Fitting parameter determination method of electronic equipment, temperature determination method and electronic equipment

Abstract

The invention provides a fitting parameter determination method and temperature determination method of electronic equipment and the electronic equipment, training sets are classified, a sub-training set corresponding to each use scene of the electronic equipment is acquired, the sub-training set comprises the actually measured temperature of the electronic equipment and the temperature of a corresponding thermistor in the electronic equipment, and the actually measured temperature of the electronic equipment and the temperature of the thermistor in the electronic equipment are acquired; and then fitting parameters corresponding to each use scene are formed based on the sub-training set corresponding to each use scene, so that the problems of incomplete coverage and over-fitting of the fitting scene can be solved, and the temperature of the electronic equipment can be described more accurately.

Description

Technical Field

[0001] The present application relates to the field of electronic technology, and in particular to a fitting parameter determination method of an electronic device, a temperature determination method and the electronic device. Background Art

[0002] At present, the temperature of electronic devices such as mobile phones, tablets, laptops, e-books, etc. can be fitted by fitting multiple thermistors and fitting parameters inside the electronic devices, so that more accurate temperature control strategies can be adopted and whether the status of the electronic devices is abnormal can be quickly determined.

[0003] However, this method will cause the problem of incomplete coverage of the fitting scene, affect the fitting accuracy, and cannot accurately describe the surface temperature of the electronic device. Summary of the invention

[0004] The present application provides a fitting parameter determination method, a temperature determination method and an electronic device for improving fitting accuracy and accurately describing the surface temperature of the electronic device.

[0005] In a first aspect, the present application provides a method for determining fitting parameters of an electronic device, comprising:

[0006] Classifying the training set to obtain a sub-training set corresponding to each usage scenario of the electronic device, the sub-training set including the measured temperature of the electronic device and the temperature of a corresponding thermistor in the electronic device;

[0007] A fitting parameter corresponding to each usage scenario is formed based on the sub-training set corresponding to each usage scenario, and the fitting parameter is used to fit the temperature of the electronic device.

[0008] In some embodiments, forming the fitting parameters corresponding to each usage scenario based on the sub-training set corresponding to each usage scenario includes:

[0009] The temperature of each thermistor in the sub-training set forms an independent variable matrix, and the measured temperature in the sub-training set forms a dependent variable matrix;

[0010] When the independent variable matrix is ​​of full rank, a loss function is calculated on the independent variable matrix and the dependent variable matrix to obtain a weighted coefficient and an intercept value of each thermistor in the sub-training set.

[0011] In some embodiments, a method for determining whether the independent variable matrix is ​​full rank includes:

[0012] Performing matrix transposition on the independent variable matrix to obtain a transposed matrix of the independent variable matrix;

[0013] Calculating a product matrix of the independent variable matrix and the transposed matrix, and determining whether the rank of the product matrix is ​​the smaller of the number of rows and the number of columns in the product matrix;

[0014] If so, the independent variable matrix is ​​full rank, and if not, the independent variable matrix is ​​not full rank.

[0015] In some embodiments, the calculating the loss function on the independent variable matrix and the dependent variable matrix includes:

[0016] Using the squared difference between the dependent variable matrix and the fitted shell temperature as the loss function;

[0017] The fitted shell temperature is the product of the independent variable matrix and the weighting matrix, and the weighting matrix is ​​a matrix composed of weighting coefficients and intercept values;

[0018] The partial derivative of the loss function with respect to the weighting matrix is ​​calculated, and when the partial derivative is a preset value, the weighting matrix is ​​obtained.

[0019] In some embodiments, before classifying the training set, the method further comprises:

[0020] The training set is preprocessed, and the preprocessing includes at least one of data cleaning and replacing abnormal values ​​by difference.

[0021] In a second aspect, the present application provides a method for determining the temperature of an electronic device, the method comprising:

[0022] Acquire a current usage scenario of the electronic device, and acquire fitting parameters corresponding to the current usage scenario according to the corresponding relationship between the usage scenario and the fitting parameters determined by the method in the first aspect and any possible design of the first aspect;

[0023] The current temperature of the electronic device is determined based on the fitting parameters corresponding to the current usage scenario.

[0024] In some embodiments, obtaining the current usage scenario of the electronic device includes:

[0025] When the electronic device is in a charging state, determining whether the electronic device is running an application, and if so, determining a current usage scenario of the electronic device based on the currently running application, and if not, determining that the current usage scenario of the electronic device is a charging scenario;

[0026] When the electronic device is in a non-charging state, it is determined whether the electronic device is running an application, and if so, a usage scenario of the electronic device is determined based on the currently running application.

[0027] In some embodiments, determining the current temperature of the electronic device based on the fitting parameters corresponding to the current usage scenario includes:

[0028] Obtaining the temperature of the thermistor corresponding to the current usage scenario;

[0029] The current temperature of the electronic device is determined based on the temperature of the thermistor corresponding to the current usage scenario and the weighted coefficient and intercept value of each thermistor in the fitting parameters.

[0030] In a third aspect, the present application provides an electronic device, including: a memory and a processor;

[0031] The memory is used to store instructions; the processor is used to call the instructions in the memory to execute the method in the first aspect and any possible design of the first aspect.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium, which stores computer instructions. When at least one processor of an electronic device executes the computer instructions, the electronic device executes the method in the first aspect and any possible design of the first aspect.

[0033] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When at least one processor of an electronic device executes the computer instructions, the electronic device executes the method in the first aspect and any possible design of the first aspect.

[0034] The present application provides a fitting parameter determination method, a temperature determination method and an electronic device for classifying a training set, obtaining a sub-training set corresponding to each usage scenario of the electronic device, wherein the sub-training set includes the measured temperature of the electronic device and the temperature of the corresponding thermistor in the electronic device, and then forming a fitting parameter corresponding to each usage scenario based on the sub-training set corresponding to each usage scenario, thereby solving the problems of incomplete coverage of fitting scenarios and overfitting, and more accurately describing the temperature of the electronic device. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 A schematic diagram of a flow chart of a method for determining fitting parameters of an electronic device provided in an embodiment of the present application;

[0037] Figure 2A schematic diagram of the correspondence between usage scenarios and fitting parameters provided in an embodiment of the present application;

[0038] Figure 3 A schematic diagram of a flow chart of a method for determining the temperature of an electronic device provided in an embodiment of the present application;

[0039] Figure 4 A schematic diagram of the structure of a device for determining fitting parameters of an electronic device provided in an embodiment of the present application;

[0040] Figure 5 A schematic diagram of the structure of a device for determining the temperature of an electronic device provided in an embodiment of the present application;

[0041] Figure 6 A schematic diagram of the hardware structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] In order to more accurately describe the temperature of electronic devices, we can assign different weights to multiple thermistors (for example, motherboard NTC, 4G NTC, 5G NTC) inside electronic devices such as mobile phones, tablets, laptops, e-books, etc., and add an intercept value to fit the temperature of the electronic device, so that we can adopt a more accurate temperature control strategy and quickly judge whether the status of the electronic device is abnormal.

[0044] The fitting form is as follows:

[0045] The fitting temperature at a certain moment = a1x1+a2x2+a3x3+…+anxn+D, x1~xn are the temperatures of different thermistors at a certain moment, a1~an are the weighting coefficients of different thermistors, and D is the intercept value. The weighting coefficients a1~an of different thermistors and the intercept value D constitute a set of fitting parameters.

[0046] It should be noted that temperature fitting is essentially a multiple linear regression based on the temperature of different thermistors. In the linear regression equation, the intercept value represents the predicted value of the dependent variable when the value of the independent variable is zero, that is, the baseline value of the dependent variable. Therefore, the role of the intercept value is to adjust the upper and lower heights of the linear regression equation. If the intercept value is positive, then when the value of the independent variable is zero, the predicted value of the dependent variable will be too high. If the intercept value is negative, then when the value of the independent variable is zero, the predicted value of the dependent variable will be too low. The intercept value can be determined according to actual needs.

[0047] The applicant found that the current fitting parameters, electronic devices have only one set of fitting parameters, which will cause the problem of incomplete coverage of fitting scenarios. Taking a single side as an example, if the location of the heat source in different usage scenarios is too different, for example, the heating area in the CPU (Central Processing Unit) overload scenario (that is, the CPU is overloaded or overloaded) is the mainboard, located in the upper half of the mobile phone, and the heating area in the charging scenario is the small board, located in the lower half of the mobile phone, then one set of fitting parameters cannot cope with such situations. CPU overload scenarios can include game scenarios, video scenarios, etc.

[0048] In addition, since the amount of training set data is large and the heating methods are diverse, if a set of fitting parameters is used in different usage scenarios, overfitting problems will occur. That is, in order to meet as many different usage scenarios as possible, the correlation coefficient of the fitting parameters in specific scenarios will decrease.

[0049] Therefore, the current fitting method affects the fitting accuracy and cannot accurately describe the temperature of the electronic device.

[0050] To this end, the present application provides a method for determining the fitting parameters of an electronic device, classifies the training set, obtains a sub-training set corresponding to each usage scenario of the electronic device, and forms the fitting parameters corresponding to each usage scenario based on the sub-training set corresponding to each usage scenario, thereby solving the problems of incomplete coverage of fitting scenarios and overfitting, and more accurately describing the temperature of the electronic device.

[0051] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0052] Figure 1 A flow chart of a method for determining fitting parameters of an electronic device provided by an embodiment of the present application is shown. Figure 1 As shown, the method provided in this embodiment may include the following steps:

[0053] S101, classifying the training set to obtain a sub-training set corresponding to each usage scenario of the electronic device, where the sub-training set includes the measured temperature of the electronic device and the temperature of a corresponding thermistor in the electronic device.

[0054] For example, the training set for temperature fitting can be split into multiple sub-training sets. For example, the use of a class of applications is classified into a usage scenario, and the training data corresponding to the class of applications in the training set is classified into a sub-training set, where the training data corresponding to the class of applications can include the measured temperature of the electronic device and the temperature of the corresponding thermistor in the electronic device when any application in the class of applications is in running state.

[0055] For example, the use of video applications is classified as video scenes, and the training sets of video applications are classified as one training set, then the video scenes correspond to one training set; the use of audio applications is classified as audio scenes, and the training sets of audio applications are classified as one training set, then the audio scenes correspond to one training set; the use of navigation applications is classified as navigation scenes, and the training sets of navigation applications are classified as one training set, then the navigation scenes correspond to one training set; the use of shopping applications is classified as shopping scenes, and the training sets of shopping applications are classified as one training set, then the shopping scenes correspond to one training set; the use of communication applications is classified as communication scenes, and the training sets of communication applications are classified as one training set, then the communication scenes correspond to one training set; the use of camera applications is classified as camera scenes, and the training sets of camera applications are classified as one training set, then the camera scenes correspond to one training set.

[0056] In some examples, considering that there may be no application in use when the electronic device is in a charging state, the charging-only scenario can also be classified as a usage scenario, and the training data in the training set where the electronic device is in a charging state can be classified as a sub-training set.

[0057] In some examples, it is also considered that when the electronic device is in a charging state and a non-charging state, the training data corresponding to each type of application may be different. Therefore, the training data corresponding to a type of application in the charging state can be classified into a sub-training set, and the training data corresponding to a type of application in the non-charging state can be classified into a sub-training set.

[0058] It should be noted that the sub-training set includes the actual measured temperature of the electronic device and the temperature of the corresponding thermistor in the electronic device, that is, the actual measured temperature of the electronic device and the temperature of the corresponding thermistor in the electronic device measured when the electronic device is in the usage scenario corresponding to the sub-training set.

[0059] In practical applications, the measured temperature and the temperature of each thermistor can be retained to one decimal place in the data. Retaining one decimal place can meet the temperature rise requirements of most electronic products and facilitate calculation and full rank determination.

[0060] In some examples, the sub-training set can be further classified to obtain multiple training groups, each training group includes the measured temperature of a surface of the electronic device and the temperature of the thermistor corresponding to the surface, so that the fitting parameters of each surface of the electronic device can be obtained, and then the temperature of each surface of the electronic device can be accurately described. It should be noted that the measured temperature of the electronic device is related to the measured temperature of each surface of the electronic device, and the sub-training set can include not only the measured temperature of the electronic device, but also the measured temperature of each surface of the electronic device.

[0061] In some embodiments, before the training set is classified, the training set may be preprocessed to improve the accuracy of the fitting parameters, thereby more accurately determining the temperature of the electronic device. The preprocessing may include at least one of data cleaning and replacing abnormal values ​​by difference.

[0062] Specifically, data cleaning may include: removing noise, filling missing values, and removing at least one of duplicate values; replacing outliers by difference means: identifying outliers, calculating the difference between the identified outliers and normal values, adding the calculated difference to the normal value, and replacing the original outliers with the new values.

[0063] In some embodiments, for any sub-training set, the measured time step of the measured temperature in the sub-training set is consistent with the reporting time step of the temperature of the thermistor in the sub-training set, ensuring that the measured temperature obtained at each moment corresponds to the temperature of each thermistor, thereby more accurately determining the fitting parameters. For example, the measured time step is one value per second, and the reporting time step of the thermistor is also once per second.

[0064] S102: forming fitting parameters corresponding to each usage scenario based on the sub-training set corresponding to each usage scenario, where the fitting parameters are used to fit the temperature of the electronic device.

[0065] In some embodiments, the sub-training set corresponding to each usage scenario can be further classified to obtain a training group corresponding to each usage scenario, each training group including the measured temperature of a surface of the electronic device and the temperature of the thermistor corresponding to the surface. Therefore, the fitting parameters of a surface of the electronic device under each usage scenario can be formed based on the training group corresponding to each usage scenario, and the fitting parameters of a point of the electronic device are used to fit the temperature of the surface of the electronic device.

[0066] For example, an electronic device includes a front, back, and side, and a sub-training set corresponding to a certain usage scenario is classified into a front training group, a back training group, and a side training group corresponding to the usage scenario. The front training group includes the measured temperature of the front of the electronic device in the usage scenario and the temperature of the thermistor corresponding to the front; the back training group includes the measured temperature of the back of the electronic device in the usage scenario and the temperature of the thermistor corresponding to the back; the side training group includes the measured temperature of the side of the electronic device in the usage scenario and the temperature of the thermistor corresponding to the side.

[0067] Accordingly, the fitting parameters corresponding to the front side in a certain usage scenario can be formed based on the corresponding front training group in the usage scenario, and the fitting parameters corresponding to the front side are used to fit the front temperature of the electronic device; the fitting parameters corresponding to the back side in a certain usage scenario can be formed based on the corresponding back training group in the usage scenario, and the fitting parameters corresponding to the back side are used to fit the back temperature of the electronic device; the fitting parameters corresponding to the side side in a certain usage scenario can be formed based on the corresponding side training group in the usage scenario, and the fitting parameters corresponding to the side side are used to fit the side temperature of the electronic device.

[0068] In some embodiments, for the fitting parameters corresponding to each usage scenario: the temperature of each thermistor in the sub-training set is formed into an independent variable matrix, and the measured temperature in the sub-training set is formed into a dependent variable matrix; when the independent variable matrix is ​​full rank, the loss function is calculated for the independent variable matrix and the dependent variable matrix to obtain the weighting coefficient and the intercept value, so as to obtain the fitting parameters under the corresponding usage scenario. Accordingly, the fitting parameters corresponding to each usage scenario include the weighting coefficient and the intercept value of each thermistor in the usage scenario. The weighting coefficient can be understood as the degree of influence of the thermistor on the temperature of the electronic device. The larger the weighting coefficient of a certain thermistor, the greater its influence on the temperature of the electronic device. The smaller the weighting coefficient of a certain thermistor, the smaller its influence on the temperature of the electronic device. In this embodiment, considering that the positions of the thermistors of the electronic device are close to each other, affected by the space of the ornaments, the positions of some thermistors, such as 4G NTC and 5G NTC, may be close to each other, resulting in the problem of linear correlation of the temperature data of the thermistors used for training, causing multicollinearity problems and reducing the fitting accuracy. Therefore, when calculating the shell temperature parameters corresponding to each usage scenario, the full rank judgment is performed on the independent variable matrix formed by the temperature of the thermistor to avoid multicollinearity problems and improve the fitting accuracy.

[0069] It should be noted that when it comes to matrix calculations, if a matrix is ​​not full rank, it means that some column vectors of the matrix have coefficient relationships, such as the matrix A = column vector B = column vector If A = λB, that is, there is a mapping relationship of coefficient λ between the column vectors AB, then AB is linearly dependent. If there are linearly dependent column vectors in the matrix, then the matrix is ​​not full rank.

[0070] An independent variable matrix with insufficient rank will cause infinite solutions in the matrix function calculation, which is not conducive to solving the accurate value. Corresponding to this embodiment, if the independent variable matrix X is not full rank, it means that the temperatures of some different thermistors are linearly correlated. For example, if the positions of two thermistors (NTC_1 and NTC_2) are very close, in some heating scenarios, the temperature of NTC_1 at each moment has a coefficient relationship with the temperature of NTC_2, then NTC_1 and NTC_2 are linearly correlated. Linearly correlated independent variable data will cause multicollinearity problems and reduce the accuracy of the regression equation.

[0071] Therefore, in some examples, if the independent variable matrix is ​​not full rank, the linearly related thermistor temperatures can be removed to avoid multicollinearity problems and improve the accuracy of the shell temperature parameters.

[0072] In some examples, the method of determining whether the independent variable matrix is ​​full rank may include: performing matrix transposition on the independent variable matrix to obtain the transposed matrix of the independent variable matrix; calculating the product matrix of the independent variable matrix and the transposed matrix, and determining whether the rank of the product matrix is ​​the smaller of the number of rows and the number of columns in the product matrix; if so, the independent variable matrix is ​​full rank, and if not, the independent variable matrix is ​​not full rank. Based on this, the determination of whether the independent variable matrix is ​​full rank can be completed.

[0073] Table 1

[0074] time NTC_A NTC_B NTC_C Measured temperature 1s A1 B1 C1 V1 2s A2 B2 C2 V2 3s A3 B3 C3 V3 4s A4 B4 C4 V4 … … … … … ns An Bn Cn Vn

[0075] For example, as shown in Table 1, the sub-training set includes the measured temperatures at different times in 1s to ns, and the temperatures of three thermistors corresponding to the usage scenario at different times.

[0076] The temperature of each thermistor in the sub-training set in Table 1 is formed into an independent variable matrix:

[0077]

[0078] Among them, the first column in the independent variable matrix X represents the intercept term, the second column represents the temperature of thermistor NTC_A in 1s~ns, the third column represents the temperature of thermistor NTC_B in 1s~ns, and the fourth column represents the temperature of thermistor NTC_C in 1s~ns.

[0079] The measured shell temperatures in the sub-training set in Table 1 are formed into a dependent variable matrix:

[0080]

[0081] Therefore, we can transpose the independent variable matrix to obtain the torque matrix X of the independent variable matrix X T Then, calculate the independent variable matrix X and the transposed matrix X T The product of X T X, judge X T Is X the identity matrix? If so, the independent variable matrix X is full rank; if not, the independent variable matrix X is not full rank.

[0082] For example, we can calculate X through Python T Whether X is full rank, in Python, you can use the NumPy library to call the linalg.matrix_rank() and numpy.transpose() functions in NumPy to calculate. The numpy.transpose() function is used to transpose the matrix, and the linalg.matrix_rank() function is used to calculate the rank of the matrix.

[0083] In some embodiments, when the independent variable matrix is ​​of full rank, a loss function is calculated on the independent variable matrix and the dependent variable matrix to obtain weighting coefficients and intercept values.

[0084] Specifically, the square difference between the dependent variable matrix and the fitted shell temperature is used as the loss function, and the fitted shell temperature is the product of the independent variable matrix and the weighted matrix, and the weighted matrix is ​​a matrix composed of weighted coefficients and intercept values. Then, the partial derivative of the loss function with respect to the weighted matrix is ​​calculated. When the partial derivative is a preset value, the weighted matrix is ​​obtained, so that the shell temperature parameter can be obtained. Among them, the preset value can be 0 or other values.

[0085] It should be noted that the essence of the loss function is the square error loss function, which is expressed as Where y is the measured value, is the predicted value, S is the sum of the squares of the difference between the measured value and the predicted value, and the linear expression in the embodiment is:

[0086] S=(Y-Xα) 2 , where Y is the measured shell temperature, Xα is the fitted temperature, X is the independent variable matrix, and α is the weighting matrix. In the multivariate linear regression model, the loss function is an indicator to measure the difference between the model prediction value and the actual observation value. Its purpose is to quantify the error between the model prediction value and the actual value. Calculate the loss function S = (Y-Xα) 2 The partial derivative of the weighted matrix α is expanded into S = Y T Y-2α T X T Y+α T X TXα, α is the shell temperature parameter matrix, that is, the matrix composed of weighting coefficients and intercept values. To solve the minimum value of S, (S is a quadratic function with an opening upward about α, and there must be a minimum value), it is necessary to solve the partial derivative about α to make it 0, that is, -2X T Y+2X T Xα=0. According to the above full rank judgment, if X T If X is not full rank, then α will have infinite solutions. Since the independent variable matrix X is full rank, -2X T Y+2X T Xα=0 has a solution, α=(X T X) -1 X T Y, where α0 is the intercept value, α1 to α n is the weight value of each thermistor.

[0087] In practical applications, calling the NumPy library on Python can achieve α=(X T X) -1 X T Y is analyzed to obtain the intercept value and the weight value of each thermistor.

[0088] At this point, the correspondence between different usage scenarios and corresponding shell temperature parameters can be determined, such as Figure 2 As shown, a game application of the device is in a running state, corresponding to the game scene, and the above embodiment can determine the fitting parameter A corresponding to the game scene; a camera application of the device is in a running state, corresponding to the camera scene, and the above embodiment can determine the fitting parameter B corresponding to the camera scene; the device is in a screen-on + charging state, corresponding to the charging usage scene, and the above embodiment can determine the fitting parameter C corresponding to the charging usage scene; the device is in a screen-off + charging state, corresponding to the charging only scene, and the above embodiment can determine the fitting parameter D corresponding to the charging only scene; a video application of the device is in a running state, corresponding to the video scene, and the above embodiment can determine the fitting parameter E corresponding to the video scene; the device is in other states, corresponding to scene F, and the above embodiment can determine the fitting parameter F corresponding to scene F.

[0089] The method for determining fitting parameters of an electronic device provided in this embodiment classifies the training set, obtains a sub-training set corresponding to each usage scenario of the electronic device, and forms fitting parameters corresponding to each usage scenario based on the sub-training set corresponding to each usage scenario, thereby solving the problems of incomplete coverage of fitting scenarios and overfitting, and more accurately describing the temperature of the electronic device.

[0090] Figure 3 FIG. 1 is a flow chart showing a method for determining the temperature of an electronic device provided by an embodiment of the present application. Figure 3As shown, with the electronic device as the execution subject, the method of this embodiment may include the following steps:

[0091] S201: Acquire a current usage scenario of the electronic device, and acquire fitting parameters corresponding to the current usage scenario according to a correspondence between usage scenarios and fitting parameters determined by the above-mentioned method for determining fitting parameters of the electronic device.

[0092] In the embodiment of the present application, since the correspondence between the usage scenario and the fitting parameters is predetermined, after the current usage scenario of the electronic device is obtained, the fitting parameters corresponding to the current usage scenario can be quickly obtained based on the correspondence, thereby improving the fitting efficiency.

[0093] For example, considering that the electronic device is in a charging state or a non-charging state, each thermistor of the electronic device corresponds to a different temperature, and the electronic device corresponds to a different temperature. Therefore, in some embodiments, the charging state and the non-charging state are distinguished to more accurately determine the fitting parameters, and then more accurately determine the temperature of the electronic device.

[0094] Specifically, when the electronic device is in a charging state, it is determined whether the electronic device is running an application. If so, the current usage scenario of the electronic device is determined based on the currently running application. If not, the current usage scenario of the electronic device is determined to be a charging scenario. For example, if the currently running application is a video application, the current usage scenario of the electronic device is determined to be a video scenario.

[0095] When the electronic device is in a non-charging state, determine whether the electronic device is running an application. If so, determine the current usage scenario of the electronic device based on the currently running application. If not, the electronic device is in a standby state or an idle state. The temperature of the electronic device may be fixed, so fitting is not necessary in this state.

[0096] As an implementation method, you can use the Android SDK to write a program that monitors the application status. When the application is started or closed, you can obtain the application status information by monitoring the system broadcast and implement the underlying recognition of the application so that you can obtain the device status.

[0097] S202: Determine the current temperature of the electronic device based on the fitting parameters corresponding to the current usage scenario.

[0098] For example, the fitting parameters corresponding to the current usage scenario may include the weighting coefficient and intercept value of the thermistor corresponding to the current usage scenario. Therefore, after obtaining the temperature of each thermistor corresponding to the current scenario and the fitting parameters corresponding to the current scenario, the current temperature of the electronic device can be determined based on the temperature of each thermistor corresponding to the current usage scenario and the weighting coefficient and intercept value of each thermistor in the fitting parameters.

[0099] For example, the current temperature of the electronic device can be fitted based on the temperature fitting formula, and the temperature fitting formula is as follows:

[0100] The current temperature of the electronic device = a1x1+a2x2+a3x3+…+anxn+D;

[0101] Among them, x1~xn are the temperatures of each thermistor corresponding to the current usage scenario at a certain moment, a1~an are the weighting coefficients of each thermistor corresponding to the current usage scenario, and D is the intercept value. Accordingly, the weighting coefficients a1~an of each thermistor corresponding to the current usage scenario and the intercept value D constitute the fitting parameters of the current usage scenario.

[0102] The temperature determination method of an electronic device provided in an embodiment of the present application predetermines fitting parameters corresponding to different usage scenarios. After determining the current usage scenario of the electronic device, the fitting parameters corresponding to the current usage scenario can be obtained, and the current temperature of the device can be determined based on the fitting parameters corresponding to the current scenario. This can solve the problems of incomplete coverage of fitting scenarios and overfitting, and more accurately describe the temperature of the electronic device.

[0103] Figure 4 FIG. 1 shows a schematic diagram of a structure of a device for determining fitting parameters of an electronic device provided by an embodiment of the present application. Figure 4 As shown, the fitting parameter determination device 10 of the electronic device of this embodiment is used to implement the operation corresponding to the electronic device in any of the above method embodiments. The fitting parameter determination device 10 of the electronic device of this embodiment includes:

[0104] A first processing module 11 is used to classify the training set and obtain a sub-training set corresponding to each usage scenario of the electronic device, wherein the sub-training set includes the measured temperature of the electronic device and the temperature of the corresponding thermistor in the electronic device;

[0105] The second processing module 12 is used to form fitting parameters corresponding to each usage scenario based on the sub-training set corresponding to each usage scenario, and the fitting parameters are used to fit the temperature of the electronic device.

[0106] The fitting parameter determination device 10 of the electronic device provided in the embodiment of the present application can execute the above method embodiment. Its specific implementation principle and technical effects can be found in the above method embodiment, and this embodiment will not be repeated here.

[0107] Figure 5 FIG. 1 shows a schematic diagram of a temperature determination device for an electronic device provided by an embodiment of the present application. Figure 5As shown, the temperature determination device 20 of the electronic device of this embodiment is used to implement the operation corresponding to the electronic device in any of the above method embodiments. The temperature determination device 20 of the electronic device of this embodiment includes:

[0108] An acquisition module 21, configured to acquire a current usage scenario of the electronic device, and acquire fitting parameters corresponding to the current usage scenario according to a correspondence between usage scenarios and fitting parameters determined by the method according to any one of claims 1 to 5;

[0109] The determination module 22 is used to determine the current temperature of the electronic device based on the fitting parameters corresponding to the current usage scenario.

[0110] The temperature determination device 20 of the electronic device provided in the embodiment of the present application can execute the above method embodiment. Its specific implementation principle and technical effects can be found in the above method embodiment, and this embodiment will not be repeated here.

[0111] Figure 6 FIG. 1 shows a hardware structure diagram of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 30 is used to implement the operations corresponding to the electronic device in any of the above method embodiments. The electronic device 30 of this embodiment may include: a memory 31, a processor 32 and a communication interface 33.

[0112] The memory 31 is used to store computer instructions. The memory 31 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a disk or an optical disk.

[0113] The processor 32 is used to execute the computer instructions stored in the memory to implement the method in the above embodiment. For details, please refer to the relevant description in the above method embodiment. The processor 32 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the invention can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0114] Optionally, the memory 31 may be independent or integrated with the processor 32 .

[0115] The communication interface 33 may be connected to the processor 32. The processor 32 may control the communication interface 33 to implement the functions of receiving and sending signals.

[0116] The electronic device provided in this embodiment can be used to execute the above method, and its implementation method and technical effect are similar, which will not be described in detail in this embodiment.

[0117] The present application also provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed by a processor, they are used to implement the methods provided in the various embodiments described above.

[0118] The present application also provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. At least one processor of a device can read the computer instructions from the computer-readable storage medium, and at least one processor executes the computer instructions so that the device implements the methods provided in the various embodiments described above.

[0119] An embodiment of the present application also provides a chip, which includes a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call and execute the computer instructions from the memory, so that a device equipped with the chip executes the methods described in the various possible implementation modes above.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the above embodiments can still be modified, or some or all of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining fitting parameters of an electronic device, characterized in that: The method comprises: Classifying the training set to obtain a sub-training set corresponding to each usage scenario of the electronic device, the sub-training set including the measured temperature of the electronic device and the temperature of a corresponding thermistor in the electronic device; A fitting parameter corresponding to each usage scenario is formed based on the sub-training set corresponding to each usage scenario, and the fitting parameter is used to fit the temperature of the electronic device.

2. The method according to claim 1, characterized in that The forming of the fitting parameters corresponding to each usage scenario based on the sub-training set corresponding to each usage scenario includes: The temperature of each thermistor in the sub-training set forms an independent variable matrix, and the measured temperature in the sub-training set forms a dependent variable matrix; When the independent variable matrix is ​​of full rank, a loss function is calculated on the independent variable matrix and the dependent variable matrix to obtain a weighted coefficient and an intercept value of each thermistor in the sub-training set.

3. The method according to claim 2, characterized in that Methods for determining whether the independent variable matrix is ​​full rank include: Performing matrix transposition on the independent variable matrix to obtain a transposed matrix of the independent variable matrix; Calculating a product matrix of the independent variable matrix and the transposed matrix, and determining whether the rank of the product matrix is ​​the smaller of the number of rows and the number of columns in the product matrix; If so, the independent variable matrix is ​​full rank, and if not, the independent variable matrix is ​​not full rank.

4. The method according to claim 3, characterized in that The calculating of the loss function on the independent variable matrix and the dependent variable matrix includes: The squared difference between the dependent variable matrix and the fitted shell temperature is used as the loss function; The fitted shell temperature is the product of the independent variable matrix and the weighting matrix, and the weighting matrix is ​​a matrix composed of weighting coefficients and intercept values; The partial derivative of the loss function with respect to the weighting matrix is ​​calculated, and when the partial derivative is a preset value, the weighting matrix is ​​obtained.

5. The method according to any one of claims 1 to 4, characterized in that: Before classifying the training set, the method further includes: The training set is preprocessed, and the preprocessing includes at least one of data cleaning and replacing abnormal values ​​by difference.

6. A method for determining the temperature of an electronic device, characterized in that: The method comprises: Acquire a current usage scenario of the electronic device, and determine a correspondence between the usage scenario and the fitting parameters according to the method described in any one of claims 1 to 5, to acquire the fitting parameters corresponding to the current usage scenario; The current temperature of the electronic device is determined based on the fitting parameters corresponding to the current usage scenario.

7. The method according to claim 6, characterized in that The obtaining of the current usage scenario of the electronic device includes: When the electronic device is in a charging state, determining whether the electronic device is running an application, and if so, determining a current usage scenario of the electronic device based on the currently running application, and if not, determining that the current usage scenario of the electronic device is a charging scenario; When the electronic device is in a non-charging state, it is determined whether the electronic device is running an application, and if so, a usage scenario of the electronic device is determined based on the currently running application.

8. The method according to claim 6, characterized in that The determining the current temperature of the electronic device based on the fitting parameters corresponding to the current usage scenario includes: Obtaining the temperature of the thermistor corresponding to the current usage scenario; The current temperature of the electronic device is determined based on the temperature of the thermistor corresponding to the current usage scenario and the weighted coefficient and intercept value of each thermistor in the fitting parameters.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

Images