Performance parameter adjusting method and device, chip, electronic equipment and medium

Abstract

The invention provides a performance parameter adjusting method and device, a chip, electronic equipment and a medium, and relates to the technical field of communication. Comprising the steps that based on indication information of network equipment, a target gear interval is determined in multiple sets of candidate gear information of performance parameters of a terminal, the performance parameters comprise frequencies and voltages, and each set of candidate gear information corresponds to a set of voltages and frequencies for a central processing unit and / or at least one hardening accelerator of the terminal; determining a target gear in the target gear interval based on the running state information of the terminal under the current working load; and respectively adjusting performance parameters of the central processing unit and / or the at least one hardening accelerator based on the target gear. According to the method provided by the invention, invalid power consumption can be greatly reduced, and the battery life is effectively prolonged; through adjustment of the determined target gear, severe fluctuation of performance is avoided, jamming caused by instantaneous high load and subsequent temperature control frequency reduction is reduced, and continuous and stable user experience is guaranteed.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a method and apparatus for adjusting performance parameters, a chip, an electronic device, and a medium. Background Technology

[0002] For terminal SOCs (System-on-a-Chip), low power consumption performance directly determines the two most critical aspects of the terminal: battery life and heat dissipation and performance stability. Adjusting the frequency and voltage of the SOC according to different business scenarios is crucial, and how to identify more refined frequency and voltage adjustment levels and adjust them accurately is an important topic. Summary of the Invention

[0003] This disclosure provides a method, apparatus, chip, electronic device, and medium for adjusting performance parameters. It proposes a method based on identifying the performance of a terminal under its current load to determine the level of performance parameters, thereby achieving precise adjustment of the performance parameters of each module of the terminal.

[0004] The first aspect of this disclosure provides a method for adjusting performance parameters, comprising: determining a target performance range from multiple candidate performance parameter ranges for a terminal based on indication information from a network device, wherein the performance parameters include frequency and voltage, and each candidate performance parameter range corresponds to a set of voltage and frequency for the terminal's central processing unit and / or at least one hardening accelerator; determining a target performance level within the target performance range based on the terminal's operating status information under the current workload and / or user habit information; and adjusting the performance parameters of the central processing unit and / or at least one hardening accelerator based on the target performance level.

[0005] In some embodiments of this disclosure, determining a target gear range from multiple sets of candidate gear range information for the performance parameters of a terminal based on the indication information of a network device includes: determining candidate gear range information, the candidate gear range information including a gear range identifier and at least one gear range in the gear range corresponding to the gear range identifier, each gear range including the frequency and voltage of a central processing unit and / or the frequency and voltage of at least one hardening accelerator; and determining the gear range below the highest gear range indicated by the indication information as the target gear range.

[0006] In some embodiments of this disclosure, determining candidate gear information includes: determining at least one gear range based on configuration information; configuring a gear corresponding to each gear range and a frequency and voltage corresponding to each gear range for a central processing unit based on at least one gear range; and / or configuring a gear corresponding to each gear range and a frequency and voltage corresponding to each gear range for each hardening accelerator in at least one hardening accelerator based on at least one gear range.

[0007] In some embodiments of this disclosure, the operating status information includes at least one of the following: foreground application identifier, background application identifier, thread load, input load, output load, network traffic, user interaction events, device posture sensor data, remaining battery power, and chip temperature.

[0008] In some embodiments of this disclosure, the runtime status information also includes user habit information, which is predicted by a model based on the runtime status information. The user habit information includes at least one of time-based habit, scene-related habit, in-application behavior habit, and performance preference habit.

[0009] In some embodiments of this disclosure, based on the terminal's operating status information under the current workload, a target gear is determined within a target gear range, including: determining at least one pre-adjustment gear corresponding to the central processing unit and / or at least one pre-adjustment gear corresponding to the hardening accelerator based on the target gear range; and determining the target gear of the central processing unit in the at least one pre-adjustment gear corresponding to the central processing unit and / or the target gear of the hardening accelerator in the at least one pre-adjustment gear corresponding to the hardening accelerator based on the operating status information and through a trained model.

[0010] In some embodiments of this disclosure, the performance parameters of the central processing unit and / or at least one hardening accelerator are adjusted based on the target gear, including: determining a first control command corresponding to the central processing unit based on the target gear of the central processing unit, and / or determining a second control command corresponding to the hardening accelerator based on the target gear of the hardening accelerator; sending the first control command to the central processing unit, and / or sending the second control command to the hardening accelerator.

[0011] In the above embodiments, a mechanism is implemented to determine the target performance range by instructing the network device and to finely select the performance level within the range based on the real-time status of the terminal, thus achieving a two-layer decision-making process for performance adjustment. By combining the theoretical capability constraints on the communication side with the actual needs perception on the terminal side, the adjustment of performance parameters not only meets network requirements but also avoids performance overkill and power waste caused by directly adopting the maximum capability configuration, thereby achieving dynamic frequency and voltage regulation on the terminal side.

[0012] A second aspect of this disclosure provides a performance parameter adjustment device, comprising: a determining module, an evaluating module, and a controlling module. The determining module is configured to determine a target performance range from multiple sets of candidate performance parameter information for a terminal based on indication information from a network device. The performance parameters include frequency and voltage, and each set of candidate performance parameter information corresponds to a set of voltage and frequency for the terminal's central processing unit and / or at least one hardening accelerator, respectively. The evaluating module is configured to determine a target performance level within the target performance range based on the terminal's operating status information under the current workload. The controlling module is configured to adjust the performance parameters of the central processing unit and / or at least one hardening accelerator based on the target performance level.

[0013] In some embodiments of this disclosure, the determining module is further configured to: determine candidate gear information, the candidate gear information including a gear interval identifier, at least one gear in the gear interval corresponding to the gear interval identifier, each gear including the frequency and voltage of the central processing unit, and / or the frequency and voltage of at least one hardening accelerator; and determine the gears below the highest gear indicated by the indication information as the target gear interval.

[0014] In some embodiments of this disclosure, the determining module is further configured to: determine at least one gear range based on configuration information; configure a gear and frequency and voltage corresponding to each gear range for the central processing unit based on the at least one gear range; and / or configure a gear and frequency and voltage corresponding to each gear range for each of the at least one hardening accelerators based on the at least one gear range.

[0015] In some embodiments of this disclosure, the operating status information includes at least one of the following: foreground application identifier, background application identifier, thread load, input load, output load, network traffic, user interaction events, device posture sensor data, remaining battery power, and chip temperature.

[0016] In some embodiments of this disclosure, the runtime status information also includes user habit information, which is predicted by a model based on the runtime status information. The user habit information includes at least one of time-based habit, scene-related habit, in-application behavior habit, and performance preference habit.

[0017] In some embodiments of this disclosure, the evaluation module is further configured to: determine at least one pre-adjustment gear corresponding to the central processing unit and / or at least one pre-adjustment gear corresponding to the hardening accelerator based on the target gear range; and determine the target gear of the central processing unit in the at least one pre-adjustment gear corresponding to the central processing unit and / or the target gear of the hardening accelerator in the at least one pre-adjustment gear corresponding to the hardening accelerator based on the operating status information and / or user habit information, using a trained model.

[0018] In some embodiments of this disclosure, the control module is further configured to: determine a first control command corresponding to the central processing unit based on the target gear of the central processing unit, and / or determine a second control command corresponding to the hardening accelerator based on the target gear of the hardening accelerator; send the first control command to the central processing unit, and / or send the second control command to the hardening accelerator.

[0019] In the above embodiments, the device avoids the problem of ineffective power consumption and effectively improves the terminal's battery life. Meanwhile, the proactive adjustments based on comprehensive state awareness and user habit prediction smooth performance output, reduce lag and overheating, and enhance the user experience.

[0020] Furthermore, the unified leveling system and coordinated control of the CPU and various hardened accelerators avoid efficiency losses caused by performance mismatch between hardware components, achieving optimal system-level energy efficiency.

[0021] A third aspect of this disclosure provides an electronic device including: a processor and a memory for storing a computer program capable of running on the processor, wherein the processor, when running the computer program, performs the method described in any embodiment of the first aspect of this disclosure.

[0022] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the methods described in any of the embodiments of the first aspect of this disclosure.

[0023] A fifth aspect of this disclosure provides a program product including computer instructions for causing a computer to perform the methods described in any of the embodiments of the first aspect of this disclosure.

[0024] A sixth aspect of this disclosure provides a chip including at least one processor and a communication interface; the communication interface is used to receive signals input to the chip or signals output from the chip, and the processor communicates with the communication interface and implements the method described in any embodiment of the first aspect of this disclosure through logic circuits or executing code instructions.

[0025] In summary, the performance parameter adjustment method proposed in this disclosure fundamentally solves the problem of ineffective power consumption caused by the theoretical peak capacity configuration being far higher than actual demand under advanced networks such as 5G / 6G. This is achieved by constructing a two-layer collaborative adjustment architecture of "network-side upper limit setting and terminal-side optimization" and introducing an AI model for refined decision-making. This effectively improves the terminal's battery life. Simultaneously, the solution's proactive adjustment based on comprehensive state awareness smooths performance output, reduces lag and heat generation, and enhances the user experience. Furthermore, the unified level system and collaborative control of the CPU and various hardened accelerators avoid efficiency losses caused by hardware performance mismatches, achieving optimal system-level energy efficiency.

[0026] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0028] Figure 1 This diagram illustrates an application scenario of the performance parameter adjustment method disclosed herein. Figure 2 This is a flowchart illustrating a method for adjusting performance parameters according to an embodiment of this disclosure. Figure 3 This is a flowchart illustrating another method for adjusting performance parameters according to an embodiment of this disclosure; Figure 4 This is a flowchart illustrating another method for adjusting performance parameters according to an embodiment of this disclosure; Figure 5 This is a flowchart illustrating another method for adjusting performance parameters according to an embodiment of this disclosure; Figure 6A This is a block diagram of the AI ​​frequency and voltage modulation mechanism architecture. Figure 6B This is a process diagram of the AI ​​frequency and voltage modulation mechanism; Figure 7 This is a schematic diagram of the structure of a performance parameter adjustment device according to an embodiment of the present disclosure; Figure 8 This is a schematic diagram of the structure of the electronic device proposed in the embodiments of this disclosure. Detailed Implementation

[0029] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0030] AI applications on user interfaces (UEs) are rapidly evolving from simple voice assistants and basic functions to intelligent agents capable of autonomously understanding, predicting, making decisions, and executing tasks. Given AI's powerful data collection, analysis, processing, and learning capabilities, it's entirely possible to leverage AI to learn users' mobile phone usage habits, collect data on the application status of all apps and their demands on system processing power and data traffic, intelligently identify low-power scenarios requiring frequency and voltage adjustments, and accurately determine the current system's frequency and voltage adjustment level, thereby reducing power consumption and improving user experience.

[0031] In related technologies, scene recognition involves the Modem protocol stack assessing the current system processing capacity requirements based on the base station's maximum capacity configuration for the UE. This requirement is then divided into different tiers, each corresponding to a set of voltage and frequency for the CPU and accelerator respectively. The Modem frequency and voltage modulation mechanism is as follows: (1) The Modem protocol stack quantizes four frequency modulation and voltage modulation levels according to the base station configuration: CFG0 (level 0), CFG1 (level 1), CFG2 (level 2), and CFG3 (level 3).

[0032] (2) The CPU is designed with 4 sets of voltage frequencies for 4 gears: DVFS-CPU-gear-0 (0 gear CPU parameter range), DVFS-CPU-gear-1 (1 gear CPU parameter range), DVFS-CPU-gear-2 (2 gear CPU parameter range), and DVFS-CPU-gear-3 (3 gear CPU parameter range).

[0033] (3) All hardening accelerators are designed with 4 sets of voltage frequencies for 4 gears: DVFS-ACCn-gear-0 (0 gear hardening accelerator parameter range), DVFS-ACCn-gear-1 (1 gear hardening accelerator parameter range), DVFS-ACCn-gear-2 (2 gear hardening accelerator parameter range), and DVFS-ACCn-gear-3 (3 gear hardening accelerator parameter range).

[0034] (4) When the Modem protocol stack receives the configuration CFGn from the base station, the CPU and all hardening accelerators immediately adjust the frequency and voltage to the corresponding voltage and frequency combination.

[0035] Based on the base station configuration, the modem protocol stack identifies and instructs various system components to perform frequency and voltage modulation. Upon receiving the base station configuration, the modem protocol stack determines the frequency and voltage modulation levels for the CPU and all hardened accelerators based on the maximum communication capacity requirements of the current configuration and completes the frequency and voltage modulation. Since the base station configuration can only theoretically assess the maximum processing capacity required by the system, but actual user usage often does not or immediately reach the maximum processing capacity, immediately adjusting from a low level to the highest level would undoubtedly waste power. Therefore, a more refined low-power frequency and voltage modulation level identification and processing scheme is needed.

[0036] Therefore, in order to solve the above-mentioned technical problems, this disclosure proposes a method for adjusting performance parameters, which uses an AI (artificial intelligence) model for frequency and voltage regulation. Specifically, in low-power scenarios, the AI ​​model can determine the frequency and voltage regulation level below the highest level indicated by the network device, thereby meeting the frequency and voltage regulation needs of low-power scenarios and avoiding the system from being constantly adjusted to the highest level in scenarios where the actual processing power requirements are relatively low, which can significantly reduce system power consumption.

[0037] The performance parameter adjustment method proposed in this disclosure can be applied to 4G, 5G and other communication systems, as well as future communication systems such as 6G.

[0038] Figure 1 This diagram illustrates an application scenario of the performance parameter adjustment method disclosed herein: a low-power frequency and voltage modulation scenario for a mobile phone SOC. The AI ​​module of the NPU (Neural Processing Unit) subsystem and the Modem module, deployed within the mobile phone SOC, collaborate to complete the precise low-power frequency and voltage modulation task for the Modem, achieving superior low-power performance. The AI ​​module can provide an AI model to determine the target power level of the terminal under the current workload.

[0039] Specifically, the AI ​​model can be a trained model, which can be determined by the AI ​​model through model training, or it can be a trained model sent to the AI ​​module by other devices for application. This disclosure does not limit this.

[0040] In embodiments of this disclosure, the trained model can be deployed within an AI module.

[0041] The performance parameter adjustment method disclosed herein can be applied to scenarios where the terminal is in a low-power scenario. In other words, the performance parameter adjustment method disclosed herein can identify whether the terminal is in a low-power scenario. When the terminal is in a low-power scenario, it determines the adjustment level of frequency and voltage, avoiding the waste of resources and performance caused by the terminal directly adjusting the level to the highest level.

[0042] The method and apparatus for adjusting the performance parameters provided in this application will now be described in detail with reference to the accompanying drawings.

[0043] Figure 2 This is a flowchart illustrating a method for adjusting performance parameters according to an embodiment of this disclosure, as shown below. Figure 2 As shown, the method includes the following steps: Step 201: Based on the indication information of the network device, determine the target range from multiple sets of candidate range information of the terminal's performance parameters.

[0044] In some embodiments, performance parameters include frequency and voltage, with each set of candidate gear information corresponding to a set of voltage and frequency for the central processing unit and / or at least one hardening accelerator of the terminal.

[0045] In some embodiments, the indication information of the network device may be carried in the indication message sent by the base station to the terminal, and the name of the indication information is not limited in this disclosure.

[0046] In some embodiments, the indication information of the network device may be an indication of a specific gear range, so that the terminal can determine the target gear range from multiple sets of candidate gear information.

[0047] In some embodiments, the indication information of the network device may be an indication of a specific gear, so that the terminal can determine a target gear range for frequency and voltage modulation based on the indicated gear, the range including multiple selectable gears.

[0048] In some embodiments, multiple sets of candidate tier information can be determined by the terminal side according to a protocol predefined or an instruction from the network device. Different candidate tier information can be constructed for different terminals.

[0049] In some embodiments, the central processing unit and / or hardening accelerator can respectively construct candidate gear information corresponding to their respective performance parameters, thereby obtaining a set of candidate gear information.

[0050] In some embodiments, the candidate gear information is the voltage and frequency ranges that the central processing unit can execute; and / or the voltage and frequency ranges that the hardening accelerator can execute. The capabilities of the central processing unit and the hardening accelerator may be the same or different for different terminals, and this disclosure does not limit this.

[0051] In some embodiments, the terminal may jointly adjust the central processing unit and the hardening accelerator, or may adjust the performance parameters of the central processing unit or the hardening accelerator separately, without limitation by this disclosure.

[0052] Step 202: Based on the terminal's operating status information under the current workload, determine the target gear within the target gear range.

[0053] In some embodiments, the running status information can be obtained by real-time detection of the terminal's running status under the current workload, where the current workload can be the load on the terminal while running the current software program.

[0054] In some embodiments, the running status information includes at least one of the following: foreground application identifier, background application identifier, thread load, input load, output load, network traffic, user interaction events, device attitude sensor data, remaining battery power, and chip temperature.

[0055] In the above embodiments, the operating status information can be operating status information that reflects the status of the device.

[0056] In some embodiments, foreground and background application identifiers can refer to the application currently receiving user focus and being interacted with, as well as the identifiers of services or processes running in the background that may consume resources. This information is used to determine the system's core service objects and potential sources of resource contention.

[0057] In some embodiments, thread load can refer to the number of software threads running or waiting to run on the CPU and their consumption of processor computing resources. It is one of the most direct indicators for measuring the real-time computing needs of a system.

[0058] In some embodiments, input load and output load can refer to the read / write data throughput and latency of the system storage device (such as UFS, memory), respectively. Input load reflects data loading demand, while output load reflects data storage or transmission demand; both together indicate the busy level of the I / O subsystem.

[0059] In some embodiments, network traffic can refer to the rate and total amount of data sent and received through interfaces such as cellular networks or Wi-Fi. It is a key parameter for evaluating the load of communication-related processing units (such as modems and network protocol stacks).

[0060] In some embodiments, user interaction events can refer to system events triggered by user input methods such as touchscreens, buttons, and voice. These events are typically highly sensitive to response latency and are direct signals that trigger rapid improvements in system performance.

[0061] In some embodiments, device attitude sensor data may refer to data provided by sensors such as accelerometers, gyroscopes, and magnetometers, used to determine the physical state of the device (e.g., stationary, moving, or facing). This data can be used to infer the user's usage scenario (e.g., handheld, vehicle-mounted).

[0062] In some embodiments, remaining battery capacity may refer to the battery's current charge level. This parameter directly affects the aggressiveness of the system's power management strategy, favoring a more conservative performance strategy to extend battery life when the battery is low.

[0063] In some embodiments, chip temperature may refer to the temperature reading of the SoC or a critical processing unit. This is a core input for system thermal management, where high temperatures trigger forced frequency reduction to protect the hardware.

[0064] In some embodiments, the runtime status information also includes user habit information, which is predicted by a model based on the runtime status information. The user habit information includes at least one of time-based habit, scene-related habit, in-application behavior habit, and performance preference habit.

[0065] In the above embodiments, the running status information may further include running status information reflecting the user's status.

[0066] In some embodiments, user habit information may be the habits determined at the current moment or under the current workload based on the real-time detected operating status information and the stored user habit table according to the correlation relationship.

[0067] In some embodiments, user habit information can be obtained by predicting current user habits using a pre-trained prediction model based on real-time detected operating status information.

[0068] In some embodiments, time-based habits can refer to regular patterns of user behavior on a device or a specific application that are learned over a long period of time (such as daily or weekly).

[0069] In some embodiments, scene-related habits can refer to a stable association between user behavior and specific physical or network scenes (such as home, office, or connecting to in-vehicle Bluetooth). For example, automatically connecting to Wi-Fi and muting the phone upon arriving at the office.

[0070] In some embodiments, in-app behavior patterns can refer to refined operating patterns of users when using a particular application. For example, whether a user engages in intense combat or idles in a game, or whether they quickly swipe to browse or read deeply in a social app.

[0071] In some embodiments, performance preference habits can refer to a user's subconscious tendency to trade off between "smoothness" and "battery life". For example, whether a user is willing to accept slightly shorter battery life for faster app launch speeds can be inferred from their historical reaction patterns to lag.

[0072] In some embodiments, within a target gear range, determining the target gear based on operating status information can be done by determining the target gear solely based on operating status information reflecting the device status, or by comprehensively determining the target gear based on operating status information reflecting both the device status and the user status, or by determining the target gear solely based on operating status information reflecting the user status.

[0073] In some embodiments, the accurate target gear can be determined within the target gear range based on the operating status information, rather than using the maximum gear of the target gear range indicated by the network device as the adjustment gear.

[0074] In some embodiments, the target level determined based on the operating status information is more in line with the energy consumption requirements of the terminal under the current workload.

[0075] In some embodiments, both the running status information and user habit information are real-time. Based on the running status information and / or user habit information, the performance parameters of the terminal can be dynamically adjusted in real time.

[0076] Specifically, in low-power scenarios, the terminal does not need to adjust the power level to the maximum level indicated by the network device. Therefore, by collecting operating status information and determining user habit information, the target power level that meets the terminal's needs can be determined within the range indicated by the network device.

[0077] In some embodiments, the target gear determined by the terminal is determined based on the central processing unit and the hardening accelerator, respectively, and the two modules are independent of each other.

[0078] In some embodiments, the operating status information is the real-time acquired status information of the terminal at the current moment. Based on the current status information, the target level at the current moment can be determined. If the status information acquired at the next moment differs from the current status information, the determined target level can also differ from the current level, thereby achieving dynamic adjustment of the terminal's performance parameters. It is understood that the frequency and voltage required by the terminal under different workloads can be different. The performance parameter adjustment method proposed in this disclosure can determine the corresponding target voltage based on real-time operating status information to achieve a dynamic increase or decrease in communication bandwidth between 0 and peak value during service operations.

[0079] Step 203: Based on the target gear, adjust the performance parameters of the central processing unit and / or at least one hardening accelerator respectively.

[0080] In some embodiments, based on the target level, the performance parameters of the central processing unit at that level, and / or the performance parameters of each hardening accelerator at that level, can be determined.

[0081] In some embodiments, the performance parameters of the central processing unit and / or at least one hardening accelerator are adjusted based on the target level. This may involve adjusting the current performance parameter of the central processing unit to the value of the performance parameter under that level, and / or adjusting the current performance parameter of each hardening accelerator to the value of the performance parameter under that level.

[0082] In the above embodiments, a mechanism is implemented to determine the target performance level range by instructing the network device, and to finely select the performance level within the range by combining the real-time device status and user status of the terminal. This achieves a two-layer decision-making process for performance adjustment. By combining the theoretical capability constraints on the communication side with the actual demand perception on the terminal side, the adjustment of performance parameters not only meets network requirements but also avoids performance overkill and power waste caused by directly adopting the maximum capability configuration.

[0083] Figure 3 This is a flowchart illustrating another method for adjusting performance parameters according to an embodiment of this disclosure, as shown below. Figure 3 As shown, Figure 3 right Figure 2 Step 201 in the document will be further explained, including the following steps: Step 301: Determine candidate gear information.

[0084] In some embodiments, the candidate gear information includes a gear interval identifier, at least one gear in the gear interval corresponding to the gear interval identifier, and each gear includes the frequency and voltage of the central processing unit and / or the frequency and voltage of at least one hardening accelerator.

[0085] In some embodiments, determining the candidate gear information includes: determining at least one gear range based on configuration information; configuring a gear and frequency and voltage corresponding to each gear range for the central processing unit based on the at least one gear range; and / or configuring a gear and frequency and voltage corresponding to each gear range for each hardening accelerator in at least one hardening accelerator based on the at least one gear range.

[0086] In some embodiments, the configuration information may be determined according to a protocol.

[0087] For example, the Modem protocol stack quantizes four frequency and voltage modulation levels according to the protocol specification configuration: CFG0 (level 0 range), CFG1 (level 1 range), CFG2 (level 2 range), and CFG3 (level 3 range).

[0088] In some embodiments, the number of gear intervals determined based on the configuration information can be determined comprehensively based on the terminal's own capabilities and the instructions of the network device. For example, 4, 6, 8, or 10 gear intervals may be quantified based on the configuration information. The specific number of gear intervals is not limited in this disclosure.

[0089] In some embodiments, based on at least one gear range, the central processing unit is configured with the gear corresponding to each gear range and the frequency and voltage corresponding to each gear range. This can be achieved by the central processing unit configuring the highest voltage and highest frequency corresponding to each gear range within each gear range according to the number of gear ranges, and allocating the voltage range and frequency range within two adjacent gear ranges to multiple gear ranges.

[0090] For example, the CPU is designed with 4 sets of maximum voltage frequencies for 4 gears: DVFS-CPU-gear-max-0 (CPU maximum gear parameter in gear 0), DVFS-CPU-gear-max-1 (CPU maximum gear parameter in gear 1), DVFS-CPU-gear-max-2 (CPU maximum gear parameter in gear 2), and DVFS-CPU-gear-max-3 (CPU maximum gear parameter in gear 3).

[0091] In some embodiments, based on at least one gear range, each hardening accelerator in at least one hardening accelerator is configured with a gear corresponding to each gear range and a frequency and voltage corresponding to each gear range. This can be done by configuring the highest voltage and highest frequency in each gear range for each hardening accelerator based on the number of gear ranges, and allocating the voltage range and frequency range in two adjacent gear ranges to multiple gears.

[0092] In some embodiments, the frequency and voltage of each gear within the gear range determined by each hardening accelerator may be different or the same, and this disclosure does not limit this.

[0093] For example, all hardening accelerators are designed with 4 sets of maximum voltage frequencies for 4 gears: DVFS-ACCn-gear-max-0 (the highest gear parameter for the 0th gear hardening accelerator), DVFS-ACCn-gear-max-1 (the highest gear parameter for the 1st gear hardening accelerator), DVFS-ACCn-gear-max-2 (the highest gear parameter for the 2nd gear hardening accelerator), and DVFS-ACCn-gear-max-3 (the highest gear parameter for the 3rd gear hardening accelerator).

[0094] For example, such as Figure 6AAs shown, based on the four gears above, the Modem and AI modules simultaneously determine four frequency and voltage modulation ranges for the CPU and all hardened accelerators: CFG0: gear_range_0: [gear-0, gear-n(<=gear-max-0)] (gear range and parameters for gear 0), CFG1: gear_range_1: [gear-n+1, ​​gear-m(<=gear-max-1)] (gear range and parameters for gear 1), CFG2: gear_range_2: [gear-m+1, gear-o(<=gear-max-2)] (gear range and parameters for gear 2), CFG3: gear_range_3: [gear-o+1, gear-p(<=gear-max-3)] (gear range and parameters for gear 3).

[0095] For example, the Modem protocol stack quantizes 6 frequency and voltage modulation levels according to the protocol specification configuration: CFG0 (level 0 range), CFG1 (level 1 range), CFG2 (level 2 range), CFG3 (level 3 range), CFG4 (level 4 range), and CFG5 (level 5 range). The central processing unit and each hardening accelerator determine six frequency and voltage modulation ranges based on the quantized six gears: CFG0: gear_range_0: [gear-0, gear-n(<=gear-max-0)] (gear range and parameters for gear 0), CFG1: gear_range_1: [gear-n+1, ​​gear-m(<=gear-max-1)] (gear range and parameters for gear 1), CFG2: gear_range_2: [gear-m+1, gear-o(<=gear-max-2)] (gear range and parameters for gear 2), CFG3: gear_range_3: [gear-o+1, gear-p(<=gear-max-3)] (gear range and parameters for gear 3), CFG4: gear_range_4: [gear-p+1, gear-q(<=gear-max-4)] (gear range and parameters for gear 4), CFG5: gear_range_5: [gear-q+1, gear-r(<=gear-max-5)] (5-gear range and parameters).

[0096] In the above embodiments, the pre-configuration and quantification of performance tuning capabilities were completed at the system design level, ensuring the determinism and reliability of the entire tuning framework in hardware adaptation and parameter management.

[0097] Step 302: Determine the gear range below the highest gear indicated by the instruction information as the target gear range.

[0098] In some embodiments, the indication information of the network device may carry a gear range identifier, thereby identifying the gears below the highest gear in at least one gear range corresponding to the gear range identifier as the target gear range. In some embodiments, the indication information of the network device may carry a gear identifier, so that the terminal can determine the gear corresponding to this identifier as the highest gear indicated by the network device, and determine all gears below this gear as the target gear range.

[0099] For example, such as Figure 6A The diagram shows that after the MODEM receives the configuration from the base station, it synchronously indicates the current frequency and voltage modulation level to the AI ​​module.

[0100] For example, such as Figure 6B As shown in the diagram, when the base station sends out the configuration CFG0 / CFG3, the Modem protocol stack synchronously instructs the AI ​​module on the current frequency and voltage modulation range: gear_range_0 / gear_range_3.

[0101] In the above embodiments, the structured composition of candidate gear information is clearly defined, mapping abstract indication information to target gear ranges containing specific gears and parameters. A clear and configurable gear mapping rule is established, providing a specific and operable implementation path for "determining the target gear range," ensuring that network indications can be accurately and efficiently transformed into performance adjustment constraints within the terminal.

[0102] Figure 4 This is a schematic flowchart illustrating another method for adjusting performance parameters according to an embodiment of this disclosure. Figure 4 based on Figures 2-3 The illustrated embodiment is for Figure 2 Step 202 in the text will be further explained, such as Figure 4 As shown, it includes the following steps: Step 401: Based on the target gear range, determine at least one pre-adjustment gear corresponding to the central processing unit and / or at least one pre-adjustment gear corresponding to the hardening accelerator.

[0103] In some embodiments, each gear range in at least one gear range of the central processing unit corresponds to multiple gears, and each gear corresponds to frequency and voltage. Based on the target gear range, multiple gears corresponding to the target gear range of the central processing unit can be determined as at least one pre-adjustment gear of the central processing unit.

[0104] In some embodiments, in at least one pre-adjustment level of the central processing unit, each pre-adjustment level includes a frequency parameter value and a voltage parameter value.

[0105] In some embodiments, for at least one hardening accelerator, in at least one gear range of each hardening accelerator, each gear range corresponds to multiple gears, each gear corresponds to frequency and voltage, and based on the target gear range, the multiple gears of the hardening accelerator corresponding to the target gear range can be determined as at least one pre-adjustment gear of the hardening accelerator.

[0106] In some embodiments, in at least one pre-adjustment setting of the hardening accelerator, each pre-adjustment setting includes a frequency parameter value and a voltage parameter value.

[0107] In the above embodiments, the terminal can determine the pre-adjustment level among the levels below the highest level indicated by the network device, thereby avoiding directly using the highest level indicated by the network device as the target level for performance parameter adjustment, and avoiding directly adjusting the central processing unit and hardening accelerator to the highest level.

[0108] Step 402: Based on the operating status information, the target gear of the central processing unit is determined in at least one pre-adjustment gear corresponding to the central processing unit, and / or the target gear of the hardening accelerator is determined in at least one pre-adjustment gear corresponding to the hardening accelerator, using a trained model.

[0109] In some embodiments, the trained model is obtained by training an initial model using training data, which includes input features and labels. The input features are feature groups composed of terminal operating status information and user habit information under different scenarios or different workloads. The labels are gears corresponding to a set of feature groups, which correspond to a set of frequencies and voltages.

[0110] In some embodiments, the trained model may be obtained by training a neural network model using training data; or, it may be obtained by training a linear model using training data; or, it may be obtained by training a tree model or a clustering model, etc. The specific type of initial model can be selected according to the scenario or requirements, and this disclosure does not limit it.

[0111] In some embodiments, after the trained model is trained on the initial model using training data to obtain the first model, the first model is used to predict the gear position, and the predicted gear position is used as feedback to adjust the parameters of the first model until the loss function is minimized to obtain a model for determining the target gear position.

[0112] In some embodiments, the trained model can output the target gear within the target gear range by taking the terminal's operating status information under the current workload and / or user habit information as input features.

[0113] In some embodiments, the trained model may pre-obtain at least one gear range of the central processing unit, and multiple gears within each gear range, and at least one gear range of at least one hardened accelerator, and multiple gears within each gear range.

[0114] In some embodiments, the trained model can obtain a target gear range determined based on the indication information of the network device, thereby determining the target gear of the central processing unit in at least one pre-adjustment gear corresponding to the central processing unit, and / or determining the target gear of the hardening accelerator in at least one pre-adjustment gear corresponding to the hardening accelerator based on the operating status information.

[0115] In some embodiments, a trained model can be used to intelligently identify the real-time power consumption requirements of the terminal based on the operating status information, so as to identify low-power scenarios and determine the target level of the terminal in low-power scenarios. This avoids determining the highest level indicated by the network device as the target level in low-power scenarios, which would otherwise waste the performance resources of the terminal.

[0116] For example, such as Figure 6A The diagram illustrates that after the modem receives the base station's configuration, it synchronously instructs the AI ​​module on the current frequency and voltage modulation level. Through its powerful data collection, analysis, processing, and learning prediction capabilities, the AI ​​module understands the user's mobile phone usage habits and the system processing power requirements of all apps. It intelligently identifies low-power frequency and voltage modulation scenarios and accurately determines the current system frequency and voltage modulation level: gear-x, which cannot exceed the maximum frequency and voltage modulation level indicated by the modem's protocol stack.

[0117] For example, such as Figure 6B As shown in the diagram, the AI ​​module dynamically adjusts the frequency and voltage adjustment ranges (gear_range_0 / gear_range_3) based on its real-time evaluation results. It will prioritize adjusting and maintaining the range at a reasonable level for the current system. The AI ​​frequency and voltage adjustment mechanism will adjust from the low level to the high level in the current range, and then from the high level to the low level, based on the actual business situation.

[0118] In the above embodiments, fine-grained performance allocation at the component level based on artificial intelligence was implemented. This enables the central processing unit and each hardened accelerator to obtain differentiated optimal performance configurations according to their actual roles and loads in different tasks, further optimizing energy efficiency.

[0119] Figure 5This is a schematic flowchart illustrating another method for adjusting performance parameters according to an embodiment of this disclosure. Figure 5 based on Figures 2-4 The illustrated embodiment is for Figure 2 Step 203 in the text will be further explained, such as Figure 5 As shown, it includes the following steps: Step 501: Based on the target gear of the central processing unit, determine the first control command corresponding to the central processing unit, and / or based on the target gear of the hardening accelerator, determine the second control command corresponding to the hardening accelerator.

[0120] In some embodiments, a first control command for adjusting the performance parameters of the central processing unit can be determined based on the target gear.

[0121] In some embodiments, after the trained model determines the target gear of the central processing unit, it can send the target gear to the Modem protocol stack so that the Modem protocol stack can generate the first control command.

[0122] In some embodiments, a second control command for adjusting the performance parameters of each hardening accelerator can be determined based on the target gear.

[0123] In some embodiments, after the trained model determines the target level of the hardening accelerator, it can send the target level to the Modem protocol stack so that the Modem protocol stack can generate a second control command.

[0124] In some embodiments, the central processing unit and the hardening accelerator can independently determine the corresponding control commands based on the target gear.

[0125] In some embodiments, the frequency and voltage corresponding to the target level determined by the central processing unit at the current moment may differ from the frequency and voltage corresponding to the previously determined target level, or the values ​​of both parameters may differ; this disclosure does not impose any restrictions on this. Specifically, when adjusting performance parameters at the current moment, the central processing unit may adjust only one performance parameter, frequency or voltage, or it may adjust both frequency and voltage simultaneously.

[0126] In some embodiments, the frequency and voltage corresponding to the target setting determined by the hardening accelerator at the current moment may differ from the frequency and voltage corresponding to the previously determined target setting, or the values ​​of both parameters may differ; this disclosure does not impose any restrictions on this. Specifically, when adjusting the performance parameters of the hardening accelerator at the current moment, it may adjust only one performance parameter, frequency or voltage, or it may adjust both frequency and voltage simultaneously.

[0127] Step 502: Send the first control command to the central processing unit, and / or send the second control command to the hardening accelerator.

[0128] In some embodiments, a first control command is sent to the central processing unit to regulate the frequency and / or voltage of the central processing unit.

[0129] In some embodiments, a second control command is sent to the hardening accelerator to regulate the frequency and / or voltage of the hardening accelerator.

[0130] In some embodiments, for each of the at least one hardening accelerators, the frequency and voltage corresponding to each configured gear can be different. Therefore, for each hardening accelerator, after executing the target gear corresponding to the second control command, its operating frequency and operating voltage can be different.

[0131] For example, the AI ​​module synchronously instructs the evaluated frequency and voltage adjustment levels to the Modem protocol stack, which then completes the frequency and voltage adjustment work for the CPU and all hardened accelerators.

[0132] In the above embodiments, a closed loop from intelligent decision-making to hardware action is completed, ensuring that the target gear can be executed accurately and synchronously, thereby achieving precise control over the performance of the central processing unit and / or hardening accelerator.

[0133] In summary, by constructing a two-layer collaborative adjustment architecture of "network-side upper limit setting and terminal-side optimization," and introducing AI models for refined decision-making, the problem of ineffective power consumption caused by theoretical peak capacity configurations far exceeding actual needs in advanced networks such as 5G / 6G is fundamentally solved, effectively improving terminal battery life. Simultaneously, the solution's proactive adjustment based on comprehensive state awareness and user habit prediction smooths performance output, reduces lag and overheating, and enhances the user experience.

[0134] Furthermore, the unified leveling system and coordinated control of the CPU and various hardened accelerators avoid efficiency losses caused by performance mismatch between hardware components, achieving optimal system-level energy efficiency.

[0135] The following is a specific implementation of a performance parameter adjustment method provided in this disclosure: The architecture diagram of the AI ​​frequency and voltage modulation mechanism is as follows: Figure 6A As shown, (1) The Modem protocol stack quantizes four frequency modulation and voltage modulation levels according to the protocol specification configuration: CFG0, CFG1, CFG2, and CFG3.

[0136] (2) The CPU is designed with 4 sets of maximum voltage frequencies for 4 gears: DVFS-CPU-gear-max-0, DVFS-CPU-gear-max-1, DVFS-CPU-gear-max-2, DVFS-CPU-gear-max-3.

[0137] (3) All hardening accelerators are designed with 4 sets of maximum voltage frequencies for 4 gears: DVFS-ACCn-gear-max-0, DVFS-ACCn-gear-max-1, DVFS-ACCn-gear-max-2, DVFS-ACCn-gear-max-3.

[0138] (4) Based on the above 4 gears, the Modem and AI modules simultaneously determine 4 frequency and voltage modulation ranges for the CPU and all hardened accelerators respectively: CFG0: gear_range_0: [gear-0, gear-n(<=gear-max-0)], CFG1: gear_range_1: [gear-n+1, ​​gear-m(<=gear-max-1)], CFG2: gear_range_2: [gear-m+1,gear-o(<=gear-max-2)], CFG3: gear_range_3: [gear-o+1, gear-p(<=gear-max-3)].

[0139] (5) When the MODEM receives the configuration from the base station, it synchronously indicates the current frequency and voltage modulation level to the AI ​​module.

[0140] (6) The AI ​​module, through its powerful data collection, analysis and processing and learning prediction capabilities, can grasp the user's mobile phone usage habits and the system processing power requirements of all APPs, intelligently identify low power consumption scenarios and frequency and voltage regulation scenarios, and accurately decide the current system frequency and voltage regulation level: gear-x, which shall not exceed the current maximum frequency and voltage regulation level indicated by the Modem protocol stack.

[0141] (7) The AI ​​module synchronously instructs the evaluated frequency and voltage adjustment levels to the Modem protocol stack, and then the Modem protocol stack completes the frequency and voltage adjustment work of the CPU and all hardened accelerators.

[0142] The process of AI frequency and voltage modulation mechanism is as follows: Figure 6B As shown, the process is briefly described below: (1) When the base station sends out the configuration CFG0 / CFG3, the Modem protocol stack synchronously instructs the AI ​​module to indicate the current frequency and voltage modulation range: gear_range_0 / gear_range_3.

[0143] (2) The AI ​​module does not directly instruct the frequency and voltage to the highest level like the modem frequency and voltage regulation mechanism: gear-n / gear-p.

[0144] (3) The AI ​​module dynamically adjusts the frequency and voltage range gear_range_0 / gear_range_3 according to its real-time evaluation results. It will prioritize adjusting and maintain the current reasonable range. The AI ​​frequency and voltage adjustment mechanism will adjust from the low range to the high range according to the actual business situation, and then adjust from the high range to the low range.

[0145] The gain of the AI ​​frequency and voltage modulation mechanism compared to the modem frequency and voltage modulation mechanism is calculated as (time spent in non-maximum power level) × (power consumption difference per unit time between the current maximum power level and the corresponding low power level) during dynamic adjustment.

[0146] In summary, during business operations, communication bandwidth dynamically fluctuates between 0 and its peak value (both increases and decreases). Modem frequency and voltage regulation mechanisms directly adjust to the highest level within the current bandwidth range, while AI frequency and voltage regulation mechanisms dynamically adjust across the entire current bandwidth range. Therefore, this dynamic fluctuation presents an opportunity for the AI ​​frequency and voltage regulation mechanism to generate power savings compared to the modem mechanism. Assuming the power consumption of the highest level in the current frequency and voltage regulation range is P_max (mA / ms), the power consumption of the i-th level adjusted by the AI ​​frequency and voltage regulation mechanism is P_i (mA / ms), the total dwell time at the i-th level is T_i (ms), and the total number of levels adjusted to is n, then the total power savings (mA) of the AI ​​frequency and voltage regulation mechanism compared to the modem frequency and voltage regulation mechanism is: P_saved = Σ [ (P_max - P_i) × T_i ], where i ranges from 1 to n.

[0147] Figure 7 A schematic diagram of the structure of a performance parameter adjustment device 70 according to an embodiment of this disclosure. (See diagram below.) Figure 7 As shown, the device includes: a determination module 710, an evaluation module 720, and a control module 730.

[0148] The determination module 710 is used to determine the target gear range from multiple sets of candidate gear information of the terminal's performance parameters based on the indication information of the network device. The performance parameters include frequency and voltage. Each set of candidate gear information corresponds to a set of voltage and frequency for the terminal's central processing unit and / or at least one hardening accelerator. The evaluation module 720 is used to determine the target gear within the target gear range based on the terminal's operating status information under the current workload. The control module 730 is used to adjust the performance parameters of the central processing unit and / or at least one hardening accelerator based on the target gear.

[0149] In some embodiments, the determining module is further configured to: determine candidate gear information, the candidate gear information including a gear range identifier, at least one gear in the gear range corresponding to the gear range identifier, each gear including the frequency and voltage of the central processing unit, and / or the frequency and voltage of at least one hardening accelerator; and determine the gears below the highest gear indicated by the indication information as the target gear range.

[0150] In some embodiments, the determining module is further configured to: determine at least one gear range based on configuration information; configure the central processing unit with a gear corresponding to each gear range and a frequency and voltage corresponding to each gear based on the at least one gear range; and / or configure the at least one hardening accelerator with a gear corresponding to each gear range and a frequency and voltage corresponding to each gear based on the at least one gear range.

[0151] In some embodiments, the running status information includes at least one of the following: foreground application identifier, background application identifier, thread load, input load, output load, network traffic, user interaction events, device attitude sensor data, remaining battery power, and chip temperature.

[0152] In some embodiments, the runtime status information also includes user habit information, which is predicted by a model based on the runtime status information. The user habit information includes at least one of time-based habit, scene-related habit, in-application behavior habit, and performance preference habit.

[0153] In some embodiments, the evaluation module is further configured to: determine at least one pre-adjustment gear corresponding to the central processing unit and / or at least one pre-adjustment gear corresponding to the hardening accelerator based on the target gear range; and determine the target gear of the central processing unit in the at least one pre-adjustment gear corresponding to the central processing unit and / or the target gear of the hardening accelerator in the at least one pre-adjustment gear corresponding to the hardening accelerator based on the operating status information and through a trained model.

[0154] In some embodiments, the control module is further configured to: determine a first control instruction corresponding to the central processing unit based on the target gear of the central processing unit, and / or determine a second control instruction corresponding to the hardening accelerator based on the target gear of the hardening accelerator; send the first control instruction to the central processing unit, and / or send the second control instruction to the hardening accelerator.

[0155] The performance parameter adjustment device proposed in this disclosure fundamentally solves the problem of ineffective power consumption caused by the configuration of theoretical peak capabilities far exceeding actual needs under advanced networks such as 5G / 6G. This is achieved by constructing a two-layer collaborative adjustment architecture of "network-side upper limit setting and terminal-side optimization" and introducing an AI model for refined decision-making. This effectively improves the terminal's battery life. At the same time, the proactive adjustment based on comprehensive state awareness and user habit prediction smooths performance output, reduces lag and overheating, and enhances the user experience.

[0156] Furthermore, the unified leveling system and coordinated control of the CPU and various hardened accelerators avoid efficiency losses caused by performance mismatch between hardware components, achieving optimal system-level energy efficiency.

[0157] Figure 8 This is a schematic diagram of the structure of an electronic device 800 for implementing the above-described method for adjusting performance parameters, according to an exemplary embodiment.

[0158] Reference Figure 8 The electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0159] Processing component 802 typically controls the overall operation of electronic device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0160] Memory 804 is configured to store various types of data to support the operation of electronic device 800. Examples of such data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0161] Power supply component 806 provides power to various components of electronic device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800.

[0162] Multimedia component 808 includes a screen that provides an output interface between electronic device 800 and user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When electronic device 800 is in an operating mode, such as a shooting mode or video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0163] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when electronic device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0164] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0165] Sensor assembly 814 includes one or more sensors for providing state assessments of various aspects of electronic device 800. For example, sensor assembly 814 can detect the on / off state of electronic device 800, the relative positioning of components such as the display and keypad of electronic device 800, changes in position of electronic device 800 or a component of electronic device 800, the presence or absence of user contact with electronic device 800, orientation or acceleration / deceleration of electronic device 800, and temperature changes of electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0166] Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices. Electronic device 800 can access wireless networks based on communication standards, such as WiFi, 2G or 3G, 4G LTE, 5G NR (NewRadio), or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0167] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0168] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of an electronic device 800 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0169] Embodiments of this disclosure also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the adjustment method of performance parameters described in the above embodiments of this disclosure.

[0170] Embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, provides a method for adjusting performance parameters as described in the above embodiments of this disclosure.

[0171] Embodiments of this disclosure also propose a chip including at least one processor and a communication interface; the communication interface is used to receive signals input to the chip or signals output from the chip, the processor communicates with the communication interface and implements the performance parameter adjustment method described in the above embodiments of this disclosure through logic circuits or executing code instructions, or includes the electronic device described in the above embodiments of this disclosure.

[0172] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0173] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0174] It should be understood that various parts of the embodiments of this disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0175] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a single processing module, or each unit can exist physically separately, or two or more units can be integrated into a single module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The aforementioned storage medium can be a read-only memory, a hard disk, or an optical disk, etc.

[0176] Although embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for adjusting a performance parameter, characterized in that, The method includes: Based on the indication information of the network device, the target range is determined from multiple sets of candidate range information of the terminal's performance parameters, the performance parameters including frequency and voltage, and each set of candidate range information corresponds to a set of voltage and frequency for the terminal's central processing unit and / or at least one hardening accelerator. Based on the terminal's operating status information under the current workload, the target gear is determined within the target gear range; Based on the target gear, the performance parameters of the central processing unit and / or the at least one hardening accelerator are adjusted respectively.

2. The method according to claim 1, characterized in that, The determination of the target performance range from multiple candidate performance level information of the terminal based on the indication information of the network device includes: The candidate gear information is determined, which includes a gear interval identifier, at least one gear in the gear interval corresponding to the gear interval identifier, and each gear includes the frequency and voltage of the central processing unit, and / or the frequency and voltage of the at least one hardening accelerator; The gears below the highest gear indicated by the instruction information are defined as the target gear range.

3. The method according to claim 2, characterized in that, Determining the candidate gear information includes: Based on the configuration information, determine at least one gear range; Based on the at least one gear range, configure the central processing unit with the gear corresponding to each gear range and the frequency and voltage corresponding to each gear range, and / or Based on the at least one gear range, each of the at least one hardening accelerators is configured with a gear corresponding to each gear range and a frequency and voltage corresponding to each gear range.

4. The method according to claim 1, characterized in that, The operating status information includes at least one of the following: foreground application identifier, background application identifier, thread load, input load, output load, network traffic, user interaction events, device attitude sensor data, remaining battery power, and chip temperature.

5. The method according to claim 4, characterized in that, The operational status information also includes user habit information. The user habit information is obtained by model prediction based on the running status information, and the user habit information includes at least one of time-based habit, scene-related habit, in-application behavior habit, and performance preference habit.

6. The method according to claim 4 or 5, characterized in that, The step of determining the target gear within the target gear range based on the terminal's operating status information under the current workload includes: Based on the target gear range, at least one pre-adjustment gear corresponding to the central processing unit and / or at least one pre-adjustment gear corresponding to the hardening accelerator are determined; Based on the operating status information, the target gear of the central processing unit is determined in at least one pre-adjustment gear corresponding to the central processing unit through a trained model, and / or the target gear of the hardening accelerator is determined in at least one pre-adjustment gear corresponding to the hardening accelerator.

7. The method according to claim 6, characterized in that, The adjustment of performance parameters of the central processing unit and / or at least one hardening accelerator based on the target gear level includes: Based on the target gear of the central processing unit, a first control command corresponding to the central processing unit is determined, and / or based on the target gear of the hardening accelerator, a second control command corresponding to the hardening accelerator is determined. The first control command is sent to the central processing unit, and / or the second control command is sent to the hardening accelerator.

8. A device for adjusting performance parameters, characterized in that, The device includes a determination module, an evaluation module, and a control module. The determining module is used to determine the target gear range from multiple sets of candidate gear information of the terminal's performance parameters based on the indication information of the network device. The performance parameters include frequency and voltage. Each set of candidate gear information corresponds to a set of voltage and frequency for the terminal's central processing unit and / or at least one hardening accelerator. The evaluation module is used to determine the target gear within the target gear range based on the terminal's operating status information under the current workload. The control module is used to adjust the performance parameters of the central processing unit and / or the at least one hardening accelerator based on the target gear.

9. The apparatus according to claim 8, characterized in that, The determining module is also used for: The candidate gear information is determined, which includes a gear interval identifier, at least one gear in the gear interval corresponding to the gear interval identifier, and each gear includes the frequency and voltage of the central processing unit, and / or the frequency and voltage of the at least one hardening accelerator; The gears below the highest gear indicated by the instruction information are defined as the target gear range.

10. The apparatus according to claim 9, characterized in that, The determining module is also used for: Based on the configuration information, determine at least one gear range; Based on the at least one gear range, configure the central processing unit with the gear corresponding to each gear range and the frequency and voltage corresponding to each gear range, and / or Based on the at least one gear range, each of the at least one hardening accelerators is configured with a gear corresponding to each gear range and a frequency and voltage corresponding to each gear range.

11. The apparatus according to claim 8, characterized in that, The operating status information includes at least one of the following: foreground application identifier, background application identifier, thread load, input load, output load, network traffic, user interaction events, device attitude sensor data, remaining battery power, and chip temperature.

12. The apparatus according to claim 11, characterized in that, The operational status information also includes user habit information. The user habit information is obtained by model prediction based on the running status information, and the user habit information includes at least one of time-based habit, scene-related habit, in-application behavior habit, and performance preference habit.

13. The apparatus according to claim 11 or 12, characterized in that, The evaluation module is also used for: Based on the target gear range, at least one pre-adjustment gear corresponding to the central processing unit and / or at least one pre-adjustment gear corresponding to the hardening accelerator are determined; Based on the operating status information, the target gear of the central processing unit is determined in at least one pre-adjustment gear corresponding to the central processing unit through a trained model, and / or the target gear of the hardening accelerator is determined in at least one pre-adjustment gear corresponding to the hardening accelerator.

14. The apparatus according to claim 13, characterized in that, The control module is also used for: Based on the target gear of the central processing unit, determine the first control command corresponding to the central processing unit, and / or Based on the target gear of the hardening accelerator, determine the second control command corresponding to the hardening accelerator; The first control command is sent to the central processing unit, and / or the second control command is sent to the hardening accelerator.

15. An electronic device, characterized in that, include: A processor and a memory for storing a computer program capable of running on the processor, wherein the processor, when running the computer program, performs the method of any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 7.

17. A program product, characterized in that, Includes computer instructions for causing a computer to perform the method of any one of claims 1 to 7.

18. A chip, characterized in that, It includes at least one processor and a communication interface; the communication interface is used to receive signals input to the chip or signals output from the chip, and the processor communicates with the communication interface and implements the method as described in any one of claims 1 to 7 through logic circuits or executing code instructions.

Images