Parameter optimization method and electronic device

Abstract

This application discloses a parameter optimization method and an electronic device. The method includes: obtaining the actual operating parameters of the memory module of the electronic device; determining the actual operating indicators of the memory module based on the actual operating parameters, wherein the operating indicators include any one or more of bandwidth, latency, stability, and power consumption; comparing the actual operating indicators with the theoretical optimal operating indicators of the memory module to determine the core operating indicators affecting the performance of the memory module, wherein the theoretical optimal operating indicators are determined based on the upper limit of the operating parameters of the memory module, motherboard, and processor of the electronic device; and determining the parameter optimization information of the memory module based on the core operating indicators and a target weight model, wherein the target weight model is determined according to the target usage scenario of the memory module.

Description

Technical Field

[0001] This application relates to the field of parameter optimization technology, and in particular to a parameter optimization method and electronic device. Background Technology

[0002] The performance of a computer's memory is a significant factor affecting its user experience. In related technologies, the parameters of memory modules used in computer devices are generally pre-configured at the factory. However, during use, these pre-configured parameters often fail to meet the user's actual memory performance needs in real-world scenarios. Therefore, optimizing memory parameters to improve performance has become an urgent problem to be solved. Summary of the Invention

[0003] Therefore, this application discloses the following technical solution:

[0004] The first aspect of this application provides a parameter optimization method, including:

[0005] Obtain the actual operating parameters of the memory module of the electronic device, and determine the actual operating indicators of the memory module based on the actual operating parameters. The operating indicators include any one or more of bandwidth, latency, stability and power consumption.

[0006] By comparing the actual operating indicators with the theoretical optimal operating indicators of the memory module, the core operating indicators affecting the performance of the memory module are determined. The theoretical optimal operating indicators are determined based on the upper limits of the operating parameters of the memory module, motherboard, and processor of the electronic device.

[0007] The parameter optimization information of the memory module is determined based on the core operating indicators and the target weight model, which is determined according to the target usage scenario of the memory module.

[0008] Optionally, determining the parameter optimization information of the memory module based on the core operating metrics and the target weight model includes:

[0009] Based on the core operating indicators, the actual operating parameters are optimized to obtain multiple sets of candidate operating parameters for the memory module;

[0010] The performance score corresponding to each group of candidate operating parameters is determined based on the target weight model.

[0011] The set of candidate operating parameters with the best corresponding performance score is determined as the parameter optimization information for the memory module.

[0012] Optionally, determining the parameter optimization information of the memory module based on the core operating metrics and the target weight model includes:

[0013] The system queries multiple alternative memory modules whose core operating metrics are superior to those of the memory module, where the current memory module refers to the memory modules currently contained in the memory module.

[0014] Based on the theoretical operating indicators corresponding to the candidate memory modules and the target weight model, the performance score corresponding to the candidate memory modules is determined;

[0015] The candidate memory module with the best performance score is identified as the recommended replacement memory module, and the model and parameters of the recommended replacement memory module are obtained as parameter optimization information for the memory module.

[0016] Optionally, the target weight model includes multiple weight values ​​corresponding to different operating indicators;

[0017] Based on the target weight model, a set of performance scores corresponding to the candidate operating parameters are determined, including:

[0018] Based on a set of candidate operating parameters, the expected operating metrics of the memory module when running based on the candidate operating parameters are determined;

[0019] Based on the weight values ​​of each operating indicator in the target weight model and the expected operating indicator, a set of performance scores corresponding to the candidate operating parameters are calculated.

[0020] Optionally, the optimization of the actual operating parameters based on the core operating metrics to obtain multiple sets of candidate operating parameters for the memory module includes:

[0021] Identify the actual operating parameters related to the core operating indicators as parameters to be optimized;

[0022] Based on multiple preset optimization ranges, the parameters to be optimized in the actual operating parameters are optimized to obtain multiple sets of candidate operating parameters for the memory module.

[0023] Optional, also includes:

[0024] In response to receiving a configuration trigger operation, the operating parameters of the memory module are configured according to the parameter optimization information, so that the memory module runs based on the operating parameters contained in the parameter optimization information;

[0025] The operating status of the memory module is detected after a preset time period;

[0026] If the operating status of the memory module does not meet the test conditions, new parameter optimization information is obtained again based on the actual operating parameters of the memory module.

[0027] Optionally, the target weight model is determined based on the target use case of the memory module, including at least one of the following:

[0028] The target usage scenario of the memory module is determined based on the scenario description information input by the user, and the target weight model corresponding to the target usage scenario is determined among multiple weight models.

[0029] Based on the applications that the electronic device has previously run and / or the applications that are currently running, the target use case of the memory module is determined, and a target weight model corresponding to the target use case is determined from multiple weight models.

[0030] Optionally, comparing the actual operating metrics with the theoretical optimal operating metrics of the memory module to determine the core operating metrics affecting the performance of the memory module includes:

[0031] Determine the difference between the actual operating indicators and the theoretical optimal operating indicators of the memory module, and obtain the ratio of the difference to the theoretical optimal operating indicators;

[0032] The operating indicator with the largest corresponding proportion is identified as the core operating indicator affecting the performance of the memory module.

[0033] Optionally, obtaining the actual operating parameters of the electronic device's memory module includes:

[0034] In response to the fulfillment of optimized triggering conditions, the actual operating parameters of the electronic device's memory module are obtained;

[0035] The conditions for satisfying the optimization trigger include at least one of the following:

[0036] The currently running application has been detected to be experiencing lag and / or abnormal interruption.

[0037] A memory optimization command entered by the user was detected.

[0038] Optionally, obtaining the actual operating parameters of the electronic device's memory module includes:

[0039] Based on the fault detection information of the electronic device, determine whether the electronic device has a memory-related fault;

[0040] The occupancy rate of the processor in the electronic device determines whether the processor is under high load.

[0041] If it is determined that there are no memory-related faults and the processor is not under high load, the actual operating parameters of the electronic device's memory module are obtained.

[0042] A second aspect of this application provides an electronic device, including a memory and a processor;

[0043] The memory is used to store computer programs;

[0044] The processor is used to execute the computer program to perform:

[0045] Obtain the actual operating parameters of the memory module of the electronic device, and determine the actual operating indicators of the memory module based on the actual operating parameters. The operating indicators include any one or more of bandwidth, latency, stability and power consumption.

[0046] By comparing the actual operating indicators with the theoretical optimal operating indicators of the memory module, the core operating indicators affecting the performance of the memory module are determined. The theoretical optimal operating indicators are determined based on the upper limits of the operating parameters of the memory module, motherboard, and processor of the electronic device.

[0047] The parameter optimization information of the memory module is determined based on the core operating indicators and the target weight model, which is determined according to the target usage scenario of the memory module. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0049] Figure 1 This is a flowchart of a parameter optimization method provided in an embodiment of this application;

[0050] Figure 2 This is a flowchart of a method for determining parameter optimization information provided in an embodiment of this application;

[0051] Figure 3 This is a flowchart of a testing method after determining parameters, provided in an embodiment of this application;

[0052] Figure 4 This is a flowchart of a method for obtaining actual operating parameters provided in an embodiment of this application;

[0053] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0054] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0055] This embodiment provides a parameter optimization method; see [link to relevant documentation] Figure 1 The method may include the following steps.

[0056] S101, obtain the actual operating parameters of the memory module of the electronic device, and determine the actual operating indicators of the memory module based on the actual operating parameters. The operating indicators include any one or more of bandwidth, latency, stability and power consumption.

[0057] The electronic device in this embodiment can be a computer device with at least one memory slot on the motherboard, which can install at least one slot-type memory module, such as, but not limited to, laptops, desktop computers, and other computer devices. The parameter optimization method in this embodiment can be executed by the processor of this computer device.

[0058] The memory module of an electronic device can be understood as a hardware module consisting of the slot on the motherboard of the electronic device for inserting memory modules and the memory modules inserted thereon. In other words, the memory module includes the memory module slot and the memory module.

[0059] Actual operating metrics refer to the actual performance indicators exhibited by the memory module in its current state. In other words, actual operating metrics include any one or more of the memory module's current actual bandwidth, actual latency, actual stability, and actual power consumption.

[0060] Among the performance metrics, bandwidth determines how much data can be read and written from the memory module per unit time. Taking video playback as an example, the higher the bandwidth, the higher the quality video frames can be read from memory per unit time, thus supporting the playback of higher quality videos. Latency determines the time it takes for the processor to actually obtain the data from memory each time it initiates a memory access. The lower the latency, the shorter this time. Stability determines the probability of memory errors under high load. The higher the stability, the less likely it is to cause errors when reading and writing data from memory. When the stability is low, problems such as memory overflow and data errors during reading and writing are more likely to occur under high load, which can lead to the crash of the currently running program. Power consumption determines the power consumption of the memory module. The lower the power consumption, the less power is consumed in the same amount of time.

[0061] S102, compare the actual operating indicators with the theoretical optimal operating indicators of the memory module to determine the core operating indicators that affect the performance of the memory module. The theoretical optimal operating indicators are determined based on the upper limit of the operating parameters of the electronic device's memory module, motherboard, and processor.

[0062] S103 determines the parameter optimization information of the memory module based on the core operating indicators and the target weight model. The target weight model is determined according to the target usage scenario of the memory module.

[0063] The beneficial effects of this embodiment are as follows:

[0064] After determining the core operating indicators that affect current performance based on actual operating indicators and theoretical optimal operating indicators, the parameters of the memory module are optimized by combining the core operating indicators with the target weight model corresponding to the specific target use scenario. This yields parameter optimization information, enabling users to adjust the operating parameters of the memory module based on the parameter optimization information. Thus, this solution can assist users in dynamically adjusting the parameters of the memory module according to the actual use scenario, so that the memory module can perform well in different scenarios and improve the user experience of electronic devices.

[0065] Actual operating parameters refer to the actual operating parameters of the memory module at the current moment. In step S101, the processor can collect the actual operating parameters of the memory module in real time through the software program and / or related sensors built into the electronic device for detecting operating parameters. For example, the actual operating parameters can be collected through the relevant data interface provided by the basic input / output system (BIOS) of the electronic device. For specific collection methods, please refer to the relevant technologies in the field of computer parameter detection, which will not be elaborated here.

[0066] As examples, the actual operating parameters obtained in S101 may include, but are not limited to, any one or more of the following:

[0067] The frequency, column address strobe delay (CAS Latency, CL), row-to-column delay (tRCD), row precharge time (tRP), row activity time (tRAS), bit width, number of channels, and voltage are all considered. Bit width indicates the amount of data that can be read or written in each read / write operation of the memory module, and the number of channels indicates the number of memory modules that can be connected to the memory module at the same time.

[0068] Among them, frequency is one of the parameters that directly affects the bandwidth of the memory module. When the memory module contains a DDR double speed memory module, the bandwidth in the actual operating indicators of the memory module represents the amount of data that can be read and written per unit time when reading and writing the memory module. Specifically, it can be approximately determined based on the frequency in the actual operating parameters according to the following formula (1): Bandwidth = frequency * bit width * number of channels * 2 / 8, (1).

[0069] CL represents the waiting time required for the memory module to receive the processor's read / write instruction and actually begin reading / writing data. This time is measured in clock cycles; the smaller the value, the lower the latency. Latency in general operating metrics can be determined using formula (2), based on CL and frequency: Latency = CL / Frequency, (2).

[0070] tRCD primarily affects the speed of sequential access to different columns, and is more sensitive to use cases involving frequent random reads and writes. These use cases include, but are not limited to, game loading scenarios and multi-task switching scenarios. In other words, in use cases involving frequent random reads and writes, tRCD will have a significant impact on latency in runtime metrics. The smaller the tRCD, the lower the actual latency of the memory module, and vice versa.

[0071] tRP primarily affects row switching speed and is more sensitive to use cases involving a large amount of random access, such as database operations. In other words, in use cases involving a large amount of random access, tRP significantly impacts latency metrics; a smaller tRP results in lower actual latency for the memory module, and vice versa.

[0072] tRAS refers to the shortest time interval between activating a row of memory and closing it. It defines the minimum number of clock cycles that must be kept on when a row of memory is accessed. In electronic devices, tRAS, tRCD, and CL should satisfy the constraint: tRAS ≥ tRCD + CL + 2. If this constraint is not met and tRAS is set too small, data will not be refreshed in time when reading and writing memory, which may lead to errors.

[0073] After obtaining the above actual operating parameters, the actual operating indicators (actual operating indicators) of the memory module can be determined based on the actual operating parameters. The actual bandwidth can be calculated by substituting the actual frequency into the formula (1) mentioned above, and the actual latency can be calculated by substituting the actual frequency and CL into the formula (2). Energy consumption is positively correlated with frequency. Generally, the higher the frequency of the memory module, the more its energy consumption increases approximately with the square of the frequency. Therefore, energy consumption can be calculated based on the formula (3) and the frequency in the actual operating parameters: Energy consumption = Frequency * Frequency * Growth coefficient, (3), where the growth coefficient can be a pre-set fixed parameter; Stability can be determined based on CL, tRCD and tRAS in the actual operating parameters according to the formula (4): Stability = tRAS - (CL + tRCD), (4). The higher the stability, the less likely it is to make mistakes when reading and writing memory, and the more stable the program runs. Conversely, the more likely it is to make mistakes, and the less stable the program runs.

[0074] Optionally, when calculating latency, different methods can be used depending on the target usage scenario. For example, in usage scenarios involving frequent random reads and writes, the ratio of (CL + tRCD) / frequency can be used as the latency, thus considering the impact of tRCD on latency; in usage scenarios involving a large number of random accesses, the ratio of (CL + tRP) / frequency can be used as the latency, thus considering the impact of tRP on latency. This allows for a more accurate assessment of the actual latency of the memory module in the corresponding usage scenario, improving the accuracy of the parameter optimization information determined in this solution.

[0075] In step S102, the upper limit of the operating parameters of the memory module can be obtained from the memory module, motherboard and processor of the electronic device.

[0076] The upper limit of operating parameters refers to the optimal operating parameters that the memory module can support under the current hardware limitations of the memory module, motherboard and processor. For example, the highest frequency that can be supported, the minimum timing parameters, etc. The timing parameters are the collective term for CL, tRCD, tRP and tRAS mentioned above.

[0077] One way to obtain the upper limit of operating parameters from a memory module is to obtain the highest frequency and minimum timing operating parameters supported by the memory module from the serial presence detection (SPD) chip of each memory module contained in the memory module.

[0078] If there is only one memory stick, the highest frequency and the lowest timing parameters can be used as the upper limit of the running parameters;

[0079] If there are multiple memory modules, the minimum of the highest frequencies of the multiple memory modules can be used as the upper limit of the frequency, and the maximum value of the timing parameters of the multiple memory modules (corresponding to the case with the longest latency) can be used as the upper limit of the timing parameters.

[0080] One way to obtain the upper limit of operating parameters from the motherboard and processor is to obtain the highest frequency of memory read / write supported by the motherboard and the highest frequency of memory read / write supported by the processor. Then, the minimum value among the highest frequency supported by the motherboard, the highest frequency supported by the processor, and the highest frequency supported by the memory module can be determined as the upper limit of the frequency.

[0081] Furthermore, the minimum timing parameters supported by the motherboard and the minimum timing parameters supported by the processor can be obtained. Thus, the maximum value among the timing parameters supported by the motherboard, processor, and memory modules can be determined as the upper limit of the timing parameters.

[0082] The upper limit of operating parameters can also include the maximum number of channels supported by the motherboard, which indicates the maximum number of memory modules that can be installed in the memory module. The upper limit of operating parameters can also include the maximum bit width supported by the memory modules.

[0083] After obtaining the above upper limits of operating parameters, the upper limits of operating parameters can be substituted into the aforementioned formulas (1) to (4). The operating indicators calculated based on these upper limits of operating parameters are the theoretical optimal operating indicators. The theoretical optimal operating indicators represent the best performance that the memory module can achieve when running with the optimal operating parameters allowed by the current hardware.

[0084] Optionally, different use cases may have different requirements for the same performance metrics. For example, when playing videos, to improve image quality, the highest possible bandwidth is required while allowing for greater latency. When running games, to respond to user actions promptly, the lowest possible latency is required while allowing for less bandwidth. Therefore, the theoretically optimal performance metrics can also vary depending on the target use case. In other words, the theoretical performance metrics corresponding to the target use case can be pre-configured based on the performance metric requirements of the target use case and the upper limit of the performance parameters.

[0085] One implementation involves pre-determining and configuring the theoretically optimal operating parameters for each common use scenario of electronic devices, including but not limited to office scenarios, gaming scenarios, design scenarios, programming scenarios, and meeting scenarios, based on the aforementioned upper limit of operating parameters. For example, if the bandwidth calculated based on the upper limit of operating parameters is 120 gigabytes per second (GB / s), then for meeting scenarios that require high bandwidth, the bandwidth in the theoretically optimal operating parameters can be configured as 120 GB / s. For gaming scenarios that allow lower bandwidth, the bandwidth in the theoretically optimal operating parameters can be slightly reduced from this, such as being configured as 110 GB / s.

[0086] The performance requirements for each operating scenario can be pre-configured by the user or relevant manufacturers, or determined based on user feedback during electronic device use. For example, if frequent lag is detected when running a game, it indicates that the game scenario has high latency requirements.

[0087] Core performance metrics can be determined based on the "barrel effect," which compares actual performance metrics with the theoretically optimal performance metrics of the memory module. The barrel effect suggests that the worst-performing metric among the actual performance metrics has the greatest impact on memory module performance and user experience. Therefore, optimizing the worst-performing metric can maximize performance and user experience improvements. Thus, by comparing and identifying the worst-performing metrics relative to the theoretical performance metrics, core performance metrics can be established for targeted optimization.

[0088] One possible way to determine core performance indicators is:

[0089] Determine the difference between the actual operating indicators and the theoretical optimal operating indicators of the memory module, and obtain the ratio of the difference to the theoretical optimal operating indicators;

[0090] The operating indicator with the largest corresponding proportion is identified as the core operating indicator affecting the performance of the memory module.

[0091] In the above determination method, the difference between each actual operating indicator and the corresponding theoretical optimal operating indicator can be calculated. The absolute value of the difference is then divided by the corresponding theoretical optimal operating indicator to obtain the proportion corresponding to this actual operating indicator.

[0092] For example, obtain the absolute value of the difference between the actual bandwidth and the theoretical optimal bandwidth, divide the absolute value by the theoretical optimal bandwidth to get the proportion corresponding to the bandwidth, and process latency, stability and energy consumption in the same way to get the proportion corresponding to latency, stability and energy consumption.

[0093] Finally, the item with the largest corresponding proportion among bandwidth, latency, stability, and energy consumption was identified as the core operating indicator. For example, the proportions of bandwidth, latency, stability, and energy consumption were 5%, 15%, 4%, and 5% respectively, indicating that the current memory module's latency was the worst relative to its theoretical optimal value, and there was considerable room for optimization. Therefore, latency was identified as the core operating indicator that needed to be optimized.

[0094] The advantage of determining core operating indicators using the above method is that:

[0095] Those operating indicators that deviate significantly from the theoretical optimal operating indicators are identified as core operating indicators. In subsequent optimization processes, these core operating indicators are prioritized for optimization. This approach not only improves optimization efficiency by quickly obtaining parameter optimization information but also achieves a substantial performance improvement.

[0096] In S103, after determining the target usage scenario, the pre-stored target weight model in the electronic device's memory can be read. The electronic device can pre-configure the corresponding weight model for each common usage scenario and record it in its memory. A weight model can include multiple weight values ​​corresponding one-to-one with the aforementioned operational indicators, such as bandwidth weight values, latency weight values, stability weight values, and energy consumption weight values. The values ​​of these weight values ​​differ in different weight models. The value of each weight in the weight model reflects the importance of the corresponding operational indicator in the corresponding usage scenario, that is, the degree of impact on the user experience. A larger weight value indicates greater importance, and vice versa. For example, in the weight model for a gaming scenario, the latency weight value is larger, and the bandwidth weight value is smaller.

[0097] Based on the above configuration, in S103, after determining the target usage scenario, the weight model corresponding to the target usage scenario can be read from the memory as the target weight model.

[0098] There are no restrictions on the method for determining the weight model for each use case. It can be manually set by users or relevant manufacturers based on experience, or it can be determined based on user feedback during the use of electronic devices. For example, if frequent stuttering is detected when running a game, it indicates that latency has a significant impact on the game scenario. Therefore, a larger latency weight value is set in the weight model corresponding to the game scenario. If the memory bandwidth load is high when playing videos, it indicates that bandwidth has a significant impact on the video playback scenario. Therefore, a larger bandwidth weight value is set in the weight model corresponding to the video playback scenario (such as a meeting scenario).

[0099] Optional, see Figure 2 The process of determining the parameter optimization information of memory modules based on core operating indicators and target weight models may include the following steps.

[0100] S201 optimizes the actual operating parameters based on core operating indicators to obtain multiple sets of candidate operating parameters for the memory module.

[0101] S202, determine the performance score corresponding to each group of candidate operating parameters based on the target weight model.

[0102] S203 determines the set of candidate operating parameters with the best corresponding performance score as the parameter optimization information for the memory module.

[0103] In step S201, priority can be given to optimizing the operating parameters related to the core operating indicators among the actual operating parameters, and other operating parameters can be appropriately optimized on this basis to make each set of candidate operating parameters match. A set of candidate operating parameters may include any one or more of the following: candidate frequency, CL, tRCD, tRP, tRAS, bit width, and number of channels.

[0104] As an example, if delay is determined to be the core operating metric, then in S201, the frequency and CL related to delay can be optimized mainly, and tRCD and tRAS can be adjusted appropriately to ensure that the aforementioned constraint relationship regarding tRAS is satisfied, thereby obtaining multiple sets of candidate operating parameters. The values ​​of frequency, CL, tRCD, and tRAS can be different between two different sets of candidate operating parameters.

[0105] In step S202, the performance score of a set of candidate operating parameters means how well the memory module can perform in the target usage scenario if it runs according to this set of candidate operating parameters. The higher the performance score, the better the performance, and vice versa.

[0106] In S203, if only one set of candidate operating parameters has the highest performance score, this set of candidate operating parameters can be identified as parameter optimization information. If multiple sets of candidate operating parameters simultaneously have the highest performance score, the set with the smallest difference from the actual operating parameters can be selected as the parameter optimization information. For example, if two sets of candidate operating parameters both have the highest performance score, but one set only requires increasing the frequency by 300MHz based on the actual operating parameters, while the other set requires increasing the frequency by 500MHz, then the former can be output as the parameter optimization information. The advantage of this approach is that it reduces the adjustment range of the actual operating parameters during optimization, avoiding potential fault hazards caused by large adjustments to the operating parameters.

[0107] The parameter optimization information obtained by the above method is equivalent to a set of recommended operating parameters. After the parameter optimization information is output, the user can configure the memory module according to the operating parameters contained therein. For example, if the recommended frequency in the parameter optimization information is 4800MHz and the recommended CL is 23, then the user can set the frequency of the memory module to 4800MHz and the CL of the memory module to 23.

[0108] Optionally, if the memory module contains multiple memory modules, then when determining candidate operating parameters, candidate optimization parameters can be determined separately for each memory module. The corresponding parameter optimization information can include the operating parameters for the multiple memory modules, such as recommending that the frequency of memory module 1 is equal to 4800MHz, and recommending that the frequency of memory module 2 is equal to 3200MHz, etc.

[0109] according to Figure 2 The advantage of this method in determining parameter optimization information is that it identifies a set of candidate operating parameters that have the best performance score on the current hardware basis as parameter optimization information. This allows users to improve the performance of the memory module by reconfiguring the operating parameters according to the instructions of the parameter optimization information without replacing the memory module's memory sticks. The operation is convenient and does not incur additional costs.

[0110] For common usage scenarios of some electronic devices, according to Figure 2 The recommended operating parameters determined by the method can be seen in the following example. The optimization direction represents the importance of different operating indicators in the corresponding use scenario. The weight values ​​contained in the weight model of different use scenarios can be set based on the optimization direction.

[0111] In an office setting, applications such as document editing, web browsing, email processing, and online office applications are primarily used. The optimization priorities are stability > energy efficiency > bandwidth. Optimized parameters include: Frequency: DDR4 3200MHz / JEDEC, DDR5 4800MHz / JEDEC; Timings: CL=22-24, tRCD=24-26, tRP=22-24, tRAS=50-55; Voltage: DDR4 1.2V, DDR5 1.1V; Energy Efficiency: Memory power saving mode enabled.

[0112] For gaming scenarios, which primarily involve various game applications, the optimization focus is on bandwidth > latency > stability. Optimization parameters include: Frequency: DDR4 3600MHz (XMP), DDR5 6000MHz (XMP); Timings: DDR4 (CL=16-18, tRCD=18-20, tRP=16-18, tRAS=40-45); DDR5 (CL=30-32, tRCD=32-34, tRP=30-32, tRAS=65-70); Voltage: DDR4 1.35V, DDR5 1.25V; Channel: Forced dual-channel enabled.

[0113] The design scenario primarily involves applications such as video editing, 3D modeling and rendering, and graphic design. High bandwidth is required to accelerate data read and write operations, while large capacity is needed to prevent cache overflow in large projects. The optimization priority is bandwidth > capacity > stability. Optimized parameters include: Frequency: DDR5 5600MHz (XMP 3.0); Timings: CL=36-38, tRCD=40-42, tRP=38-40, tRAS=80-85 (satisfying tRAS≥tRCD+CL+2); Voltage: DDR5 1.2V; Capacity: Total capacity ≥ 64GB, expandable to 128GB.

[0114] In programming scenarios, primarily running applications involving code compilation, virtual machines, and database development, a balance between timing and bandwidth is required to ensure no crashes during simultaneous multi-process operation. The optimization direction prioritizes stability over bandwidth during multi-task concurrency. Optimized parameters include: Frequency: DDR4 3200MHz, DDR5 5200MHz; Timing: DDR4 (CL=20-22, tRCD=22-24, tRP=20-22, tRAS=55-60); DDR5 (CL=36-38, tRCD=38-40, tRP=36-38, tRAS=75-80); Voltage: DDR4 1.2V, DDR5 1.1V; Functionality: Enable flexible memory allocation mode.

[0115] For meeting scenarios, primarily running online meetings and video calls, a low-frequency and low-voltage combination is needed to extend battery life, while relaxed timings ensure smooth real-time audio and video transmission. The optimization priorities are power consumption > stability > real-time transmission smoothness (bandwidth). Optimization parameters include: Frequency: DDR4 2666MHz / JEDEC, DDR5 4800MHz / JEDEC; Timings: DDR4 (CL=19-21, tRCD=21-23, tRP=19-21, tRAS=45-50); DDR5 (CL=40-42, tRCD=42-44, tRP=40-42, tRAS=85-90); Voltage: Battery mode (DDR4 1.05V, DDR5 1.0V), Power-on mode (DDR4 1.2V, DDR5 1.1V).

[0116] Optional, see Figure 3 After obtaining the above-mentioned parameter optimization information, the method of this embodiment may further include the following steps.

[0117] S301, in response to obtaining the configuration trigger operation, configures the operating parameters of the memory module according to the parameter optimization information, so that the memory module runs based on the operating parameters contained in the parameter optimization information.

[0118] S302 detects the operating status of the memory module after a preset time.

[0119] S303: If the operating status of the memory module does not meet the test conditions, new parameter optimization information is obtained again based on the actual operating parameters of the memory module.

[0120] If the operating status of the memory module meets the test conditions, the method in this embodiment ends.

[0121] The method of obtaining the configuration trigger operation is not limited. When the electronic device outputs parameter optimization information, it can also display a clickable button to trigger the configuration of the memory module parameters. When the user triggers this button, the electronic device recognizes this trigger operation as a configuration trigger operation and then executes step S301. Alternatively, the electronic device can also determine that a configuration trigger operation has been obtained when it recognizes specific input information, such as recognizing the voice "Configure memory parameters as suggested here".

[0122] After receiving the configuration trigger, the processor of the electronic device can configure the operating parameters of the memory module to the operating parameters contained in the parameter optimization information through the relevant interface. For example, the frequency of the memory module can be set to the frequency indicated in the parameter optimization information (such as 4800MHz) through the interface provided by the BIOS for configuring memory operating parameters. The bit width and number of channels can be configured by disabling or enabling the available channels in the BIOS. For specific configuration methods, please refer to the relevant technologies.

[0123] Through step S301, this embodiment can achieve one-click optimization in response to configuration triggering operation after obtaining parameter optimization information. That is, after the user triggers the operation, the memory module's operating parameters are automatically set according to the parameter optimization information, further improving convenience.

[0124] The preset duration of the S302 can be set as needed. If a shorter test time is required, a shorter preset duration can be set; if a more accurate test of the reliability of the configured parameters is required, a longer preset duration can be set. For example, the preset duration can be 30 minutes.

[0125] One way to detect the operating status of the memory module is to check whether the electronic device experiences memory module-related errors within a preset time period, such as memory overflow errors or data read / write errors from memory. If no memory module-related errors occur within the preset time period, the operating status is determined to meet the test conditions. If at least one memory module-related error occurs within the preset time period, the operating status is determined to not meet the test conditions.

[0126] In step S303, if the operating state of the memory module does not meet the test conditions, the test can be re-executed. Figure 1 The corresponding parameter optimization method is used to obtain new parameter optimization information. After obtaining the new parameter optimization information, the above steps S301 to S303 can be continued until the running parameters of the memory module are configured and the running status of the memory module can meet the test conditions.

[0127] Optionally, to obtain more accurate test results, in S302, if the read / write load of the memory module is low, the electronic device can use a test program to frequently read and write to the memory module to increase the load of the memory module within a preset time period, thereby testing whether the operating state of the memory module under high load meets the test conditions. If the memory module is already under high load (such as running a large game), it is only necessary to check whether an error has occurred, and it is not necessary to enable the above program.

[0128] application Figure 3 The advantage of this method is that after configuring the memory module's operating parameters according to the parameter optimization information, it is possible to determine through testing whether the memory module can run stably with the newly configured operating parameters. If it cannot run stably, the stability of the memory module can be improved by re-executing the parameter optimization method in real time.

[0129] Optionally, the target weight model includes multiple weight values ​​corresponding to different operating indicators;

[0130] Step S202, which determines the performance scores corresponding to a set of candidate operating parameters based on the target weight model, may include:

[0131] Based on a set of candidate operating parameters, determine the expected operating metrics of the memory module when it runs based on the candidate operating parameters;

[0132] Based on the weight values ​​of each operational indicator and the expected operational indicators in the target weight model, a set of performance scores corresponding to candidate operational parameters are calculated.

[0133] In this embodiment, for any set of candidate operating parameters, the parameter values ​​contained in this set of candidate operating parameters, such as frequency, CL, tRCD, etc., can be substituted into the aforementioned formulas (1) to (4) for calculating operating indicators to calculate the expected operating indicators. This expected operating indicator represents the performance that the memory module is expected to exhibit if it operates according to this set of candidate operating parameters. For example, if the bandwidth in the expected operating indicator is 120GB / s, it means that if the memory module operates according to this set of candidate operating parameters, the memory module will have a bandwidth of 120GB / s. The expected operating indicators may include any one or more of the following: expected bandwidth, expected stability, expected latency, and expected power consumption.

[0134] Then, the obtained expected operating indicators are weighted and summed according to the weight values ​​contained in the target weight model to obtain the performance score corresponding to this set of candidate operating parameters. For example, the performance score can be calculated according to formula (5): Performance score = expected bandwidth * bandwidth weight value + (-expected latency) * latency weight value + expected stability * stability weight value + (-expected energy consumption) * energy consumption weight value, (5). Among them, latency and energy consumption are negatively correlated with the performance, that is, the higher the latency and the higher the energy consumption, the worse the performance, and vice versa. Therefore, when calculating the performance score, the expected latency and expected energy consumption can be negative to represent the negative correlation.

[0135] Using the methods described above, this solution can accurately determine the performance of each set of candidate operating parameters under the target usage scenario. By combining the target usage scenario, it can determine the set of operating parameters that best meets the usage requirements of the memory module under this scenario as parameter optimization information, thereby maximizing the performance of the memory module.

[0136] Optionally, based on core operating metrics, the actual operating parameters are optimized to obtain multiple sets of candidate operating parameters for the memory module, including:

[0137] Identify the actual operating parameters related to the core operating indicators as parameters to be optimized;

[0138] Based on multiple preset optimization ranges, the parameters to be optimized in the actual operating parameters are optimized to obtain multiple sets of candidate operating parameters for the memory module.

[0139] The actual operating parameters related to the core operating indicators can be determined based on the method of calculating the core operating indicators. For example, if the core operating indicator is bandwidth, the actual operating parameters related to bandwidth can be determined according to the aforementioned formula (1), including frequency, bit width and number of channels. If the core operating indicator is delay, the actual operating parameters related to delay can be determined according to the aforementioned formula (2), including frequency and CL, and so on.

[0140] Multiple optimization levels can be pre-configured and stored in the memory of the electronic device. For example, multiple optimization levels can include, but are not limited to, any number of the following: 10% reduction, 20% reduction, 10% increase, 20% increase, and 30% increase.

[0141] After determining the parameters to be optimized, the electronic device can apply an optimization magnitude of increasing the parameter to the parameters that are positively correlated with performance (such as frequency) to increase the parameter based on the actual operating parameters, thereby obtaining multiple candidate values. For the parameters that are negatively correlated with performance (such as CL), apply an optimization magnitude of decreasing the parameter to decrease the parameter based on the actual operating parameters, thereby obtaining multiple candidate values.

[0142] For example, the parameters to be optimized include frequency and CL. In the actual operating parameters, the frequency is 4500MHz. By applying the above optimization range, three candidate values ​​of 4950MHz, 5400MHz and 5850MHz can be obtained based on 4500MHz. In the actual operating parameters, the CL is 24. By applying the above optimization range, two candidate values ​​of 22 and 20 can be obtained based on 24.

[0143] After obtaining candidate values, it is possible to verify whether these candidate values ​​are within the range of hardware constraints of electronic devices and exclude candidate values ​​that exceed the range of hardware constraints. For example, if a candidate value for frequency exceeds the upper limit of the frequency supported by the motherboard and processor, or is lower than the lower limit required to ensure the basic operation of the operating system, it will be excluded.

[0144] It can also verify whether these candidate values ​​and other actual operating parameters meet the relevant constraints. For example, whether the candidate values ​​22 and 20 of CL meet the constraints of tRAS mentioned above. If they do not meet the constraints, other actual operating parameters can be adjusted to ensure that they meet the corresponding constraints. If they do meet the constraints, no adjustment is needed.

[0145] Finally, by combining the obtained candidate values ​​with other adjusted or unadjusted actual operating parameters, multiple sets of candidate operating parameters can be obtained. For example, the first set of candidate optimized parameters can be: frequency equal to 4950MHz, CL equal to 24, and the values ​​of other operating parameters are consistent with the actual operating parameters; the second set of candidate optimized parameters can be: frequency equal to 5400MHz, CL equal to 22, and the values ​​of other operating parameters are consistent with the actual operating parameters, and so on.

[0146] Using the above method, multiple sets of candidate operating parameters can be quickly calculated based on preset optimization ranges, which helps to improve the execution efficiency of the method in this embodiment.

[0147] The above is merely one example of obtaining candidate optimization parameters. In another example, an electronic device can collect the operating parameters, performance limits, and other relevant information of its memory module, motherboard, processor, and other modules (such as power supply, display, etc., without limitation). This information, along with the target usage scenario and prompts, is input into a pre-built memory optimization model (large language model or other neural network model). The prompts may include core operating metrics and parameters to be optimized, instructing the model to primarily optimize the parameters to be optimized and prioritize ensuring that core operating metrics are as good as possible (e.g., as high bandwidth or low latency as possible). Then, multiple sets of selectable candidate optimization parameters can be obtained from the model's output. The above model can be deployed locally on the electronic device or on a cloud server with a communication connection.

[0148] Optionally, parameter optimization information for the memory module can be determined based on core operating metrics and a target weight model, including:

[0149] The query function identifies multiple alternative memory modules that outperform the current memory module in terms of core performance metrics. The current memory module refers to the memory modules currently included in the memory module.

[0150] Based on the theoretical operating indicators and target weight model corresponding to the candidate memory modules, determine the performance score corresponding to the candidate memory modules;

[0151] The candidate memory module with the best performance score is identified as the recommended replacement memory module, and the model and parameters of the recommended replacement memory module are obtained as parameter optimization information for the memory module.

[0152] Alternate memory modules refer to memory modules that are currently supported by the motherboard and processor of an electronic device but are not yet installed in the memory module. Information about alternative memory modules can be obtained by the electronic device from a network search or pre-imported by the user.

[0153] In this embodiment, the electronic device can obtain relevant information (including but not limited to supported operating parameters, capacity, etc.) of various replaceable memory modules supported by the current motherboard and processor of the electronic device and not yet installed in the memory module through network search or user pre-import method, and then select alternative memory modules from these replaceable memory modules.

[0154] A backup memory module refers to a memory module whose core performance metrics are superior to those of the current memory module. Superior core performance metrics mean that the theoretical value of the backup memory module in this core performance metric is greater than the actual value of the current memory module. For example, if the core performance metric is bandwidth, and the calculated theoretical bandwidth (i.e., theoretical performance metric) of the backup memory module is 60GB / s, while the actual bandwidth (i.e., actual performance metric) of the current memory module is 50GB / s, then the backup memory module's core performance metric is superior to that of the current memory module.

[0155] The theoretical operating parameters of the alternative memory module can be calculated based on the operating parameters supported by the alternative memory module and the formula for calculating the operating parameters mentioned above. For example, if the frequency supported by a certain alternative memory module is 6000MHz and the CL is 21, then the frequency of 6000MHz and the CL of 21 can be substituted into formula (2) to calculate the theoretical latency of this alternative memory module.

[0156] For each candidate memory module, the electronic device can calculate a performance score by weighting its theoretical operating indicators according to the weight values ​​contained in the target weight model. The calculation method can be found in formula (5). Then, one or more candidate memory modules with the highest corresponding performance scores are selected as recommended replacement memory modules, thereby obtaining the model and parameters of the recommended replacement memory modules as parameter optimization information for the memory module. Furthermore, to improve convenience, the parameter optimization information can also include information such as the price and purchase link of the recommended replacement memory modules.

[0157] In some optional embodiments, the recommended replacement memory modules can be more precisely selected based on the user's purchasing needs. For example, if the user needs to maximize performance, the one with the best performance score can be determined as the recommended replacement memory module using the method described above. If the user needs to improve performance within a limited price range, the alternative memory modules with a price lower than the user's given price limit and a corresponding performance score higher than the current memory module can be selected as the recommended replacement memory modules. If the user needs to choose the one with the best cost performance for replacement, the performance score can be divided by the price to obtain the cost performance of each alternative memory module, and one or more of the modules with the highest cost performance and a higher performance score than the current memory module can be selected as the recommended replacement memory modules.

[0158] Through the above method, this embodiment can effectively provide users with suggestions on replacing memory modules when memory performance is insufficient, enabling users to replace memory modules as needed to improve memory performance.

[0159] Optionally, the target weight model is determined based on the target use case of the memory module, including at least one of the following:

[0160] Method 1: Determine the target usage scenario of the memory module based on the scenario description information input by the user, and determine the target weight model for the corresponding target usage scenario among multiple weight models;

[0161] Method 2 involves determining the target usage scenario of the memory module based on the applications that the electronic device has previously run and / or the applications that are currently running, and then selecting the target weight model for the corresponding target usage scenario from among multiple weight models.

[0162] In method one, the electronic device can obtain scene description information input by the user through voice input, keyboard input, etc., and then use a neural network model (such as a large language model) with natural language recognition and processing capabilities to process this scene description information to determine the target usage scenario that meets the user's needs. For example, if the user receives the voice message "The game is lagging too much, optimize the memory," the target usage scenario is determined to be a gaming scenario; if the user receives the text input from the keyboard "Let's have an online meeting to discuss this," the target usage scenario is determined to be a meeting scenario. After determining the target usage scenario, the electronic device can read the weight model corresponding to the target usage scenario from multiple weight models pre-stored in memory for different usage scenarios as the target weight model.

[0163] In method two, the target usage scenario can be determined based on the applications that have been run in the past. This can be achieved by statistically analyzing the frequency of various applications run on the electronic device over a recent period (e.g., the last 20 days, the last week, etc.), and identifying the usage scenario corresponding to the most frequently used application as the target usage scenario. For example, if the most frequently used application in the last week is a code compilation application, then the electronic device can be determined to be primarily used for programming, thus the target usage scenario is a programming scenario.

[0164] In method two, the electronic device can also determine the target usage scenario based on the usage scenario corresponding to the currently running application. For example, if a video player application is currently running, the target usage scenario can be determined to be a video playback scenario.

[0165] Optionally, if the electronic device is currently running a specific application, the target usage scenario can be determined based on the currently running application to prioritize meeting the current usage needs. If the electronic device is not currently running a specific application and only displays the system desktop, the target usage scenario can be determined based on previously run applications to perform targeted optimization according to the user's usage habits.

[0166] Using the methods described above, this embodiment can flexibly determine the target usage scenario based on multiple approaches, thereby meeting the different needs of users.

[0167] Optionally, obtain the actual operating parameters of the electronic device's memory module, including:

[0168] In response to the fulfillment of optimized triggering conditions, the actual operating parameters of the electronic device's memory module are obtained;

[0169] The optimization trigger conditions must be met, including at least one of the following:

[0170] Condition 1: A freeze and / or abnormal interruption is detected in the currently running application;

[0171] Condition 2: A memory optimization command input by the user was detected.

[0172] In other words, the parameter optimization method in this embodiment can only be executed by the electronic device when a specific optimization triggering condition is met; if the optimization triggering condition is not met, the electronic device will not execute the aforementioned parameter optimization method.

[0173] In condition one, the electronic device can detect the content displayed on the screen in real time during the running of the application. If the content displayed on the screen does not change for a certain period of time (e.g., 2 seconds), it can be determined that the application is lagging. If the number of times the lag occurs in a short period of time exceeds a certain threshold (e.g., 3 times in 5 minutes, 4 times in 8 minutes, etc.), it can be determined that the current memory performance is insufficient. Thus, it can be determined that condition one is met, triggering the execution of the parameter optimization method of this embodiment.

[0174] In condition one, the electronic device can also detect the running status of the application in real time. If the application is running normally or is closed normally based on the user's operation, it is determined that the application is running normally and no parameter optimization is required.

[0175] If an abnormal interruption of the application is detected, i.e., the application suddenly shuts down during runtime and is not caused by user operation, the electronic device can further obtain the interruption information output by the application at the time of the abnormal interruption, determine the cause of the abnormal interruption of the application based on the interruption information, and if it is determined that the cause is related to the performance of the memory module, for example, if it is determined that the cause is an error when reading or writing memory, then it is determined that condition one is met, and the parameter optimization method of this embodiment is triggered.

[0176] In condition two, the form of memory optimization instructions is not limited. For example, it can be a voice instruction, a text instruction, an instruction to press a specific keyboard shortcut, an instruction to launch an application or program plugin for memory optimization, etc., which will not be elaborated here.

[0177] Through the above methods, this embodiment can automatically detect whether the performance of the electronic device's memory module meets the user's needs based on condition one, and automatically optimize parameters when it is detected that the needs are not met. It can also optimize parameters based on the user's active need to optimize memory, further improving the convenience of optimizing memory performance.

[0178] Optional, see Figure 4 To obtain the actual operating parameters of the memory module of the electronic device, including:

[0179] S401, determine whether there is a memory-related fault in the electronic device based on the fault detection information of the electronic device.

[0180] If a memory-related fault exists, proceed to step S402 and pause the execution of the method in this embodiment. The actual operating parameters of the electronic device's memory module will be obtained only after the memory-related fault has been resolved. If no memory-related fault exists, proceed to step S403.

[0181] Memory-related faults can include, but are not limited to, poor contact in memory slots, disconnected or interfering circuits on the motherboard used to access memory modules, etc. For methods of obtaining fault detection information and determining the existence of memory-related faults based on that information, please refer to relevant technologies in the field of memory fault detection.

[0182] S402 outputs fault message describing memory-related faults, prompting the user to troubleshoot the corresponding faults.

[0183] For details on how fault information is obtained and output, please refer to relevant technologies.

[0184] S403, the processor utilization rate based on the electronic device satisfies whether the processor is under high load.

[0185] A high-load state can be defined as a state where the processor utilization rate is greater than a preset high-load threshold. The high-load threshold can be set as needed, such as 80%. Therefore, if the utilization rate is greater than 80%, the processor is in a high-load state; if the utilization rate is less than or equal to 80%, the processor is not in a high-load state.

[0186] If the processor is under high load, execute step S404 to reduce the processor load. If the processor is not under high load, execute step S405 to obtain the actual operating parameters.

[0187] S404 closes processes one by one from high to low processor utilization until the processor is no longer under high load.

[0188] After executing S404, you can return to execute S403 to determine again whether you are in a high-load state. If you determine that you are not in a high-load state, then execute S405.

[0189] S405 obtains the actual operating parameters of the electronic device's memory module after determining that there are no memory-related faults and the processor is not under high load.

[0190] The beneficial effect of this embodiment is that, before obtaining the actual operating parameters, it eliminates factors that may interfere with memory performance evaluation, namely, memory-related faults and high processor load states, to ensure that the obtained actual operating parameters can accurately reflect the actual performance of the memory module, thereby improving the accuracy of the subsequently determined parameter optimization information.

[0191] This application also provides an electronic device, see [link to relevant documentation] Figure 5 This includes a memory 501 and a processor 502;

[0192] Memory 501 is used to store computer programs;

[0193] Processor 502 is used to execute computer programs to perform:

[0194] Obtain the actual operating parameters of the memory module of the electronic device, and determine the actual operating indicators of the memory module based on the actual operating parameters. The operating indicators include any one or more of bandwidth, latency, stability and power consumption.

[0195] By comparing actual operating metrics with the theoretical optimal operating metrics of the memory module, the core operating metrics affecting the performance of the memory module are determined. The theoretical optimal operating metrics are determined based on the upper limits of the operating parameters of the electronic device's memory module, motherboard, and processor.

[0196] The parameter optimization information of the memory module is determined based on the core operating indicators and the target weight model, which is determined according to the target usage scenario of the memory module.

[0197] The working principle of the electronic device in this embodiment can be found in the relevant steps of the parameter optimization method in the foregoing embodiment, and will not be repeated here.

[0198] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. In this document, relational terms such as first, second, third, and fourth are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise limited, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0199] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A parameter optimization method, comprising: Obtain the actual operating parameters of the memory module of the electronic device, and determine the actual operating indicators of the memory module based on the actual operating parameters. The operating indicators include any one or more of bandwidth, latency, stability and power consumption. By comparing the actual operating indicators with the theoretical optimal operating indicators of the memory module, the core operating indicators affecting the performance of the memory module are determined. The theoretical optimal operating indicators are determined based on the upper limits of the operating parameters of the memory module, motherboard, and processor of the electronic device. The parameter optimization information of the memory module is determined based on the core operating indicators and the target weight model, which is determined according to the target usage scenario of the memory module.

2. The method according to claim 1, wherein determining the parameter optimization information of the memory module based on the core operating indicators and the target weight model includes: Based on the core operating indicators, the actual operating parameters are optimized to obtain multiple sets of candidate operating parameters for the memory module; The performance score corresponding to each group of candidate operating parameters is determined based on the target weight model. The set of candidate operating parameters with the best corresponding performance score is determined as the parameter optimization information for the memory module.

3. The method according to claim 1, wherein determining the parameter optimization information of the memory module based on the core operating indicators and the target weight model includes: The system queries multiple alternative memory modules whose core operating metrics are superior to those of the memory module, where the current memory module refers to the memory modules currently contained in the memory module. Based on the theoretical operating indicators corresponding to the candidate memory modules and the target weight model, the performance score corresponding to the candidate memory modules is determined; The candidate memory module with the best performance score is identified as the recommended replacement memory module, and the model and parameters of the recommended replacement memory module are obtained as parameter optimization information for the memory module.

4. The method according to claim 2, wherein the target weight model includes multiple weight values ​​corresponding to different operating indicators; Based on the target weight model, a set of performance scores corresponding to the candidate operating parameters are determined, including: Based on a set of candidate operating parameters, the expected operating metrics of the memory module when running based on the candidate operating parameters are determined; Based on the weight values ​​of each operating indicator in the target weight model and the expected operating indicator, a set of performance scores corresponding to the candidate operating parameters are calculated.

5. The method according to claim 2, wherein optimizing the actual operating parameters based on the core operating indicators to obtain multiple sets of candidate operating parameters for the memory module includes: Identify the actual operating parameters related to the core operating indicators as parameters to be optimized; Based on multiple preset optimization ranges, the parameters to be optimized in the actual operating parameters are optimized to obtain multiple sets of candidate operating parameters for the memory module.

6. The method according to claim 2, further comprising: In response to receiving a configuration trigger operation, the operating parameters of the memory module are configured according to the parameter optimization information, so that the memory module runs based on the operating parameters contained in the parameter optimization information; The operating status of the memory module is detected after a preset time period; If the operating status of the memory module does not meet the test conditions, new parameter optimization information is obtained again based on the actual operating parameters of the memory module.

7. The method according to claim 1, wherein determining the target weight model based on the target use scenario of the memory module includes at least one of the following: The target usage scenario of the memory module is determined based on the scenario description information input by the user, and the target weight model corresponding to the target usage scenario is determined among multiple weight models. Based on the applications that the electronic device has previously run and / or the applications that are currently running, the target use case of the memory module is determined, and a target weight model corresponding to the target use case is determined from multiple weight models.

8. The method according to claim 1, wherein obtaining the actual operating parameters of the memory module of the electronic device includes: In response to the fulfillment of optimized triggering conditions, the actual operating parameters of the electronic device's memory module are obtained; The conditions for satisfying the optimization trigger include at least one of the following: The currently running application has been detected to be experiencing lag and / or abnormal interruption. A memory optimization command entered by the user was detected.

9. The method according to claim 1, wherein obtaining the actual operating parameters of the memory module of the electronic device includes: Based on the fault detection information of the electronic device, determine whether the electronic device has a memory-related fault; The occupancy rate of the processor in the electronic device determines whether the processor is under high load. If it is determined that there are no memory-related faults and the processor is not under high load, the actual operating parameters of the electronic device's memory module are obtained.

10. An electronic device, comprising a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program to perform: Obtain the actual operating parameters of the memory module of the electronic device, and determine the actual operating indicators of the memory module based on the actual operating parameters. The operating indicators include any one or more of bandwidth, latency, stability and power consumption. By comparing the actual operating indicators with the theoretical optimal operating indicators of the memory module, the core operating indicators affecting the performance of the memory module are determined. The theoretical optimal operating indicators are determined based on the upper limits of the operating parameters of the memory module, motherboard, and processor of the electronic device. The parameter optimization information of the memory module is determined based on the core operating indicators and the target weight model, which is determined according to the target usage scenario of the memory module.

Images