A method for calibrating performance parameters of mobile phone motherboard based on artificial intelligence

Abstract

The present invention relates to the field of telephone communications, and in particular to a method for calibrating the performance parameters of a mobile phone motherboard based on artificial intelligence. It mainly includes: first, obtaining raw data, including mobile phone motherboard performance parameter data, environmental data and usage mode data, designing an edge computing framework, integrating data stratification, graph optimization and adaptive learning and adjustment computing strategies, and processing the raw data through an adaptive data processing system; then, using the Lorenz chaotic system, the optimal parameter configuration is predicted by simulating the nonlinear dynamic behavior of the mobile phone motherboard performance parameters, and an optimization framework is constructed to correct the parameter configuration by simulating the dynamic behavior of the mobile phone motherboard performance parameters, topological data analysis and adaptive filtering technology. It solves the technical problems of insufficient energy efficiency, lack of performance adaptability, inflexible temperature management, low data processing efficiency, weak environmental adaptability, high equipment failure rate and limited user experience in the existing technology.

Description

Technical Field

[0001] The present invention relates to the field of telephone communications, and in particular to a method for calibrating performance parameters of a mobile phone mainboard based on artificial intelligence. Background Art

[0002] In the context of the rapid development of smartphone technology, the optimization and calibration of motherboard performance parameters have become crucial. The motherboard is the core component of a smartphone, responsible for key functions such as processor, memory, and power management. With the diversification of smartphone applications and the continuous growth of user needs, the requirements for motherboard performance are also getting higher and higher, including faster processing speed, higher energy efficiency, better temperature control, and stronger environmental adaptability.

[0003] The Chinese patent application number: CN201010156481.7, published on November 9, 2011, discloses a method for rapid calibration of mobile phone motherboard performance parameters, which includes the following steps: first, running a rapid calibration program, automatically configuring the test environment of the test instrument and the controllable power supply through the GPIB line; second, automatically controlling the mobile phone motherboard to enter the test mode through the USB serial port line, and automatically configuring the mobile phone motherboard performance parameter test environment through the USB serial port line; finally, reading the initial test value of the motherboard performance parameter from the test instrument, and automatically dynamically adjusting the temporary upper and lower bounds of the performance parameter value during the calibration process, and quickly searching for the appropriate calibration value of the mobile phone motherboard performance parameter within a relatively small range. The rapid calibration method will become more and more effective as the number of calibrated motherboards increases. Compared with the existing traditional calibration method, it optimizes the performance parameter calibration algorithm and shortens the performance parameter calibration time.

[0004] However, the above-mentioned technologies have at least the following technical problems: insufficient energy efficiency, lack of performance adaptability, inflexible temperature management, low data processing efficiency, poor environmental adaptability, high equipment failure rate and limited user experience. The above-mentioned technical problems are due to the fact that traditional methods lack a dynamic adjustment mechanism in processor speed and power management, cannot effectively predict and adapt to changes in user behavior and environmental conditions, lack effective data processing optimization and temperature control strategies, and have deficiencies in precise performance parameter calibration and optimization, resulting in the inability of the device to maintain efficient operation under different operating conditions, affecting the overall user experience. Summary of the invention

[0005] The present invention provides a method for calibrating the performance parameters of a mobile phone motherboard based on artificial intelligence, which solves the technical problems of insufficient energy efficiency, lack of performance adaptability, inflexible temperature management, low data processing efficiency, weak environmental adaptability, high equipment failure rate and limited user experience in the prior art. These technical problems are due to the fact that traditional methods lack a dynamic adjustment mechanism in processor speed and power management, cannot effectively predict and adapt to changes in user behavior and environmental conditions, lack effective data processing optimization and temperature control strategies, and have deficiencies in accurate performance parameter calibration and optimization, resulting in the inability of the device to maintain efficient operation under different operating conditions, affecting the overall user experience. Efficient calibration of the performance parameters of the smartphone motherboard is achieved, balancing the relationship between high performance and low energy consumption, while adapting to dynamically changing environments and user behaviors.

[0006] The present invention provides a method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence, which specifically includes the following technical solutions:

[0007] A method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence, comprising the following steps:

[0008] S1. Obtain raw data, design edge computing framework, integrate data stratification, graph optimization and adaptive learning adjustment computing strategies, and process raw data through adaptive data processing system;

[0009] S2. Using the Lorenz chaotic system, the optimal parameter configuration is predicted by simulating the nonlinear dynamic behavior of the performance parameters of the mobile phone motherboard, and an optimization framework is constructed to correct the parameter configuration by simulating the dynamic behavior of the performance parameters of the mobile phone motherboard, topological data analysis and adaptive filtering technology.

[0010] Preferably, the S1 specifically includes:

[0011] Obtain raw data, including mobile phone motherboard performance parameter data, environmental data, and usage pattern data; stratify the raw data by entropy, and classify each layer according to the importance and processing requirements of the raw data; and determine the stratification of the raw data by setting an entropy value threshold.

[0012] Preferably, the S1 further includes:

[0013] Within each layer, graph theory-based methods are used to analyze the correlation of raw data and identify potential connections between raw data.

[0014] Preferably, the S1 further includes:

[0015] Design an adaptive learning algorithm to dynamically adjust the flow of raw data between layers and define the data flow regulation function.

[0016] Preferably, the S2 specifically includes:

[0017] In the process of simulating the dynamic behavior of performance parameters of mobile phone motherboard based on Lorenz chaotic system, the parameters of Lorenz chaotic system are calibrated, and the output of Lorenz chaotic system is converted into a format suitable for topological analysis to obtain the parameter configuration vector.

[0018] Preferably, the S2 further includes:

[0019] The topological features are extracted from the parameter configuration vector. The specific implementation method is as follows: First, a complex is constructed according to the parameter configuration vector. The complex is a tool for representing the geometric structure of data, which is composed of points, edges, and triangle elements, including Vietoris-Rips complex or complex; further, filtering the complex, gradually adding elements of the complex, and observing the appearance and disappearance of holes, wherein the holes include loops and cavities, generating a persistent graph during the filtering process, extracting topological features of the parameter configuration vector from the persistent graph, wherein the topological features include time points of appearance and disappearance of the holes; converting the topological features into a format suitable for the filter.

[0020] Preferably, the S2 further includes:

[0021] The Kalman filter method is used to correct and optimize parameter configuration in real time; the Kalman filter uses the converted topological features to perform real-time state estimation and parameter adjustment.

[0022] Preferably, the S2 further includes:

[0023] The state estimate obtained from the Kalman filter is mapped to the performance parameters of the mobile phone motherboard, and the state estimate is converted into hardware parameters, wherein the hardware parameters include processor speed, power management settings, and temperature control thresholds; the output of the Kalman filter is converted into actual performance parameters so that the mobile phone motherboard can dynamically adjust the performance settings according to the current state estimate.

[0024] The beneficial effects of the technical solution of the present invention are:

[0025] 1. Improve energy efficiency by dynamically adjusting the performance parameters of the mobile phone motherboard, such as processor speed and power management settings. This optimization is suitable for mobile devices with limited battery life and helps to extend the use time of the device. Use the Lorenz system to simulate the nonlinear dynamic behavior of the performance parameters of the mobile phone motherboard, which can predict and adapt to changes in performance requirements, which is crucial to meeting the performance requirements of users in different application scenarios. By monitoring and adjusting the temperature control parameters of the motherboard in real time, the risk of overheating is effectively reduced, and the reliability and durability of the device are enhanced.

[0026] 2. The data association analysis based on graph theory and the multi-level adaptive data processing system are adopted to optimize the data processing process, improve the processing efficiency and response speed; by integrating environmental data and user usage patterns, it can better adapt to changes in the external environment and user behavior, thereby optimizing performance parameter settings; through precise performance parameter calibration and optimization, it reduces equipment failures and maintenance costs caused by improper parameter settings, and improves the reliability of the overall equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A flow chart of a method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence provided by an embodiment of the present invention; DETAILED DESCRIPTION

[0028] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0030] The following is a detailed description of a method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence provided by the present invention in conjunction with the accompanying drawings.

[0031] See attached Figure 1 , which shows a flow chart of a method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence provided by an embodiment of the present invention, the method comprising the following steps:

[0032] S1. Obtain raw data, design edge computing framework, integrate data stratification, graph optimization and adaptive learning adjustment computing strategies, and process raw data through adaptive data processing system;

[0033] Obtain raw data, including mobile phone motherboard performance parameter data, environmental data, and usage pattern data. Collect various performance parameter data of the mobile phone motherboard, such as processor load, temperature, voltage, etc., through the mobile phone's built-in sensors and performance monitoring software. Obtain environmental data through network services, such as temperature, humidity and other information provided by weather applications. Collect user usage pattern data, such as application software usage frequency, network usage, etc., to help understand changes in performance requirements.

[0034] In order to deal with the balance between high performance and low energy consumption in the calibration of mobile phone motherboard performance parameters, an edge computing framework is proposed. Through a multi-level adaptive data processing system, efficient processing of raw data is achieved while reducing energy consumption. The edge computing framework integrates multiple computing strategies, including data stratification, graph optimization, and adaptive learning adjustment, to cope with complex data processing requirements and dynamically changing environmental conditions.

[0035] First, the original data is layered using the concept of entropy, and each layer is classified according to the importance and processing requirements of the original data. For example, frequently accessed or critical data is assigned to a high priority layer for quick processing. The importance of data is effectively distinguished, thereby optimizing the overall processing flow. The entropy measurement formula is:

[0036]

[0037] Among them, X is the original data, represents the entropy of the original data X, p(χ i ) is the i-th data point χ i The probability in the original data. Based on the calculated entropy value, the original data is divided into multiple levels. A high entropy value indicates that the original data has a high degree of uncertainty and complexity, and the original data is assigned to a high level that requires higher computing resources. On the contrary, the original data with a low entropy value is assigned to a lower level. The decision criterion for stratification is to set the entropy value threshold according to the actual situation to decide to which level the original data should be assigned.

[0038] Inside each layer, graph-based methods are used to analyze the relevance of raw data and identify potential connections between raw data so that related data can be processed more efficiently. This ensures that data processing is not only fast but also intelligent, because centralized processing of related data can improve overall efficiency. The graph theory association metric formula is:

[0039]

[0040] Where C(G) represents the average correlation of graph G, N is the number of nodes in the graph, and d(i, i′) is the shortest path length between node i and node i′. The data in each layer is optimized based on the results of graph theory analysis. For example, for data points whose average correlation exceeds a preset threshold, batch processing or parallel processing can be used to improve processing efficiency. Batch processing or parallel processing methods are both existing technologies.

[0041] In order to adapt to the changes in raw data processing capabilities between different layers and the overall performance requirements of the multi-level adaptive data processing system, an adaptive learning algorithm is designed to dynamically adjust the flow of raw data between layers. The data flow adjustment function is:

[0042]

[0043] Among them, Λ jj′ (t) is the data flow from layer j to layer j′ at time t, Γ j (t) and Γ j′ (t) is the data processing capacity of the jth layer and the j′th layer at time t, and κ(t) is the adjustment coefficient. The adaptive learning algorithm dynamically adjusts the data flow according to the processing capacity of each layer and the performance requirements of the overall adaptive data processing system. When the processing capacity of a layer decreases due to data overload, the adaptive learning algorithm can reduce the amount of data flowing to the layer, and vice versa. The edge computing framework provides the basis for data processing for the subsequent mobile phone motherboard performance parameter calibration process.

[0044] S2. Using the Lorenz chaotic system, the optimal parameter configuration is predicted by simulating the nonlinear dynamic behavior of the performance parameters of the mobile phone motherboard, and an optimization framework is constructed to correct the parameter configuration by simulating the dynamic behavior of the performance parameters of the mobile phone motherboard, topological data analysis and adaptive filtering technology.

[0045] The Lorenz system (Lorenz chaotic system) in chaos theory is used to predict the optimal parameter configuration by simulating the nonlinear dynamic behavior of the performance parameters of the mobile phone motherboard, so as to dynamically adjust the parameter configuration to adapt to the real-time performance requirements. The Lorenz system was chosen because it can reveal the regularity and predictable structure hidden in complex dynamic behaviors, even though these behaviors appear chaotic and random on the surface. Dynamic behavior refers to the behavior of the performance parameters of the mobile phone motherboard changing over time and under different conditions (such as motherboard temperature, CPU load, power supply status, etc.). The parameters of the Lorenz system are adjusted so that its simulated behavior matches the actual performance parameter changes of the mobile phone motherboard. In this way, the Lorenz system becomes a tool for understanding and predicting the dynamic response of the performance parameters of the mobile phone motherboard under different working conditions. In this way, the Lorenz system can optimize the performance parameter settings of the mobile phone motherboard to ensure the best efficiency and accuracy in telephone communication applications.

[0046] A multi-stage hybrid optimization framework is constructed to perform parameter calibration by simulating the dynamic behavior of mobile phone motherboard performance parameters based on the Lorenz system, topological data analysis, and adaptive filtering technology. The specific formula for simulating the dynamic behavior of mobile phone motherboard performance parameters based on the Lorenz system is:

[0047]

[0048] Among them, x, y, and z are the state variables of the Lorenz system, representing the dynamic behavior of the Lorenz system in different dimensions; Respectively represent the rate of change of x, y, and z with time t; σ is a Lorenz system parameter, which affects the behavior of the Lorenz system in the x and y directions; ρ is a Lorenz system parameter, which is related to the behavior of the Lorenz system in the z direction; β is a constant that affects the stability of the Lorenz system in the z direction. As a specific embodiment, a large amount of mobile phone motherboard performance parameter data is collected to record the changes in parameters such as processor load, temperature, and voltage when the mobile phone is in use. Using the collected mobile phone motherboard performance parameter data, the parameters σ, ρ, and β of the Lorenz system are calibrated. This process usually involves numerical optimization techniques, such as genetic algorithms or particle swarm optimization algorithms, to find a set of parameter values ​​that make the behavior of the Lorenz system closest to the actual performance data. Convert the output of the Lorenz system into a format suitable for topological analysis:

[0049] V = Φ(x, y, z)

[0050] Where V represents the parameter configuration vector obtained from the Lorenz system, and Φ is a mapping function. To extract topological features from the parameter configuration vector, first construct a complex (such as the Vietoris-Rips complex or Complex), a complex is a tool that can be used to represent the geometric structure of data, consisting of elements such as points, edges, triangles, etc. Next, a filtering process is applied to the complex. During the filtering process, elements of the complex (such as points, edges, triangles, etc.) are gradually added, and the appearance and disappearance of "holes" (such as rings and cavities) are observed. This process produces a persistent graph, from which the topological features of the parameter configuration vector can be extracted. These topological features include the time points when the "holes" appear and disappear, which can be used to understand the structural characteristics of the parameter configuration vector. And the topological features are converted into a format that the filter can process. The specific formula is:

[0051] S = Θ(Ψ(V))

[0052] Among them, S represents the converted topological features, Ψ represents the feature extraction process, and Θ represents the conversion function.

[0053] In order to perform real-time correction and optimization of parameter configuration of mobile phone motherboard performance parameters, especially in the face of external environmental interference and internal noise of mobile phone motherboard. Kalman filter is an effective prediction-correction method suitable for situations where there is uncertainty and noise in mobile phone motherboard. Kalman filter uses the converted topological features to perform real-time state estimation and parameter adjustment. Topological features provide a global perspective on parameter configuration, while Kalman filter is responsible for detailed adjustments based on the global perspective and real-time data. The formula for implementing correction and optimization of parameter configuration by Kalman filter is as follows:

[0054]

[0055]

[0056]

[0057]

[0058] P k|k =(IK k H k ) k|k-1

[0059] in, is the state estimate at time point k, based on the information before time point k-1; P k|k-1 is the predicted value of the estimated error covariance, that is, the uncertainty of the predicted state before time point k; K k is the Kalman gain; S k is the transformed topological feature of the input at time point k; F k is the state transition matrix, used to predict the current state from the previous state; is the state estimate at time k-1, based on all the information at time k-1; B k is the control input matrix, which converts the external control signal into the state space; P k-1|k-1 is the covariance of the state estimation error calculated after the state estimation at time point k-1 based on all information before (including) time point k-1; T represents transposition; Q k is the process noise covariance; H k is the observation model matrix, which maps the state space to the observation space; z k is the actual observed value at time point k; R k is the observation noise covariance; is the state estimate at time point k, taking into account all information at time point k; P k|k is the updated value of the estimated error covariance, that is, the uncertainty of the state estimate after time point k, and I is the identity matrix.

[0060] The state estimate obtained from the Kalman filter Mapped to the performance parameters of the mobile phone motherboard, the state estimation value is converted into specific hardware parameters, such as processor speed, power management settings, temperature control thresholds, etc. As a specific embodiment, assume is the state estimate of the Kalman filter at time k, which contains information such as processor load, energy consumption, temperature, etc., and maps the state estimate to specific performance parameters of the mobile phone motherboard, such as processor clock frequency, power management settings, etc. For processor clock frequency mapping:

[0061]

[0062] Among them, F cpu (k) is the processor clock frequency at time k, F base is the base frequency of the processor, α is the adjustment coefficient, which is used to adjust the frequency variation. It is estimated from the state Processor load estimates extracted from . For power management settings mapping:

[0063]

[0064] Among them, P power (k) is the power management setting at time k, P base is the baseline setting for power management. is the adjustment factor, which is used to adjust the power setting change. It is estimated from the state The estimated temperature, T optimal It is the optimal operating temperature of the equipment.

[0065] Converting the output of the Kalman filter into actual performance parameters enables the phone motherboard to dynamically adjust its performance settings based on the current state estimate. For example, if the state estimate shows that the processor load will increase, the processor's clock frequency can be increased in advance to cope with the upcoming load, thereby optimizing performance and energy consumption under different operating conditions.

[0066] In summary, a method for calibrating performance parameters of mobile phone motherboards based on artificial intelligence has been completed.

[0067] The embodiments of the present invention improve energy efficiency by dynamically adjusting the performance parameters of the mobile phone motherboard, such as processor speed and power management settings. This optimization is suitable for mobile devices with limited battery life and helps to extend the use time of the device. The Lorenz system is used to simulate the nonlinear dynamic behavior of the performance parameters of the mobile phone motherboard, which can predict and adapt to changes in performance requirements, and is crucial for meeting the performance requirements of users in different application scenarios. By real-time monitoring and adjustment of the temperature control parameters of the motherboard, the risk of overheating is effectively reduced, and the reliability and durability of the device are enhanced.

[0068] The embodiment of the present invention adopts data association analysis based on graph theory and a multi-level adaptive data processing system to optimize the data processing process and improve processing efficiency and response speed; by integrating environmental data and user usage patterns, it can better adapt to changes in the external environment and user behavior, thereby optimizing performance parameter settings; through precise performance parameter calibration and optimization, it reduces equipment failures and maintenance costs caused by improper parameter settings, thereby improving the reliability of the overall equipment.

[0069] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0071] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence, characterized in that: The following steps are involved: S1. Obtain raw data, design edge computing framework, integrate data stratification, graph optimization and adaptive learning adjustment computing strategies, and process raw data through adaptive data processing system; S2. Using the Lorenz chaotic system, we simulate the nonlinear dynamic behavior of the performance parameters of the mobile phone motherboard to predict the optimal parameter configuration and build an optimization framework; In the process of simulating the dynamic behavior of the performance parameters of the mobile phone motherboard based on the Lorenz chaotic system, the parameters of the Lorenz chaotic system are calibrated, and the output of the Lorenz chaotic system is converted into a format suitable for topological analysis to obtain a parameter configuration vector; the topological features are extracted from the parameter configuration vector. The specific implementation method is as follows: First, a complex is constructed according to the parameter configuration vector, wherein the complex is a tool for representing the geometric structure of data, and is composed of points, edges, and triangle elements, including a Vietoris-Rips complex or a Čech complex; the complex is filtered, elements of the complex are gradually added, and the appearance and disappearance of holes are observed, wherein the holes include rings and cavities, and the topological features of the parameter configuration vector are extracted, wherein the topological features include the time points of the appearance and disappearance of the holes; and the topological features are converted into a format suitable for the filter; Correct and optimize parameter configuration in real time through Kalman filtering method; use the converted topological features through Kalman filtering to perform real-time state estimation and parameter adjustment; The state estimate obtained from the Kalman filter is mapped to the performance parameters of the mobile phone motherboard, and the state estimate is converted into hardware parameters, which include processor speed, power management settings and temperature control thresholds; the output of the Kalman filter is converted into actual performance parameters so that the mobile phone motherboard can dynamically adjust the performance settings.

2. The method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence according to claim 1, characterized in that: The S1 specifically includes: Obtain raw data, including mobile phone motherboard performance parameter data, environmental data, and usage pattern data; stratify the raw data through entropy and classify each layer.

3. The method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence according to claim 2, characterized in that: Said S1 further comprises: Within each layer, graph theory-based methods are used to analyze the correlation of the original data.

4. The method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence according to claim 1, characterized in that: Said S1 further comprises: Design an adaptive learning algorithm to dynamically adjust the flow of raw data between layers and define the data flow regulation function.

Images