Data processing method and device, electronic equipment and storage medium

Abstract

The invention provides a data processing method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a first target temperature of the electronic equipment under the operation of a first performance parameter, and the first target temperature comprises at least one of the processor temperature of the electronic equipment, the circuit board temperature and the internal temperature of the electronic equipment; inputting the first target temperature to a first prediction model through the transmission channel to obtain a second target temperature of the electronic device, the second target temperature being used for representing a surface prediction temperature of the electronic device; based on the second target temperature and the standard temperature of the electronic equipment under the first performance parameter, whether the first performance parameter is adjusted to the second performance parameter or not is determined; wherein the standard temperature is obtained based on the environment temperature grade when the electronic equipment operates by adopting the first performance parameter. By utilizing the electronic equipment, the electronic equipment can adapt to variable temperature environments, so that the performance of the electronic equipment is greatly improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a data processing method, device, equipment and storage medium. Background Art

[0002] The performance of electronic devices such as laptops is affected by many factors. One of these factors is the ambient temperature, but in actual applications, the ambient temperature of laptops is variable. In related technologies, the variability of ambient temperature is not taken into account, and 25°C is uniformly used as the standard temperature to tune the performance of electronic devices. Obviously, this performance tuning solution cannot adapt to the variable temperature environment, which greatly limits the performance of electronic devices. Summary of the invention

[0003] The present disclosure provides a data processing method, device, equipment and storage medium to at least solve the above technical problems existing in the prior art.

[0004] According to a first aspect of the present disclosure, there is provided a data processing method, comprising:

[0005] Obtaining a first target temperature of the electronic device when the electronic device is operating at a first performance parameter, wherein the first target temperature includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device;

[0006] Inputting the first target temperature into the first prediction model through the transmission channel to obtain a second target temperature of the electronic device, where the second target temperature is used to characterize the predicted surface temperature of the electronic device;

[0007] Based on the second target temperature and the standard temperature of the electronic device under the first performance parameter, it is determined whether to adjust the first performance parameter to the second performance parameter; wherein the standard temperature is obtained based on the ambient temperature level of the electronic device when it operates with the first performance parameter.

[0008] In one possible implementation manner, the standard temperature of the electronic device is obtained based on the ambient temperature level in which the electronic device operates using the first performance parameter, and includes:

[0009] Obtaining timing data and non-timing data when the electronic device operates with the first performance parameter, wherein the timing data includes at least one of a processor temperature, a processor usage rate, and a processor power consumption, and the non-timing data includes at least one of an ambient humidity and an ambient air pressure;

[0010] Based on the statistical characteristics of time series data and non-time series data, a feature vector is obtained;

[0011] Inputting the feature vector into a second prediction model to obtain an ambient temperature level of the electronic device when the electronic device is operated with the first performance parameter;

[0012] Based on the ambient temperature level, a standard temperature of the electronic device under a first performance parameter is obtained.

[0013] In one embodiment, the method further comprises:

[0014] Preprocess time series data;

[0015] Calculate statistics on preprocessed time series data;

[0016] The calculation results are used as statistical features of time series data.

[0017] In one embodiment, the method further comprises:

[0018] Obtaining first sample data and a first sample label of the electronic device under target performance parameter operation, wherein the first sample data includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device under the target performance parameter; and the first sample label includes a first surface temperature and a second surface temperature under the target performance parameter;

[0019] The first sample data and the first sample label are input into the linear regression model to be trained to train the linear regression model to be trained, thereby obtaining a first prediction model.

[0020] In one embodiment, the method further comprises:

[0021] Obtaining second sample data and second sample labels of the electronic device under operation of multiple performance parameters, wherein the second sample data includes a timing sample and a non-timing sample, and the second sample label includes an ambient temperature level of the electronic device under each performance parameter;

[0022] Based on the statistical characteristics of time series samples and non-time series samples, a sample feature vector is obtained;

[0023] The sample feature vector is input into the long short-term memory model to be trained to train the long short-term memory model and obtain a second prediction model.

[0024] In one embodiment, the method further comprises:

[0025] Preprocessing the first target temperature;

[0026] The preprocessed first target temperature is input into the first prediction model.

[0027] In one possible implementation, determining whether to adjust the first performance parameter to the second performance parameter based on the first target temperature and the standard temperature of the electronic device under the first performance parameter includes:

[0028] In response to the second target temperature and the standard temperature of the electronic device under the first performance parameter being different or not similar, determining to adjust the first performance parameter to the second performance parameter;

[0029] In response to the second target temperature and the standard temperature of the electronic device under the first performance parameter being the same or similar, it is determined not to adjust the first performance parameter to the second performance parameter.

[0030] According to a second aspect of the present disclosure, there is provided a data processing device, comprising:

[0031] A first obtaining unit, configured to obtain a first target temperature of the electronic device when the electronic device is operating with a first performance parameter, wherein the first target temperature includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device;

[0032] A second obtaining unit is used to input the first target temperature into the first prediction model through the transmission channel to obtain a second target temperature of the electronic device, where the second target temperature is used to characterize the surface temperature of the electronic device;

[0033] The first determination unit is used to determine whether to adjust the first performance parameter to the second performance parameter based on the second target temperature and the standard temperature of the electronic device under the first performance parameter; wherein the standard temperature is obtained based on the ambient temperature level when the electronic device operates with the first performance parameter.

[0034] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0035] at least one processor; and

[0036] a memory communicatively connected to the at least one processor; wherein,

[0037] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present disclosure.

[0038] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the present disclosure.

[0039] The present disclosure determines whether to adjust the performance parameters of the electronic device by using the predicted surface temperature of the electronic device and the standard temperature of the electronic device under the first performance parameter obtained by the ambient temperature level output by the second prediction model. It can adapt to the variable temperature environment, so that the performance of the electronic device is greatly improved.

[0040] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0042] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0043] Figure 1 The implementation process of the data processing method of the present disclosure is shown in FIG. Figure 1 ;

[0044] Figure 2 A block diagram of the data processing method according to the embodiment of the present disclosure is shown;

[0045] Figure 3 A block diagram showing an implementation of a training method for a first prediction model according to an embodiment of the present disclosure is shown;

[0046] Figure 4 The implementation process of the data processing method of the present disclosure is shown in FIG. Figure 2 ;

[0047] Figure 5 A flowchart of the implementation of the training method of the second prediction model in the embodiment of the present disclosure is shown;

[0048] Figure 6 A schematic diagram showing a timing sample of an embodiment of the present disclosure is shown;

[0049] Figure 7 A schematic diagram showing the composition structure of a data processing device according to an embodiment of the present disclosure is shown;

[0050] Figure 8 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0051] In order to make the purpose, features, and advantages of the present disclosure more obvious and easy to understand, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0052] The electronic device in the present disclosure may be a laptop computer, a tablet computer, a desktop computer, an all-in-one computer, etc., and may also be a smart wearable device such as a smart watch, a smart bracelet, etc. Preferably, the electronic device is a laptop computer.

[0053] The present disclosure involves two models: a first prediction model (a trained linear regression model) and a second prediction model (a trained long short-term memory model LSTM). In the present disclosure, at least one of the processor temperature, circuit board temperature, and internal temperature of the electronic device under the operation of the first performance parameter of the electronic device is input into the first prediction model through a transmission channel, and the first prediction model predicts the predicted surface temperature (second target temperature) of the electronic device. The standard temperature of the electronic device under the first performance parameter obtained by the predicted surface temperature of the electronic device and the ambient temperature level output by the second prediction model is used to determine whether the performance parameter of the electronic device is adjusted.

[0054] In the present disclosure, if the predicted surface temperature of the electronic device is regarded as the temperature condition of the electronic device itself, and the standard temperature obtained by the ambient temperature level output by the second prediction model is regarded as the embodiment of the ambient temperature of the electronic device, then the present disclosure can be regarded as a scheme for determining whether to adjust the performance parameters of the electronic device according to the temperature condition of the electronic device itself and the temperature condition of the environment in which it is located. If it is determined that the adjustment can be made, it can be regarded as a scheme for dynamically adjusting the performance parameters according to the temperature condition of the electronic device itself and the temperature state of the environment in which it is located.

[0055] The technical solution of the present disclosure is described in detail below.

[0056] Figure 1 The implementation process of the data processing method of the present disclosure is shown in FIG. Figure 1 .like Figure 1 As shown, the method includes:

[0057] S (step) 101: Obtain a first target temperature of an electronic device under operation of a first performance parameter, wherein the first target temperature includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device.

[0058] The performance parameters of the electronic device in the present disclosure include at least one of the processor usage rate, processor power consumption, and fan speed. The first performance parameter and the second performance parameter of the present disclosure refer to the difference in the value of at least one of the above. For example, the fan speed has different values ​​and the processor power consumption is different. The processor includes any reasonable device or chip with processing function that can be set in the electronic device. For example, a central processing unit (CPU), a graphics processing unit (GPU), a neural network processor (NPU), etc.

[0059] In the present disclosure, one or more temperature sensors are provided on the hardware to obtain the temperature. Figure 2 As shown, a processor, a circuit board (PCB) and a corresponding temperature sensor are arranged inside the electronic device. Each temperature sensor collects its own temperature, thereby achieving the acquisition of a first target temperature of the electronic device under the operation of the first performance parameter.

[0060] S102: Inputting the first target temperature into the first prediction model through the transmission channel to obtain a second target temperature of the electronic device, where the second target temperature is used to characterize the predicted surface temperature of the electronic device.

[0061] Combination Figure 2 As shown, the processor temperature, circuit board temperature and internal temperature of the electronic device are information collected by the temperature sensor hardware. The first prediction model is a model located at the application layer. The information collected by the temperature sensor also needs to transmit the collected temperature from the hardware layer to the application layer through a certain transmission channel. Specifically, the processor temperature, circuit board temperature and internal temperature of the electronic device can be transmitted from the temperature sensor of the hardware layer to the basic input and output system (Bios) of the electronic device via the embedded chip (EC) of the electronic device. The Bios transmits the first target temperature to the application layer of the electronic device through the driver, and inputs it into the first prediction model of the application layer, so as to transmit the temperature information collected from the hardware layer to the model of the application layer through the transmission channel.

[0062] In the present disclosure, the processor temperature, the circuit board temperature and the internal temperature of the electronic device are input into the trained LSTM model (first prediction model). The LSTM model analyzes the input temperature itself through the learned temperature characteristics, thereby obtaining the predicted surface temperature of the electronic device. That is, the LSTM model predicts the surface temperature of the electronic device at this time through the input of three temperature data, namely, the processor temperature, the circuit board temperature and the internal temperature of the electronic device.

[0063] In the optional solution of the present disclosure, when the processor temperature, the circuit board temperature and the internal temperature of the electronic device are transmitted from the hardware layer to the application layer, the first target temperature including the processor temperature, the circuit board temperature and the internal temperature of the electronic device can be preprocessed. The preprocessing can specifically be a normalization operation. The preprocessed first target temperature is input into the first prediction model. Among them, the three temperature values ​​are normalized so that their values ​​are between 0 and 1, which can speed up the output of the prediction result by the first prediction model.

[0064] The LSTM model is a machine learning model, which is usually robust, robust, and stable. By using such a machine learning model, the surface temperature of electronic equipment can be accurately predicted, thereby ensuring the accurate determination of whether to adjust the performance parameters.

[0065] S103: Determine whether to adjust the first performance parameter to a second performance parameter based on the second target temperature and a standard temperature of the electronic device under the first performance parameter; wherein the standard temperature is based on the ambient temperature level of the electronic device when the electronic device operates with the first performance parameter.

[0066] In this step, the predicted surface temperature of the electronic device and the obtained standard temperature are used to determine whether to adjust the performance parameters of the electronic device. For example, the first performance parameter originally used by the electronic device is adjusted to a second performance parameter different from the first performance parameter. For example, the performance parameter is adjusted by increasing or decreasing the processor power, increasing or decreasing the fan speed, etc.

[0067] In this step, the standard temperature of the electronic device under the first performance parameter is obtained in the following manner: the ambient temperature level in which the electronic device is operating using the first performance parameter is obtained, and based on the obtained ambient temperature level, the standard temperature of the electronic device under the first performance parameter is obtained. That is, the standard temperature in the present disclosure is no longer a single temperature (25°C) in the related art, but a temperature standard obtained by the ambient temperature level in which the electronic device is currently located. In the present disclosure, the temperature standard (the value of the standard temperature) is different for different ambient temperature levels. By using different standard temperatures, the performance of the electronic device can be optimized to adapt to a changing temperature environment, so that the performance of the electronic device is greatly improved.

[0068] In this step, when implemented, the second target temperature is compared with the standard temperature of the electronic device under the first performance parameter. If the second target temperature and the standard temperature of the electronic device under the first performance parameter are different or not similar, then in response to the second target temperature and the standard temperature of the electronic device under the first performance parameter being different or not similar, it is determined that the first performance parameter is adjusted to the second performance parameter. If the second target temperature and the standard temperature of the electronic device under the first performance parameter are the same or similar temperature, then in response to the second target temperature and the standard temperature of the electronic device under the first performance parameter being the same or similar temperature, it is determined not to adjust the first performance parameter to the second performance parameter. Among them, two temperatures with a temperature difference of 1°C are regarded as similar temperatures.

[0069] The second target temperature and the standard temperature are different or not close to each other, including the second target temperature being greater than the standard temperature of the electronic device under the first performance parameter, and the second target temperature being less than the standard temperature of the electronic device under the first performance parameter. If greater than, reduce the CPU load, reduce the CPU usage, increase the fan speed, etc. If less than, increase the CPU load, increase the CPU usage, reduce the fan speed, etc.

[0070] In S101 to S103, the electronic device surface predicted temperature and the standard temperature of the electronic device under the first performance parameter obtained by the ambient temperature level output by the second prediction model are used to determine whether the performance parameter of the electronic device is to be adjusted. The performance of the electronic device can be optimized by using different standard temperatures, so that it can adapt to a variable temperature environment, and the performance of the electronic device is greatly improved.

[0071] The above scheme is a scheme for applying the trained first prediction model. The present disclosure also includes a scheme for training the linear regression model to be trained to obtain the trained first prediction model. The scheme for training the linear regression model to be trained to obtain the first prediction model includes steps A01 and A02.

[0072] A01: Obtain first sample data and a first sample label of an electronic device operating under target performance parameters, wherein the first sample data includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device under the target performance parameters; and the first sample label includes a first surface temperature and a second surface temperature under the target performance parameters.

[0073] The target performance parameter may be one or more target performance parameters of the electronic device. Figure 3 As shown, in Figure 3In the figure, PCB Sensor APU represents the processor temperature; PCB Sensor represents the circuit board temperature; and PCB Sensor Remote represents the internal temperature of the electronic device. These three temperatures can be used as the (first) sample data when training the linear regression model to be trained. The sample data can also be regarded as an independent variable in the machine learning model, and the value of the sample data can be used as the value (feature value) of the independent variable. Figure 3 The value of the independent variable under a certain performance parameter is given in . In the linear regression model to be trained, the dependent variable (target variable) of the machine learning model includes two, one of which is the actual surface temperature of the center of the electronic device, such as Figure 3 The other dependent variable is the actual surface temperature of the edge of the electronic device, as shown in the CH0021 column. The first surface temperature and the second surface temperature are the two dependent variables mentioned above. That is, the (first) sample label is the actual surface temperature of the center of the machine and the actual surface temperature of the edge of the machine.

[0074] Among them, the actual surface temperature of the center of the machine and the actual surface temperature of the edge of the machine can be obtained through infrared scanning. The processor temperature, circuit board temperature and the internal temperature of the electronic equipment machine can be obtained through the collection of temperature sensors.

[0075] A02: Inputting the first sample data and the first sample label into the linear regression model to be trained to train the linear regression model to be trained, and obtaining a first prediction model.

[0076] In the present disclosure, the model to be trained is a model using a linear regression algorithm - a linear regression model. The model parameters of the linear regression model include feature parameters and intercept (parameters). The training of the linear regression model is to use sample data and sample labels to calculate the feature parameters and intercept parameters. Figure 3 In the code section shown, the left code indicates that the first sample data and the actual surface temperature of the machine center are input into the linear regression model to be trained, and the characteristic parameters and intercept parameters of the model to be trained are obtained. The right code indicates that the first sample data and the actual surface temperature of the machine edge are input into the linear regression model to be trained, and the characteristic parameters and intercept parameters of the model to be trained are obtained. The coefficients in the code indicate the characteristic parameters of the linear regression model.

[0077] In this step, the (first) sample data and the (first) sample label are input into the linear regression model to be trained to realize iterative calculation of the linear regression model. That is, the linear regression model is trained using the sample label of the actual surface temperature at the edge of the machine and the actual surface temperature at the center of the machine at the same time. When the loss function of the linear regression model is less than the first preset threshold or the number of iterations reaches the maximum value, the training is completed or trained. The trained linear regression model is used as the first prediction model. It can be understood that in the present disclosure, the actual surface temperature of the center of the machine and the actual surface temperature of the center of the machine are used as labels at the same time, taking into account the influence of the actual surface temperatures of the center of the machine and the edge of the machine on the model training, which can ensure the accuracy of the model training. It provides a more accurate guarantee for the performance tuning of electronic equipment.

[0078] In an optional solution of the present disclosure, the standard temperature of the electronic device under the first performance parameter can be obtained by Figure 4 The solution shown in the figure can be used to achieve this. Figure 4 As shown, the data processing method in the present disclosure also includes S401 to S404.

[0079] S401: Obtain timing data and non-timing data when the electronic device operates with a first performance parameter, wherein the timing data includes at least one of a processor temperature, a processor usage rate, and a processor power consumption, and the non-timing data includes at least one of ambient humidity and ambient air pressure.

[0080] In this step, the processor temperature can be collected through a temperature sensor. The processor usage rate and processor power consumption can be obtained by reading the existing data of the laptop. The weather application is called from the application program interface (API) through a Hypertext Transfer Protocol (HTTP) request to obtain the ambient humidity and ambient air pressure.

[0081] S402: Obtain a feature vector based on the statistical features of the time series data and the non-time series data;

[0082] In this step, the time series data is preprocessed; statistics are calculated for the preprocessed time series data; and the calculation results are used as statistical features of the time series data.

[0083] Among them, the preprocessing includes normalizing the time series data so that the values ​​of the time series data are between 0 and 1 to speed up the calculation of the second prediction model. The normalized time series data is calculated for statistical quantities such as the mean, maximum value, minimum value, and standard deviation, and the calculated statistics are used as statistical features of the time series data. The statistical features and the values ​​of the non-time series data are spliced, and the spliced ​​results are used as feature vectors.

[0084] If the non-time series data includes the shell material of the electronic device in addition to the ambient humidity and ambient pressure, the shell material information can be converted into a binary variable using the unique hot encoding method. It is then concatenated with the statistical features of the time series data, the ambient humidity, and the ambient pressure values ​​to obtain a feature vector.

[0085] S403: Input the feature vector into a second prediction model to obtain an ambient temperature level of the electronic device when the electronic device operates with the first performance parameter.

[0086] In this step, the feature vector is input into the trained LSTM model - the second prediction model. The second prediction model outputs the information of the ambient temperature level of the electronic device under the input according to the feature vector and the features learned in the training stage.

[0087] S404: Based on the ambient temperature level, obtain a standard temperature of the electronic device under the first performance parameter.

[0088] In the present disclosure, there is the following correspondence between the ambient temperature level and the standard temperature: ambient temperature level 1 (ambient temperature above 30°): the standard temperature is 35°C. Ambient temperature level 2 (ambient temperature between 20°C and 30°C): the standard temperature is 25°C. Ambient temperature level 3 (ambient temperature between 10°C and 20°C): the standard temperature is 15°C; ambient temperature level 4 (ambient temperature below 10°C): the standard temperature is 5°C.

[0089] In the aforementioned corresponding relationship, according to the ambient temperature level output by the second prediction model, a search for the corresponding standard temperature is performed, and the searched standard temperature is used as the ambient temperature of the electronic device.

[0090] In S401 to S404, the second prediction model is a machine learning model. The machine learning model is robust, robust and stable. By predicting the ambient temperature level through the machine learning model, the accuracy of the prediction of the ambient temperature level can be guaranteed, thereby ensuring the accuracy of the ambient temperature, and providing a guarantee for whether to accurately adjust the performance parameters.

[0091] In the present disclosure, the standard temperature is determined based on the ambient temperature level. Compared with the solution in the related art that uniformly uses 25°C as a single standard temperature, the present disclosure determines the ambient temperature according to the ambient temperature level of the actual environment where the electronic device is located, which can ensure the accuracy of the ambient temperature. The electronic device can adapt to the changing temperature environment, so that the performance of the electronic device is greatly improved.

[0092] The above scheme is a scheme for applying the trained second prediction model. The present disclosure also includes a scheme for training the LSTM model to be trained to obtain the trained second prediction model. Figure 5 As shown, the solution for training the LSTM model to be trained to obtain the first prediction model includes steps B01-B03.

[0093] B01: Obtain second sample data and second sample labels of the electronic device under operation of multiple performance parameters, wherein the second sample data includes timing samples and non-timing samples, and the second sample labels include the ambient temperature level of the electronic device under each performance parameter.

[0094] The timing samples include at least one of the processor temperature, processor usage rate and processor power consumption. The non-timing samples include at least one of the ambient humidity and ambient air pressure. In practical applications, data such as CPU real-time power consumption, CPU usage rate, CPU surface temperature, GPU real-time power consumption, GPU usage rate, GPU surface temperature, electronic equipment such as notebook fan speed, notebook battery status, etc. can be used as timing samples. The current environmental humidity, air pressure, current notebook shell material and other data are used as non-timing samples. The second sample label can refer to the aforementioned four ambient temperature levels (ambient temperature level 1 to ambient temperature level 4).

[0095] Figure 6 The waveform diagram of the timing samples when the ambient temperature level is level 3. Among them, CPU_usage indicates CPU usage. CPU_p indicates CPU power. CPU_temp indicates CPU surface temperature. GPU_usage indicates GPU usage. GPU_p indicates GPU power. GPU_temp indicates GPU surface temperature.

[0096] The time series samples are written into the file file_name, where file_name is the time series data file of different ambient temperature levels. Together with the non-time series samples and the (second) sample labels, they are used as the training data for the LSTM model, as shown in Table 1.

[0097]

[0098] B02: Based on the statistical characteristics of time series samples and non-time series samples, a sample feature vector is obtained.

[0099] Formula (1) is used to preprocess the time series samples, such as normalization. X is the value of a certain time series sample, such as GPU cpu, Xmin is the minimum value of the time series sample, Xmax is the maximum value of the time series sample, and Xnew is the normalized value of the time series sample.

[0100]

[0101] The preprocessed time series samples are subjected to calculation of statistical quantities such as mean, maximum value, minimum value, and standard deviation; and the calculation results are used as the statistical features of the time series samples.

[0102] The shell material information is converted into a binary variable using the one-hot encoding method. It is then concatenated with the statistical characteristics of the time series samples, the values ​​of ambient humidity and ambient pressure to obtain the sample feature vector.

[0103] The sample feature vector is used as the data set in the training scheme, and the data set is divided into a training set and a test set. The training set accounts for 7 parts of the entire data set, and the test set accounts for 3 parts of the entire data set. The training set is used for model training and tuning. The test set is used for model testing. Both the training set and the test set are used as training samples.

[0104] The above scheme can be regarded as a scheme for processing the second sample data and the second sample label to obtain a data set.

[0105] B03: Inputting the sample feature vector into the long short-term memory model to be trained to train the long short-term memory model and obtain a second prediction model.

[0106] In this step, the sample feature vector used for training is input into the LSTM model to be trained to train it.

[0107] The LSTM model can process time series data and use non-time series data as additional input features. It focuses on parsing the intrinsic time dependency of sequence data. Through its unique gating mechanism, LSTM can remember and forget information in the sequence, effectively handle long-range dependency problems, and ensure that the model can understand the dynamic evolution of the data. The LSTM model performs nonlinear transformation on the extracted features through the activation function to further enhance the feature expression. Subsequently, these multi-dimensional features are passed to the fully connected layer for the final multi-classification. The loss function is shown in formula (2), thereby achieving accurate classification of the data.

[0108]

[0109] Among them, yi is the true score of the model's input sample xi belonging to a certain category (ambient temperature level); f θ (x i ) is the predicted score of the sample xi that belongs to a certain ambient temperature level predicted by the LSTM model based on the model input. The softmax function is a normalized exponential function. L is the loss function, which is used to measure the loss between the score and the predicted score. n is the number of samples.

[0110] In the present disclosure, the LSTM model is used to predict the ambient temperature level of the electronic device. In practical applications, at least one of the following indicators is used to ensure that the model can accurately detect different ambient temperature levels: recall rate, accuracy rate and precision rate.

[0111] The trained LSTM model is tested using the test set. After the test passes, the LSTM model is deployed to the application layer of the electronic device. The aforementioned application solution is used to predict the ambient temperature level of the electronic device.

[0112] The present disclosure can be regarded as a solution for determining whether to adjust the performance parameters of an electronic device based on the temperature conditions of the electronic device itself and the temperature conditions of the environment in which it is located. The purpose is to dynamically adjust the performance parameters based on the real-time ambient temperature and the temperature conditions of the notebook itself to achieve the best performance of the notebook computer. The solution mainly includes:

[0113] Intelligent identification of ambient temperature: The second prediction model combines the power consumption, usage rate and temperature data of key components such as CPU and GPU to accurately predict the ambient temperature level of the electronic device, and determines the standard temperature of the current environment through the ambient temperature level. The standard temperature is used as the ambient temperature of the current environment.

[0114] Intelligent calculation of predicted surface temperature: Using the built-in temperature sensor data of the laptop, the predicted surface temperature of the electronic device is calculated through an optimized linear regression model as an important basis for performance adjustment.

[0115] Dynamic adjustment of performance parameters: Determine whether to adjust the performance parameters based on the predicted ambient temperature and the calculated predicted surface temperature to ensure that the electronic device can achieve optimal performance at different ambient temperatures. In this disclosure, not only temperature and power consumption parameters are covered, but also environmental factors such as humidity and air pressure are combined to provide more comprehensive data support. Among them, humidity affects the heat conduction and heat dissipation efficiency of the air. By monitoring humidity, the impact of the environment on the heat dissipation of the device can be more accurately evaluated. For example, in a high humidity environment, the moisture in the air will increase the heat conduction resistance, resulting in a poor heat dissipation effect. Changes in air pressure will affect the air density, which in turn affects the heat dissipation effect. By monitoring air pressure, the impact of the environment on the heat dissipation of the device can be more accurately evaluated. For example, in a low pressure environment, the air density decreases and the heat dissipation effect may deteriorate. In this disclosure, the external ambient temperature is predicted in combination with humidity and air pressure to ensure the accuracy of the prediction. The calculation of the external ambient temperature is achieved through multi-source data fusion (fusion of data such as temperature, power consumption, humidity and air pressure), which can ensure the accuracy of the ambient temperature calculation.

[0116] Calculation of predicted surface temperature of electronic equipment: The predicted surface temperature is calculated using the optimized linear regression algorithm model according to the readings of each temperature sensor and the machine learning model, which can improve the accuracy of temperature calculation. Among them, the introduced machine learning model uses a machine learning algorithm to improve the accuracy of temperature estimation by training the model to learn the temperature change law under different ambient temperatures in the laboratory temperature control room. In the present disclosure, more meaningful feature combinations are extracted through feature engineering optimization, such as temperature change rate, power consumption fluctuation, etc., to improve the generalization ability and prediction accuracy of the model. This not only improves the accuracy of temperature estimation, but also enhances the robustness of the model.

[0117] Dynamic performance parameter adjustment: In this disclosure, it is mainly divided into standard ambient temperature, low ambient temperature and high ambient temperature. Among them,

[0118] Standard ambient temperature (25°C):

[0119] Under long-term high load conditions, the standard power consumption control strategy is maintained, that is, the power consumption is reduced to PL1min. Through the adaptive learning mechanism of the machine learning model, the model can continuously optimize itself according to user usage habits and environmental changes, improving the robustness and accuracy of the prediction.

[0120] Low temperature environment (<25℃):

[0121] Under the same high load conditions, due to the low ambient temperature, the temperature of internal components rises slowly, and the power consumption limit (such as PL1min+ΔP1) can be appropriately increased to improve system performance without touching the safety threshold. The specific adjustment amount ΔP1 is calculated by a specific function f(VST,T_env) to ensure the scientificity and rationality of the adjustment, and can also be adjusted more finely to a temperature of 15°C and 5°C (below).

[0122] Temperature protection point: VST+ΔT1, where ΔT1 is calculated by a specific function g(VST,T_env), which ensures dynamic adjustment of the temperature protection point and switches to the low temperature performance mode parameter setting table to improve performance.

[0123] If it is at an extremely low ambient temperature, such as 5°C, the surface temperature requirements can be relaxed while improving performance, so that the heating function can be achieved in a low temperature environment.

[0124] High temperature environment (>35℃):

[0125] In the face of high ambient temperatures, in order to prevent the surface temperature of electronic equipment from exceeding the standard and affecting user experience or device safety, the power consumption limit needs to be lowered in advance (for example, PL1min-ΔP2) to ensure that the surface temperature is controlled within a safe range. The specific adjustment amount ΔP2 is calculated by a specific function h(VST,T_env) to ensure the scientificity and rationality of the adjustment.

[0126] Temperature protection point: VST-ΔT2, where ΔT2 is calculated by a specific function k(VST,T_env), ensuring dynamic adjustment of the temperature protection point and switching to the high temperature performance mode parameter setting table, taking into account both performance and surface temperature.

[0127] The above specific functions in the present disclosure are intended to implement the adjustment of the increment, and any function that can implement the increment adjustment may be within the coverage of the present disclosure.

[0128] It can be seen that the present disclosure can adapt to variable temperature environments, so that the performance of electronic equipment is greatly improved.

[0129] The present disclosure also provides a data processing device, such as Figure 7 As shown, the device comprises:

[0130] A first obtaining unit 701 is used to obtain a first target temperature of the electronic device under operation of a first performance parameter, wherein the first target temperature includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device;

[0131] A second obtaining unit 702 is used to input the first target temperature into the first prediction model through the transmission channel to obtain a second target temperature of the electronic device, where the second target temperature is used to characterize the predicted surface temperature of the electronic device;

[0132] The first determination unit 703 is used to determine whether to adjust the first performance parameter to the second performance parameter based on the second target temperature and the standard temperature of the electronic device under the first performance parameter; wherein the standard temperature is obtained based on the ambient temperature level when the electronic device operates with the first performance parameter.

[0133] In some embodiments, the apparatus further comprises a third obtaining unit, configured to:

[0134] Obtaining timing data and non-timing data when the electronic device operates with the first performance parameter, wherein the timing data includes at least one of a processor temperature, a processor usage rate, and a processor power consumption, and the non-timing data includes at least one of an ambient humidity and an ambient air pressure;

[0135] Based on the statistical characteristics of time series data and non-time series data, a feature vector is obtained;

[0136] Inputting the feature vector into a second prediction model to obtain an ambient temperature level of the electronic device when the electronic device is operated with the first performance parameter;

[0137] Based on the ambient temperature level, a standard temperature of the electronic device under a first performance parameter is obtained.

[0138] In some embodiments, the third obtaining unit is further used to:

[0139] Preprocess time series data;

[0140] Calculate statistics on preprocessed time series data;

[0141] The calculation results are used as statistical features of time series data.

[0142] In some embodiments, the apparatus comprises a first training unit configured to:

[0143] Obtaining first sample data and a first sample label of the electronic device under target performance parameter operation, wherein the first sample data includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device under the target performance parameter; and the first sample label includes a first surface temperature and a second surface temperature under the target performance parameter;

[0144] The first sample data and the first sample label are input into the linear regression model to be trained to train the linear regression model to be trained, thereby obtaining a first prediction model.

[0145] In some embodiments, the apparatus comprises a second training unit for:

[0146] Obtaining second sample data and second sample labels of the electronic device under operation of multiple performance parameters, wherein the second sample data includes a timing sample and a non-timing sample, and the second sample label includes an ambient temperature level of the electronic device under each performance parameter;

[0147] Based on the statistical characteristics of time series samples and non-time series samples, a sample feature vector is obtained;

[0148] The sample feature vector is input into the long short-term memory model to be trained to train the long short-term memory model and obtain a second prediction model.

[0149] In some embodiments, the second obtaining unit 702 is further configured to:

[0150] Preprocessing the first target temperature;

[0151] The preprocessed first target temperature is input into the first prediction model.

[0152] In some embodiments, the first determining unit 703 is configured to:

[0153] In response to the second target temperature and the standard temperature of the electronic device under the first performance parameter being different or not similar, determining to adjust the first performance parameter to the second performance parameter;

[0154] In response to the second target temperature and the standard temperature of the electronic device under the first performance parameter being the same or similar, it is determined not to adjust the first performance parameter to the second performance parameter.

[0155] It should be noted that the data processing device of the embodiment of the present application solves the problem in a principle similar to that of the aforementioned data processing method. Therefore, the implementation process and implementation principle of the data processing device can refer to the description of the implementation process and implementation principle of the aforementioned method, and the repeated parts will not be repeated.

[0156] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0157] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0158] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0159] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0160] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

[0161] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0162] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0163] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0164] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0165] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0166] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0167] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0168] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0169] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A data processing method, characterized in that: include: Obtaining a first target temperature of the electronic device when the electronic device is operating at a first performance parameter, wherein the first target temperature includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device; Inputting the first target temperature into the first prediction model through the transmission channel to obtain a second target temperature of the electronic device, where the second target temperature is used to characterize the predicted surface temperature of the electronic device; Based on the second target temperature and the standard temperature of the electronic device under the first performance parameter, it is determined whether to adjust the first performance parameter to the second performance parameter; wherein the standard temperature is obtained based on the ambient temperature level of the electronic device when it operates with the first performance parameter.

2. The method according to claim 1, characterized in that The standard temperature of the electronic device is obtained based on the ambient temperature level of the electronic device when the electronic device is operated with the first performance parameter, and includes: Obtaining timing data and non-timing data when the electronic device operates with the first performance parameter, wherein the timing data includes at least one of a processor temperature, a processor usage rate, and a processor power consumption, and the non-timing data includes at least one of an ambient humidity and an ambient air pressure; Based on the statistical characteristics of time series data and non-time series data, a feature vector is obtained; Inputting the feature vector into a second prediction model to obtain an ambient temperature level of the electronic device when the electronic device is operated with the first performance parameter; Based on the ambient temperature level, a standard temperature of the electronic device under a first performance parameter is obtained.

3. The method according to claim 2, characterized in that The method further comprises: Preprocess time series data; Calculate statistics on preprocessed time series data; The calculation results are used as statistical features of time series data.

4. The method according to claim 1, characterized in that: The method further comprises: Obtaining first sample data and a first sample label of the electronic device under target performance parameter operation, wherein the first sample data includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device under the target performance parameter; and the first sample label includes a first surface temperature and a second surface temperature under the target performance parameter; The first sample data and the first sample label are input into the linear regression model to be trained to train the linear regression model to be trained, thereby obtaining a first prediction model.

5. The method according to claim 2 or 3, characterized in that: The method further comprises: Obtaining second sample data and second sample labels of the electronic device under operation of multiple performance parameters, wherein the second sample data includes a timing sample and a non-timing sample, and the second sample label includes an ambient temperature level of the electronic device under each performance parameter; Based on the statistical characteristics of time series samples and non-time series samples, a sample feature vector is obtained; The sample feature vector is input into the long short-term memory model to be trained to train the long short-term memory model and obtain a second prediction model.

6. The method according to claim 1, characterized in that The method further comprises: Preprocessing the first target temperature; The preprocessed first target temperature is input into the first prediction model.

7. The method according to claim 1, characterized in that The determining whether to adjust the first performance parameter to the second performance parameter based on the first target temperature and the standard temperature of the electronic device under the first performance parameter includes: In response to the second target temperature and the standard temperature of the electronic device under the first performance parameter being different or not similar, determining to adjust the first performance parameter to the second performance parameter; In response to the second target temperature and the standard temperature of the electronic device under the first performance parameter being the same or similar, it is determined not to adjust the first performance parameter to the second performance parameter.

8. A data processing device, characterized in that: include: A first obtaining unit, configured to obtain a first target temperature of the electronic device when the electronic device is operating with a first performance parameter, wherein the first target temperature includes at least one of a processor temperature, a circuit board temperature, and an internal temperature of the electronic device; A second obtaining unit is used to input the first target temperature into the first prediction model through the transmission channel to obtain a second target temperature of the electronic device, where the second target temperature is used to characterize the surface temperature of the electronic device; The first determination unit is used to determine whether to adjust the first performance parameter to the second performance parameter based on the second target temperature and the standard temperature of the electronic device under the first performance parameter; wherein the standard temperature is obtained based on the ambient temperature level when the electronic device operates with the first performance parameter.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to make a computer execute the method according to any one of claims 1-7.

Images