Laptop Battery Life Optimization Method Integrated with AI Technology

Abstract

The present invention discloses a method for optimizing the battery life of a laptop computer in combination with AI technology, which relates to the technical field of data processing. The method includes: obtaining the user's battery life optimization target, where the user's battery life optimization target includes the target battery life and the battery life constraint conditions; obtaining the remaining battery power of the user's laptop computer; obtaining a battery life target threshold according to the remaining battery power of the user's laptop computer and the target battery life; positioning the optimization target parameters according to the battery life constraint conditions; taking the battery life target threshold as the optimization target, and performing strategy optimization on the optimization target parameters according to the battery life constraint conditions to obtain a battery life control parameter strategy. It solves the technical problem in the prior art that the user's usage scenario and actual operating state are not fully considered, resulting in the inability to perform dynamic optimization of the battery life according to the user's personalized needs, and achieves the technical effect of intelligently extending the battery life of the laptop computer on the premise of meeting the user's specific needs.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a method for optimizing the battery life of a laptop computer by combining AI technology. Background Art

[0002] With the continuous improvement of the performance of modern laptop computers, especially the enhancement of the performance of processors and graphics chips, laptop computers have been widely used in various fields such as work, entertainment, and education. However, the battery life of laptop computers has always been an important issue for users during use. Especially in scenarios without an external power supply, how to effectively extend the battery usage time has become the key to optimizing the user experience. Traditional methods for optimizing the battery life of laptop computers dynamically adjust hardware resources (such as processors, memory, graphics cards, etc.) and combine power consumption management at the software level to achieve the best battery life effect. To a certain extent, these methods solve the battery life problem of laptop computers, but they rely on fixed optimization strategies or power management modes based on static settings, usually failing to fully consider the user's usage scenarios, needs, and the actual operating status of the device, and unable to perform personalized battery life optimization according to the specific needs of different users, thus affecting the battery life of laptop computers.

[0003] In the current related technologies for optimizing the battery life of laptop computers, there is a technical problem that the user's usage scenarios and actual operating status are not fully considered, resulting in the inability to perform dynamic battery life optimization according to the personalized needs of users. Summary of the Invention

[0004] This application provides a method for optimizing the battery life of a laptop computer by combining AI technology, which solves the technical problem in the prior art that the user's usage scenarios and actual operating status are not fully considered, resulting in the inability to perform dynamic battery life optimization according to the personalized needs of users, and achieves the technical effect of intelligently extending the battery life of the laptop computer on the premise of meeting the specific needs of users.

[0005] This application provides a method for optimizing the battery life of a laptop computer by combining AI technology, including: obtaining the user's battery life optimization target, where the user's battery life optimization target includes the target battery life time and battery life constraint conditions, and the battery life constraint conditions are software or hardware that must be used during the user's battery life; obtaining the remaining battery power of the user's laptop computer; obtaining a battery life target threshold according to the remaining battery power of the user's laptop computer and the target battery life time; positioning the optimization target parameters according to the battery life constraint conditions; and performing strategy optimization on the optimization target parameters with the battery life target threshold as the optimization target according to the battery life constraint conditions to obtain a battery life control parameter strategy.

[0006] In a possible implementation, the laptop battery life optimization method combined with AI technology further performs the following processing: obtaining the charging duration and charging constraint conditions set by the user, where the charging constraint condition is the application system that cannot be shut down during charging; obtaining the charging access power parameters through the charging interface; according to the user-set charging duration and charging access power parameters, combined with the charging constraint condition, performing optimization parameter search for charging with the goal of maximizing the charging amount, and obtaining a charging optimization control strategy.

[0007] In a possible implementation, the laptop battery life optimization method combined with AI technology further performs the following processing: obtaining the health status information of the laptop battery and the charge and discharge monitoring log, fitting the charging power battery life characteristics according to the health status information and the charge and discharge monitoring log, where the charging power battery life characteristics have a discharge attenuation rate; obtaining the current battery level after charging is completed, and using the charging power battery life characteristics to perform fitting projection on the current battery level to obtain the mapped attenuation rate performance of the current battery level; according to the standard battery level attenuation rate, performing standard share division on the mapped attenuation rate performance of the current battery level to obtain the remaining battery level of the user's laptop.

[0008] In a possible implementation, the laptop battery life optimization method combined with AI technology further performs the following processing: calculating the average power consumption according to the remaining battery level of the user's laptop and the target battery life time, where the average power consumption is the maximum power consumption per hour; performing power consumption calculation according to the average power consumption to obtain the average power, where the average power is the maximum power per hour; performing ratio calculation according to the average power consumption and the standard average power consumption, and configuring the segmentation time granularity based on the ratio relationship, where the segmentation time granularity includes single or multiple levels; performing grid segmentation on the average power according to the segmentation time granularity, and configuring the battery life target threshold for each segmentation grid, where the battery life target threshold has the time granularity identifier of the grid.

[0009] In a possible implementation, the laptop battery life optimization method combined with AI technology further performs the following processing: performing constraint power consumption analysis according to the battery life constraint condition to obtain the constraint power consumption characteristics; establishing the energy-saving adjustment relationship of the optimization target parameters and constructing the target evaluation function; establishing the alignment constraint relationship between the battery life target threshold and the constraint power consumption characteristics to obtain the battery life target power consumption value; based on the target evaluation function, performing optimization target parameter control search with the goal of minimizing the proximity difference of the battery life target power consumption value to obtain the battery life control parameter strategy.

[0010] In a possible implementation, the notebook computer battery life optimization method combining AI technology further performs the following processing: performing granular clustering on the battery life target threshold according to the time granularity identifier, and performing continuous splicing according to the chronological relationship to construct the chronological battery life target threshold for each granularity; establishing the chronological feature of the constrained power consumption according to the constrained power consumption feature; and establishing an alignment constraint relationship between the chronological battery life target threshold for each granularity and the constrained power consumption feature according to the time correspondence relationship.

[0011] In a possible implementation, the notebook computer battery life optimization method combining AI technology further performs the following processing: establishing an initial solution space based on the historical battery life optimization samples of the optimization target parameters.

[0012] Searching for an excellent candidate solution set from the initial solution space according to the target evaluation function, where the excellent candidate solution set is the initial solution whose target evaluation result reaches the target sorting threshold; randomly obtaining a search center solution and a search direction solution from the excellent candidate solution set; taking the search center solution as the search center and the search direction solution as the optimization direction, and performing iterative search and update based on the target evaluation function with the goal of minimizing the proximity difference of the battery life target power consumption value to obtain the battery life control parameter strategy, where the expression of the target evaluation function is: , is the battery life target power consumption value, is the total power consumption value of the optimization target parameters, is the i-th optimization target parameter, and n is the number of optimization target parameters.

[0013] In a possible implementation, the notebook computer battery life optimization method combining AI technology further performs the following processing: when there are multiple user battery life optimization targets, obtaining the preset penalty coefficients for each user battery life optimization target, where the preset penalty coefficients are proportional to the influence of the battery life optimization targets; constructing a penalty evaluation function according to the correspondence between the preset penalty coefficients and the user battery life optimization targets, and adding the penalty evaluation function to the target evaluation function to perform optimization target parameter control and optimization.

[0014] The method for optimizing the battery life of a laptop computer combined with AI technology proposed in this application is to obtain the user's battery life optimization goal, which includes the target battery life and battery life constraint conditions; obtain the remaining battery power of the user's laptop computer; obtain the battery life target threshold according to the remaining battery power and the target battery life of the user's laptop computer; locate the optimization target parameters according to the battery life constraint conditions; take the battery life target threshold as the optimization target, and perform strategy optimization on the optimization target parameters according to the battery life constraint conditions to obtain the battery life control parameter strategy. This solves the technical problem in the prior art that the user's usage scenario and actual operating state are not fully considered, resulting in the inability to perform dynamic optimization of the battery life according to the user's personalized needs, and achieves the technical effect of intelligently extending the battery life of the laptop computer on the premise of meeting the specific needs of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0016] Figure 1 It is a schematic flowchart of the method for optimizing the battery life of a laptop computer combined with AI technology provided by the embodiment of the present application;

[0017] Figure 2 It is a schematic flowchart of obtaining the remaining battery power in the method for optimizing the battery life of a laptop computer combined with AI technology provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically illustrates the specific embodiments of this application.

[0019] In order to make the purpose, technical solution and advantages of this application clearer, the present application will be further described in detail below in conjunction with the drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first" and "second" are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0021] An embodiment of this application provides a method for optimizing the battery life of a laptop computer in combination with AI technology, as Figure 1 shown, the method includes:

[0022] Step S100, obtaining a user's battery life optimization target, where the user's battery life optimization target includes a target battery life and battery life constraint conditions, and the battery life constraint conditions are software or hardware that must be used during the user's battery life.

[0023] Preferably, obtaining the user's battery life optimization target means collecting the specific demand targets of the user for optimizing the battery life of the laptop computer through a certain method (which may be the user's input or automatic recognition). Among them, the user's battery life optimization target includes a target battery life and battery life constraint conditions. Specifically, the target battery life refers to the time that the user hopes the laptop computer can continue to work under the current remaining battery power. For example, the user may hope that the computer can be used for at least 3 hours when the remaining battery power is 20%, or the expected battery life in different usage scenarios (for example, hoping to reach 8 hours in the office mode and 4 hours in the video playback mode). The setting of the target battery life is closely related to the user's specific needs and usage scenarios, such as whether working while out and about or performing high-load tasks.

[0024] Preferably, the battery life constraint conditions refer to the key software or hardware that must continue to run when the user sets the battery life target, that is, the key functions or components that must be kept running. These cannot be ignored or overly adjusted during the battery life optimization process. These constraint conditions are usually explicitly specified by the user, requiring that during the battery optimization process, the performance of certain specific functions cannot be turned off or reduced. This may include software that must be used. For example, the user may need to continue using a certain professional software (such as design software, video conferencing and office software, programming IDE or development tools, etc.) in the battery mode. Even if these software consume more power, their performance cannot be completely turned off or reduced. It also includes hardware that must be used. For example, the user needs certain hardware components in the laptop (such as Wi-Fi module, Bluetooth module, external devices such as USB, specific sensors, etc.) to continue working. The operation of these hardware will affect the battery life, but they cannot be turned off due to battery life optimization.

[0025] Preferably, assume that a user hopes to extend the battery life of a laptop to 4 hours. Under this target battery life, the user still needs to use some high-power-consuming software (such as video editing software), and keep the Wi-Fi and Bluetooth turned on for remote work or video conferencing. When performing battery life optimization, these software and hardware battery life constraint conditions will be considered to ensure that they continue to run while extending the battery life through other means (such as adjusting the processor frequency, reducing the display brightness, etc.).

[0026] Further, step S100 further includes step S110 of obtaining the charging duration and charging constraint conditions set by the user, where the charging constraint condition is the application system that cannot be turned off during charging; step S120 of obtaining the charging access power parameters through the charging interface; and step S130 of optimizing the charging parameters with the goal of maximizing the charging amount according to the user-set charging duration, charging access power parameters, and in combination with the charging constraint conditions to obtain a charging optimization control strategy.

[0027] Preferably, charging optimization is performed based on the charging duration and charging constraint conditions set by the user to maximize the charging amount, and the charging access power parameters and the user's constraint requirements are considered. Specifically, the charging duration set by the user and the charging constraint conditions are obtained. The charging duration set by the user refers to the charging duration preset by the user, that is, the user hopes that the device is fully charged or charged within a certain specific time. For example, the user hopes that the laptop is fully charged 1 hour before going out. The charging constraint conditions are some specific restrictions that need to be considered during the charging process. Usually, the user needs to ensure that some important applications or functions can still be used during charging. For example, the user may require that during the charging process, some key applications (such as video playback, important work software, etc.) must remain running; the charging access power parameters are obtained through sensors or power management chips at the charging interface, including charging power, voltage, current, etc., which reflect the power status provided by the charger to the device during the charging process.

[0028] Preferably, according to the charging duration set by the user, the charging access power parameters, and in combination with the charging constraint conditions, charging optimization parameter search is performed with the goal of maximizing the charging amount. That is, within the charging duration set by the user, as much electrical energy as possible is input into the battery, while balancing the charging duration, charging power, and constraint conditions to ensure that the charging amount is maximized in the shortest time. Optimization algorithms (such as gradient descent, genetic algorithms, etc.) are used to adjust multiple parameters during the charging process to find the best charging strategy. For example, the charging speed is optimized by adjusting the charging power, and the power consumption of the device is adjusted to avoid affecting the normal use of the device during charging. By combining these parameters, the charging amount is maximized within a given time, and finally a charging optimization control strategy is obtained, including charging power control, adjusting the output power of the charger to ensure the maximization of the charging amount; device power consumption management. If there are multiple applications running on the device, the charging optimization strategy may adjust the power consumption of these applications or allocate resources to the applications; the balance between charging duration and battery charge, optimizing the time arrangement during the charging process, minimizing the charging time as much as possible, while ensuring that the battery is charged to the maximum capacity.

[0029] Step S200, obtain the remaining battery power of the user's laptop.

[0030] Preferably, obtaining the remaining battery power of the user's laptop refers to real-time monitoring and obtaining the current remaining battery power of the laptop through a certain method (usually hardware sensors and the battery management module of the operating system), which is usually presented in the form of a percentage, indicating the proportion of the remaining electrical energy of the current battery to the total battery capacity. Specifically, the operating system (such as Windows, macOS, etc.) will regularly obtain the real-time status information of the battery from the hardware battery management module and transfer it to the user interface. The user can see a battery icon in the system tray or menu bar, and the icon will display the percentage of the remaining battery power; calculating and monitoring the battery power of the laptop is achieved through a battery control chip (usually an intelligent management chip embedded in the battery). The battery control chip can measure parameters such as the voltage, current, and temperature of the battery, thereby calculating the remaining battery power. For example, if the maximum capacity of the battery is 50Wh and the current battery power is 25Wh, the remaining battery power is 50%; in some advanced application scenarios, software (such as battery optimization tools or power management software) helps to judge the current battery health status, remaining battery power, and predicted remaining usage time (such as remaining 2 hours) by calling the API provided by the operating system to read the battery status in real time.

[0031] Further, as Figure 2 shown, step S200 further includes step S210, obtaining the health status information and charge-discharge monitoring log of the laptop battery, fitting the charge power endurance characteristics according to the health status information and charge-discharge monitoring log, and the charge power endurance characteristics have a discharge attenuation rate; step S220, obtaining the current power at the end of charging, and using the charge power endurance characteristics to perform fitting projection on the current power to obtain the mapped attenuation rate performance of the current power; step S230, dividing the mapped attenuation rate performance of the current power according to the standard power attenuation rate to obtain the remaining battery power of the user's laptop.

[0032] Preferably, by analyzing the battery health status information and the charge-discharge monitoring log, the method of fitting and projection is used to calculate the remaining power of the laptop, and the battery attenuation situation and the fact that some batteries are charged with false electricity and discharge quickly are considered, and finally a more accurate remaining power value is provided. Specifically, the battery health status information and the charge-discharge monitoring log of the laptop battery are obtained. Among them, the battery health status information refers to the degree of decline of the current state of the battery relative to its initial state, usually including the capacity attenuation of the battery, that is, the ratio of the current maximum available capacity of the battery to the maximum capacity of the new battery, the number of battery cycles, the number of times the battery has experienced during the charge-discharge process, and usually the battery performance will decline after exceeding a certain number of times, the internal resistance, and the internal resistance of the battery may increase with the increase of the use time, affecting the charge-discharge efficiency of the battery; the charge-discharge monitoring log records data such as the charging status, discharging status and voltage change of the battery at different time points, which helps to understand the behavior of the battery in actual use (for example, charging rate, discharging rate, working temperature, etc.) and is used to analyze the change of battery performance; according to the health status information and the charge-discharge monitoring log, the charging power endurance characteristics with a discharge attenuation rate are fitted, that is, by analyzing the historical charge-discharge records of the battery, the usage characteristics of the battery after charging are fitted, especially its endurance performance at a specific power. The discharge attenuation rate refers to the relationship between the power and time during the discharge process of the battery. As the battery ages, the discharge rate may gradually increase, that is, the speed at which the power drops during the discharge process of the battery will become faster.

[0033] Preferably, the current power after charging is obtained, that is, the remaining power of the battery after charging is completed, which usually refers to the charging power of the battery in the current state (such as the actual power when the battery shows 100%). According to the fitted charging power endurance characteristics, the current power is mapped, that is, using information such as the discharge attenuation rate, the current power is further "projected" to predict the future consumption rate of the current power. Fitting projection means that through a mathematical model (such as the fitted discharge attenuation rate), the attenuation characteristics of the current power are mapped, so as to calculate the power attenuation behavior during the future discharge process, that is, to obtain the mapped attenuation rate performance of the current power, indicating the actual consumption speed and attenuation trend of the current power, reflecting the discharge rate of the current power under the existing battery health status, increasing with the increase of the battery use time, indicating that the battery efficiency decreases and the discharge process is faster.

[0034] Preferably, according to the standard power attenuation rate, the mapping attenuation rate performance of the current power is divided into standard shares. The standard power attenuation rate refers to the normal battery attenuation rate defined according to standards such as battery health and discharge rules. The standard share division means comparing the mapping attenuation rate of the current power with the standard attenuation rate, analyzing the attenuation performance of the battery under the current state, and dividing it into different "shares" or levels. For example, the attenuation rate of the current battery power may be divided into several levels (such as low, medium, high), and each level represents a different health state and endurance ability. Then, the remaining power of the user's laptop is obtained, that is, the actual power after the standardized power attenuation rate division. Considering factors such as the health state of the battery, the power attenuation characteristics, and the charge and discharge history, it can more accurately predict the actual available time of the battery, which is more accurate than the remaining power percentage and significantly improves the prediction accuracy of battery endurance.

[0035] Step S300: Obtain a battery endurance target threshold based on the remaining power of the user's laptop and the target endurance time.

[0036] Preferably, by calculating and analyzing the remaining power of the user's current battery and the target endurance time he expects, the battery endurance target threshold is determined, which represents the power consumption limit that needs to be reached to ensure the realization of the user's target endurance time. For example, if the total capacity of the battery is 50 Wh and the remaining power is 25 Wh, then the remaining power is 50%. The target endurance time is 5 hours. Calculate the battery consumption rate based on the remaining power and the target endurance time, that is, the power consumed per hour is 5 Wh. The battery endurance target threshold is then 5 Wh of power consumption per hour to ensure that the battery can support 5 hours of use. Optimize the operation of the laptop according to the battery endurance target threshold (such as adjusting the CPU frequency, monitor brightness, etc.) to ensure that the usage time is extended as much as possible with limited battery power.

[0037] Further, step S300 further includes step S310: Calculate the average power consumption based on the remaining power of the user's laptop and the target endurance time, where the average power consumption is the maximum power consumption per hour; step S320: Perform power consumption calculation based on the average power consumption to obtain the average power, where the average power is the maximum power per hour; step S330: Calculate the ratio of the average power consumption to the standard average power consumption, and configure the segmentation time granularity based on the ratio relationship. The segmentation time granularity includes single or multiple levels; step S340: Perform grid segmentation on the average power based on the segmentation time granularity, and configure the battery endurance target threshold for each segmented grid, where the battery endurance target threshold has a time granularity identifier for the grid.

[0038] Preferably, based on the remaining battery power and the target battery life of the user's laptop, the average power consumption is calculated, that is, the maximum power consumption per hour, which represents the power consumption of the laptop per hour under the target battery life. Then, according to the average power consumption, it is converted into the power consumption per unit time, that is, the product of the average power consumption and the battery voltage. The average power consumption reflects the maximum power consumed per hour. By calculating the ratio of the average power consumption to the standard average power consumption, a ratio value is obtained, which represents the change in the current power consumption relative to the standard power consumption. Among them, the standard average power consumption is the average power consumption during normal operation given according to the laptop brand, specifications, historical data, etc., which reflects the normal power consumption of the laptop in the standard usage scenario; based on the ratio relationship, the split time granularity is configured, and according to the actual power consumption level of the device, the granularity of the battery life is adjusted, and different time periods are used to optimize the use and management of the battery. The granularity takes into account the relationship of power usage. If the battery power is sufficient, the granularity can be larger; if the battery power is insufficient, the granularity is smaller, ensuring that the target battery life can be achieved. Among them, the split time granularity includes single or multiple levels, that is, it can be a fixed single granularity split or a dynamic multi-stage multi-granularity. Different time granularities help to manage the battery life more flexibly, especially in the case of large power consumption changes.

[0039] Preferably, the average power consumption is segmented into a grid according to the split time granularity. Specifically, the time is divided into multiple small blocks, each small block represents an independent time period, and there is a battery life target threshold in each time period, so as to more finely control the battery life distribution, ensure that the power consumption in each small time period can be within the set range, and thus optimize the overall battery life. Then, the battery life target thresholds of each segmented grid are configured. The battery life target threshold refers to the maximum allowable power consumption within each segmented grid, which represents the maximum available battery power within that time period. For example, if the time granularity is 1 hour, calculate the maximum power consumption within this hour to ensure that it does not exceed this limit within that time period. The battery life target threshold with the time granularity identifier of the grid means that each grid (i.e., each time period) is associated with a specific time granularity (such as 1 hour, 30 minutes, 15 minutes, etc.), and this granularity will mark and limit the power consumption of each time period during calculation, which helps to dynamically adjust the battery management strategy and ensure that the battery consumption can be managed according to the set target threshold within each time period.

[0040] Step S400, locate the optimization target parameters according to the battery life constraint conditions.

[0041] Preferably, during the battery life optimization process, the system needs to determine which specific hardware or software parameters need to be optimized according to the battery life constraint conditions set by the user (such as specific software or hardware that must run), in order to achieve the purpose of extending the battery life. Among them, the optimization target parameters refer to the variables that can be adjusted, controlled or optimized during the battery life optimization process. The battery life constraint conditions include the hardware or software functions that the user sets must be kept running or given priority. When performing battery life optimization, the power consumption of these key functions cannot be reduced or restricted. According to the battery life constraint conditions, retain those key functions that must remain active, identify which hardware or software parameters need to be optimized, and determine other adjustable parameters. For example, the processor frequency (adjust the working frequency of the CPU, reduce the load of the processor, and reduce power consumption), the display brightness (reduce the screen brightness to reduce battery consumption), the working mode of the hard disk and storage device (extend the battery life by reducing the read and write operations of the hard disk or reducing the power consumption of the storage device), etc., to achieve the purpose of extending the battery life and ensure that the battery consumption is optimized without affecting the core needs of the user.

[0042] Step S500: Taking the battery life target threshold as the optimization target, perform strategy optimization on the optimization target parameters according to the battery life constraint conditions to obtain a battery life control parameter strategy.

[0043] Preferably, taking the battery life target threshold as the optimization target, perform strategy optimization on the optimization target parameters according to the battery life constraint conditions, that is, adjust and optimize the various parameters of the laptop to achieve the best performance of the battery life, while ensuring that the battery life constraint conditions set by the user are not violated during the optimization process. Among them, strategy optimization is an optimization algorithm that finds an optimal control strategy by repeatedly testing, adjusting, calculating and comparing different optimization schemes, so that the battery consumption rate is as low as possible while ensuring that the key functions can run normally. It involves adjusting and optimizing the optimization target parameters to meet the battery life target threshold and the user's battery life constraint conditions. Specifically, based on the battery life target threshold, determine the maximum amount of power that can be consumed per hour, keep the power consumption per hour not exceeding this threshold, and gradually adjust the optimization target parameters, such as the CPU frequency, screen brightness, etc., to ensure that each parameter adjustment can minimize the power consumption while ensuring compliance with the constraint conditions, such as reducing the CPU load of unimportant applications but not closing essential applications; then continuously adjust these parameters through optimization algorithms (such as linear programming, genetic algorithms, etc.), perform multiple calculations and simulations, and gradually optimize to ensure that the battery consumption rate does not exceed the target threshold while meeting all the constraint conditions. Finally, obtain a set of control strategies, that is, the battery life control parameter strategy, which can maintain the operation of the hardware and software required by the user without exceeding the battery life target threshold and maximize the extension of the battery life.

[0044] Further, step S500 further includes step S510 of analyzing and obtaining constraint power consumption characteristics according to the endurance constraint conditions; step S520 of establishing an energy-saving adjustment relationship of the optimization target parameters and constructing a target evaluation function; step S530 of establishing an alignment constraint relationship between the endurance target threshold and the constraint power consumption characteristics to obtain an endurance target power consumption value; and step S540 of performing optimization target parameter control optimization based on the target evaluation function with the goal of minimizing the proximity difference of the endurance target power consumption value to obtain the endurance control parameter strategy.

[0045] Preferably, in charging and endurance optimization, the power consumption of the device is analyzed and evaluated according to the endurance constraint conditions. For example, when the user sets that certain applications cannot be closed, the power consumed by the operation of these applications is calculated, and endurance optimization is performed on this basis to obtain the constraint power consumption characteristics, that is, the power consumption characteristics required by the laptop under the given constraint conditions, such as the power consumed by certain application programs, or the minimum non-adjustable power consumption during the operation of the device. An energy-saving adjustment relationship of the optimization target parameters is established, that is, the relationship between the key parameters affecting the endurance of the laptop (including the screen brightness, processor frequency, etc. of the device) and the energy-saving effect is established. For example, lowering the screen brightness or reducing the CPU frequency can usually significantly reduce the power consumption, thereby extending the endurance time of the device, and thus constructing a target evaluation function to reflect the power consumption level and endurance performance under different parameter adjustment combinations.

[0046] Preferably, establishing an alignment constraint relationship between the endurance target threshold and the constraint power consumption characteristics means aligning the power consumption requirements under the constraint conditions with the target endurance. For example, when the user sets that certain applications cannot be closed and the actual power consumption of the device increases due to these applications, it is necessary to find a balance between the actual power consumption characteristics and the target endurance. By comparing the target endurance threshold with the power consumption characteristics under the constraint conditions, the endurance target power consumption value is calculated, that is, the power consumption level that the device is expected to reach under the condition of meeting the user-set endurance target and constraint conditions. In other words, it is the power consumption value required under the constraint conditions to ensure that the device can work within the target endurance time. Then, according to the target evaluation function, with the goal of minimizing the proximity difference of the endurance target power consumption value (making the actual power consumption of the device as close as possible to the user-set endurance target power consumption value, and thus minimizing the error between the actual power consumption and the target power consumption), optimization target parameter control optimization is performed, that is, the parameters of the device are adjusted to repeatedly calculate and evaluate different parameter combinations to ensure that the difference between the actual power consumption and the target power consumption is minimized until the optimal endurance control parameter strategy is determined, such as adjusting the screen brightness of the device, closing unnecessary applications, adjusting the processor frequency, etc., to ensure that the device achieves the longest endurance time under the condition of meeting the user-set endurance target and constraint conditions.

[0047] Further, step S530 further includes step S531, clustering the endurance target threshold according to the time granularity identifier, and performing continuous splicing according to the time sequence relationship to construct the time-sequence endurance target threshold for each granularity; step S532, establishing the time-sequence feature of the constrained power consumption according to the constrained power consumption feature; step S533, establishing the alignment constraint relationship between the time-sequence endurance target threshold for each granularity and the constrained power consumption feature according to the time correspondence relationship.

[0048] Preferably, clustering the endurance target threshold according to the time granularity identifier, that is, clustering the endurance target threshold according to different time periods. For example, the endurance target within each hour may be different. In different time periods, the power consumption and endurance target of the device may vary greatly. Then, splice the endurance target thresholds of different time periods in chronological order to form the time-sequence endurance target threshold, that is, the endurance target sequence divided by time granularity. By merging and connecting the target power consumption values of each time period, it is convenient to accurately manage and optimize the endurance of the device; then, establish the time-sequence feature of the constrained power consumption according to the constrained power consumption feature, that is, establish the change law of the constrained power consumption feature in the time dimension. For example, the power consumption of the device may be relatively low at the beginning of charging, but as time goes by, the power consumption may increase due to the enabling of high-load applications. By establishing the time-sequence feature of the constrained power consumption, the specific pattern of the power consumption change of the device during the charging process can be obtained; then, associate the time granularity with the power consumption change to ensure that the endurance target within each time period matches the power consumption feature, and establish the alignment constraint relationship between the time-sequence endurance target threshold and the constrained power consumption feature, that is, align the endurance target thresholds under different time granularities with the constrained power consumption feature to ensure their consistency in the time dimension and meet the endurance requirements of the device.

[0049] Further, step S540 further includes step S541, establishing an initial solution space based on the historical endurance optimization samples of the optimization target parameters; step S542, searching for an excellent candidate solution set from the initial solution space according to the target evaluation function, where the excellent candidate solution set is the initial solution whose target evaluation result reaches the target sorting threshold; step S543, randomly obtaining a search center solution and a search direction solution in the excellent candidate solution set; step S544, using the search center solution as the search center and the search direction solution as the optimization direction, and performing iterative search and update based on the target evaluation function with the goal of minimizing the proximity difference of the endurance target power consumption value to obtain the endurance control parameter strategy, where the expression of the target evaluation function is: , is the endurance target power consumption value, is the total power consumption value of the optimization target parameters, is the i-th optimization target parameter, and n is the number of optimization target parameters.

[0050] Preferably, an initial solution space is established based on the historical battery life optimization samples (optimization data under different usage scenarios, such as the actual battery life of the computer under different parameter settings) of the user's laptop, that is, a set of all possible combinations of optimization target parameters. An excellent candidate solution set is searched from the initial solution space according to the objective evaluation function. Specifically, the gap between the target power consumption value of the battery life target and the actual power consumption value is calculated using the objective evaluation function to evaluate the optimization effect. Then, multiple candidate optimal solutions are selected from the initial solution space as the excellent candidate solution set. Then, one is randomly selected from the excellent candidate solution set, that is, the search center solution, as the starting point of the optimization search, and another is randomly selected as the search direction solution to provide a possible direction for iterative optimization.

[0051] Preferably, taking the search center solution as the current optimal solution and the search direction solution as the possible optimization direction, iterative search is carried out in the solution space. Through multiple iterations, the parameters of the solution are adjusted according to the objective evaluation function until the best strategy for minimizing the difference between the target power consumption value of the battery life and the actual power consumption value is found, that is, the search center solution and the search direction solution are updated according to the feedback of the objective evaluation function. Through repeated search and update, the optimal solution is gradually approached, that is, the actual power consumption value is made as close as possible to the target power consumption value, so as to maximize the battery life effect and obtain the battery life control parameter strategy to help the device achieve the longest battery life performance. Among them, the expression of the objective evaluation function is: , is the target power consumption value of the battery life, is the total power consumption value of the optimization target parameters, is the i-th optimization target parameter, and n is the number of optimization target parameters.

[0052] Further, step S544 further includes step S544a. When there are multiple user battery life optimization targets, the preset penalty coefficients of each user battery life optimization target are obtained, and the preset penalty coefficients are proportional to the influence of the battery life optimization target; step S544b. According to the corresponding relationship between the preset penalty coefficient and the user battery life optimization target, a penalty evaluation function is constructed, and the penalty evaluation function is added to the objective evaluation function to perform optimization target parameter control optimization.

[0053] Preferably, in some cases, a user may have multiple goals, and these goals may conflict with each other. For example, one goal may be to extend the battery life of the device, while another goal may be to optimize the device performance or keep certain applications running. A penalty coefficient is assigned to each goal. Among them, the penalty coefficient reflects the influence degree of each goal on the optimization process. The goal with a greater influence will be assigned a higher penalty coefficient, while the goal with a smaller influence will be assigned a lower penalty coefficient. And the preset penalty coefficient is proportional to the influence of the battery life optimization goal, that is, the magnitude of the penalty coefficient is proportional to the importance and priority of the goal in the battery life optimization. According to the corresponding relationship between the preset penalty coefficient and the user's battery life optimization goal, a penalty evaluation function is constructed. The optimization results of each goal will be considered, and the penalty value will be calculated according to its corresponding penalty coefficient, which is used to measure the penalty degree when each goal fails to meet the expectation in the multi-goal optimization. Finally, the penalty evaluation function is added to the goal evaluation function so that the goal evaluation function can consider the weights and penalties of different goals simultaneously when evaluating the optimization effect, and then conduct the control optimization of the optimization target parameters, that is, search for the optimal parameter combination to minimize the result of the goal evaluation function while considering the influence of the penalty coefficient, so as to ensure that multiple goals can be reasonably balanced in the overall optimization, and make the device achieve the best battery life performance on the premise of meeting all requirements.

[0054] The above specific implementation manners do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be executed in a different order from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for optimizing the battery life of a laptop computer combined with AI technology, characterized in that, The method includes: Obtaining the user's battery life optimization goal, where the user's battery life optimization goal includes a target battery life time and battery life constraint conditions, and the battery life constraint conditions are software or hardware that must be used during the user's battery life; Obtaining the remaining battery power of the user's laptop; Obtaining a battery life target threshold based on the remaining battery power of the user's laptop and the target battery life time; Locating the optimization target parameters according to the battery life constraint conditions; Taking the battery life target threshold as the optimization target, and performing strategy optimization on the optimization target parameters according to the battery life constraint conditions to obtain a battery life control parameter strategy; Obtaining the user-set charging duration and charging constraint conditions, where the charging constraint conditions are application systems that cannot be turned off during charging; Obtaining the charging access power parameters through the charging interface; According to the user-set charging duration and charging access power parameters, combined with the charging constraint conditions, performing optimization parameter search for charging with the goal of maximizing the charging amount to obtain a charging optimization control strategy; The obtaining of the remaining battery power of the user's laptop includes: Obtaining the health status information of the laptop battery and the charge and discharge monitoring log, fitting the charge power battery life characteristics according to the health status information and the charge and discharge monitoring log, and the charge power battery life characteristics have a discharge attenuation rate; Obtaining the current battery power when charging is completed, and performing fitting projection on the current battery power using the charge power battery life characteristics to obtain the mapped attenuation rate performance of the current battery power; Dividing the mapped attenuation rate performance of the current battery power according to the standard battery power attenuation rate to obtain the remaining battery power of the user's laptop.

2. The laptop battery life optimization method combined with AI technology according to claim 1, characterized in that Obtaining a battery life target threshold based on the remaining battery power of the user's laptop and the target battery life time, including: Calculating the average power consumption based on the remaining battery power of the user's laptop and the target battery life time, where the average power consumption is the maximum power consumption per hour; Performing power consumption calculation based on the average power consumption to obtain the average power, where the average power is the maximum power per hour; Performing a ratio calculation based on the average power consumption and the standard average power consumption, and configuring the segmentation time granularity based on the ratio relationship, where the segmentation time granularity includes single or multiple levels; Performing grid segmentation on the average power according to the segmentation time granularity, and configuring the battery life target threshold for each segmented grid, where the battery life target threshold has a time granularity identifier for the grid.

3. The laptop battery life optimization method combined with AI technology according to claim 2, wherein Taking the battery life target threshold as the optimization target, and performing strategy optimization on the optimization target parameters according to the battery life constraint conditions to obtain a battery life control parameter strategy, including: Performing constraint power consumption analysis according to the battery life constraint conditions to obtain constraint power consumption characteristics; Establishing an energy-saving adjustment relationship for the optimization target parameters and constructing a target evaluation function; Establishing an alignment constraint relationship between the battery life target threshold and the constraint power consumption characteristics to obtain a battery life target power consumption value; Based on the target evaluation function, with the goal of minimizing the proximity difference of the battery life target power consumption value, performing optimization target parameter control search to obtain the battery life control parameter strategy.

4. The laptop battery life optimization method combined with AI technology according to claim 3, characterized in that, Establishing an alignment constraint relationship between the battery life target threshold and the constraint power consumption characteristics includes: Perform granular clustering on the endurance target threshold according to the time granularity identifier, and perform continuous splicing according to the chronological relationship to construct the chronological endurance target threshold for each granularity; Establish the chronological characteristics of the constrained power consumption according to the constrained power consumption characteristics; Establish the alignment constraint relationship between the chronological endurance target threshold of each granularity and the constrained power consumption characteristics according to the time correspondence relationship.

5. The method for optimizing the battery life of a laptop computer combined with AI technology according to claim 3, characterized in that Based on the target evaluation function, with the goal of minimizing the proximity difference of the endurance target power consumption value, perform optimization of the target parameter control to obtain the endurance control parameter strategy, including: Establish an initial solution space based on the historical endurance optimization samples of the optimized target parameters; Search for an excellent candidate solution set from the initial solution space according to the target evaluation function, and the excellent candidate solution set is the initial solution whose target evaluation result reaches the target sorting threshold; Randomly obtain a search center solution and a search direction solution from the excellent candidate solution set; Using the search center solution as the search center and the search direction solution as the optimization direction, perform iterative search and update based on the target evaluation function with the goal of minimizing the proximity difference of the endurance target power consumption value to obtain the endurance control parameter strategy, where the expression of the target evaluation function is: is the target power consumption value for endurance, is the total power consumption value of the optimization target parameter, is the i-th optimization target parameter, and n is the number of optimization target parameters.

6. The laptop battery life optimization method combined with AI technology according to claim 5, characterized in that, It also includes: When there are multiple user endurance optimization targets, obtain the preset penalty coefficients for each user endurance optimization target, and the preset penalty coefficients are proportional to the influence of the endurance optimization targets; Construct a penalty evaluation function according to the correspondence between the preset penalty coefficients and the user endurance optimization targets, add the penalty evaluation function to the target evaluation function, and perform optimization of the target parameter control.

Images