Temperature control method, device, terminal and storage medium for a terminal

Abstract

The present application discloses a temperature control method, device, terminal and storage medium for a terminal. The temperature control method for the terminal includes: collecting data of at least two dimensions of a first terminal; wherein, the at least two dimensions include a first dimension and at least one second dimension; the first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal; inputting the collected data into a random forest model to obtain a first perceived temperature; wherein, the random forest model is trained based on the collected data of M dimensions corresponding to each of a plurality of second terminals and the calibration values of training samples; the M dimensions include the first dimension and at least one second dimension; the calibration value corresponding to the training sample represents the perceived temperature calibrated for the corresponding terminal; adjusting the temperature control strategy based on the first perceived temperature.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a temperature control method, device, terminal, and storage medium for a terminal. Background Art

[0002] In the related art, based on the measured temperature of the temperature acquisition points in the terminal, corresponding temperature control strategies are executed. For example, the processor frequency of the terminal is restricted, the brightness of the display screen of the terminal is reduced, etc., so as to adjust the power consumption of the terminal, and then adjust the heat generated during the operation of the terminal. However, this temperature control solution may cause the user to be unable to use some functions or applications, which does not meet the actual needs of the user. Summary of the Invention

[0003] In view of this, embodiments of this application provide a temperature control method, device, terminal, and storage medium for a terminal to solve the technical problem that the temperature control solution in the related art may cause the user to be unable to use some functions or applications.

[0004] To achieve the above object, the technical solution of this application is realized as follows:

[0005] Embodiments of this application provide a temperature control method for a terminal, including:

[0006] Collect data of at least two dimensions of the first terminal; wherein, the at least two dimensions include a first dimension and at least one second dimension; the first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal;

[0007] Input the collected data into a random forest model to obtain a first perceived temperature;

[0008] Wherein, the random forest model is trained based on the collected data of M dimensions corresponding to each second terminal among multiple second terminals and the calibration value of the training sample; the M dimensions include a first dimension and at least one second dimension; the calibration value corresponding to the training sample represents the perceived temperature calibrated for the corresponding terminal;

[0009] Adjust the temperature control strategy based on the first perceived temperature; wherein, the temperature control strategy is used to control the heat generated during the operation of the first terminal.

[0010] In the above solution, the random forest model is trained in the following manner:

[0011] Sampling N training sample sets based on the collected data of M dimensions corresponding to each second terminal among multiple second terminals; wherein, each training sample in the training sample set is sampled based on the collected data of one second terminal, and the sampled dimensions and / or the number of dimensions are random; the dimensions corresponding to each training sample include a first dimension and at least one second dimension; N is greater than or equal to 2;

[0012] Using each training sample set in the N training sample sets and the calibration value corresponding to the training sample to train a decision tree respectively, to obtain a random forest model including N decision trees.

[0013] In the above solution, inputting the collected data into the random forest model includes:

[0014] Based on the names of the non-leaf nodes of each decision tree among the N decision trees, determining the data of the dimensions corresponding to the decision tree from the collected data, and inputting the determined data into the corresponding decision tree.

[0015] In the above solution, the second dimension includes at least one of the following:

[0016] The attribute information of the first terminal user;

[0017] The operation data of the first terminal;

[0018] The behavior preference data of the first terminal user.

[0019] Collecting the data of at least two dimensions of the first terminal includes one of the following:

[0020] Based on the Net Promoter Score (NPS) report, collecting the attribute information of the first terminal user;

[0021] Collecting the operation data of the first terminal;

[0022] Based on the application list of the first terminal and / or the usage data of the application, determining the behavior preference data of the first terminal user.

[0023] In the above solution, adjusting the temperature control strategy based on the first perceived temperature includes: determining the second perceived temperature of the first terminal based on the first perceived temperature output by each decision tree in the random forest model;

[0024] Adjusting the temperature control strategy based on the second perceived temperature.

[0025] In the above solution, adjusting the temperature control strategy based on the second perceived temperature includes:

[0026] When the measured temperature of the first terminal is greater than or equal to the set threshold, execute the temperature control strategy corresponding to the second perceived temperature.

[0027] In the above solution, executing the temperature control strategy corresponding to the second perceived temperature includes:

[0028] When the second perceived temperature is higher than the measured temperature of the first terminal, execute the first temperature control strategy; or

[0029] When the second perceived temperature is lower than the measured temperature of the first terminal, execute the second temperature control strategy; wherein, the terminal power consumption generated by the first temperature control strategy is less than the terminal power consumption generated by the second temperature control strategy.

[0030] The embodiment of the present application further provides a temperature control device for a terminal, including:

[0031] An acquisition unit, configured to acquire data of at least two dimensions of the first terminal; the at least two dimensions include a first dimension and at least one second dimension; the first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal;

[0032] A prediction unit, configured to input the acquired data into a random forest model to obtain a first perceived temperature; wherein, the random forest model is trained based on the acquired data of M dimensions corresponding to each of the multiple second terminals and the calibration values of the training samples; the M dimensions include a first dimension and at least one second dimension; the calibration value corresponding to the training sample represents the perceived temperature calibrated for the corresponding terminal;

[0033] A temperature control unit, configured to adjust the temperature control strategy based on the first perceived temperature; wherein, the temperature control strategy is used to control the heat generated during the operation of the first terminal.

[0034] The embodiment of the present application further provides a terminal, including: a processor and a memory for storing a computer program that can run on the processor, wherein, when the processor is used to run the computer program, it executes the steps of the above-mentioned temperature control method for the terminal.

[0035] The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the above-mentioned temperature control method for the terminal.

[0036] In an embodiment of the present application, data of at least two dimensions of a first terminal is collected, where the at least two dimensions include a first dimension and at least one second dimension; the first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal; the collected data is input into a trained random forest model to obtain the perceived temperature of the first terminal, and the temperature control strategy is adjusted based on the first perceived temperature. Thus, the perceived temperature of the first terminal can be predicted, and accordingly, the corresponding temperature control strategy can be executed according to the perceived temperature of the first terminal, improving the matching degree between the executed temperature control strategy and the actual needs of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic flowchart of the implementation process of the temperature control method for the terminal provided by the embodiment of the present application;

[0038] Figure 2 It is a schematic diagram of the temperature control method for the terminal provided by the embodiment of the present application;

[0039] Figure 3 It is a schematic flowchart of the implementation process of the model training method provided by the embodiment of the present application;

[0040] Figure 4 It is a schematic diagram of the model training method provided by the embodiment of the present application;

[0041] Figure 5 It is a schematic flowchart of the implementation process of the temperature control method for the terminal provided by the application embodiment of the present application;

[0042] Figure 6 It is a schematic diagram of the structure of the temperature control device for the terminal provided by the embodiment of the present application;

[0043] Figure 7 It is a schematic diagram of the hardware composition structure of the terminal provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] In the related art, the terminal executes the corresponding temperature control strategy based on the measured temperature of the temperature collection point in the terminal. However, for the same measured temperature, different users may have different thermal sensations of the terminal. For example, some users may feel that the terminal is not hot, while some users may feel that the terminal is hot. Since different users have different thermal sensations of the terminal device, their requirements for the temperature control strategy may also be different. In the related art, the perceived temperature of the user for the terminal is not considered, and executing the corresponding temperature control strategy according to the measured temperature may cause the user to be unable to use some functions or applications, which does not meet the actual needs of the user.

[0045] Based on this, an embodiment of the present application provides a temperature control method for a terminal, which collects data of at least two dimensions of a first terminal, and the at least two dimensions include a first dimension and at least one second dimension; the first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal; the collected data is input into a trained random forest model to obtain the perceived temperature of the first terminal, and the temperature control strategy is adjusted based on the first perceived temperature. Thus, the perceived temperature of the first terminal can be predicted, and accordingly, the corresponding temperature control strategy can be executed according to the perceived temperature of the first terminal, improving the matching degree between the executed temperature control strategy and the actual needs of the user.

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

[0047] Figure 1 FIG. is a schematic flowchart of the implementation of the temperature control method for the terminal provided by the embodiment of the present application. Among them, the execution subject of the process is a terminal such as a mobile phone, a tablet computer, a wearable device, etc. As Figure 1 shown, the temperature control method of the terminal includes:

[0048] Step 101: Collect data of at least two dimensions of a first terminal; the at least two dimensions include a first dimension and at least one second dimension; the first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal.

[0049] Here, the first terminal collects data of at least two dimensions of the first terminal. For example, the first terminal collects the measured temperature of each temperature monitoring point in the first terminal, and collects data of at least one second dimension. The temperature collection points are set at positions in the first terminal close to key devices, and the key devices include a processor.

[0050] In order to improve the accuracy of the predicted perceived temperature, in some embodiments, the second dimension includes at least one of the following:

[0051] Attribute information of the user of the first terminal;

[0052] Operating data of the first terminal;

[0053] Behavior preference data of the user of the first terminal.

[0054] Here, the attribute information of the user of the first terminal includes at least one of age, education level, occupation and gender.

[0055] The running data of the first terminal includes at least one of the application package names, network status, screen brightness, volume, screen refresh rate, processor frequency, application frame rate, and working mode of the first terminal when running in the foreground. Among them, the network status represents the network currently connected by the terminal, and this network is a wireless local area network or a cellular network. The working mode includes a power-saving mode, a performance mode, or a balanced mode. The power-saving mode means that the processor always runs at a lower frequency to save power. The performance mode means that the processor always runs at a higher frequency, and the performance of the terminal is the highest. The balanced mode means that the running frequency is automatically adjusted according to the processor load, so as to save power when the load is small and provide higher performance when the load is large.

[0056] The behavior preference data of the first terminal user represents the behavior preferences of the terminal user for the applications in the terminal. For example, the application usage habits such as the applications that the terminal user likes to use, the usage time periods of the applications, and the setting parameters of the applications.

[0057] It should be noted that the second dimension may also include the frame material of the terminal.

[0058] In order to improve the accuracy of the data in the second dimension, in some embodiments, collecting the data of at least two dimensions of the first terminal includes one of the following:

[0059] Collecting the attribute information of the first terminal user based on the Net Promoter Score (NPS) report;

[0060] Collecting the running data of the first terminal;

[0061] Determining the behavior preference data of the first terminal user based on the application list and / or application usage data of the first terminal. Here, since the Net Promoter Score (NPS) report includes the attribute information of the terminal user, the first terminal collects the attribute information of the first terminal user from the NPS report obtained by the first terminal. Of course, when the attribute information of the first terminal user is stored in the database, the first terminal can also obtain the attribute information of the first terminal user from the database. Among them, NPS represents the recommendation degree of the user to recommend a certain application or service of the terminal to others, and can reflect the user's satisfaction with the product or service.

[0062] The first terminal obtains at least one of the application package names, network status, screen brightness, volume, screen refresh rate, processor frequency, application frame rate, and working mode when running in the foreground, and obtains the running data of the first terminal.

[0063] The first terminal determines the behavior preference data of the first terminal user based on the application list and application usage data in the first terminal. For example, determining the applications preferred by the terminal user, the usage time periods of the applications, and the setting parameters of the applications, etc.

[0064] Step 102: Input the collected data into the random forest model to obtain the first perceived temperature; wherein, the random forest model is trained based on the collected data of M dimensions corresponding to each of the multiple second terminals and the calibration values of the training samples; the M dimensions include a first dimension and at least one second dimension; the calibration value corresponding to the training sample represents the perceived temperature calibrated by the corresponding terminal.

[0065] Here, the first terminal inputs the collected data into the random forest model, and the random forest model processes the collected data to predict the first perceived temperature of the first terminal.

[0066] Among them, the random forest model is used to predict the perceived temperature of the terminal user for the terminal. The random forest model includes N decision trees; the N decision trees are trained based on the decision tree algorithm using N training sample sets and the calibration values corresponding to the training samples, and each training sample set and the calibration value corresponding to the training sample are used to train one decision tree. The N training sample sets are obtained by sampling the collected data of M dimensions corresponding to each of the multiple second terminals. The dimensions corresponding to each training sample include a first dimension and at least one second dimension. Both M and N are greater than or equal to 2. It should be noted that one of the multiple second terminals can be the first terminal; the multiple second terminals can also be any terminal other than the first terminal.

[0067] It should be noted that the number of the first perceived temperatures can be N or 1. The N first perceived temperatures are respectively output by the N decision trees in the random forest model. For example, as Figure 2 shown, the first terminal inputs the collected data into the random forest model, and the N decision trees in the random forest model process the input data to obtain the first perceived temperature output by each of the N decision trees. When the number of the first perceived temperatures is N, the terminal needs to determine the final perceived temperature based on the N first perceived temperatures. When the number of the first perceived temperatures is 1, it represents that the first perceived temperature is the final perceived temperature of the first terminal, and the first perceived temperature is determined based on the perceived temperatures output by each decision tree in the random forest model.

[0068] It should be noted that the data input into each decision tree in the random forest model can be the same or different. The data input into the decision tree includes at least the data related to all internal nodes of the decision tree. For example, the types of internal nodes in decision tree 1 of the random forest model include the age, occupation, application package name running in the foreground, network status, and user behavior preferences of the terminal user. Then, the data input into decision tree 1 includes at least the age, occupation, application package name running in the foreground, network status of the first terminal user, and the data of the behavior preferences of the first terminal user.

[0069] The random forest model can be trained by a first terminal, or can be trained by other terminals or servers. As Figure 3 shown, in some embodiments, the random forest model is trained in the following manner:

[0070] Step 301: Based on the acquisition data of M dimensions corresponding to each second terminal among multiple second terminals, sample to obtain N training sample sets; wherein, each training sample in the training sample set is sampled based on the acquisition data of one second terminal, and the sampled dimensions and / or the number of dimensions are random; the dimensions corresponding to each training sample include a first dimension and at least one second dimension; N is greater than or equal to 2;

[0071] Step 302: Use each training sample set in the N training sample sets and the calibration value corresponding to the training sample to respectively train a decision tree, and obtain a random forest model including N decision trees.

[0072] In step 301, obtain the acquisition data of M dimensions corresponding to each second terminal among multiple second terminals, and perform sampling with replacement on the acquisition data of M dimensions corresponding to each terminal among multiple terminals to obtain N training sample sets. Among them, the acquisition data of M dimensions corresponding to the second terminal can be obtained from a database or reported by the corresponding terminal. Sampling with replacement is a random sampling method. During the process of random sampling with replacement, after recording the acquisition data of any dimension drawn, the drawn acquisition data is put back. The acquisition data of the first dimension includes at least one. Each training sample set includes one or more training samples, and each training sample in the training sample set is sampled based on the acquisition data of one terminal, and the sampled dimensions and / or the number of dimensions are random; the dimensions corresponding to each training sample include a first dimension and at least one second dimension. For example, draw the acquisition data of the first dimension from the acquisition data of M dimensions corresponding to the second terminal; perform sampling with replacement on the acquisition data of M - 1 second dimensions corresponding to the second terminal, and randomly draw at least one second dimension of acquisition data, and generate one training sample corresponding to the second terminal based on the drawn acquisition data of the first dimension and at least one second dimension of acquisition data.

[0073] It should be noted that the dimensions corresponding to the training samples in the same training sample set can be the same or different; the dimensions corresponding to different training sample sets are not completely the same. In actual application, the dimensions corresponding to the same training sample set are the same, and the dimensions corresponding to different training sample sets are different.

[0074] Considering that different groups of people and different behavior habits may have different degrees of thermal sensation and tolerance to the heat generated by the terminal, in order to more accurately predict the perceived temperature of different terminal users for the heat generated by the terminal, in some embodiments, the second dimension among the M dimensions includes at least one of the following:

[0075] Attribute information of the terminal user;

[0076] Operation data of the terminal;

[0077] Behavior preference data of the terminal user.

[0078] Exemplarily, the acquisition data of the M dimensions corresponding to multiple second terminals are as follows:

[0079]

[0080]

[0081] In order to improve the accuracy of the acquisition data in the training sample set, in some embodiments, before sampling to obtain N training sample sets, the method further includes at least one of the following:

[0082] Collect the attribute information of the terminal user based on the Net Promoter Score (NPS) report reported by the terminal;

[0083] Receive the operation data reported by the terminal;

[0084] Determine the behavior preference data of the terminal user based on the application list of the terminal and / or the usage data of the application.

[0085] Here, the attribute information of the terminal user is collected from the NPS report reported by the terminal. Based on the application list of the terminal and / or the usage data of the application, at least one of the applications preferred by the terminal user, the usage period of the application, and the setting parameters of the application is determined to obtain the behavior preference data of the terminal user.

[0086] In step 302, the random forest model includes N decision trees, and the terminal or the server can independently train each decision tree in the random forest model. For example, as Figure 4 shown, based on the set decision tree algorithm, one training sample set and the calibration value corresponding to each training sample in the training sample set are used to train one decision tree correspondingly. The set decision tree algorithm includes the ID3 algorithm, the C4.5 algorithm, or the Classification and Regression Tree (CART) algorithm. It should be noted that the terminal or the server can also use the training samples and the corresponding calibration values from the same terminal to jointly train the N decision trees included in the random forest model.

[0087] A decision tree includes a root node, internal nodes, and leaf nodes. The root node contains the corresponding training sample set; the leaf nodes represent the results of the decision; the internal nodes represent the dimensions corresponding to the training samples. That is to say, the internal nodes of the decision tree are determined by the dimensions corresponding to the corresponding training samples. For example, when the dimensions corresponding to the training sample set represent the measured temperature of the terminal, the attribute information of the terminal user, and the operation data of the terminal, the terminal or the server determines the internal nodes of the decision tree based on the measured temperature of the terminal, the type identifier of the attribute information of the terminal user, and the type identifier of the operation data of the terminal.

[0088] During the process of training the decision tree, the terminal or the server adjusts the relevant parameters of the decision tree based on the calibration value corresponding to the training sample of the decision tree and the output result of the decision tree until the accuracy of the output result of the decision tree meets the set requirements. The relevant parameters of the decision tree include the division point or split point corresponding to the internal node of the decision tree, and may also include the internal nodes of the decision tree. The division point or split point represents the classification decision boundary and can be a threshold value.

[0089] Among them, the calibration value corresponding to the training sample is calibrated based on the temperature experience data of the terminal user reported by the terminal. The terminal can collect the temperature experience data of the terminal user by means of system pop-up windows or return visit questionnaires; it can also obtain the temperature experience data of the terminal user from the return visit reports of batch trial users. In actual applications, different calibration values are used to represent different body feeling temperatures of the terminal user. In one embodiment, 0 is used to represent that the user's body feeling temperature of the terminal is not hot, and 1 is used to represent that the user's body feeling temperature of the terminal is hot. In another embodiment, 0 is used to represent that the user's body feeling temperature of the terminal is not hot, 1 is used to represent that the user's body feeling temperature of the terminal is slightly hot, and 2 is used to represent that the user's body feeling temperature of the terminal is extremely hot or hot to the touch, etc. Of course, more types of body feeling temperatures can be set according to the actual situation.

[0090] It should be noted that after the random forest model is trained, the random forest model can be put into use. For example, in the scenario of predicting the body feeling temperature of the terminal, the electronic device can use the random forest model trained through the above embodiments to predict the body feeling temperature of the terminal.

[0091] In this embodiment, based on the collected data of M dimensions corresponding to each second terminal among multiple second terminals, N training sample sets are sampled, and each training sample set in the N training sample sets and the calibration value corresponding to the training sample are used to train a decision tree respectively, obtaining a random forest model including N decision trees. Thus, the body feeling temperature of the terminal can be predicted by using the trained random forest model. Since the random forest model includes N decision trees, based on the body feeling temperatures predicted by the N decision trees, the final body feeling temperature of the terminal is determined, which can improve the accuracy of the predicted body feeling temperature.

[0092] Based on obtaining a random forest model including N decision trees, considering that data unrelated to the non-leaf nodes of the decision tree is invalid data for that decision tree, in order to save the time consumed by the decision tree in screening valid data and improve data processing efficiency, in some embodiments, inputting the collected data into the random forest model includes:

[0093] Based on the names of the non-leaf nodes of each of the N decision trees, determine the data of the corresponding dimension of the decision tree from the collected data, and input the determined data into the corresponding decision tree.

[0094] Here, the first terminal determines the data related to the root node and internal nodes from the collected data based on the names of the root node and internal nodes of each decision tree, obtains the data of the corresponding dimension of the decision tree, and inputs the determined data into the corresponding decision tree.

[0095] Step 103: Adjust the temperature control strategy based on the first perceived temperature; wherein, the temperature control strategy is used to control the heat generated by the first terminal during operation.

[0096] Here, the first terminal adjusts the temperature control strategy based on the first perceived temperature output by the random forest model. For example, when the first perceived temperature is lower than the measured temperature of the first terminal, the first terminal can increase at least one of the processor frequency, screen refresh rate, and application frame rate of the foreground application, thereby improving the performance of the first terminal.

[0097] When the first perceived temperature is higher than the measured temperature of the first terminal, the first terminal can reduce at least one of the processor frequency, screen refresh rate, and application frame rate of the foreground application, thereby reducing the power consumption of the first terminal and further reducing the heat generated by the first terminal.

[0098] In this embodiment, at least two dimensions of data of the first terminal are collected; the collected data is input into the random forest model to obtain the first perceived temperature; and the temperature control strategy is adjusted based on the first perceived temperature. Thus, the matching degree between the executed temperature control strategy and the actual needs of the user can be improved.

[0099] In order to improve the accuracy of the determined perceived temperature and thus improve the temperature control accuracy, in some embodiments, adjusting the temperature control strategy based on the first perceived temperature includes:

[0100] Based on the first perceived temperature output by each decision tree in the random forest model, determine the second perceived temperature of the first terminal;

[0101] Adjust the temperature control strategy based on the second perceived temperature.

[0102] Here, as Figure 2 shown, the first terminal determines the number of the same first perceived temperatures based on the first perceived temperatures output by each decision tree in the random forest model, and determines the first perceived temperature with the largest number as the second perceived temperature of the first terminal. Alternatively, the first terminal determines the mean value of the perceived temperatures based on the first perceived temperatures output by each decision tree, and determines the mean value as the second perceived temperature of the first terminal.

[0103] When the first terminal determines the second perceived temperature, it adjusts the temperature control strategy based on the second perceived temperature. It should be noted that the implementation manner of adjusting the temperature control strategy based on the second perceived temperature is similar to that of adjusting the temperature control strategy based on the first perceived temperature, and will not be elaborated here.

[0104] To improve the matching degree between the executed temperature control strategy and the actual needs of the terminal user, in some embodiments, adjusting the temperature control strategy based on the second perceived temperature includes:

[0105] When the measured temperature of the first terminal is greater than or equal to the set threshold, execute the temperature control strategy corresponding to the second perceived temperature; wherein, the temperature control strategy is used to control the heat generated during the operation of the first terminal.

[0106] Here, when the measured temperature of the first terminal is greater than or equal to the set threshold, it indicates that the temperature control strategy needs to be executed on the first terminal currently. At this time, the first terminal determines the temperature control strategy corresponding to the second perceived temperature according to the set corresponding relationship between the perceived temperature and the temperature control strategy, and executes the determined temperature control strategy. It should be noted that the set threshold is less than the minimum value of the rated operating temperatures of all devices in the first terminal.

[0107] To improve the temperature control accuracy, in some embodiments, executing the temperature control strategy corresponding to the second perceived temperature includes:

[0108] When the second perceived temperature is higher than the measured temperature of the first terminal, execute the first temperature control strategy; or

[0109] When the second perceived temperature is lower than the measured temperature of the first terminal, execute the second temperature control strategy;

[0110] wherein, the terminal power consumption generated by the first temperature control strategy is less than the terminal power consumption generated by the second temperature control strategy.

[0111] Here, when the second body temperature of the first terminal is higher than the measured temperature of the first terminal, it indicates that the user of the first terminal is more sensitive to the heat generated by the first terminal. At this time, the first terminal executes the first temperature control strategy to quickly reduce the heat generated by the first terminal. The first temperature control strategy includes at least one of reducing the processor frequency, reducing the screen refresh rate, and reducing the application frame rate of the foreground application. The processor includes a central processing unit (CPU) and / or a graphics processing unit (GPU).

[0112] When the second body temperature of the first terminal is lower than the measured temperature of the first terminal, it indicates that the user of the first terminal is not sensitive to the heat generated by the first terminal and is more concerned about the performance of the first terminal. At this time, the second temperature control strategy is executed to reduce the heat generated by the first terminal while ensuring the performance of the first terminal. The second temperature control strategy includes reducing the screen brightness and / or reducing the volume, etc. For example, when the user of the first terminal uses a game application or a video playback application, the user of the first terminal is more concerned about the performance of the first terminal. At this time, the first terminal executes the corresponding temperature control strategy on the premise of performance priority to ensure the smoothness of the screen and minimize the occurrence of screen stuttering as much as possible.

[0113] It should be noted that in one embodiment, when the measured temperature of the first terminal is greater than or equal to the set threshold and the second body temperature indicates that the user's body temperature of the terminal is not hot, it indicates that the second body temperature of the first terminal is lower than the measured temperature of the first terminal; when the measured temperature of the first terminal is greater than or equal to the set threshold and the second body temperature indicates that the user's body temperature of the terminal is hot, it indicates that the second body temperature of the first terminal is higher than the measured temperature of the first terminal. In another embodiment, when the second body temperature indicates that the user's body temperature of the terminal is not hot, or the user's body temperature of the terminal is slightly hot, it indicates that the second body temperature of the first terminal is lower than the measured temperature of the first terminal; when the second body temperature indicates that the user's body temperature of the terminal is scorching hot or hot to the touch, it indicates that the second body temperature of the first terminal is higher than the measured temperature of the first terminal.

[0114] Figure 5 FIG. is a schematic flowchart of the implementation process of the temperature control method for the terminal provided by the application embodiment of the present application, where the execution subject of the process is a terminal such as a mobile phone, a tablet computer, or a wearable device. As Figure 5 shown, the temperature control method of the terminal includes:

[0115] Step 501: Collect data of at least two dimensions of the first terminal; the at least two dimensions include a first dimension and at least one second dimension; the first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal.

[0116] Step 502: Input the collected data into the random forest model to obtain the first perceived temperature output by each of the N decision trees.

[0117] Step 503: Determine the second perceived temperature of the first terminal based on the first perceived temperature output by each decision tree.

[0118] Step 504: When the measured temperature of the first terminal is greater than or equal to the set threshold, execute the temperature control strategy corresponding to the second perceived temperature.

[0119] To implement the temperature control method for the terminal in the embodiments of the present application, the embodiments of the present application also provide a temperature control device for a terminal, as Figure 6 shown, the temperature control device for the terminal includes:

[0120] A collection unit 61, configured to collect data of at least two dimensions of the first terminal; the at least two dimensions include a first dimension and at least one second dimension; the first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal;

[0121] A prediction unit 62, configured to input the collected data into the random forest model to obtain the first perceived temperature; wherein, the random forest model is trained based on the collected data of M dimensions corresponding to each of the multiple second terminals and the calibration values of the training samples; the M dimensions include a first dimension and at least one second dimension; the calibration value corresponding to the training sample represents the calibrated perceived temperature of the corresponding terminal;

[0122] A temperature control unit 63, configured to adjust the temperature control strategy based on the first perceived temperature; wherein, the temperature control strategy is used to control the heat generated during the operation of the first terminal.

[0123] In some embodiments, the random forest model is trained in the following manner:

[0124] Based on the collected data of M dimensions corresponding to each of the multiple second terminals, sample to obtain N training sample sets; wherein, each training sample in the training sample set is sampled based on the collected data of one second terminal, and the sampled dimensions and / or the number of dimensions are random; the dimensions corresponding to each training sample include a first dimension and at least one second dimension; N is greater than or equal to 2;

[0125] For each training sample set in the N training sample sets and the calibration value corresponding to the training sample, train a decision tree to obtain a random forest model including N decision trees.

[0126] In some embodiments, the prediction unit 72 is specifically configured to: based on the names of the non-leaf nodes of each decision tree in the N decision trees, determine the data of the dimension corresponding to the decision tree from the collected data, and input the determined data into the corresponding decision tree.

[0127] In some embodiments, the second dimension includes at least one of the following:

[0128] Attribute information of the first end user;

[0129] Operation data of the first terminal;

[0130] Behavior preference data of the first end user.

[0131] In some embodiments, the acquisition unit 61 is specifically configured to perform one of the following:

[0132] Based on the Net Promoter Score (NPS) report, acquire the attribute information of the first end user;

[0133] Acquire the operation data of the first terminal;

[0134] Based on the application list of the first terminal and / or the usage data of the application, determine the behavior preference data of the first end user.

[0135] In some embodiments, the temperature control unit 63 is specifically configured to:

[0136] Based on the first perceived temperature output by each decision tree in the random forest model, determine the second perceived temperature of the first terminal;

[0137] Based on the second perceived temperature, adjust the temperature control strategy. In some embodiments, the temperature control unit 63 is specifically configured to:

[0138] When the measured temperature of the first terminal is greater than or equal to the set threshold, execute the temperature control strategy corresponding to the second perceived temperature.

[0139] In some embodiments, the temperature control unit 63 is specifically configured to:

[0140] When the second perceived temperature is higher than the measured temperature of the first terminal, execute the first temperature control strategy; or

[0141] When the second body sensation temperature is lower than the measured temperature of the first terminal, a second temperature control strategy is executed; wherein, the terminal power consumption generated corresponding to the first temperature control strategy is less than the terminal power consumption generated corresponding to the second temperature control strategy.

[0142] In practical applications, the acquisition unit 61, the prediction unit 62, and the temperature control unit 63 can be implemented by a processor in the temperature control device of the terminal, such as a CPU, DSP, MCU, or FPGA.

[0143] It should be noted that: when the temperature control device of the terminal provided in the above embodiment performs temperature prediction, only the division of the above program modules is used for illustration. In practical applications, the above processing can be allocated to different program modules according to needs, that is, the internal structure of the device is divided into different program modules to complete all or part of the above-described processing. In addition, the temperature control device of the terminal provided in the above embodiment and the embodiment of the temperature control method of the terminal belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be elaborated here.

[0144] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of the present application, the embodiments of the present application also provide a terminal. Figure 7 This is a schematic diagram of the hardware composition structure of the terminal provided by the embodiments of the present application, as Figure 7 shown, the terminal 7 includes:

[0145] A communication interface 71, capable of interacting with other devices such as network devices.

[0146] A processor 72, connected to the communication interface 71 to implement information interaction with other devices, and when running a computer program, executes the temperature control method of the terminal provided by the above one or more technical solutions. And the computer program is stored on the memory 73.

[0147] Of course, in practical applications, the various components in the terminal 7 are coupled together through a bus system 74. It can be understood that the bus system 74 is used to realize the connection and communication between these components. The bus system 74 includes not only a data bus, but also a power bus, a control bus, and a status signal bus. However, for the sake of clear illustration, in Figure 7 all kinds of buses are labeled as the bus system 74.

[0148] The memory 73 in the embodiments of the present application is used to store various types of data to support the operation of the terminal 7. Examples of these data include: any computer program for operating on the terminal 7.

[0149] It can be understood that the memory 73 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only Memory), an electrically erasable programmable read-only memory (EEPROM, Electrically Erasable Programmable Read-Only Memory), a ferromagnetic random access memory (FRAM, ferromagnetic random access memory), a flash memory (Flash Memory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM, Compact Disc Read-Only Memory); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM, Random Access Memory), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as a static random access memory (SRAM, Static Random Access Memory), a synchronous static random access memory (SSRAM, Synchronous Static Random Access Memory), a dynamic random access memory (DRAM, Dynamic Random Access Memory), a synchronous dynamic random access memory (SDRAM, Synchronous Dynamic Random Access Memory), a double data rate synchronous dynamic random access memory (DDR SDRAM, Double Data Rate Synchronous Dynamic Random Access Memory), an enhanced synchronous dynamic random access memory (ESDRAM, Enhanced Synchronous Dynamic Random Access Memory), a sync link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), a direct rambus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 73 described in the embodiments of the present application is intended to include, but is not limited to, these and any other suitable types of memory.

[0150] The method disclosed in the embodiments of the present application above can be applied to the processor 72 or implemented by the processor 72. The processor 72 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 72 or the instructions in the form of software. The above-mentioned processor 72 may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 72 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. Combining the steps of the method disclosed in the embodiments of the present application, it can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in the storage medium, and this storage medium is located in the memory 73. The processor 72 reads the program in the memory 73 and combines its hardware to complete the steps of the foregoing method.

[0151] Optionally, when the processor 72 executes the program, it implements the corresponding processes in the various methods of the embodiments of the present application. For the sake of brevity, it will not be elaborated here.

[0152] In an exemplary embodiment, the embodiments of the present application also provide a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as the first memory 73 that stores a computer program. The above computer program can be executed by the processor 72 of the terminal to complete the steps of the foregoing method. The computer-readable storage medium may be a FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM, etc.

[0153] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be electrical, mechanical, or other forms.

[0154] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, in each embodiment of the present application, all the functional units may be integrated into one processing module, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of a combination of hardware and software functional units.

[0156] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical discs.

[0157] It should be noted that the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0158] It should be noted that the term "and / or" in the embodiments of the present application is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" in this article means any one of multiple or any combination of at least two of multiple. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set composed of A, B, and C.

[0159] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A temperature control method for a terminal, characterized in that, it includes: Collect data of at least two dimensions of the first terminal; wherein, the at least two dimensions include a first dimension and at least one second dimension; the first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal; the second dimension includes at least one of the following: attribute information of the first terminal user, behavioral preference data of the first terminal user; wherein, the behavioral preference data of the first terminal user represents the behavioral preference of the first terminal user for the applications in the first terminal; Input the collected data into a random forest model to obtain a first perceived temperature; wherein, the random forest model is used to predict the perceived temperature of the terminal user for the terminal; wherein, the random forest model is trained based on the collected data of M dimensions corresponding to each of the multiple second terminals and the calibration values of the training samples; the M dimensions include a first dimension and at least one second dimension; the calibration value corresponding to the training sample represents the calibrated perceived temperature of the corresponding terminal; Adjust the temperature control strategy based on the first perceived temperature; wherein, the temperature control strategy is used to control the heat generated during the operation of the first terminal; wherein, the random forest model is trained in the following manner: Based on the collected data of M dimensions corresponding to each of the multiple second terminals, sample to obtain N training sample sets; wherein, each training sample in the training sample set is sampled based on the collected data of one second terminal, and the sampled dimensions and / or the number of dimensions are random; the dimensions corresponding to each training sample include a first dimension and at least one second dimension; N is greater than or equal to 2; Use each of the N training sample sets and the calibration values corresponding to the training samples to train a decision tree respectively, to obtain a random forest model including N decision trees; wherein, the calibration value corresponding to the training sample is calibrated based on the temperature experience data of the terminal user reported by the terminal.

2. The method according to claim 1, characterized in that, The inputting the collected data into the random forest model includes: Based on the names of the non-leaf nodes of each decision tree among the N decision trees, determine the data of the dimensions corresponding to the decision tree from the collected data, and input the determined data into the corresponding decision tree.

3. The method according to claim 1, characterized in that, The second dimension further includes: The operation data of the first terminal.

4. The method according to claim 1, characterized in that, The collecting data of at least two dimensions of the first terminal includes one of the following: Collect the attribute information of the first terminal user based on the Net Promoter Score (NPS) report; Collect the operation data of the first terminal; Determine the behavioral preference data of the first terminal user based on the application list of the first terminal and / or the usage data of the application.

5. The method according to claim 1, characterized in that, The adjusting the temperature control strategy based on the first perceived temperature includes: Determine the second perceived temperature of the first terminal based on the first perceived temperature output by each decision tree in the random forest model; Adjust the temperature control strategy based on the second perceived temperature.

6. The method according to claim 5, wherein, the adjusting the temperature control strategy based on the second perceived temperature includes: When the measured temperature of the first terminal is greater than or equal to a set threshold, execute the temperature control strategy corresponding to the second perceived temperature.

7. The method according to claim 6, wherein, the executing the temperature control strategy corresponding to the second perceived temperature includes: When the second perceived temperature is higher than the measured temperature of the first terminal, execute the first temperature control strategy; or When the second perceived temperature is lower than the measured temperature of the first terminal, execute the second temperature control strategy; wherein, the terminal power consumption generated by the first temperature control strategy is less than the terminal power consumption generated by the second temperature control strategy.

8. A temperature control device for a terminal, wherein, it includes: An acquisition unit, configured to acquire data of at least two dimensions of the first terminal; the at least two dimensions include a first dimension and at least one second dimension; The first dimension represents the measured temperature of the first terminal, and the second dimension represents the user usage data of the first terminal; the second dimension includes at least one of the following: the attribute information of the first terminal user; the behavior preference data of the first terminal user; wherein, the behavior preference data of the first terminal user represents the behavior preference of the first terminal user for the applications in the first terminal; A prediction unit, configured to input the acquired data into a random forest model to obtain a first perceived temperature; wherein, the random forest model is used to predict the perceived temperature of the terminal user for the terminal; wherein, the random forest model is trained based on the acquisition data of M dimensions corresponding to each of multiple second terminals and the calibration values of the training samples; the M dimensions include a first dimension and at least one second dimension; the calibration value corresponding to the training sample represents the calibrated perceived temperature of the corresponding terminal; A temperature control unit, configured to adjust the temperature control strategy based on the first perceived temperature; wherein, the temperature control strategy is used to control the heat generated during the operation of the first terminal; wherein, the random forest model is trained in the following manner: Based on the acquisition data of M dimensions corresponding to each of multiple second terminals, sample to obtain N training sample sets; wherein, each training sample in the training sample set is sampled based on the acquisition data of one second terminal, and the sampled dimensions and / or the number of dimensions are random; the dimensions corresponding to each training sample include a first dimension and at least one second dimension; N is greater than or equal to 2; Use each training sample set in the N training sample sets and the calibration value corresponding to the training sample to train a decision tree respectively, to obtain a random forest model including N decision trees; wherein, the calibration value corresponding to the training sample is calibrated based on the temperature experience data of the terminal user reported by the terminal.

9. A terminal, It is characterized in that including: a processor and a memory for storing a computer program capable of running on the processor, wherein when the processor is used to run the computer program, it executes the steps of the temperature control method of the terminal according to any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, it is characterized in that when the computer program is executed by a processor, it realizes the steps of the temperature control method of the terminal according to any one of claims 1 to 7.

Images