is used to process wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 1210, but may be implemented by a separate chip.

[0152] The memory 1220 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 1220 includes a non-transitory computer-readable storage medium. The memory 1220 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 1220 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc.; the data storage area may store data (such as audio data, a phone book), etc., created according to the use of the electronic device 1200.

[0153] The display screen 1230 is a display component for displaying a user interface. Optionally, the display screen 1230 is a display screen with a touch function, through which the user can use any suitable object such as a finger, a touch pen, etc. to perform touch operations on the display screen 1230.

[0154] The display screen 1230 is usually arranged on the front panel of the electronic device 1200. The display screen 1230 can be designed as a full screen, a curved screen, a special-shaped screen, a double-sided screen or a folding screen. The display screen 1230 can also be designed as a combination of a full screen and a curved screen, a combination of a special-shaped screen and a curved screen, etc., which is not limited in this embodiment.

[0155] In addition, those skilled in the art can understand that the structure of the electronic device 1200 shown in the above drawings does not constitute a limitation on the electronic device 1200, and the electronic device 1200 may include more or fewer components than shown, or combine certain components, or arrange the components differently. For example, the electronic device 1200 also includes a microphone, a speaker, a radio frequency circuit, an input unit, a sensor, an audio circuit, a wireless fidelity (Wireless Fidelity, Wi-Fi) module, a power supply, a Bluetooth module and other components, which will not be described in detail here.

[0156] An embodiment of the present application also provides a computer-readable medium, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the performance parameter adjustment method shown in the above embodiments.

[0157] An embodiment of the present application also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the performance parameter adjustment method shown in the above embodiments.

[0158] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented with hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein the communication media include any media that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that a general or special-purpose computer can access.

[0159] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A performance parameter adjustment method, characterized in that: The method comprises: Acquire application status information of the terminal, where the application status information is status information when the terminal runs a target application based on a first performance parameter; Displaying a pop-up window on the terminal, the pop-up window including a plurality of performance feedback options, and in response to a triggering operation of the target object on at least one of the plurality of performance feedback options, acquiring the triggered performance feedback option, and obtaining feedback information of the target object; or sending questionnaire survey information to the terminal, acquiring information fed back by the target object based on the questionnaire survey information, and obtaining feedback information of the target object, the feedback information being feedback information of the target object on the terminal running the target application under the application state information, and the feedback information including at least one of a little stuck, a little hot, and not bad; Based on the application state information and the feedback information, determine the performance requirement label of the target object, and obtain parameter adjustment information matching the performance requirement label from the requirement correspondence, wherein the performance requirement label includes at least one of a heat-sensitive label, a freeze-sensitive label, a heat-tolerant label, and a freeze-tolerant label, and the requirement correspondence is used to store a correspondence between the performance requirement label and the parameter adjustment information; adjusting the first performance parameter based on the parameter adjustment information; The generation process of the performance requirement label includes the following steps: Acquire multiple performance training samples, each performance training sample including application state information of a sample terminal and feedback information of a sample object; For the multiple performance training samples, the performance training samples with a temperature lower than a preset temperature, a frame rate lower than a preset frame rate and feedback information of being a little hot are clustered into a first label cluster, the performance training samples with a temperature lower than a preset temperature, a frame rate lower than a preset frame rate and feedback information of being a little stuck are clustered into a second label cluster, the performance training samples with a temperature higher than a preset temperature, a frame rate greater than a preset frame rate and feedback information of being a little stuck are clustered into a third label cluster, and the performance training samples with a temperature higher than a preset temperature, a frame rate greater than a preset frame rate and feedback information of being a little hot are clustered into a fourth label cluster; Determine the performance requirement labels corresponding to the first label cluster, the second label cluster, the third label cluster and the fourth label cluster respectively, and obtain at least one of the heat-sensitive label, the jamming-sensitive label, the heat-tolerant label and the jamming-tolerant label.

2. The method according to claim 1, characterized in that: The determining the performance requirement label of the target object based on the application state information and the feedback information includes: The application status information and the feedback information are input into a demand prediction model to obtain a performance requirement label of the target object. The demand prediction model is trained based on the application status information of the sample terminal, the feedback information of the sample object and the performance requirement label, and the demand prediction model is used to predict the performance requirement label of the object.

3. The method according to claim 2, characterized in that The method further comprises: Acquire multiple performance training samples, each performance training sample includes application state information of a sample terminal and feedback information of a sample object, the application state information of the sample terminal is state information when the sample terminal runs the target application based on a second performance parameter, and the feedback information of the sample object is feedback information of the sample object to the sample terminal when the sample terminal runs the target application under the application state information; Based on the multiple performance training samples, determining multiple performance requirement labels, each performance requirement label corresponds to at least one performance training sample; Model training is performed based on the multiple performance training samples and the multiple performance demand labels to obtain the demand prediction model.

4. The method according to claim 3, characterized in that The determining a plurality of performance requirement labels based on the plurality of performance training samples comprises: Clustering the multiple performance training samples to obtain multiple label clusters, each label cluster including at least one performance training sample, and sample objects corresponding to the performance training samples in the same label cluster have the same performance requirements for sample terminals to run the target application; The performance requirement labels corresponding to the multiple label clusters are determined to obtain the multiple performance requirement labels.

5. The method according to claim 1, characterized in that The method also includes at least one of the following implementations: In response to an exit operation, obtaining feedback information of the target object, wherein the exit operation is used to indicate that the target application is exited; In response to a switching operation, feedback information of the target object is obtained, wherein the switching operation is used to instruct the target application to enter a next level from a current level or to re-enter the current level.

6. The method according to claim 1, characterized in that The adjusting the first performance parameter based on the parameter adjustment information includes: The parameter adjustment information includes a third performance parameter, and the first performance parameter is adjusted to the third performance parameter; or, The parameter adjustment information includes an adjustment direction and an adjustment amplitude, and the first performance parameter is adjusted to the adjustment amplitude based on the adjustment direction.

7. The method according to claim 1, characterized in that Before determining the performance requirement tag of the target object based on the application state information and the feedback information and obtaining parameter adjustment information matching the performance requirement tag from the requirement correspondence, the method further includes: Based on the feedback information, determining state requirement information of the target object, the state requirement information being used to indicate whether the application state information meets the state requirement of the target object; If the state requirement information indicates that the application state information does not meet the state requirement of the target object, the step of determining the parameter adjustment information of the target application based on the application state information and the feedback information is performed.

8. The method according to claim 1, characterized in that The application status information includes a plurality of status data, and the method further includes: Determine at least one target state data among the plurality of state data, wherein the target state data is state data that the target object is concerned about; Parameter adjustment information of the target application is determined based on the at least one target state data and the feedback information.

9. A performance parameter adjustment device, characterized in that: The device comprises: A first acquisition module, configured to acquire application status information of a terminal, wherein the application status information is status information when the terminal runs a target application based on a first performance parameter; a second acquisition module, configured to display a pop-up window on the terminal, wherein the pop-up window includes a plurality of performance feedback options, and in response to a triggering operation of a target object on at least one of the plurality of performance feedback options, acquire the triggered performance feedback option to obtain feedback information of the target object; or, to send questionnaire survey information to the terminal, acquire information fed back by the target object based on the questionnaire survey information, and obtain feedback information of the target object, wherein the feedback information is feedback information of the target object on the terminal running the target application under the application state information, and the feedback information includes at least one of a little stuck, a little hot, and not bad; A first determination module is configured to determine a performance requirement label of the target object based on the application state information and the feedback information, and obtain parameter adjustment information matched by the performance requirement label from a requirement correspondence relationship, wherein the performance requirement label includes at least one of a heat-sensitive label, a freeze-sensitive label, a heat-tolerant label, and a freeze-tolerant label, and the requirement correspondence relationship is used to store a correspondence between the performance requirement label and the parameter adjustment information; an adjustment module, configured to adjust the first performance parameter based on the parameter adjustment information; A third acquisition module is used to acquire multiple performance training samples, each performance training sample includes application state information of a sample terminal and feedback information of a sample object; The second determination module is used to cluster the performance training samples with a temperature lower than a preset temperature, a frame rate lower than a preset frame rate and feedback information of being a little hot into a first label cluster, cluster the performance training samples with a temperature lower than a preset temperature, a frame rate lower than a preset frame rate and feedback information of being a little stuck into a second label cluster, cluster the performance training samples with a temperature higher than a preset temperature, a frame rate higher than a preset frame rate and feedback information of being a little stuck into a third label cluster, and cluster the performance training samples with a temperature higher than a preset temperature, a frame rate higher than a preset frame rate and feedback information of being a little hot into a fourth label cluster; determine the performance requirement labels corresponding to the first label cluster, the second label cluster, the third label cluster and the fourth label cluster respectively, and obtain at least one of the heat-sensitive label, the jamming-sensitive label, the heat-tolerant label and the jamming-tolerant label.

10. An electronic device, characterized in that: The electronic device includes one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement the performance parameter adjustment method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The storage medium stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the performance parameter adjustment method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The computer program product stores at least one program code, and the at least one program code is used to be executed by a processor to implement the performance parameter adjustment method according to any one of claims 1 to 8.

Images