670 results about "Performance enhancement" patented technology

The invention provides a Python monitoring task resource use method and system, and relates to the technical field of intelligent monitoring and resource optimization, and the method comprises the steps: extracting process call stack information through a multilayer convolutional neural network, constructing a process dependency graph, calculating a process criticality score, and recognizing a core monitoring process. And obtaining resource use data of the core monitoring process through a resource monitoring coroutine, determining an optimal sampling period by adopting a self-adaptive feedback control algorithm, and writing the data into a time sequence database. And performing data aggregation analysis by using a sliding time window algorithm to obtain a performance index, and constructing an anomaly detection model. Dimensionality reduction is carried out based on a principal component analysis method to construct feature vectors, and load types are divided by adopting a clustering algorithm; and generating a differentiated process optimization strategy according to the feature vector and the load type. When performance fluctuation is detected, an optimization strategy is executed, the anomaly detection model and the deep reinforcement learning model are updated according to the performance improvement index, and finally an optimization diagnosis report is generated.

The invention provides a large model cue word design method, system and device in an industrial scene and a medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: constructing a private cue word template library, and forming a domain special knowledge unit set through multi-source industrial data collection, intelligent semantic analysis and classified storage; customizing a four-layer structured template, sequentially establishing a task overview layer, a step disassembly layer, an instruction refining layer and an output specification layer, and constructing a layered mapping model from task definition to output execution; template library management and iterative optimization are carried out, and dynamic updating and performance improvement of a cue word system are realized through centralized system management, multi-source feedback acquisition and data-driven optimization. According to the method, a cue word design and optimization system based on a hierarchical structure is constructed for complex task requirements in an industrial scene, and the task processing performance of a large model in scenes of industrial production, quality detection, equipment operation and maintenance and the like is improved.

The invention provides an intelligent maintenance decision-making method and system based on bridge big data, and belongs to the technical field of bridge safety. The intelligent maintenance decision-making method comprises the steps of 1, collecting basic information, a detection report, a maintenance record and real-time state data of a bridge; 2, key features influencing the bridge performance are mined from the data collected in the step 1, the current state of the bridge is analyzed and evaluated, and the change trend of the bridge condition in a period of time in the future is predicted; 3, generating a plurality of possible maintenance strategy schemes based on the result of the step 2; step 4, carrying out cost benefit analysis on the maintenance strategy scheme generated in the step 3; 5, a multi-objective optimization algorithm is utilized, bridge performance improvement, maintenance cost, construction time and traffic influence factors are comprehensively considered, and an optimal scheme is selected from the maintenance strategy schemes evaluated in the step 4; and 6, formulating a detailed maintenance plan according to the optimal strategy and implementing the detailed maintenance plan.

The invention belongs to the technical field of Linux kernel schedulers, and particularly relates to a Linux kernel scheduler parameter optimization system and method.The Linux kernel scheduler parameter optimization system comprises a data collection module, a large model training and optimization module, a kernel scheduler module, a code generation and verification module, a small model training module and a small model reasoning module; the large model is responsible for periodically providing a visual angle of global optimization, generating an initial weight and a scheduler prototype of the small model, extracting a rule from long-term accumulated data, and ensuring that an optimization strategy has a global visual field. Meanwhile, the small model serves as a local adapter to process the dynamic scheduling requirement of a kernel mode in real time. The layered optimization mechanism can balance short-term adaptability and long-term performance improvement.

The invention provides a lithium battery hybrid power motorcycle performance improvement control strategy generation method, which comprises the steps that vehicle driving states comprise a sliding state and a braking state, if the current vehicle is in the sliding state, a preset sliding energy recovery mode is activated, and if the current vehicle is in the braking state, a preset braking energy recovery mode is activated; different energy recovery strategies are combined and optimized according to the subdivision result of the energy recovery strategies in the sliding state and the braking state, and the vehicle speed, the battery charging state and the energy recovery potential value parameters are input to obtain a target energy recovery strategy combination scheme; the intention of acceleration, deceleration or constant speed of a driver is judged according to the operation characteristics of an accelerator and a brake, the operation characteristics refer to the force of stepping on an accelerator pedal and a brake pedal, and the driver intention obtained through judgment serves as the basis for dynamic adjustment of the energy recovery strategy.

The invention discloses an RAG performance improvement method based on process optimization. The method comprises the following steps: S1, preprocessing text data; s2, performing hierarchical text segmentation, obtaining a document, storing the text by utilizing a database after the document is segmented, converting the text into vectors, and storing the vectors into a vector knowledge base; s3, querying and rewriting to obtain a rewritten question; s4, combining parent document search with mixed retrieval, and retrieving related contexts for the rewritten questions; s5, performing rearrangement and denoising to obtain a final context; and S6, generating an answer, and sending the final context into a large language model for understanding questions and answers. According to the method, the links of text preprocessing, text partitioning, text embedding, query optimization, retrieval, retrieval post-processing, generation and the like are sequentially optimized according to the data flowing direction, the semantic retrieval precision is improved, and the performance of RAG in the aspects of text retrieval precision, answer generation quality, user interaction and the like can be remarkably improved; and the flexibility and the practicability of the system are enhanced, so that the system is more excellent in practical application.

The embodiment of the invention provides a thread pool operation state monitoring method and device, and the method comprises the steps: dividing the fluctuation range of the ratio of the number of active threads to the number of core threads into a high-load interval, a normal interval and a low-load interval, and calculating the optimization coefficient of the core threads based on the interval distribution characteristics; calculating the variance of the ratio of the total thread count to the maximum thread count, and extracting the adjustment coefficient of the maximum thread through the fluctuation characteristics of a variance curve; taking a difference value between the task growth rate and the processing rate as a calibration factor of the queue capacity; respectively comparing the evaluation results of the three parameters with a preset reasonable interval boundary to generate a parameter rationality score; counting the performance improvement effect of each preset adjustment strategy from a historical adjustment record; calculating a current adjustment step length based on the reference strategy; recording the adjustment suggestions and the calculation basis thereof into a version library, and setting corresponding effective conditions; according to the application, the efficiency and accuracy of monitoring the running state of the thread pool can be improved.

The invention relates to the technical field of industrial equipment control, and discloses an industrial equipment intelligent control system and method based on deep reinforcement learning. The system comprises an equipment state monitoring module, a reinforcement learning decision-making module, a control parameter adjustment module, an abnormity intervention module and an equipment performance optimization module. The equipment state monitoring module collects real-time operation data of equipment, analyzes state change by means of a deep reinforcement learning algorithm, and generates a state feature data set; the reinforcement learning decision-making module calculates a control strategy by using a deep reinforcement learning model and generates a control strategy parameter set; the control parameter adjusting module optimizes the operation efficiency according to the adjusted parameters and generates an optimized control parameter set; the abnormity intervention module monitors abnormity, recognizes intervention through deep reinforcement learning, and generates an abnormity intervention adjustment data set; and the equipment performance optimization module optimizes the performance indexes according to the parameters and generates a performance optimization parameter table. The system realizes accurate monitoring of equipment, intelligent optimization of strategies, timely intervention of abnormities and performance improvement, and meets intelligent management and control requirements of the equipment.

The invention provides an air tightness optimization method for a soft pressurization cabin, and the method comprises the steps: presetting a dynamic sensor array at a specific position where a structure is liable to fail according to a failure risk assessment table, collecting stress concentration data caused by non-uniform pressure distribution in real time, and generating a stress distribution dynamic graph containing a time sequence; the dynamic adjusting device is driven to operate through the homogenized pressure distribution adjusting scheme, pressure field data in the cabin body is updated in real time, whether material fatigue is within the fracture risk range or not is judged, and a fatigue state monitoring report is generated; obtaining a fracture risk index in the fatigue state monitoring report, carrying out iterative adjustment on the fiber weaving density and the elastic modulus of the key area by adopting a material design optimization algorithm, and determining a final structure layout parameter for improving the performance; and extracting a limiting condition of dynamic adjustment difficulty from the final structure layout parameters, simulating a cabin operation state in an extreme environment through a digital twin technology, calculating a boundary value of performance limitation, and obtaining a verification result of performance improvement.

The invention provides an arch dam shape efficient intelligent optimization method and system based on an agent model. The method comprises the steps that an arch dam physical-numerical model is constructed, a double optimization target with structural safety and economical efficiency as the core is determined, design parameters are selected, a constraint function is set, and an evaluation index system is established; samples are generated through Latin hypercube sampling, a data set is constructed in combination with finite element calculation, and a multi-task learning architecture is adopted to train a high-precision agent model. And then, coupling the proxy model with a multi-objective optimization algorithm, quickly searching a Pareto optimal solution set, and screening out a comprehensive optimal figure by using a multi-attribute decision-making method. And finally, through a finite element simulation verification result, prediction precision and performance improvement are ensured. The method has the advantages of lightweight modeling, efficient prediction and accurate search, and provides an effective tool for intelligent optimization and rapid decision making of hydraulic structures such as arch dams and the like.

The invention relates to the technical field of artificial intelligence, and particularly discloses a modular computation efficiency testing method, system, device and equipment, a medium and a product. Determining a model performance parameter, a model data throughput parameter and a calculation performance parameter according to the model calculation task, and determining the model calculation efficiency of the tested model calculation system according to the model performance parameter, the model data throughput parameter and the calculation performance parameter, so as to carry out quantitative evaluation on the model performance improvement effect of the calculation power improvement. Therefore, quantitative evaluation of the model calculation performance of the tested model calculation system comprising the tested model, the tested software framework and the tested equipment is realized. As an evaluation scheme suitable for various model calculation tasks, the comparability indexes of different models running on different devices are enhanced, and a reference basis is provided for improvement and perfection of the model and a model calculation system.

The invention discloses an electric energy meter and environment automatic test management method and system, and the method comprises the steps: collecting electric energy meter data and laboratory environment data, dividing the standardized data into a plurality of layers for processing, carrying out the multi-layer weight fusion, and obtaining a final fusion result through an adaptive weighting and cross validation mechanism; a multi-layer hybrid neural network optimization algorithm is utilized to map the final fusion result and the environmental data to a high-dimensional space, spatial-temporal features are extracted through a spatial-temporal convolution layer, feature integration and final prediction are carried out through a dynamic feedback loop layer and an adaptive weight control full-connection layer, and an electric energy meter performance evaluation result is generated; based on a multi-target adaptive scheduling algorithm, experimental requirements, environmental parameters and an electric energy meter performance evaluation result, a scheduling strategy is optimized through a gradient descent method, the updated scheduling strategy is applied to a test process and experimental conditions, closed-loop control is formed, and continuous optimization and performance improvement of the system are ensured.

The invention belongs to the technical field of artificial intelligence, and relates to a fine-grained instruction following evaluation method and system based on a large language model. The method comprises the steps that (1) an instruction is collected from an actual application scene, a corresponding response is generated for the instruction, constraints in the instruction are decomposed, a constraint check list is generated, a plurality of comments are generated for each constraint, and each comment comprises explanation and judgment; 2) selecting an optimal comment for each constraint through a comment filtering mechanism, and forming a training data set based on the instruction, the corresponding response, the constraint check list and the optimal comment; 3) supervising and fine-tuning the large language model to obtain a supervised and fine-tuned large language model; 4) performing preference optimization on the supervised and fine-tuned large language model to obtain a preference-optimized large language model, and 5) performing fine-grained instruction following evaluation by using the preference-optimized large language model, so that greater performance improvement can be brought under lower calculation overhead, and the reliability of instruction following evaluation is improved.

The invention discloses an interpretable recommendation optimization system based on user feedback driving, and the system is characterized in that the system comprises an offline strategy reinforcement learning framework, a personalized reward prompt of target perception, multi-view interpretation optimization based on Pareto optimum, an overall target function, and a complete learning algorithm; by introducing user subjective evaluation and a multi-objective optimization strategy, the problems that recommendation interpretation quality is low and user requirements cannot be accurately reflected are solved. According to the method, the performance of the original basic model is remarkably improved in the aspects of recommendation quality and generation of the recommendation explanation text.

The invention provides a STAR-RIS auxiliary transmission passive Internet of Things performance enhancement method, and aims to solve the problems of half-space limitation and low energy and information transmission efficiency of an RIS auxiliary passive Internet of Things. According to the invention, the STAR-RIS is deployed between the passive BDs and the access point to assist the BDs to transmit information to the access point, so that the total space distribution of the BDs is realized. In addition, beamforming is constructed at an energy station configured with multiple antennas to improve energy transmission efficiency. The invention provides an iterative algorithm based on a double-layer frame, and aims to solve the problem of joint optimization of a beam forming vector based on NOMA and an STAR-RIS element coefficient, and maximize the system sum rate, thereby remarkably improving the performance of a passive Internet of Things system.

The invention discloses a wireless communication method, device and equipment, and belongs to the field of communication, and the wireless communication method comprises the steps that a terminal sends first information to network side equipment; wherein the first information is used for indicating at least one of the following items: preference of the terminal for executing the first operation and information obtained by mobility reasoning based on an AI model; the first operation comprises at least one of the following items: cell switching, cell redirection, connection reestablishment, cell selection, cell reselection, activation of a turned-off cell, entering an idle state, leaving a connection state, shutdown, entering a flight mode, and mobility reasoning based on an AI model. In the embodiment of the invention, the terminal reports the preference of the terminal for executing the first operation or the information obtained by the mobility reasoning based on the AI model, so that the network side equipment can perform terminal-level configuration optimization according to the preference information of the terminal or the information obtained by the mobility reasoning based on the AI model, and the performance improvement taking the terminal as the center is realized.

The invention discloses a formula optimization method and device of an insulating material, equipment and a storage medium, and relates to the technical field of chemical materials.The method comprises the steps that initial formula information corresponding to the current insulating material is obtained, and a physical constraint model is constructed according to the initial formula information; the physical constraint model is composed of a component compatibility constraint condition, a process feasibility constraint condition and a material performance threshold condition; generating an initial candidate formula according to a physical constraint model based on the initial formula information; performing iterative optimization on the initial candidate formula by adopting a gradient response optimization algorithm to obtain a current candidate formula; and performing physical property prediction on the current candidate formula, and determining a target optimization formula according to a physical property prediction result. The optimization process is based on a scientific model and algorithm, the limitation of traditional experience can be broken through, the relation between different performance indexes is balanced, the formula combination which may be ignored is explored, and a new possibility is provided for performance improvement of the insulating material.

The invention discloses a method and system for assisting weak supervision full slide image classification performance improvement in the technical field of computer vision and computational pathology, and the method comprises the steps: obtaining an image block instance set of WSI through a data preprocessing module, and obtaining an instance feature matrix through a pre-training feature extractor; learning features which are related to tasks but possibly contain deviation by using observation branches, and adaptively fusing observation representation and potential causal representation by intervention branches through a causal gate unit so as to correct false correlation; and combining the two-branch classification loss and cross-branch adversarial supervision loss joint optimization model, and finally outputting WSI classification prediction fusing double-branch results. According to the method and the system for assisting weak supervision full slide image classification performance improvement, shortcut learning can be effectively inhibited without explicitly annotating confounding factors, the generalization performance of a model on data outside distribution is remarkably improved, and the method and the system can be flexibly embedded into various mainstream MIL frames as a universal module.

The invention relates to a microprism reflective film integrated with three types of triangular pyramid combinations and a manufacturing method of a mold of the microprism reflective film, which are characterized in that the surface of the microprism reflective film is formed by the same parallelogram unit array, and each parallelogram unit consists of four same triangular pyramids A, two mixed triangular pyramids B and two mixed triangular pyramids C, the bottom surfaces of the triangular pyramids A, the mixed triangular pyramids B and the mixed triangular pyramids C are the same equilateral triangles, the inclination angles of the three pyramid surfaces of each triangular pyramid A are alpha / 2, the inclination angles of the pyramid surfaces of the mixed triangular pyramids B are alpha / 2, alpha / 2 and beta L, and the inclination angles of the three pyramid surfaces of the mixed triangular pyramids C are alpha / 2, alpha / 2 and beta R; according to the method, the performance under different application conditions can be reasonably optimized, so that wide-angle performance improvement and optimization and balance of overall comprehensive performance can be realized.

The invention discloses a traditional building micro-reconstruction performance improving system based on machine learning. According to the method, the inherent contradiction between traditional building protection and performance improvement is effectively broken through an intelligent multi-dimensional data fusion and generative design technology. A holographic information model constructed by the multi-source data acquisition module completely retains historical genes and space passwords of a building, and provides an accurate space-time reference for subsequent transformation; a two-channel analysis mechanism of the performance evaluation module brings physical structure safety and cultural value continuity into a unified evaluation system, and ensures that a transformation scheme not only meets modern use requirements but also inherits and builds wisdom. The pattern generation and space reconstruction technology of the module is creatively designed, the limitation of traditional craftsman experience inheritance is broken through, contemporary expression of traditional building languages is achieved in the digital twinning environment, and historical style protection is changed from passive limitation to active innovation.

The invention is suitable for the technical field of permanent magnet synchronous motor performance improvement, and provides a motor multi-objective optimization method and system based on an improved dung beetle optimization algorithm, and the method comprises the steps: building a mathematical model of the torque ripple and dynamic response capability of a motor, and determining initial design parameters which affect the torque ripple and dynamic response capability; according to the simulation data of the stator skewed slot of the motor, determining an optimal angle meeting a first constraint condition so as to establish a motor model; based on the motor model, motor structure parameters influencing the initial design parameter sensitivity are analyzed, and the obtained motor structure parameters include the stator outer diameter, the permanent magnet thickness, the tooth width and the air gap length; according to the invention, research is carried out from the angle of a stator skewed slot, and an optimal angle with large torque pulsation reduction and small dynamic response capability reduction is obtained; the initial design parameters are subjected to sensitivity analysis to obtain structure parameters, algorithm optimization is carried out after fitting, and multi-objective optimization of the motor is achieved.

The invention relates to the technical field of storage data processing, in particular to a data processing method and system of a storage device and a storage medium. The method comprises the following steps that an input data stream is received, the data stream comprises a plurality of data units, and noise filtering and signal standardization are executed through an initial preprocessing module so that the integrity of the data stream can be improved; and splitting the preprocessed data stream through a multi-mode interference divider, and performing spatial and frequency domain decomposition of the signal by the divider according to the length and wavelength difference of the optical path for subsequent parallel processing. According to the invention, photon calculation and storage technologies are combined, and a traditional electronic calculation part is replaced by an efficient photon signal processing module. Specifically, a photon calculation module is utilized, the speed of data processing is increased, and particularly, performance improvement by several times can be provided when large-scale and high-concurrency data requests are processed.

The invention provides a GPU acceleration system and method based on medium sparseness large language model sparse matrix multiplication, and belongs to the technical field of computers. The system cuts a large model weight matrix through an unstructured cutting module to obtain a sparse weight matrix; a sparse matrix is converted into an MLSF format through a sparse tensor kernel layer, a slot filling layer and a residual element layer in the sparse matrix preprocessing module so as to minimize storage and decoding overhead; a sparse matrix multiplication GPU operation module is used, an MLSF format and a dense matrix are used as input, a fragmentation strategy and asynchronous loading are combined, a pipeline mechanism of data loading, decoding and calculation is constructed, and high overlapping of calculation and memory access operation is achieved. According to the method, dense matrix calculation with sparse matrix multiplication performance exceeding highly optimized performance is realized under medium sparseness, performance improvement of 5.29 times at most is obtained, and technical support is provided for efficient deployment of a large language model.

The invention provides a computer performance dynamic adjusting system and method based on user operation behaviors, and relates to the technical field of computers. Comprising an event capture module, an operation semantic association module, a system resource optimization module and an adaptive correction module. The event capturing module obtains user operation data and generates an operation event sequence with a timestamp. The operation semantic association module is used for matching an operation event and an operation mode through a nonlinear time axis, and generating a resource demand vector in combination with a window focus and a process stack calling relationship. And the system resource optimization module selects a resource allocation scheme with the lowest power consumption on the basis of an ant colony algorithm under the condition that response time constraints are met, and reallocates resources. And the adaptive correction module adjusts the matching weight of the operation mode by comparing the deviation between the actual response time and the expected response time, and feeds back a corrected matching threshold. The system can dynamically adjust computer performance, improve response speed and reduce power consumption.

The invention discloses an imitated radio frequency division multiplexing signal detection method based on low-complexity optimization expected propagation, and belongs to the signal detection technology of multi-carrier communication. According to the method, information is updated through iteration to approach an ML result, and the complexity is reduced from an exponential level to a cubic level; in order to reduce the complexity of the EP, sparse and quasi-banded channel structures in the DAFT domain are utilized. Through matrix block decomposition, upper and lower triangular decomposition and upper triangular matrix forward substitution, low-complexity matrix inversion is successfully realized, and the complexity of the EP algorithm is reduced to a linear level. In addition, the EP algorithm performance is further improved through a deep learning optimization moment matching strategy, so that the process becomes more adaptive through trainable positive and negative component parameters. In addition, DAFT domain iteration detection and decoding can be achieved based on the method, external information of a decoder is fed back to a detector, and the reliability of the whole system is remarkably improved. According to the invention, effective balance between performance improvement and calculation complexity is realized.

The invention relates to the technical field of communication, particularly discloses a phased array transmitting and receiving circuit and a transmitting control method, and brings double advantages of system structure simplification and performance improvement through highly integrated design of three core links of baseband, frequency conversion and beam control. In the aspect of the structure, the physical size of the circuit is obviously reduced, and the hardware complexity and the manufacturing cost are reduced. In addition, in terms of performance, signal loss and delay are effectively suppressed by shortening an internal signal transmission path. Furthermore, the same signal processing unit uniformly outputs the baseband signal and the beam control signal, so that accurate and low-delay synchronization between data processing and beam pointing adjustment is realized, and the inherent time sequence error of a discrete scheme is avoided.

The invention discloses an RSU auxiliary multi-hop task unloading method based on asynchronous deep reinforcement learning, relates to the technical field of edge unloading and deep reinforcement, and accurately evaluates the connection stability between nodes by establishing a vehicle movement model and a communication model; modeling a task unloading problem into a high-dimensional MDP, and solving the problem by adopting an A3C algorithm; according to the A3C algorithm, a plurality of agents are asynchronously trained, so that the optimization problem in a large-scale action space is effectively solved, and a better task unloading strategy is realized in a complex and changeable car networking environment; compared with an existing task unloading strategy, the method has the advantages that the performance is remarkably improved in the aspects of reducing task processing delay and improving the computing resource utilization rate, and particularly in a multi-RSU and high-dynamic scene, the task completion rate and the resource utilization efficiency of the system are remarkably improved; in addition, the method also has good expansibility, and can adapt to more complex application requirements in the future Internet of Vehicles.

The invention discloses a design method and application of a multi-stage centrifugal pump transition runner splitter plate. Relates to the design improvement of the transition runner splitter plate structure of the multi-stage middle-open centrifugal pump. By improving the structure of the transition flow channel, the hydraulic loss in the transition flow channel is reduced, the working efficiency is improved, and the purpose of saving energy is achieved. The method comprises the following steps that S1, a mathematical model of the deviation angle of the transition flow channel splitter plate is established, S2, numerical simulation verification of the multi-stage centrifugal pump is conducted according to the mathematical model, and S3, a target model is found according to the numerical simulation verification result. According to the design method, the hydraulic characteristics of the multi-stage centrifugal pump in actual operation are analyzed, the arrangement rule of the longitudinal splitter plates is creatively revealed, and a better solution of a target model is obtained on the basis of a nonlinear rule. According to the method, r / R and alpha serve as interactive variables, and the comprehensive influence of r / R and alpha on lift and efficiency is researched through numerical simulation. The limitation of a single parameter in a traditional design is broken through, and a new thought and technical means are provided for improving the performance of the multi-stage pump.

The invention relates to the technical field of battery management, and particularly discloses a lithium ion battery cycle performance improving method based on multi-feature analysis. Key parameters of capacity, internal resistance, charge and discharge efficiency and temperature fluctuation of a battery are monitored in real time; according to the method, the electrolyte decomposition risk can be accurately evaluated and early warning can be provided by utilizing the advanced algorithms such as dynamic time warping, Kalman filtering, fast Fourier transform and Haar wavelet transform to calculate corresponding characteristic values and combining a gradient boosting decision-making tree and a machine learning model of a support vector machine, and once the potential risk is detected, the risk of electrolyte decomposition can be accurately evaluated and early warning can be provided. The system automatically starts the PID controller to precisely regulate and control the charging and discharging process and the temperature, it is ensured that the battery operates under the optimal condition, the comprehensive monitoring and regulation and control mechanism effectively prevents potential safety hazards such as electrolyte decomposition, the service life of the battery is remarkably prolonged, and the overall safety of the system is improved.

The embodiment of the invention discloses a thread priority adjustment method and related equipment which are applied to electronic equipment, and the electronic equipment runs a first application. A first process of the first application comprises a plurality of first threads; identifying an associated thread of the first thread from the threads of the second process; the second process is a process which is operated by the electronic equipment, except the first process and the resident process and provides service for the first application; when it is detected that the running state of the first application is changed, the priority of the first thread is adjusted, the priority of the associated thread is adjusted, and the priority adjustment trend of the associated thread is consistent with the priority adjustment trend of the first thread. By adopting the embodiment of the invention, the response speed and performance of the system can be improved, and the user experience is improved.