Power consumption optimization method and device, terminal equipment and storage medium

Abstract

The embodiment of the invention relates to the technical field of communication, in particular to a power consumption optimization method and device, terminal equipment and a storage medium, the method is applied to the terminal equipment, and the method comprises the following steps: acquiring modem power consumption related data of a target scene; extracting power consumption data characteristics from the modem power consumption related data; obtaining first predicted power consumption corresponding to the power consumption data characteristics in the target scene through a prediction model according to the power consumption data characteristics; the target scene is at least one scene; by judging the first predicted power consumption and the preset power consumption threshold value corresponding to the target scene, the power consumption strategy corresponding to the target scene is adjusted, the power consumption of the modem is reduced, the endurance time of the terminal equipment is prolonged, and the user experience is further improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a power consumption optimization method, apparatus, terminal equipment and storage medium. Background Art

[0002] With the rapid development of technology, smartphones have higher requirements for data transmission rate and network stability. At the same time, the battery life of mobile phones has become more prominent. As the core module responsible for communication in mobile phones, the power consumption of modems has a significant impact on the overall battery life of mobile phones. While pursuing high data transmission rates and complex communication environments, how to effectively reduce unnecessary modem power consumption has become an urgent problem to be solved. Summary of the invention

[0003] The embodiments of the present application provide a modem power consumption optimization method, apparatus, terminal device, and storage medium, which can effectively reduce the power consumption of the modem, extend the battery life of the terminal device, and further improve the user experience.

[0004] A first aspect of the present application provides a power consumption optimization method, which is applied to a terminal device, and the method includes:

[0005] Acquire the modem power consumption related data of the target scene; extract the power consumption data features from the modem power consumption related data;

[0006] According to the power consumption data characteristics, a first predicted power consumption corresponding to the power consumption data characteristics in the target scenario is obtained through a prediction model; the target scenario is at least one scenario; by judging the size of the first predicted power consumption and a preset power consumption threshold corresponding to the target scenario, the power consumption strategy corresponding to the target scenario is adjusted.

[0007] In some embodiments, adjusting the power consumption strategy corresponding to the target scenario by judging the first predicted power consumption and the preset power consumption threshold corresponding to the target scenario includes:

[0008] If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the modem power consumption strategy to reduce power consumption;

[0009] If the first predicted power consumption is less than the preset power consumption threshold, the power consumption is increased by adjusting the modem power consumption strategy.

[0010] In some embodiments, the priority of the modem parameters that affect the power consumption of the target scenario is pre-set, and the higher the priority, the greater the impact on the power consumption reduction of the target scenario. If the first predicted power consumption is greater than the preset power consumption threshold, the power consumption is reduced by adjusting the modem power consumption strategy, including:

[0011] If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting to obtain a second predicted power consumption;

[0012] If the second predicted power consumption is greater than the preset power consumption threshold, the second high priority modem parameter setting is adjusted to obtain a third predicted power consumption, and so on, until the obtained predicted power consumption is less than or equal to the preset power consumption threshold.

[0013] In some embodiments, the priority of the modem parameters that affect the power consumption of the target scenario is pre-set, and the higher the priority, the greater the impact on the power consumption improvement of the target scenario. If the first predicted power consumption is less than the preset power consumption threshold, the power consumption is increased by adjusting the modem power consumption strategy, including:

[0014] If the first predicted power consumption is less than the preset power consumption threshold, adjusting the first high priority modem parameter setting to obtain a second predicted power consumption;

[0015] If the second predicted power consumption is less than the preset power consumption threshold, the second high priority modem parameter setting is adjusted to obtain a third predicted power consumption, and so on, until the obtained predicted power consumption is equal to the preset power consumption threshold.

[0016] In some embodiments, if the target scene includes multiple sub-scenes, the power consumption priorities of the multiple sub-scenes are pre-set, and the power consumption of the sub-scene with a higher priority has a greater impact on the power consumption reduction of the target scene. If the first predicted power consumption is greater than the preset power consumption threshold, the first high priority modem parameter setting is adjusted to obtain the second predicted power consumption, including:

[0017] If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting of the first high priority sub-scenario to obtain a second predicted power consumption;

[0018] If the second predicted power consumption is greater than the preset power consumption threshold, adjusting the second high priority modem parameter setting to obtain a third predicted power consumption, and so on, until the obtained predicted power consumption is less than or equal to the preset power consumption threshold, including:

[0019] If the second predicted power consumption is greater than the preset power consumption threshold, adjust the second high priority modem parameter setting of the first high priority sub-scenario to obtain the third predicted power consumption; after the preset number of modem parameter settings of the first high priority sub-scenario are adjusted, if the obtained predicted power consumption of the first high priority sub-scenario is greater than the preset power consumption threshold, adjust the modem parameter setting of the second high priority sub-scenario until the obtained predicted power consumption is less than or equal to the preset power consumption threshold.

[0020] In some embodiments, if the target scenario includes multiple sub-scenarios, if the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting to obtain a second predicted power consumption includes:

[0021] Acquire non-critical sub-scenes, wherein the non-critical sub-scenes include scenes whose usage frequency in a preset historical time period is lower than a preset frequency threshold or scenes whose usage frequency ranks in the bottom preset ranking among the current multiple sub-scenes, and / or other sub-scenes other than the preset critical sub-scenes;

[0022] If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting of the non-critical sub-scenario to obtain a second predicted power consumption;

[0023] If the second predicted power consumption is greater than the preset power consumption threshold, the second high priority modem parameter setting of the non-critical sub-scenario is adjusted to obtain a third predicted power consumption until the obtained predicted power consumption is less than or equal to the preset power consumption threshold.

[0024] In some embodiments, the prediction model includes: a deep neural network DNN, a convolutional neural network CNN, a recurrent neural network RNN ​​or a reinforcement learning model.

[0025] A second aspect of the present application provides a power consumption optimization device, which is applied to a terminal device, and the device includes:

[0026] Acquisition module: acquiring the modem power consumption related data of the target scene; extracting the power consumption data features from the modem power consumption related data;

[0027] Processing module: obtaining a first predicted power consumption corresponding to the power consumption data feature in the target scenario through a prediction model according to the power consumption data feature; the target scenario is at least one scenario; adjusting the power consumption strategy corresponding to the target scenario by judging the size of the first predicted power consumption and a preset power consumption threshold corresponding to the target scenario.

[0028] A third aspect of the present application provides a terminal device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the power consumption optimization method described in any one of the first aspect of the present application when executing the computer program.

[0029] The fourth aspect of the present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the power consumption optimization method described in any one of the embodiments of the first aspect of the present application are implemented.

[0030] The technical solution provided by the embodiment of the present application includes at least the following beneficial effects:

[0031] By acquiring the modem power consumption related data of the target scenario; extracting the power consumption data features from the modem power consumption related data; obtaining the first predicted power consumption corresponding to the power consumption data features in the target scenario through a prediction model according to the power consumption data features; the target scenario is at least one scenario; by judging the first predicted power consumption and the size of the preset power consumption threshold corresponding to the target scenario, adjusting the power consumption strategy corresponding to the target scenario, a suitable modem power consumption strategy can be formulated according to the needs of different scenarios, and the power consumption of the modem can be effectively reduced while ensuring the communication performance, thereby further improving the endurance of the terminal device. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of a flow chart of a power consumption optimization method proposed in an embodiment of the present application;

[0033] Figure 2 A flowchart of another power consumption optimization method proposed in an embodiment of the present application;

[0034] Figure 3 A flowchart of another power consumption optimization method proposed in an embodiment of the present application;

[0035] Figure 4 A flowchart of another power consumption optimization method proposed in an embodiment of the present application;

[0036] Figure 5 A flowchart of another power consumption optimization method proposed in an embodiment of the present application;

[0037] Figure 6 A schematic diagram of the structure of a device for the power consumption optimization method proposed in an embodiment of the present application;

[0038] Figure 7 A schematic diagram of the structure of another device of the power consumption optimization method proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0040] In order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first" and "second" are used to distinguish the same items or similar items with substantially the same functions and effects. For example, the first instruction and the second instruction are to distinguish different user instructions, and their order is not limited. Those skilled in the art can understand that the words "first" and "second" do not limit the quantity and execution order, and the words "first" and "second" do not necessarily limit them to be different.

[0041] It should be noted that, in the embodiments of the present application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0042] In addition, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can mean: a, or b, or c, or a and b, or a and c, or b and c, or a, b and c, where a, b, c can be single or multiple.

[0043] It should be noted that in the embodiments of the present application, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0044] With the rapid development of technology, smartphones have higher and higher requirements for data transmission rate and network stability. At the same time, the problem of mobile phone battery life has become more prominent. As the core module responsible for communication in mobile phones, the power consumption of modems has a significant impact on the overall battery life of mobile phones. While pursuing high data transmission rates and complex communication environments, how to effectively reduce the power consumption of modems has become an urgent problem to be solved in the industry.

[0045] Power consumption is a measure of the efficiency of an electronic device or system in converting electrical energy into other forms of energy during operation, usually expressed in watts (W). It includes static power consumption, which is the power consumption caused by internal leakage current when the device is idle; dynamic power consumption, which is closely related to the activity of the device when performing tasks, such as processor calculations or data transmission; idle power consumption, which is the power consumption of the device when it is on standby; peak power consumption, which is the maximum power consumption of the device when it is operating at high load; and average power consumption, which is the average level of power consumption of the device over a certain period of time. For portable devices such as smartphones and laptops, power consumption is directly related to battery life, while for data centers and servers, power consumption is related to operating costs and cooling requirements. Reducing power consumption not only saves energy and reduces costs, but also reduces device heat generation, improves stability and reliability, and is environmentally friendly because it helps reduce greenhouse gas emissions during power generation.

[0046] A modem is a network hardware device that can convert digital signals into analog signals for transmission over analog communication lines such as telephone lines and radio waves. It can also convert received analog signals back into digital signals for use by digital devices. It not only supports data transmission, but also has error detection and correction functions to ensure data accuracy, and can improve transmission efficiency through data compression. Modems also support encryption technology to protect data security and can adapt to different communication frequency bands. As technology advances, modem firmware can be updated through software to improve performance and security. They can be external devices or built into devices such as smartphones, tablets, and laptops.

[0047] The power consumption of a modem is affected by many factors, including data transmission, signal strength, network type, operating mode, hardware design, software optimization, usage frequency, power-saving mode, environmental factors, and equipment maintenance. During data transmission, the greater the amount of data transmitted, the more power the modem requires to process and send data; the strength of the signal will also affect power consumption, because the modem needs to consume more energy to search and maintain weak signals; different network types, such as 2G to 5G, have different effects on power consumption, among which the new generation of network technology is usually designed to be more energy-efficient; the working mode of the modem will also affect power consumption, for example, the power consumption is the lowest when it is not connected, and the power consumption is the highest when it is activated; hardware design, including the chip's process technology and power management capabilities, is directly related to power consumption; the degree of optimization of firmware and software will also affect power consumption, and a good power management strategy can effectively reduce unnecessary energy consumption; the more frequently the modem is used and the longer it works, the more power consumption it will have; supported energy-saving modes, such as modem sleep mode, light sleep mode, and deep sleep mode, can reduce power consumption when not in use; environmental factors, such as temperature and humidity, may also affect the power consumption of the modem because they may affect the heat dissipation efficiency of the device; finally, cleanliness and good ventilation of the device can help improve operating efficiency and extend its service life, while also affecting power consumption.

[0048] How to comprehensively consider and optimize these factors, effectively reduce unnecessary modem power consumption, extend the service life of the equipment, and reduce energy consumption is an urgent problem to be solved.

[0049] Based on this, the embodiment of the present application proposes a method for optimizing modem power consumption. By acquiring the modem power consumption related data of the target scene; extracting the power consumption data features from the modem power consumption related data; obtaining the first predicted power consumption corresponding to the power consumption data features in the target scene through a prediction model according to the power consumption data features; the target scene is at least one scene; by judging the size of the preset power consumption threshold corresponding to the first predicted power consumption and the target scene, adjusting the power consumption strategy corresponding to the target scene, a suitable modem power consumption strategy can be formulated according to the needs of different scenes, and under the premise of ensuring communication performance, the unnecessary power consumption of the modem can be effectively reduced, and the endurance of the terminal device can be further improved.

[0050] Exemplarily, the power consumption optimization method proposed in the embodiment of the present application is applied to a terminal device;

[0051] In some possible embodiments, the terminal devices include but are not limited to the following categories: smart phones, tablet computers, laptops, IoT devices and other mobile devices. In addition, the power consumption optimization method can also be applied to vehicle communications, drones and other application fields to achieve more intelligent and efficient power consumption management. The operating system running on the terminal device may include but is not limited to Android system, IOS system, Linux, Windows, Unix, etc. This application embodiment is not specifically limited.

[0052] In order to have a more detailed understanding of how the power consumption optimization method proposed in this application adjusts the power consumption of the modem, the following is a detailed step-by-step process of the power consumption optimization method. Figure 1 As shown:

[0053] Step 101: Obtaining data related to the power consumption of a modem in a target scenario;

[0054] For example, the data related to the modem power consumption of the target scene includes the relevant data in the current preset time period of the target scene. In order to more comprehensively understand the background and trend of power consumption changes, the relevant data in the historical time period is also important. These historical data can provide past power consumption patterns, which are helpful to identify anomalies or verify the effectiveness of energy-saving measures.

[0055] For example, in order to collect data related to modem power consumption, multiple sensors and software algorithms built into the terminal device are usually used.

[0056] For example, a temperature sensor is responsible for monitoring the temperature of the modem during operation, because an increase in power consumption often leads to an increase in temperature. Voltage and current sensors directly measure the power consumed by the modem and provide accurate power consumption data. In addition, environmental sensors can detect surrounding environmental factors, such as signal strength, which may directly affect the energy consumption of the modem.

[0057] Exemplarily, in terms of software, data acquisition software periodically reads data from these sensors and transmits it to a data processing unit. The power consumption analysis algorithm analyzes the collected data to identify power consumption patterns and find periods of abnormally high power consumption.

[0058] Data related to modem power consumption obtained through the built-in sensors and software algorithms of the terminal device, including but not limited to signal strength, data transmission rate, network type (2G / 3G / 4G / 5G), user behavior patterns (such as calls, Internet access, video streaming, etc.), battery status, device temperature, etc.

[0059] In order to use the prediction model more accurately to predict the power consumption under different operating conditions, at this stage, the embodiment of the present application will conduct an in-depth analysis of the collected modem power consumption data to extract key power consumption data features.

[0060] Step 102: extracting power consumption data features from the modem power consumption related data;

[0061] Features are extracted from the data collected in step 101, which will be used to train the prediction model. The data features include historical power consumption data, network usage patterns, timestamps (to identify daily usage patterns), geographic locations, etc.

[0062] Among them, data feature extraction is the process of identifying and extracting key information from raw data. It is essential for simplifying data sets, reducing noise, reducing dimensions, identifying patterns, and improving the performance of machine learning models. Through feature extraction, we can compress large amounts of complex data into smaller feature sets for easy storage, transmission, and visualization, while improving the interpretability and adaptability of the algorithm. In addition, feature extraction also helps with data preprocessing, converting data into a format suitable for analysis and reducing the risk of overfitting. It also plays an important role in multimodal data processing. By integrating information from different types of data, it helps to discover hidden knowledge in the data and provide support for decision support systems and intelligent systems. Therefore, feature extraction is an indispensable step in the data analysis process.

[0063] Next, the extracted power consumption data features are input into the prediction model for model training to predict the power consumption in the target scenario. The detailed process is as shown in step 103.

[0064] Step 103: obtaining a first predicted power consumption corresponding to the power consumption data feature in the target scenario through a prediction model according to the power consumption data feature;

[0065] When predicting the power consumption of a modem in a target scenario, it is critical to select an appropriate prediction model.

[0066] For example, such as a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), or a reinforcement learning model. The model is trained using the collected historical data. The goal of the training is to enable the model to learn to predict the best power consumption adjustment strategy under a specific target scenario.

[0067] For example, the DNN model is suitable for processing complex nonlinear relationships and can predict power consumption by learning deep features of data.

[0068] CNN performs well in processing time series data and can capture the local features and temporal dependencies of power consumption data.

[0069] RNN: In particular, Long Short-Term Memory (LSTM) networks, which can take into account the effects of time delays and persistent features when processing time series data, are suitable for power consumption prediction.

[0070] Reinforcement learning models: These models can learn and optimize policies in dynamic environments and are very useful for adjusting power consumption policies in real time.

[0071] When training the model using collected historical data, the goal of this application is to have the model learn to predict the best power adjustment strategy in a specific scenario. For example, if historical data shows that reducing the operating frequency of the modem can significantly reduce power consumption at night when the network is not busy, the model can learn this pattern and apply this strategy in future predictions.

[0072] For example, a CNN model is used for prediction, and a neural network regression model with two convolutional layers is constructed. The model has a vertical convolution kernel and a horizontal convolution kernel, which respectively learn the correlation between signal activity and power consumption at adjacent positions and time. Through training, the CNN model can learn the nonlinear relationship between features and power consumption labels, thus having an advantage in accuracy.

[0073] By inputting data features into the machine learning model and training it, the predicted power consumption can be obtained. Next, the corresponding power consumption strategy of the target scenario is optimized based on the comparison between the predicted power consumption and the power consumption threshold of the target scenario, so as to reduce the power consumption of the modem while ensuring communication performance, and further improve the endurance of the terminal device.

[0074] After obtaining the first predicted power consumption, how to adjust the modem power consumption strategy? Step 104 provides further explanation.

[0075] Step 104: adjusting the power consumption strategy corresponding to the target scenario by determining the magnitude of the first predicted power consumption and a preset power consumption threshold corresponding to the target scenario.

[0076] According to the predicted power consumption of the machine learning model, compared with the size of the preset power consumption threshold corresponding to the target scenario, the power consumption strategy of the modem is adjusted. For example: reduce or increase the wake-up frequency and transmission power (TransmitPower, Tx Power) of the modem to match the current data transmission requirements. In wireless communications, Tx Power refers to the power level used by the device when sending a signal. This parameter has an important impact on the coverage, transmission quality and power consumption of the signal. When high-speed data transmission is not required, the modem is switched to low-power mode to further optimize the modem's signal measurement, network search and ping-pong switching processes, and reduce unnecessary modem-side protocol power consumption during standby.

[0077] Exemplarily, the preset power consumption threshold corresponding to the target scenario can first calculate the average current within a specified time from the load conditions in the actual scenario according to a software algorithm, and then calculate the average power consumption based on the calculated average current and the operating voltage of the device, and set the power consumption threshold accordingly.

[0078] For example, the average current in a general network search scenario is 90mA, and in a screen-off standby scenario it is 10mA, and so on.

[0079] By determining the first predicted power consumption and the preset power consumption threshold corresponding to the target scenario, when adjusting the power consumption strategy corresponding to the target scenario, the power consumption strategy is adjusted in the following two cases, and the adjustment steps are as follows: Figure 2-Figure 3 As shown:

[0080] The first case is: if the first predicted power consumption is greater than the preset power consumption threshold, the power consumption is reduced by adjusting the modem power consumption strategy;

[0081] The second situation is: if the first predicted power consumption is less than the power consumption threshold, the power consumption is increased by adjusting the modem power consumption strategy.

[0082] In the first case: before adjusting the modem power consumption strategy, the priority of the modem parameters that affect the power consumption of the target scenario is pre-set, the higher the priority, the greater the impact on the power consumption reduction of the target scenario, and if the first predicted power consumption is greater than the preset power consumption threshold.

[0083] Exemplarily, the preset power consumption threshold is determined based on the specific needs of the device, usage scenarios, and user experience requirements, and multiple factors need to be considered comprehensively to ensure that power consumption is minimized and battery life is extended while meeting basic communication quality.

[0084] First, consider device specifications and battery capacity. For example, a smartphone with a battery capacity of 3000mAh should maintain low power consumption when in standby mode at night. Next, analyze user needs and usage scenarios to ensure that the device can continue to operate for at least 8 hours and maintain basic communication quality when in standby mode at night.

[0085] Then, referring to historical data and benchmark test results, it was found that controlling power consumption within 0.3W can significantly extend battery life. At the same time, referring to industry standards and competitors' performance, a competitive power consumption threshold was set. For example, the power consumption of similar devices in standby mode at night usually does not exceed 0.4W, while the power consumption of similar devices of competitors in standby mode at night is about 0.35W.

[0086] Finally, combined with user feedback and market research, we understand users' specific expectations for power consumption. User feedback shows that most users want to minimize battery consumption during night standby. Taking all the above factors into consideration, we finally determined that the preset power consumption threshold for night standby scenarios is 0.3W, which can not only meet users' battery life needs, but also ensure basic communication quality. Through scientific methods and meticulous analysis, we can set a reasonable and effective power consumption threshold to achieve the best power consumption optimization effect.

[0087] For example, the adjustment steps of the power consumption strategy in the first case are as follows: Figure 2 shown.

[0088] Step 201: If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting to obtain a second predicted power consumption;

[0089] Exemplarily, the first predicted power consumption is obtained by a prediction model, such as Figure 1 The detailed steps are as follows:

[0090] Step 101: Obtaining data related to the power consumption of a modem in a target scenario;

[0091] Step 102: extracting power consumption data features from the modem power consumption related data;

[0092] Step 103: obtaining a first predicted power consumption corresponding to the power consumption data feature in the target scenario through a prediction model according to the power consumption data feature;

[0093] Exemplarily, the second predicted power consumption is obtained in the same manner as the first predicted power consumption, except that the input of the prediction model is different. The input of the second prediction model is the data feature after adjusting the first high priority modem parameter setting.

[0094] It should be understood that the detailed explanation and specific operation of each step have been described in detail in the above embodiments and will not be repeated here.

[0095] Exemplarily, the modem parameters that can be adjusted include: transmit power, modulation mode, coding mode, sleep / wake-up period, signal measurement period, signal reporting period, ping-pong switching suppression, uplink transmit power suppression, etc.

[0096] By adjusting these modem parameters, power consumption can be optimized in different usage scenarios, ensuring that power consumption is minimized or increased while meeting basic communication quality. The specific adjustment strategy needs to be flexibly selected based on the actual application scenario and user needs.

[0097] Step 202: If the second predicted power consumption is greater than the preset power consumption threshold, adjust the second high priority modem parameter setting to obtain a third predicted power consumption;

[0098] Continue to adjust subsequent priority modem parameters until the obtained predicted power consumption is less than or equal to the preset power consumption threshold.

[0099] Exemplarily, the first high priority has a greater impact on power consumption reduction than the second high priority, and so on, the nth high priority is greater than the n+1th high priority.

[0100] For example, in a user driving scenario, the first predicted power consumption is 1.2W, and the preset power consumption threshold is 1.0W. In order to reduce power consumption, the first high priority parameter is adjusted first: transmit power. The transmit power is reduced from the default 23dBm to 20dBm, and the power consumption prediction is performed again, and the second predicted power consumption is 1.15W.

[0101] Since the second predicted power consumption of 1.15W is still greater than the preset power consumption threshold of 1.0W, the second high priority parameter, the encoding mode, is adjusted. The encoding mode is changed from Turbo encoding to convolutional encoding, and the power consumption is predicted again, and the third predicted power consumption is 1.08W.

[0102] The third predicted power consumption of 1.08W is still greater than the preset power consumption threshold of 1.0W, so the third high priority parameter - sleep / wake cycle is adjusted. The sleep / wake cycle is changed from 1 second to 2 seconds, and a new power consumption prediction is performed, and the fourth predicted power consumption is 0.98W.

[0103] At this time, the fourth predicted power consumption of 0.98W is less than the preset power consumption threshold of 1.0W, and the condition is met, so the adjustment is stopped and the final parameter setting is applied. By gradually adjusting the transmit power, encoding method and sleep / wake cycle, the predicted power consumption is successfully reduced to below 1.0W, thereby achieving power consumption optimization.

[0104] For example, in the night standby scenario, the modem can be put into sleep mode as soon as possible by reducing the signal measurement cycle, suppressing signal reporting, turning off the data switch and the WiFi switch, etc., thereby reducing the wake-up frequency of the modem and thus reducing power consumption.

[0105] Exemplarily, in an embodiment of the present application, in the night standby scene, the first predicted power consumption initially predicted by the prediction model is 0.5W, and the preset power consumption threshold is 0.3W. In order to reduce power consumption, the signal measurement cycle is first set to the first high priority, extended from 10 seconds to 60 seconds, and the second predicted power consumption is 0.45W after re-prediction. Then, the signal reporting cycle is set to the second high priority, extended from 30 seconds to 120 seconds, and the third predicted power consumption is 0.4W after re-prediction. Then, turning off the data switch and stopping data transmission are set to the third high priority, and the predicted power consumption is further reduced to 0.35W (the fourth predicted power consumption). By analogy, finally, turning off the WiFi switch, stopping the WiFi connection, and finally predicting the power consumption to be 0.3W, which is equal to the preset power consumption threshold. By gradually adjusting parameters such as the signal measurement cycle, the signal reporting cycle, the data switch, and the WiFi switch, the predicted power consumption is successfully reduced from 0.5W to 0.3W, reaching the preset power consumption threshold, thereby significantly reducing the power consumption in the night standby state and extending the battery life.

[0106] In addition, ping-pong scenario: In LTE networks, in order to prevent the power consumption and communication performance impact caused by the terminal constantly switching between cells, a strategy to suppress ping-pong switching can be adopted.

[0107] For example, in the no-service network search scenario, in areas with poor network signals or no service, the network search cycle can be extended to reduce unnecessary network search actions of the modem, thereby reducing power consumption. The operation of extending the network search cycle can be set to the first highest priority. If the predicted power consumption after adjustment is less than or equal to the preset threshold value, the optimization is stopped. Otherwise, the second highest priority parameters are adjusted, and so on.

[0108] The power consumption adjustment strategy in the first case ensures that the power consumption is minimized and the battery life of the device is extended while ensuring the basic communication quality. The detailed adjustment parameters and methods of each step can be flexibly selected according to the actual application scenario and device characteristics.

[0109] In the second case, if the first predicted power consumption is less than the power consumption threshold, the power consumption is increased by adjusting the modem power consumption strategy. The priority of the modem parameters affecting the power consumption of the target scenario needs to be pre-set, and the higher the priority, the greater the impact on the power consumption increase of the target scenario.

[0110] Exemplarily, the first high priority has a greater impact on power consumption reduction than the second high priority, and so on, the nth high priority has a greater impact on power consumption reduction than the n+1th high priority.

[0111] For example, the adjustment steps of the power consumption strategy in the second case are as follows: Figure 3 As shown;

[0112] Step 301: If the first predicted power consumption is less than the preset power consumption threshold, adjusting the first high priority modem parameter setting to obtain a second predicted power consumption;

[0113] Step 302: If the second predicted power consumption is less than the preset power consumption threshold, adjust the second high priority modem parameter setting to obtain a third predicted power consumption;

[0114] Continue adjusting subsequent priority modem parameters until the obtained predicted power consumption is equal to the preset power consumption threshold.

[0115] Exemplarily, the adjustment may be stopped when the predicted power consumption is approximately equal to the preset power consumption threshold, as long as the higher requirements of the user's current target scenario are met.

[0116] For example, in a scenario where the user is walking and the signal strength is good, the initial first predicted power consumption is 0.85W, and the preset power consumption threshold is 1.0W. In order to improve power consumption to make full use of the available power consumption budget, the first high priority parameter, the transmit power, is adjusted first. The transmit power is increased from the default 17dBm to 20dBm, and the power consumption prediction is re-performed, resulting in a second predicted power consumption of 0.95W.

[0117] Since the second predicted power consumption of 0.95W is still less than the preset power consumption threshold of 1.0W, the second high priority parameter - modulation mode is adjusted next. QAM (Quadrature Amplitude Modulation) is a digital modulation technology used to transmit data in wireless and wired communications. QAM represents different symbols by simultaneously changing the amplitude and phase of the carrier signal, thereby transmitting more data in the same bandwidth. Adjusting the second high priority parameter - modulation mode can change the modulation mode from 16QAM to 64QAM, where each symbol of 64QAM can carry 6 bits of information, while each symbol of 16QAM can only carry 4 bits of information. Therefore, using 64QAM can significantly increase the data transmission rate. Continue to perform power consumption prediction again, and the third predicted power consumption is 0.98W.

[0118] The third predicted power consumption of 0.98W is still less than the preset power consumption threshold of 1.0W, so the third high priority parameter - encoding mode is adjusted. The encoding mode is changed from convolutional coding to Turbo coding, and a new power consumption prediction is performed, and the fourth predicted power consumption is 1.0W. Among them, the encoding and decoding process of Turbo coding is more complicated than convolutional coding, requiring more computing resources and time. Higher computing complexity usually leads to higher power consumption.

[0119] At this time, the fourth predicted power consumption of 1.0W is equal to the preset power consumption threshold of 1.0W, and the condition is met, so the adjustment is stopped and the final parameter setting is applied. By gradually adjusting the transmission power, modulation mode and coding mode, the predicted power consumption is successfully increased to 1.0W, thereby achieving power consumption optimization.

[0120] This approach ensures that the available power budget is maximized while ensuring basic communication quality, providing better performance and user experience. The detailed adjustment parameters and methods of each step can be flexibly selected according to the actual application scenario and device characteristics.

[0121] In addition to adjusting the power consumption strategy by comparing the predicted power consumption with the preset power consumption threshold as mentioned above, you can also predict a change in the usage scenario in the next time period by comparing the predicted power consumption with the preset power consumption threshold. For example, if it is predicted based on the user's usage habits that the screen will be in standby mode for the next few hours, consider entering the power consumption strategy for the screen-off standby scenario in advance; or if it is predicted that the device will continue to search the network, enter the network search power consumption optimization strategy in advance.

[0122] The above implementation discusses setting the modem parameter priority to reduce or increase the modem power consumption in the target scenario to meet the communication needs of the user. In addition, there may be other situations, for example, when the target scenario includes multiple sub-scenarios, how to adjust the power consumption strategy.

[0123] In some embodiments, if the target scene includes multiple sub-scenes, the power consumption priorities of the multiple sub-scenes are pre-set, and the higher the priority, the greater the impact of the power consumption of the multiple sub-scenes on the power consumption reduction of the target scene. If the first predicted power consumption is greater than the preset power consumption threshold, the first high priority modem parameter setting is adjusted to obtain the second predicted power consumption. The power consumption optimization of multiple sub-scenes includes the following steps, such as Figure 4 .

[0124] Step 401: If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting of the first high priority sub-scenario to obtain a second predicted power consumption;

[0125] Step 402: If the second predicted power consumption is greater than the preset power consumption threshold, adjust the second high priority modem parameter setting to obtain a third predicted power consumption, until the obtained predicted power consumption is less than or equal to the preset power consumption threshold.

[0126] If the second predicted power consumption is greater than the preset power consumption threshold, adjust the second high priority modem parameter setting of the first high priority sub-scene to obtain the third predicted power consumption, until the preset number of modem parameter settings of the first high priority sub-scene are adjusted, and then continue to adjust the modem parameters of the next sub-scene.

[0127] Step 403: When the predicted power consumption of the first high priority sub-scenario is greater than the preset power consumption threshold, adjust the modem parameter settings of the second high priority sub-scenario.

[0128] Until the obtained predicted power consumption is equal to the preset power consumption threshold, no further scene power consumption optimization is required.

[0129] An example of multi-scenario power consumption optimization is as follows:

[0130] In some embodiments, the target scenario includes multiple sub-scenarios. In order to optimize power consumption more effectively, the power consumption priorities of these sub-scenarios can be pre-set. The higher the priority, the greater the impact of the power consumption of the sub-scenario on the overall power consumption. The following example illustrates how to gradually adjust the modem parameters in multiple sub-scenarios to reduce power consumption.

[0131] Exemplarily, the sub-scenarios included in the target scenario are: night standby scenario (first high priority), ping-pong switching scenario (second high priority), and no-service network search scenario (third high priority).

[0132] Among them, the first predicted power consumption output by the prediction model of the target scenario is 0.5W, and the preset power consumption threshold is 0.3W.

[0133] Exemplarily, the optimization steps in the embodiments of the present application are as follows:

[0134] 1. Adjust the modem parameters of the first highest priority sub-scene;

[0135] When the sub-scenario is a night standby scenario, the first highest priority parameter is set to the signal measurement period;

[0136] In the night standby sub-scenario, the initial first predicted power consumption is 0.5W, and the preset power consumption threshold is 0.3W. In order to reduce power consumption, the first high priority parameter, the signal measurement period, is adjusted first. The signal measurement period is extended from the initial setting of 10 seconds to 60 seconds, and the power consumption is re-predicted through the prediction model, and the second predicted power consumption is 0.45W.

[0137] In order to further reduce power consumption, the second highest priority parameter, the signal reporting period, is adjusted. The signal reporting period is extended from the initial setting of 30 seconds to 120 seconds, and the power consumption is re-predicted through the prediction model, and the third predicted power consumption is 0.4W.

[0138] In the night standby scenario, the third predicted power consumption is 0.4W, while the preset power consumption threshold is 0.3W. In order to further reduce power consumption, the third high priority parameter, the data switch, is adjusted next. The data switch is adjusted from the initially set on state to off, and the power consumption is re-predicted through the prediction model, and the fourth predicted power consumption is 0.35W. At this point, the predicted power consumption of 0.35W is still greater than the preset power consumption threshold of 0.3W, so continue to adjust the parameters of other sub-scenarios.

[0139] 2. Adjust the modem parameters of the second high priority sub-scenario;

[0140] Next, adjust the sub-scenario to a ping-pong switching scenario. The first high priority parameter is to suppress ping-pong switching. Adjust the ping-pong switching from the initially set allowed state to suppress ping-pong switching, and re-predict the power consumption through the prediction model to obtain the sixth predicted power consumption of 0.3W. At this point, the predicted power consumption of 0.3W is equal to the preset power consumption threshold of 0.3W, and the conditions are met. Stop adjusting and apply the final parameter setting. By gradually adjusting the signal measurement period, signal reporting period, data switch, and suppressing ping-pong switching, the predicted power consumption was successfully reduced from 0.5W to 0.3W, reaching the preset power consumption threshold.

[0141] This method ensures that power consumption is minimized and battery life is extended while ensuring basic communication quality. The adjustment parameters and methods of each step can be flexibly selected according to the actual application scenario and device characteristics.

[0142] In some embodiments, if the target scene includes multiple sub-scenes, the power consumption priorities of the multiple sub-scenes are pre-set. The higher the priority, the greater the impact of the power consumption of the multiple sub-scenes on the power consumption reduction of the target scene. If the first predicted power consumption is less than the preset power consumption threshold, the sub-scene with the greatest impact on the user's target scene can also be adjusted by setting the sub-scene priority. The adjustment of the modem parameters in the sub-scene is as follows: Figure 3 In the method shown, if the predicted power consumption still does not reach the preset threshold in this sub-scenario, the power consumption of the second sub-scenario can be further adjusted, and so on. The method proposed in the embodiment of the present application maximizes the user experience of the target scenario on the terminal device while ensuring that the predicted power consumption is within the preset power consumption threshold range.

[0143] In another embodiment, when setting the priority of power consumption reduction of a scene, it can also be determined by critical sub-scenes and non-critical sub-scenes, as shown in step 5.

[0144] Step 501: Acquire a non-critical sub-scene;

[0145] The non-critical sub-scenario includes a scenario whose usage frequency in a preset historical time period is lower than a preset frequency threshold or a scenario whose usage frequency ranks in the bottom preset position among the current multiple sub-scenarios, and / or other sub-scenario other than the preset critical sub-scenario;

[0146] For example, in the night standby scenario, we identified non-critical sub-scenarios by analyzing the log data of the past 30 days. Based on the preset frequency threshold (less than 5 times per day) and the bottom 3 usage frequency ranking conditions, the following sub-scenarios were identified as non-critical sub-scenarios:

[0147] Video streaming: used twice a day (below the preset frequency threshold and ranked last in frequency of use);

[0148] Music playback: used once a day (lower than the preset frequency threshold and ranked last in frequency of use);

[0149] Navigation: used once a day (lower than the preset frequency threshold and ranked last in frequency of use);

[0150] Games: 4 times per day (below the preset frequency threshold);

[0151] Email checking: used 3 times per day (below the preset frequency threshold);

[0152] Alternatively, the following sub-scenarios do not belong to the pre-set critical sub-scenarios (night standby, ping-pong switching, no-service network search) and can also be classified as non-critical sub-scenarios: such as data throughput and calls, social media.

[0153] These sub-scenarios are less frequently used in the night standby scenario or are not included in the key sub-scenarios. These non-key sub-scenarios can be adjusted more flexibly in the subsequent power consumption optimization process to further reduce the overall power consumption.

[0154] Exemplarily, a user may customize settings for key sub-scenes, for example, a call scene may be set as a key sub-scene.

[0155] Step 502: If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting of the non-critical sub-scenario to obtain a second predicted power consumption;

[0156] The first high-priority modem parameter setting of the non-critical sub-scenario is adjusted to reduce power consumption while ensuring the user's communication quality or basic needs. The non-critical sub-scenario is adjusted because these scenarios have less impact on user experience and communication quality, ensuring the performance of the critical sub-scenario is prioritized, and reducing the modem power consumption of the non-critical sub-scenario can better meet the user's basic needs.

[0157] Step 503: If the second predicted power consumption is greater than the preset power consumption threshold, adjust the second high priority modem parameter setting of the non-critical sub-scenario to obtain a third predicted power consumption;

[0158] If the third predicted power consumption is still greater than the preset power consumption threshold, then the modem parameter settings of the key sub-scenes are further adjusted to reduce power consumption. Of course, this operation is performed with the user's permission. If the user wants to reduce power consumption, that is, save power, the modem parameters of the user's key sub-scenes can be adjusted.

[0159] For example, in a sub-scenario, the priority setting of some sub-scenario can be defined by the user. For example, if the sub-scenario is that the user is watching videos, then when reducing the power consumption of this sub-scenario, the strategy for adjusting the sub-scenario to reduce power consumption should be set with a lower priority, and the power consumption of other sub-scenarios that do not affect the user's current video-watching needs should be adjusted first. In other words, the user can customize the video-watching scene as a key sub-scenario.

[0160] It should be understood that although Figure 1-5 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-5 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0161] In some embodiments, by learning the user's usage habits and preferences, the user's communication needs are predicted through a machine learning algorithm, and the modem power consumption settings are adjusted in advance to achieve more intelligent and efficient power consumption management.

[0162] In some embodiments, the power consumption of the modem can be further reduced by combining the hardware design of the modem with the machine learning algorithm. For example, the hardware of the modem uses low-power materials, improves the circuit design, or optimizes the signal processing algorithm.

[0163] In one embodiment, Figure 6 As shown, a power consumption optimization device is provided, including: an acquisition module 601 and a processing module 602, wherein:

[0164] Acquisition module 601: Acquisition of modem power consumption related data of a target scenario; Extraction of power consumption data features from the modem power consumption related data;

[0165] Processing module 602: obtaining a first predicted power consumption corresponding to the power consumption data feature in the target scenario through a prediction model according to the power consumption data feature; the target scenario is at least one scenario; adjusting the power consumption strategy corresponding to the target scenario by judging the size of the first predicted power consumption and a preset power consumption threshold corresponding to the target scenario.

[0166] For further limitations on the power consumption optimization device, please refer to the limitations on the power consumption optimization method above, which will not be repeated here. Each module in the above power consumption optimization device can be implemented in whole or in part by software, hardware, and a combination thereof. The above modules can be embedded in or independent of the processor in the terminal device in hardware form, or can be stored in the memory of the terminal device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0167] Another embodiment provides a computer-readable storage medium, which is used to store a computer program. This computer program includes instructions for implementing the method described in the embodiment of the present application. By installing this computer program on a computer, the computer can execute the corresponding method to optimize power consumption.

[0168] Another embodiment proposes that this embodiment provides a computer program product, which includes computer program codes. When these computer program codes are run on a computer, they enable the computer to implement the method proposed in the embodiment of the present application. In this way, the user can monitor blood pressure changes by using this computer program product.

[0169] For example, Figure 7 It is a schematic block diagram of a device for another power consumption optimization method provided in an embodiment of the present application.

[0170] Figure 7The power consumption optimization device 700 shown is composed of four main parts: a processor 701, a memory 702, a communication interface 703 and a bus 704. Each part has its specific function and role, and these components and their roles in power consumption optimization will be explained in detail below.

[0171] Processor 701 is the core component of the device, responsible for performing various computing tasks, including running power optimization algorithms, processing sensor data, training and predicting machine learning models, etc., and coordinating the work of various components to ensure that they can work together and efficiently; based on the collected data and prediction results, processor 701 can make real-time decisions and dynamically adjust the modem's operating mode and parameters to optimize power consumption.

[0172] Memory 702 is used to store various data, including collected current data, historical power consumption data, user behavior data, network condition data, etc. It also stores the software code and configuration files required to run the power consumption optimization algorithm, as well as the parameters and weights of the machine learning model, and is used as a temporary cache during data processing to store intermediate calculation results and temporary data. By storing a large amount of historical data and real-time data, memory 702 provides rich information support for power consumption optimization, ensures the stability and reliability of the system, and supports continuous improvement and adaptation to new usage scenarios.

[0173] The communication interface 703 is responsible for exchanging data with other devices or systems, supporting multiple communication protocols (such as USB, Wi-Fi, Bluetooth, etc.), ensuring the compatibility and reliability of data transmission, so that the device 700 can obtain the latest data in real time and promptly apply the optimized power consumption strategy to the actual device, while supporting remote monitoring and management.

[0174] As the main data transmission channel connecting the processor 701, the memory 702 and the communication interface 703, the bus 704 is responsible for transmitting data and instructions between various components, ensuring the correctness and timing of data transmission, and achieving high-speed data transmission and low-latency communication through efficient bus design, thereby improving overall performance and supporting multi-task parallel processing. This comprehensive approach not only improves the energy efficiency of the device, but also enhances the user experience and extends battery life.

[0175] It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0176] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor executes the instructions in the memory, and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0177] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0179] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0180] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0182] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0183] The above is only a specific implementation of the embodiment of the present application, but the protection scope of the embodiment of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the embodiment of the present application, which should be included in the protection scope of the embodiment of the present application. Therefore, the protection scope of the embodiment of the present application should be based on the protection scope of the claims.

Claims

1. A power consumption optimization method, characterized in that: Applied to a terminal device, the method comprises: Acquire the modem power consumption related data of the target scene; extract the power consumption data features from the modem power consumption related data; According to the power consumption data characteristics, a first predicted power consumption corresponding to the power consumption data characteristics in the target scenario is obtained through a prediction model; the target scenario is at least one scenario; by judging the size of the first predicted power consumption and a preset power consumption threshold corresponding to the target scenario, the power consumption strategy corresponding to the target scenario is adjusted.

2. The method according to claim 1, characterized in that The adjusting the power consumption strategy corresponding to the target scenario by judging the first predicted power consumption and the preset power consumption threshold corresponding to the target scenario includes: If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the modem power consumption strategy to reduce power consumption; If the first predicted power consumption is less than the preset power consumption threshold, the power consumption is increased by adjusting the modem power consumption strategy.

3. The method according to claim 2, characterized in that The priority of the modem parameter affecting the power consumption of the target scenario is pre-set, the higher the priority, the greater the impact on the power consumption reduction of the target scenario, if the first predicted power consumption is greater than the preset power consumption threshold, the power consumption is reduced by adjusting the modem power consumption strategy, including: If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting to obtain a second predicted power consumption; If the second predicted power consumption is greater than the preset power consumption threshold, the second high priority modem parameter setting is adjusted to obtain a third predicted power consumption, and so on, until the obtained predicted power consumption is less than or equal to the preset power consumption threshold.

4. The method according to claim 2, characterized in that: The priority of the modem parameter affecting the power consumption of the target scenario is pre-set, the higher the priority, the greater the impact on the power consumption improvement of the target scenario, if the first predicted power consumption is less than the preset power consumption threshold, the power consumption is increased by adjusting the modem power consumption strategy, including: If the first predicted power consumption is less than the preset power consumption threshold, adjusting the first high priority modem parameter setting to obtain a second predicted power consumption; If the second predicted power consumption is less than the preset power consumption threshold, the second high priority modem parameter setting is adjusted to obtain a third predicted power consumption, and so on, until the obtained predicted power consumption is equal to the preset power consumption threshold.

5. The method according to claim 3, characterized in that: If the target scene includes multiple sub-scenes, pre-setting the power consumption priorities of the multiple sub-scenes, the power consumption of the sub-scenes with higher priorities has a greater impact on the power consumption reduction of the target scene, and if the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting to obtain a second predicted power consumption, including: If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting of the first high priority sub-scenario to obtain a second predicted power consumption; If the second predicted power consumption is greater than the preset power consumption threshold, adjusting the second high priority modem parameter setting to obtain a third predicted power consumption until the obtained predicted power consumption is less than or equal to the preset power consumption threshold, including: If the second predicted power consumption is greater than the preset power consumption threshold, adjust the second high priority modem parameter setting of the first high priority sub-scenario to obtain the third predicted power consumption, and so on, until the preset number of modem parameter settings of the first high priority sub-scenario are adjusted, and if the obtained predicted power consumption of the first high priority sub-scenario is greater than the preset power consumption threshold, adjust the modem parameter setting of the second high priority sub-scenario until the obtained predicted power consumption is less than or equal to the preset power consumption threshold.

6. The method according to claim 3, characterized in that If the target scenario includes multiple sub-scenarios, if the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting to obtain a second predicted power consumption includes: Acquire non-critical sub-scenes, wherein the non-critical sub-scenes include scenes whose usage frequency in a preset historical time period is lower than a preset frequency threshold or scenes whose usage frequency ranks in the bottom preset ranking among the current multiple sub-scenes, and / or other sub-scenes other than the preset critical sub-scenes; If the first predicted power consumption is greater than the preset power consumption threshold, adjusting the first high priority modem parameter setting of the non-critical sub-scenario to obtain a second predicted power consumption; If the second predicted power consumption is greater than the preset power consumption threshold, adjust the second high priority modem parameter setting of the non-critical sub-scenario to obtain a third predicted power consumption, and so on, until the obtained predicted power consumption is less than or equal to the preset power consumption threshold.

7. The method according to claim 1, characterized in that The prediction model includes: a deep neural network DNN, a convolutional neural network CNN, a recurrent neural network RNN ​​or a reinforcement learning model.

8. A power consumption optimization device, applied to a terminal device, characterized in that: The device comprises: Acquisition module: acquiring the relevant data of the modem power consumption of the target scene; extracting the power consumption data features from the relevant data of the modem power consumption; Processing module: obtaining a first predicted power consumption corresponding to the power consumption data feature in the target scenario through a prediction model according to the power consumption data feature; the target scenario is at least one scenario; adjusting the power consumption strategy corresponding to the target scenario by judging the size of the first predicted power consumption and a preset power consumption threshold corresponding to the target scenario.

9. A terminal device, characterized in that: The terminal device includes a memory and a processor, the memory stores a computer program, and is characterized in that the processor implements the steps of the power consumption optimization method described in any one of claims 1 to 7 when executing the computer program.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power consumption optimization method according to any one of claims 1 to 7 are implemented.

Images