CN114385256B

CN114385256B - Configuration method and configuration device of system parameters

Info

Publication number: CN114385256B
Application number: CN202011136341.3A
Authority: CN
Inventors: 谢鹏程; 孙涛; 雷晓松
Original assignee: Huawei Cloud Computing Technologies Co Ltd
Current assignee: Huawei Cloud Computing Technologies Co Ltd
Priority date: 2020-10-22
Filing date: 2020-10-22
Publication date: 2024-06-11
Anticipated expiration: 2040-10-22
Also published as: CN114385256A

Abstract

The application provides a configuration method and a configuration device for system parameters, which are used for enabling a configuration parameter value range output by a parameter configuration rule system to restrict the configuration parameter value range output by a machine learning system by combining the parameter configuration rule system with the machine learning system, helping the machine learning system to carry out optimization solution in a more possible optimal solution area, and further obtaining a more accurate target value range of the configuration parameters.

Description

Configuration method and configuration device of system parameters

Technical Field

The present application relates to the field of information technologies, and in particular, to a method and an apparatus for configuring system parameters.

Background

With the development of electronic information technology and artificial intelligence, the use of information technology (information technology, IT) facilities, such as computers, hard disks, video cloud transcoding systems or database systems, etc., has become more and more popular.

IT facilities include hardware facilities and software facilities. Whether hardware or software facilities, their configuration parameters are often vastly variable, facing different users, different operating environments, and/or different traffic loads, because if uniformly configured using the same configuration parameters, performance maximization of the IT facility will not be achieved.

In a method for configuring parameters of an IT facility to make the performance of the IT facility better, a maximum value range of configuration parameters of the IT facility and performance requirements of the IT facility can be input to a machine learning system, then the machine learning system selects a value range of configuration parameters capable of enabling the IT facility to meet the performance requirements from the maximum value range of the configuration parameters based on a specified machine learning algorithm, and performs parameter configuration on the IT facility based on the value range of the configuration parameters selected by the machine learning system.

However, since the machine learning system is essentially a black box model, the range of values of the configuration parameters selected based on the machine learning system may be inaccurate, thereby causing an abnormality of IT facilities and presenting a safety hazard.

Disclosure of Invention

The application provides a configuration method of system parameters, which realizes more accurate target value range of configuration parameters and further increases the robustness of a machine learning system.

In a first aspect, the present application provides a method for configuring system parameters. The configuration method of the system parameters comprises the following steps: acquiring configuration information of a target system, wherein the configuration information is used for indicating a value range of at least one configuration parameter of the target system; outputting M parameter value ranges based on configuration information by using a parameter configuration rule system, wherein the M parameter value ranges are in one-to-one correspondence with M configuration parameters of a target system, and M is a positive integer; using a machine learning system to output N first parameter value ranges based on configuration information, wherein the N first parameter value ranges are in one-to-one correspondence with N configuration parameters of a target system, N is a positive integer greater than or equal to M, and M configuration parameters are included in the N configuration parameters; determining a target value range of each of the N configuration parameters according to the M parameter value ranges and the N first parameter value ranges, wherein the target value range of the first configuration parameter of the N configuration parameters comprises all or part of the parameter value ranges corresponding to the first configuration parameter of the M parameter value ranges and the parameter value ranges corresponding to the first configuration parameter of the N first parameter value ranges; and configuring a target system according to the target value range of each configuration parameter in the N configuration parameters.

According to the configuration method of the system parameters, the parameter configuration rule system is combined with the machine learning system, so that the parameter value range output by the parameter configuration rule system is constrained by the parameter value range output by the machine learning system, the machine learning system is helped to carry out optimization solution in a more possible optimal solution area, and therefore the more accurate target value range of the configuration parameters is obtained.

With reference to the first aspect, in one possible implementation manner, configuring the target system according to the target value range of each configuration parameter in the N configuration parameters includes: using a machine learning system to output N second parameter value ranges based on the performance and configuration information of the target system; the method comprises the steps of determining a target value range of each configuration parameter in N configuration parameters again according to M parameter value ranges and N second parameter value ranges, wherein the target value range of a first configuration parameter in the N configuration parameters comprises all or part of the parameter value ranges corresponding to the first configuration parameter in the M parameter value ranges and all or part of the parameter value ranges corresponding to the first configuration parameter in the N second parameter value ranges; and configuring the target system according to the target value range redetermined for each of the N configuration parameters.

According to the configuration method of the system parameters, provided by the application, the machine learning system continuously updates the configuration parameter value range of the target system under the constraint of the parameter configuration rule system, so that a more accurate target value range is obtained; in addition, when the performance of the target system is greater than the requirement threshold, the target system is configured according to default configuration parameters, so that the robustness of the machine learning system is improved.

With reference to the first aspect, in one possible implementation manner, configuring the target system according to the target value range of each configuration parameter in the N configuration parameters includes: if the performance of the target system exceeds the performance threshold, configuring the target system according to the default value range of the N configuration parameters.

According to the configuration method of the system parameters, when the performance of the target system exceeds the performance threshold, the default configuration parameters are used for configuring the target system, so that the robustness of the machine learning system is improved.

With reference to the first aspect, in one possible implementation manner, the target value range of the second configuration parameter in the N configuration parameters includes a third parameter value range in the parameter value ranges corresponding to the second configuration parameter in the N first parameter value ranges, and the third parameter value range includes all or part of the parameter value ranges corresponding to the second configuration parameter in the M parameter value ranges and the parameter value ranges corresponding to the second configuration parameter in the N first parameter value ranges that do not overlap.

The configuration method of the system parameters provided by the application ensures that the target value range of the second configuration parameters of the target system is not contained in the value range output by the parameter configuration rule system, thereby obtaining a more accurate target value range under the condition that the value range output by the parameter configuration rule system is inaccurate.

With reference to the first aspect, in one possible implementation manner, the target value range of any one configuration parameter except the first configuration parameter in the N configuration parameters is all or part of the value ranges of the parameter corresponding to any one configuration parameter in the M parameter value ranges and the parameter value range corresponding to any one configuration parameter in the N first parameter value ranges.

The configuration method of the system parameters ensures that the first parameter value ranges output by the machine learning system are all required to be contained in the parameter value ranges output by the parameter configuration rule system, thereby improving the safety performance of the target system while obtaining a more accurate target value range.

With reference to the first aspect, in one possible implementation manner, the machine learning system is implemented based on a bayesian algorithm, a genetic algorithm, or a particle swarm algorithm.

In a second aspect, the present application provides a configuration apparatus for system parameters, including: the acquisition module is used for acquiring configuration information of the target system, wherein the configuration information is used for indicating a value range of at least one configuration parameter of the target system; the first parameter output module is used for outputting M parameter value ranges based on configuration information by using a parameter configuration rule system, wherein the M parameter value ranges are in one-to-one correspondence with M configuration parameters of the target system, and M is a positive integer; the second parameter output module is used for outputting N first parameter value ranges based on configuration information by using the machine learning system, the N first parameter value ranges are in one-to-one correspondence with N configuration parameters of the target system, N is a positive integer greater than or equal to M, and the M configuration parameters are included in the N configuration parameters; the processing module is used for determining a target value range of each configuration parameter in the N configuration parameters according to the M parameter value ranges and the N first parameter value ranges, wherein the target value range of the first configuration parameter in the N configuration parameters comprises all or part of the parameter value ranges corresponding to the first configuration parameter in the M parameter value ranges and the parameter value ranges corresponding to the first configuration parameter in the N first parameter value ranges; the configuration module is used for configuring the target system according to the target value range of each configuration parameter in the N configuration parameters.

With reference to the second aspect, in one possible implementation manner, the second parameter output module is further configured to: using a machine learning system to output N second parameter value ranges based on the performance and configuration information of the target system; the processing module is also used for: the method comprises the steps of determining a target value range of each configuration parameter in N configuration parameters again according to M parameter value ranges and N second parameter value ranges, wherein the target value range of a first configuration parameter in the N configuration parameters comprises all or part of the parameter value ranges corresponding to the first configuration parameter in the M parameter value ranges and all or part of the parameter value ranges corresponding to the first configuration parameter in the N second parameter value ranges; the configuration module is also used for: and configuring the target system according to the target value range redetermined for each of the N configuration parameters.

With reference to the second aspect, in one possible implementation manner, the configuration module is further configured to: if the performance of the target system exceeds the performance threshold, configuring the target system according to the default value range of the N configuration parameters.

With reference to the second aspect, in one possible implementation manner, the target value range of the second configuration parameter in the N configuration parameters includes a third parameter value range in the parameter value ranges corresponding to the second configuration parameter in the N first parameter value ranges, and the third parameter value range includes all or part of the parameter value ranges corresponding to the second configuration parameter in the M parameter value ranges and the parameter value ranges corresponding to the second configuration parameter in the N first parameter value ranges that do not overlap.

With reference to the second aspect, in one possible implementation manner, the target value range of any one configuration parameter except the first configuration parameter in the N configuration parameters is all or part of the value ranges of the parameter corresponding to any one configuration parameter in the M parameter value ranges and the parameter value range corresponding to any one configuration parameter in the N first parameter value ranges.

With reference to the second aspect, in one possible implementation manner, the machine learning system is implemented based on a bayesian algorithm, a genetic algorithm, or a particle swarm algorithm.

In a third aspect, the present application provides a configuration apparatus for system parameters, including: a memory and a processor; the memory is used for storing program instructions; the processor is configured to invoke program instructions in the memory to perform a method of configuring system parameters as described in the first aspect or any one of the possible implementations thereof.

In a fourth aspect, the present application provides a chip comprising at least one processor and a communication interface, the communication interface and the at least one processor being interconnected by a wire, the at least one processor being configured to execute a computer program or instructions to perform a method of configuring system parameters as described in the first aspect or any one of the possible implementations thereof.

In a fifth aspect, the present application provides a computer readable medium storing program code for execution by a device, the program code comprising means for performing the configuration method of system parameters according to the first aspect or any one of the possible implementations thereof.

In a sixth aspect, the present application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of configuring system parameters as described in the first aspect or any one of the possible implementations.

In a seventh aspect, the present application provides a server comprising at least one processor and a communication interface, the communication interface and the at least one processor being interconnected by a line, the communication interface being in communication with a target system, the at least one processor being configured to execute a computer program or instructions to perform a method of configuring system parameters as described in the first aspect or any one of the possible implementations thereof.

Drawings

FIG. 1 is a schematic diagram of an IT system in accordance with one embodiment of the present application;

FIG. 2 is a schematic diagram of a parameter configuration system according to an embodiment of the present application;

FIG. 3 is a schematic flow chart of a method for configuring system parameters according to one embodiment of the present application;

FIG. 4 is a schematic flow chart of a method for configuring system parameters according to another embodiment of the present application;

FIG. 5 is a schematic structural diagram of a configuration device of system parameters according to an embodiment of the present application;

Fig. 6 is a schematic structural diagram of a configuration device according to another embodiment of the present application.

Detailed Description

For the purpose of understanding, the relevant terms to which the present application relates will be first described.

1. Rule engine

The rules engine, developed by the inference engine, is a component embedded in the application that separates business decisions from the application code and can write rules using predefined semantic modules.

It represents the basic knowledge in a regular form, which can be generally expressed in a if-then form, and if a part contains given information or factors, a part is the corresponding behavior. For example, a rule may be a statement expressed in terms of "if this condition is met, then its action should be taken". For example, if an animal is a mammal and eats meat, then such an animal is referred to as a carnivorous animal.

Rules are used as a knowledge, typically applied by the practice of drawing conclusions from a given set of rules. This conclusion may be a static result or a set of operations that need to be performed. The process of applying such rules is called reasoning. If the inference process is handled by a program, then this program is called an inference engine.

The control strategies adopted by the inference engine according to the knowledge representation are also different, and common types include neural network-based, case-based, and rule-based inference engines. Among other things, rule-based inference engines, also referred to as "rule engines", are easy to understand, easy to obtain, and easy to manage.

2. Machine learning

Machine learning is a generic term for a class of algorithms that attempt to mine the underlying laws from a vast array of historical data and is used for prediction or classification. More specifically, machine learning can be seen as finding a function where the input is sample data and the output is the desired result. Typically, this function is more complex than the price, and is not very convenient to express in formalism.

It will be appreciated that the goal of machine learning is to adapt the learned function well to the "new sample" rather than just performing well on the training sample.

Generally, an algorithm in machine learning is used to find a function, which is mainly divided into the following three steps:

In a first step, a suitable model is selected, which usually needs to be selected according to the actual problem, and the model is a set of functions for different problems and tasks.

And secondly, judging whether a function is good or bad, wherein a measurement standard, namely a loss function, is required to be determined, the determination of the loss function is also required to be determined according to specific problems, such as regression problems generally adopt Euclidean distance, and classification problems generally adopt cross entropy cost functions.

Third, find the "best" function. Common methods are gradient descent algorithm or least square method.

After learning the "best" function, a test can be performed on the new sample to test whether the function is truly a "good" function.

3. Genetic algorithm

There are a great number of problems related to optimization and self-adaption in modern scientific theory research and practice, but except for some simple cases, the problems of optimization and self-adaption of large-scale complex systems still cannot be considered. However, organisms in nature exhibit excellent abilities in terms of adaptation, they can survive and multiply with superior and inferior, self-evolving rules of survival of the fittest, and gradually produce superior species with very high adaptability to their living environment. The genetic algorithm is a search algorithm based on natural selection and population genetic mechanisms, which simulates the phenomena of propagation, hybridization and mutation in natural selection and natural genetic processes. When the problem is solved by using a genetic algorithm, each possible solution of the problem is encoded into one "chromosome", i.e. an individual, several individuals constituting a population. At the beginning of the genetic algorithm, individuals are always randomly generated, each individual being evaluated according to a predetermined objective function, giving an fitness value. Based on this fitness value, some individuals are selected to produce the next generation, and the selection operation embodies the principle of "survival of the fittest". "good" individuals are used to generate the next generation. "bad" individuals are eliminated. And then, the selected individuals are recombined through crossing and mutation operators to generate a new generation, and the individuals of the new generation inherit some excellent characters of the previous generation, so that the performance of the individuals of the new generation is better than that of the previous generation, and the individuals of the new generation gradually evolve towards the optimal solution. Thus, the genetic algorithm can be seen as a process of initial evolution of a population consisting of viable solutions.

When solving a problem using genetic algorithms, the objective function and variables of the problem are first determined and then the variables are encoded, mainly because in genetic algorithms, the solution of the problem is represented using a string of numbers and the genetic operators operate directly on the string. Encoding variables can be classified into binary encoding and real encoding. And after the coding modes of the objective function and the variable are determined, genetic operation can be performed. From the perspective of optimizing search, genetic operations can optimize the solution of the problem generation by generation, approach the optimal solution, and genetic operations can include the following three genetic operators: selection, crossover and mutation. Wherein the selection and crossover essentially completes most of the search functions of the genetic algorithm, and the variation increases the ability of the genetic algorithm to find the optimal solution. The selection, crossover and mutation in genetic manipulation are explained below, respectively.

Selecting: selection refers to the operation of selecting superior individuals from a population and eliminating inferior individuals. It is based on fitness evaluation. The greater the fitness of an individual, the greater the likelihood of being selected and the greater the number of its "offspring" in the next generation. The selection methods commonly used at present are a roulette method, an optimal individual reservation method, a desired value method, a sorting selection method, a competition method, a linear standardization method and the like.

Crossing: the crossover refers to the operation of replacing and recombining part of structures of two father individuals to generate new individuals, and the purpose of crossover is to generate new individuals in the next generation, and the searching capability of a genetic algorithm is dramatically improved through crossover operation. The crossover is an important means for acquiring excellent individuals by a genetic algorithm, and is carried out by randomly selecting two individuals in a matching library according to a certain crossover probability, wherein the crossover position is also random, and the crossover probability is generally quite large and is 0.6-0.9.

Variation: mutation is the random change of the values of certain genes of individuals in a population with small mutation probability, and the basic process of mutation operation is as follows: generating a random number between 0 and 1, and if the random number is smaller than the mutation probability, performing mutation operation. The mutation operation is a local random search, and is combined with the selection and crossing operators, so that permanent loss of certain information caused by the selection and crossing operators can be avoided, the effectiveness of the genetic algorithm is ensured, the genetic algorithm has the capability of local random search, and meanwhile, the genetic algorithm can keep the diversity of groups so as to prevent premature convergence.

4. Particle swarm algorithm

In the field of computer intelligence, and in particular in the population intelligent optimization algorithm, one of the most commonly used algorithms at the present time is the particle swarm algorithm (PARTICLE SWARM optimization algorithm, PSO). PSO is an evolutionary computing technique, derived from behavioral studies on bird predation, and has proven to be a good optimization method.

The PSO algorithm is to initialize a group of particles in a feasible solution space, each particle represents a potential optimal solution of the extremum optimizing problem, and three indexes of position, speed and fitness value are used for representing the particle characteristics. The particles move in the solution space and the individual positions are updated by tracking the individual extremum and the population extremum.

The individual extremum refers to the calculated fitness optimal position in the positions experienced by the individual, and the population extremum refers to the fitness optimal position searched by all particles in the population. And calculating a fitness value once every time the particle is updated, and updating the positions of the individual extremum and the group extremum by comparing the fitness of the new particle with the fitness values of the individual extremum and the group extremum.

5. Bayesian algorithm

The bayesian method is generally referred to as a bayesian analysis method, and provides a method for calculating the hypothesis probability, and the bayesian method is developed by the uk mathematician bayes and is used for describing the relationship between the two conditional probabilities. The bayesian formula refers to the probability that when an analysis sample is large to approach the population, the probability of occurrence of events in the population will be close to the probability of occurrence of the events in the population. In general, the probability of event a under the condition that event B occurs is different from the probability of event B under the condition of event a; however, both are in a deterministic relationship, and the Bayesian approach is a description of this relationship. The method is that the prior information about the unknown parameters is integrated with the sample information, the posterior information is obtained according to the Bayesian formula, and then the unknown parameters are inferred according to the posterior information.

Fig. 1 is a schematic diagram of an IT system according to an embodiment of the present application. As shown in FIG. 1, the IT system 100 of the present application may include a hardware facility 110 and a software facility 120. Hardware facilities 110 may include handheld devices, desktops, servers, routers, switches, hubs, notebooks, printers, basic input output system (basic input output system, BIOS) systems, etc., and software facilities 120 may include databases, video cloud transcoding, operating systems, etc.

For the IT system shown in fig. 1, there are a number of configuration parameters that affect ITs performance, both the hardware facility 110 and the software facility 120.

The relationship between configuration parameters and performance of an IT system is described below with respect to the hardware facility 110 being a BIOS system.

The BIOS system is solidified on the main board of the computer, and stores the most important basic input and output program, system setting information, self-checking program after starting up and system self-starting program of the computer, and the main functions of the BIOS system are to provide the bottommost and most direct hardware setting and control for the computer. In addition, the BIOS system provides some system configuration parameters to the operating system. When the computer runs, the BIOS system is firstly entered, and whether the performance of the computer is superior or not depends on whether the BIOS system on the computer motherboard is advanced or not to a great extent. For example, the BIOS system has a thread number parameter of a central processing unit (central processing unit, CPU) thereon, and when the load number is high, the thread number parameter may be adjusted, or when the energy consumption is low, some configuration parameters of the BIOS system may be adjusted, so that the load runs faster or the energy consumption is low.

The relationship between configuration parameters and performance of an IT system is described below with the software facility 120 being a database system.

A database system (DBS) is a desirable data processing system developed to accommodate data processing requirements, and is composed of a database and its software, which mainly includes an operating system, a utility program, and a database management system. Often, the operating environment and traffic load faced when the database carries different users is also changing. For example, the same DBS provides users with some data services, and during interaction with the business system, some users may read more densely, while some users may update the database (write data) frequently. For another example, some of the service data have a relatively large number of repeated data, and some of the service data have a relatively large number of columns. That is, different users have different requirements on the database, and thus the same DBS should be loaded with different configuration parameters for different users or different services. Or the same configuration parameter in the same DBS, the values of the configuration parameters can be different when facing different users. For example, the DBS system has a connection duration parameter thereon, which can be adjusted to adjust the time of the load connection when the number of loads is high or low.

The relationship between configuration parameters and performance of an IT system is described below with the software facility 120 being a video cloud transcoding system.

A video cloud transcoding system is a system that converts video through a server (cloud) into a video format suitable for mobile device playback. In general, when downloading movies, most of them are in audio-video interlaced format (audio video interleaved, AVI), and some mobile devices, such as mobile phones, do not support the playing of these formats, so that the user needs to perform a manual movie transcoding operation, and the mobile device can play after transcoding. For video cloud transcoding, a set of configuration parameters, such as GOP duration parameters, are included in the video codec. If the GOP duration is relatively long, there may be some effect on the black screen. The requirements of different users on video cloud transcoding are different, and the requirements may also be different in different time periods, for example, the load faced by a video cloud transcoding system is high at night, and at this time, corresponding configuration parameters in video encoding and decoding need to be adjusted.

In the IT system 100 shown in fig. 1, whether IT is a hardware facility 110 or a software facility 120, at present, there are two main methods for configuring parameters of the IT system 100, one is optimizing based on configuration of a rule engine, that is, a service expert extracts optimization logic according to experience, formulates optimization rules for a specific system, and then forms a rule engine to optimize configuration of system parameters; another is configuration optimization using a machine learning system, such as a genetic algorithm-based machine learning system or a bayesian optimization algorithm-based machine learning system.

As an example, fig. 2 is a schematic diagram of a parameter configuration system to which the technical solution provided by the embodiment of the present application may be applied. As shown in fig. 2, the parameter configuration system may include a configuration device and a target system, the configuration device being an external device to the target system. The configuration device can receive initial configuration information of the target system and/or performance requirement information of the target system in a cloud service mode, and configures parameters of the target system based on the initial configuration information and/or the performance requirement information of the target system in the cloud service mode.

For example, when optimizing BIOS system parameter configuration using a configuration device including a machine learning system, the configuration device including the machine learning system may send the learned BIOS system parameters to the BIOS system. The configuration device of the parameter configuration system may be a configuration device including a rule engine algorithm or a configuration device including a machine learning system. The target system may be any of the hardware facilities 110 or may be any of the software facilities 120.

However, in the face of massive parameters, due to limited experience of business specialists, it is difficult to form a superior rule engine and find the optimal solution; in the process of searching the optimal parameters, the machine learning system is a black box model in nature, so that the problem of poor learned system parameters can occur, the abnormal condition of the system is caused, and potential safety hazards exist.

Aiming at the problems, the application provides a configuration method of system parameters, which combines the configuration optimization based on a rule engine with the configuration optimization of a machine learning system, takes the rule engine as prior information and helps the machine learning system to carry out optimization solution in a more possible optimal solution area, thereby obtaining more accurate parameters. In addition, when the performance of the target system exceeds the performance threshold, the default configuration parameters are used for configuring the target system, so that the robustness of the machine learning system is improved.

Fig. 3 is a schematic flow chart of a configuration method of system parameters according to an embodiment of the present application. As shown in fig. 3, the method of the present embodiment may include S301, S302, S303, S304, and S305. The configuration method may be performed by the configuration apparatus shown in fig. 2.

S301, acquiring configuration information of a target system. The configuration information is used to indicate a range of values of at least one attribute of a configuration parameter of the target system.

In this embodiment, the target system refers to a system to be tuned that contains configuration parameters, and may be used to implement one or more functions. For example, the target system may be the IT system 100 shown in fig. 1.

The configuration information in this embodiment is used to indicate a value range of at least one configuration parameter of the target system (i.e., the system to be tuned). A configuration parameter may include one or more attributes and the range of values for the configuration parameter may include the range of values for each attribute of the configuration parameter. For example, an attribute of a configuration parameter may include both a value type and a value size, the value range of the value type includes an enumeration type, an integer type, and a floating point type, and the value range of the value size includes an integer between 1 and 5.

It will be appreciated that the configuration information may be different for different target systems, i.e. the range of values of the configuration parameters of the system to be tuned may be different. For example, the number of configuration parameters of the BIOS system, the value range of each configuration parameter, the type value range of each configuration parameter, and the number of configuration parameters of the DBS system, the value range of each configuration parameter, and the type value range of each configuration parameter may be different.

In one implementation, the configuration information of the target system may be recorded in a configuration file in JSON format, JSON being an abbreviation for JavaScript Object Notation. In this way, the configuration means of the system parameters can read the configuration information from the configuration file.

S302, outputting M parameter value ranges based on configuration information of a target system by using a parameter configuration rule system. The M parameter value ranges are in one-to-one correspondence with M configuration parameters of the target system, and M is a positive integer.

In this embodiment, the M configuration parameters may be part of the configuration parameters in the target system, or may be all the configuration parameters in the target system. For example, the number of configuration parameters of the target system is 10, and the output M parameter value ranges can be the value ranges of 5 configuration parameters or the value ranges of 10 configuration parameters based on the configuration information by using the parameter configuration rule system.

In this embodiment, the parameter configuration rule system is a system for optimizing configuration parameters of the target system, and is generally different for different target systems, and may be designed according to different functions of the target system. For DBS, for example, the parameter rule configuration system may be formulated according to the empirical knowledge of the expert in the DBS field; for BIOS, the parameter rule configuration system can be formulated according to the experience knowledge of the expert in the BIOS field.

Alternatively, the parameter configuration rule system in this embodiment may include a plurality of types of rules.

For example, a parameter configuration rule system may include multiple rules for one configuration parameter. As an example, assuming that the target system has only one configuration parameter a, the parameter configuration rule system is a system that optimizes the configuration parameter a of the target system, which contains two types of rules: in the condition 1, the value range of the parameter a is [1,2]; in condition 2, the value of the parameter a is a numerical value.

For another example, the parameter configuration rule system may include a plurality of rules for a plurality of configuration parameters. As an example, assume that the target system has 2 configuration parameters w and z, and the parameter configuration rule system outputs a value range of w under condition 1, and outputs a value range of z under condition 2.

In this embodiment, the input of the parameter configuration rule system is configuration information, and the output is M parameter value ranges. Because the M parameter value ranges are obtained through configuration information, and the configuration information comprises attribute information of the configuration parameters, the M parameter value ranges output by the parameter configuration rule system are positioned in the corresponding value ranges of the configuration information.

In one implementation, the parameter configuration rule system may provide a JSON-formatted file that allows a user to enter a series of rules. Wherein the rule may include a rule represented by an if (if) statement.

S303, outputting N first parameter value ranges based on configuration information of a target system by using a machine learning system. The N first parameter value ranges are in one-to-one correspondence with N configuration parameters of the target system, N is a positive integer greater than or equal to M, and the N configuration parameters comprise M configuration parameters.

In this embodiment, the N configuration parameters may include all configuration parameters of the target system, or may include part of configuration parameters of the target system. In some implementations, the machine learning system may output a range of values of all configuration parameters of the target system, where the N configuration parameters may include the aforementioned M configuration parameters, i.e., N is a positive integer greater than or equal to M.

Alternatively, in other implementations, the machine learning system may output a range of values for a portion of the configuration parameters of the target system. For example, the target system has 10 configuration parameters, and assuming that 1 configuration parameter is not required to be optimized, the machine learning system may be used to output a value range corresponding to the remaining 9 configuration parameters.

In this embodiment, the machine learning system refers to a system capable of outputting a range of values of configuration parameters of a target system based on configuration information and performance requirements of the target system using a machine learning algorithm.

The machine learning system in this embodiment may be a reinitialized system or a system trained by historical data, that is, a machine learning system trained by historical data before the target system, which is not limited in this aspect of the application.

The same machine learning algorithm may be used for different target systems, or different machine learning algorithms may be used. For example, for DBS and video cloud transcoding systems, the same machine learning system that incorporates bayesian algorithms may be used; alternatively, the DBS may use a machine learning system that includes a bayesian algorithm, while the video cloud transcoding uses a machine learning system that includes a genetic algorithm.

Similarly, similar to step S302, the input of the machine learning system is configuration information, and the output is N first parameter value ranges. Because the N first parameter value ranges are also obtained through the configuration information, and the configuration information comprises the attribute information of the configuration parameters, the N first parameter value ranges output by the machine learning system are positioned in the corresponding configuration information value ranges.

It is further described that, a specific implementation process of outputting the N first parameter value ranges by using the algorithm principle of the bayesian algorithm and the algorithm principle of the neural network in the example may refer to the description in the related art, which is not repeated herein.

S304, determining a target value range of each configuration parameter in the N configuration parameters according to the M parameter value ranges and the N first parameter value ranges, wherein the target value range of the first configuration parameter in the N configuration parameters comprises all or part of the parameter value ranges corresponding to the first configuration parameter in the M parameter value ranges and the parameter value ranges corresponding to the first configuration parameter in the N first parameter value ranges.

In this embodiment, the target value range of the first configuration parameter includes all or part of the value ranges of the M parameter value ranges corresponding to the first configuration parameter and the N first parameter value ranges overlapping with the value range of the parameter corresponding to the first configuration parameter, which may be understood as: the value range of the first configuration parameter cannot exceed the value range output by the parameter configuration rule system for the first configuration parameter, and cannot exceed the value range output by the machine learning system for the first configuration parameter.

As an example, one configuration parameter of the target system is denoted as a, the value range of the value size of a output by the parameter configuration rule system includes values in 0 to 2, and the value range of the value size of a output by the machine learning system is a value in 0 to 5, so that the target value range of the value size of a may include a portion where 0 to 2 and 0 to 5 completely overlap, that is, 0 to 2, and may also include a portion of the value range in 0 to 2, such as including 0 to 1.

As another example, one configuration parameter of the target system is denoted as b, the value range of the value size of b output by the parameter configuration rule system includes a value of 0.6, the value range of the value size of b output by the machine learning system includes a value of 0 to 1, and the target value range of the value size of b may include a value of 0.6.

It can be understood that, because the target value range of each of the N configuration parameters is affected by the M parameter value ranges output by the parameter configuration rule system and the N first parameter value ranges output by the machine learning system, the quality of the target value of each of the N configuration parameters is affected by the parameter configuration rule system and the machine learning system.

S305, configuring a target system according to the target value range of each configuration parameter in the N configuration parameters.

As an example, after obtaining the target value range for each of the N configuration parameters, a final value for each configuration parameter may be selected from the target value range for the configuration parameter, and the value for the configuration parameter in the target system may be configured as the final value. For example, a random selection method may be adopted to randomly select the final value of each configuration parameter from the target value range of the configuration parameter. In this embodiment, the method for selecting the final value of each configuration parameter from the target value ranges of the configuration parameters is not limited.

It can be appreciated that in this embodiment, configuring the target system according to the target value ranges of the N configuration parameters may include: and sending the target value ranges of the N configuration parameters to the target system so that the target system can configure the values of the N configuration parameters as values in the target value ranges.

According to the configuration method of the system parameters, the parameter configuration rule system is combined with the machine learning system, so that the parameter value range output by the parameter configuration rule system is constrained to the parameter value range output by the machine learning system, the machine learning system is helped to perform optimization solution in a more possible optimal solution area, and therefore the more accurate target value range of the configuration parameters is obtained.

In one possible implementation manner of this embodiment, the first configuration parameter may be any one of the above-mentioned M configuration parameters. That is, the target value range of any one of the N configuration parameters other than the first configuration parameter is all or part of the value ranges overlapping the value range of the parameter corresponding to any one of the M parameter value ranges and the value range of the parameter corresponding to any one of the N first parameter value ranges.

Or, the target value range of each of the N configuration parameters is a total or partial value range where the corresponding parameter value range of the M parameter value ranges overlaps the corresponding parameter value range of the N first parameter value ranges. In other words, the target value range of each configuration parameter of the target system cannot exceed the parameter value range output by the parameter configuration rule system, nor cannot exceed the parameter value range output by the machine learning system.

As an example, assuming that the target system has 20 configuration parameters, which respectively correspond to the value ranges of 20 configuration parameters output by the parameter configuration rule system and the value ranges of 20 configuration parameters output by the machine learning system, the target value ranges of all configuration parameters should be in a range where the value ranges of 20 configuration parameters output by the parameter configuration rule system and the value ranges of 20 configuration parameters output by the machine learning system overlap, that is, the value ranges of 20 configuration parameters output by the parameter configuration rule system cannot be violated.

According to the configuration method of the system parameters in the implementation mode, the first parameter value ranges output by the machine learning system are all required to be contained in the parameter value ranges output by the parameter configuration rule system, so that the safety performance of the target system is improved while the more accurate target value ranges are obtained.

In another possible implementation manner of this embodiment, the target value range of the second configuration parameter in the N configuration parameters includes a third parameter value range in the parameter value ranges corresponding to the second configuration parameter in the N first parameter value ranges, and the third parameter value range includes all or part of the parameter value ranges corresponding to the second configuration parameter in the M parameter value ranges and the parameter value ranges corresponding to the second configuration parameter in the N first parameter value ranges that do not overlap.

In this embodiment, the second configuration parameter refers to at least one configuration parameter of the N configuration parameters, and a third parameter value range of the N first parameter value ranges corresponding to the second configuration parameter indicates that the third parameter value range is a parameter value range corresponding to the machine learning system output.

In this embodiment, the third parameter value range includes all or part of the M parameter value ranges corresponding to the second configuration parameter and the N first parameter value ranges corresponding to the second configuration parameter, where the all or part of the parameter value ranges do not overlap with the parameter value ranges corresponding to the second configuration parameter, is the configuration parameter of the target system, and the target value range may not be included in the M parameter value ranges corresponding to the target parameter value range, that is, the parameter value range output by the parameter configuration rule system may not be satisfied, that is, the parameter value range output by the parameter configuration rule system may be allowed to be partially violated.

As an example, assume that the target system has two configuration parameters c and d, where, for parameter d, parameter d output by the parameter configuration rule system is a range of values, such as1 to 2. The parameter d output by the machine learning system is also a range of values, such as1 to 5. Assuming that the type of the required parameter is an integer, the range of the value of the parameter d output by the parameter configuration rule system and the range of the value of the parameter d output by the machine learning system are not overlapped in the range of 2 to 5, and if the method of randomly determining the configuration parameter in the range of 2 to 5 is adopted, the determined target value range of the configuration parameter d can be 3, i.e. the value range of the configuration parameter d violates the value range of the configuration parameter d output by the parameter configuration rule system.

As another example, assume that the target system configures two parameters e and f, where for parameter e, the parameter e output by the parameter configuration rule system is a specific value, assuming 0.5. The parameter e output using the machine learning system is a range of values, such as 0 to 1. The determined target value of the configuration parameter e may be 0.6, i.e. the target value of the configuration parameter e violates its value range output by the parameter configuration rule system.

According to the configuration method of the system parameters in the implementation mode, the target value range of the second configuration parameters of the target system can be not included in the value range output by the parameter configuration rule system, so that the more accurate target value range can be obtained under the condition that the value range output by the parameter configuration rule system is inaccurate.

Optionally, configuring the target system according to the target value range of each configuration parameter in the N configuration parameters includes: if the performance of the target system exceeds the performance threshold, configuring the target system according to the default value range of the N configuration parameters.

In this embodiment, after N first parameter value ranges are input to the target system, the performance of the corresponding target system is obtained. Because there may be a case where the performance of the target system is poor after the N first parameter value ranges are input to the target system and then input to the target system, a performance threshold and a default parameter may be specified for the performance of the target system. After the target system is configured based on the N first parameter value ranges, if the performance of the target system exceeds the performance threshold, the target system may configure the target system using default configuration parameters.

Or after configuring the target system based on the N first parameter value ranges, the target system may feed back the performance of the target system to the configuration device, and if the performance is greater than a preset performance threshold, the configuration device reconfigures a default configuration parameter for the target system, for example, reconfigures the default configuration parameter to the target system; otherwise, the configuration device can adjust parameters in the machine learning system based on the performance so that the machine learning system can output a better range of values of the configuration parameters.

As an example, the CPU utilization is one performance of the target system, and the CPU utilization of the target system is 92% after N first parameter value ranges are input. However, when the CPU exceeds 90%, the corresponding processing speed is reduced. Therefore, it is possible to designate that the performance threshold of the CPU utilization is 90%, and when the performance threshold of the CPU utilization of the target system is greater than 90% after the N first parameter value ranges are input, the default configuration parameter is adopted.

In one possible implementation, the performance threshold and default configuration parameters may be obtained through a JSON formatted file.

Fig. 4 is a schematic flow chart of a configuration method of system parameters according to another embodiment of the present application. As shown in fig. 4, the method of the present embodiment may include S401, S402, S403, S404, S405, S406, and S407. The configuration method may be performed by a configuration device of system parameters.

S401, acquiring configuration information of a target system.

In this embodiment, the configuration information is used to indicate a value range of at least one configuration parameter of the target system, and specific reference may be made to the related description in each embodiment, which is not repeated herein.

S402, the parameter configuration rule system processes.

Specifically, the parameter configuration rule system processes the configuration information of the target system, and outputs M parameter value ranges, wherein the M parameter value ranges correspond to the M configuration parameters of the target system one by one. The parameter configuration rule system outputs M parameter value ranges based on the configuration information, which may be described in relation to S302 in the embodiment shown in fig. 3, and will not be described herein.

S403, the machine learning system performs processing.

Specifically, the machine learning system processes the configuration information of the target system, and the machine learning system outputs N first parameter value ranges, wherein the N first parameter value ranges are in one-to-one correspondence with N configuration parameters of the target system. The machine learning system may refer to the description related to S303 in the embodiment shown in fig. 3 for outputting N first parameter value ranges based on the configuration information, which is not described herein.

S404, determining a target value range of each configuration parameter.

Specifically, determining the target value range of each configuration parameter includes determining the target value range of each configuration parameter according to the M parameter value ranges and the N first parameter value ranges. The implementation process of this step may be referred to as S304 in the embodiment shown in fig. 3, which is not described herein.

S405, configuring a target system according to the target value range of each configuration parameter.

This step may be referred to the relevant description in the above embodiments, and will not be repeated here.

S406, judging whether the performance of the target system exceeds a performance threshold, if so, re-executing S403, otherwise, executing S407.

Re-execution can be understood as feeding back the performance of the target system to the machine learning system, which learns and re-inputs the range of values of the configuration parameters of the target system.

As one example, the performance of the target system is fed back to the machine learning system, which learns, may include: and outputting N second parameter value ranges based on the performance and configuration information of the target system by using a machine learning system.

And re-determining the target value range of each configuration parameter in the N configuration parameters according to the M parameter value ranges and the N second parameter value ranges. The target value range of the first configuration parameter in the N configuration parameters comprises all or part of the value ranges of the parameters corresponding to the first configuration parameter in the M parameter value ranges and all or part of the value ranges of the parameters corresponding to the first configuration parameter in the N second parameter value ranges.

And configuring the target system according to the target value range redetermined for each of the N configuration parameters.

The machine learning system may adjust parameters of the machine learning system itself based on performance and configuration information of the target system. For example, a machine learning system that includes a bayesian algorithm may adjust parameters of the bayesian algorithm based on performance and configuration information of the 20 th round target system to update the machine learning system.

Optionally, the machine learning system is used to output N second parameter value ranges different from the corresponding N first parameter value ranges based on the performance and configuration information of the target system, that is, the N first parameter value ranges are adjusted. For example, the target system contains two configuration parameters m and x, in 2 first parameter value ranges obtained by first-round learning of the machine learning system, the parameter value range of m is 0 to 5, the parameter value range of x is 2 to 6, and the parameter value ranges of m and x obtained by first-round learning are input into the target system to obtain the performance of the corresponding target system; and the machine learning system performs second-round learning according to the performance and configuration information of the target system obtained by the first-round learning, wherein the parameter value range of m is 0 to 4, and the parameter value range of x is 4 to 6.

In this embodiment, the performance of the target system may be considered as the output of the target system, for example, the performance of the target system may be the CPU usage, time, or throughput. The performance threshold refers to a threshold specified for the performance of the target system. For example, the CPU usage performance threshold of the target system may be specified as 90% or the time performance threshold of the target system may be specified as 0.5 seconds.

It should be noted that the target systems are different and their corresponding performance may be different.

In this embodiment, after the N first parameter value ranges are input to the target system, if training is not finished, the N configuration parameters may be learned again based on the performance and configuration information of the target system. For example, the machine learning system may perform the second round of learning based on the performance of the target system obtained in the first round, or the machine learning system may perform the tenth round of learning based on the performance of the target system obtained in the ninth round.

It should be appreciated that there are a number of ways to determine whether the training process is complete. As an example, the training process may be ended by setting the number of iterations of the training, such as setting the number of iterations to not more than 100 rounds, that is, when the number of iterations is greater than 100 rounds. As another example, it may be determined whether the training process is ended by setting an error threshold, such as setting the error threshold to 0.01, i.e., ending the training process if the error is less than 0.01.

Since the parameter configuration rule system is unchanged, the first configuration parameter is unchanged during each learning of the system parameters based on the performance of the target system. The machine learning system is a continuously learned model, so that the machine learning system can continuously learn according to the performance and configuration information of the target system after the N first parameter value ranges are input into the target system, and N second parameter value ranges are obtained again.

In one possible implementation manner, the N second parameter value ranges may be obtained by inputting the N first parameter value ranges and the N first parameter value ranges into the machine learning system after inputting the performance of the target system into the target system, that is, the N second parameter value ranges and the N second parameter value ranges are input into the target system, and the performance of the target system forms a set of data capable of updating the machine learning system.

In this embodiment, the M parameter value ranges, that is, the M parameter value ranges described in S302, are unchanged because the parameter configuration rule system is unchanged. The target value range of the first configuration parameter includes all or part of the value ranges overlapping with the value range of the parameter corresponding to the first configuration parameter in the M value ranges of the parameter and the value range of the parameter corresponding to the first configuration parameter in the N second value ranges of the parameter, which can be understood as: the value range of the first configuration parameter cannot exceed the value range output by the parameter configuration rule system for the first configuration parameter, and cannot exceed the value range output by the machine learning system for the first configuration parameter.

In this embodiment, since the machine learning system performs learning and outputs the second value ranges of the N parameters, the target value range of each of the N configuration parameters needs to be redetermined. The implementation process of redefining the target value range of each configuration parameter in the N configuration parameters may refer to: and determining the related description in the target value range of each of the N configuration parameters according to the M parameter value ranges and the N first parameter value ranges, namely, step S304. And will not be described in detail herein.

In this embodiment, after obtaining the target value range redetermined by each of the N configuration parameters, the target system is configured.

It is further explained that this embodiment provides only one update procedure of the configuration parameters of the target system. In actual use, the number of times the system parameters are updated may be manually specified, for example, 100 times of updating, or 200 times of updating may be specified. However, the specific implementation process of updating the system parameters each time is similar to steps S401 to S406, and will not be repeated here.

S407, if the performance of the target system exceeds the performance threshold, configuring the target system according to the default value range of the N configuration parameters.

In this embodiment, since there may be a case where the range of values of the N configuration parameters learned by the machine learning system is not good, the performance of the corresponding target system is poor. Therefore, a performance threshold and a default parameter can be specified for the performance of the target system, and when the determined target value range of each configuration parameter is input to the target system, if the performance of the target system exceeds the performance threshold, the target system is configured according to the default parameter. Again, the specific meaning of the performance threshold may be as described in the above embodiments.

In one implementation, the performance of the target system corresponding to the range of values of the N configuration parameters obtained by each round of learning of the machine learning system is compared with a performance threshold, and if the performance of the target system exceeds the performance threshold, the target system is configured according to the default parameters.

As an example, assuming that the machine learning system trains 100 rounds, at the time of round 30, the performance of the target system corresponding to the value ranges of the N configuration parameters obtained by the machine learning system learning exceeds the performance threshold, at this time, the machine learning system finishes learning, and configures the target system with default configuration parameters.

According to the configuration method of the system parameters, provided by the embodiment, under the constraint of the parameter configuration rule system, the machine learning system continuously updates the configuration parameter value range of the target system, so that a more accurate target value range is obtained; in addition, when the performance of the target system is greater than the requirement threshold, the target system is configured according to default configuration parameters, so that the robustness of the machine learning system is improved.

Alternatively, the machine learning system in any of the above-described embodiments may be implemented based on a bayesian algorithm, a genetic algorithm, or a particle swarm algorithm.

Any of the above embodiments may be implemented alone or in combination with at least two of the above embodiments, and is not limited thereto.

Fig. 5 is a schematic structural diagram of a configuration device of system parameters according to an embodiment of the present application. The configuration device of the system parameters shown in fig. 5 may be used to perform the configuration method of the system parameters described in any of the foregoing embodiments.

As shown in fig. 5, the configuration apparatus 500 of the system parameters of the present embodiment includes: an acquisition module 501, a first parameter output module 502, a second parameter output module 503, a processing module 504 and a configuration module 505.

The acquiring module 501 is configured to acquire configuration information of a target system.

The first parameter output module 502 is configured to output M parameter value ranges based on the configuration information using a parameter configuration rule system.

The second parameter output module 503 is configured to output N first parameter value ranges based on the configuration information using a machine learning system.

The processing module 504 is configured to determine, according to the M parameter value ranges and the N first parameter value ranges, a target value range of each of the N configuration parameters, where the target value range of the first configuration parameter of the N configuration parameters includes all or part of the parameter value ranges corresponding to the first configuration parameter of the M parameter value ranges and the parameter value range corresponding to the first configuration parameter of the N first parameter value ranges that overlap.

The configuration module 505 is configured to configure the target system according to the target value range of each configuration parameter in the N configuration parameters.

As an example, the obtaining module 501 may be configured to perform the step of obtaining the configuration information of the target system in the configuration method of the system parameters described in any one of fig. 3 to fig. 4. For example, the acquisition module 501 is configured to execute S301.

As another example, the first parameter output module 503 may be used to perform the step of outputting M parameter value ranges in the configuration method of the system parameters described in any one of fig. 3 to 4. For example, the first parameter output module 503 is used to perform S302 or S402.

As yet another example, the configuration module 505 may be used to perform the steps of configuring the target system in the configuration method of system parameters described in any of fig. 3-4. For example, the configuration module 505 is used to perform S305 or S405.

In one possible implementation, the second parameter output module 503 is further configured to output N second parameter value ranges based on the performance and configuration information of the target system using the machine learning system.

The processing module 504 is further configured to redetermine a target value range of each of the N configuration parameters according to the M parameter value ranges and the N second parameter value ranges, where the target value range of the first configuration parameter of the N configuration parameters includes all or part of the parameter value ranges corresponding to the first configuration parameter of the M parameter value ranges and the parameter value range corresponding to the first configuration parameter of the N second parameter value ranges that overlap.

The configuration module 505 is further configured to configure the target system according to the target value range redetermined for each of the N configuration parameters.

In one possible implementation, the configuration module 505 is further configured to: and if the performance of the target system exceeds a performance threshold, configuring the target system according to the default value range of the N configuration parameters.

In one possible implementation, the target value range of the second configuration parameter in the N configuration parameters includes a third parameter value range in the parameter value ranges corresponding to the second configuration parameter in the N first parameter value ranges, and the third parameter value range includes all or part of the parameter value ranges corresponding to the second configuration parameter in the M parameter value ranges and the parameter value ranges corresponding to the second configuration parameter in the N first parameter value ranges that do not overlap.

In one possible implementation manner, the target value range of any one configuration parameter except the first configuration parameter in the N configuration parameters is a parameter value range corresponding to any one configuration parameter in the M parameter value ranges and all or part of the value ranges of the parameter value ranges corresponding to any one configuration parameter in the N first parameter value ranges overlap.

In one possible implementation, the machine learning system is implemented based on a bayesian algorithm, a genetic algorithm, or a particle swarm algorithm.

Fig. 6 is a schematic structural diagram of a configuration device according to another embodiment of the present application. The apparatus shown in fig. 6 may be used to perform the method of configuring system parameters described in any of the foregoing embodiments.

As shown in fig. 6, the apparatus 600 of the present embodiment includes: memory 601, processor 602, communication interface 603 and bus 604. The memory 601, the processor 602, and the communication interface 603 are connected to each other by a bus 604.

The memory 601 may be a Read Only Memory (ROM), a static storage device, a dynamic storage device, or a random access memory (random access memory, RAM). The memory 601 may store a program, and the processor 602 is configured to perform the steps of the method shown in fig. 5 when the program stored in the memory 601 is executed by the processor 602.

The processor 602 may employ a general-purpose central processing unit (central processing unit, CPU), microprocessor, application Specific Integrated Circuit (ASIC), or one or more integrated circuits for executing associated programs to implement the lane-reasoning method or lane-training reasoning model of the method embodiments of the present application.

The processor 602 may also be an integrated circuit chip with signal processing capabilities. In implementation, various steps of a method of planning an autonomous vehicle according to an embodiment of the present application may be performed by instructions in the form of integrated logic circuits or software of hardware in the processor 602.

The processor 602 may also be a general purpose processor, a digital signal processor (DIGITAL SIGNAL processing unit, DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (field programmable GATE ARRAY, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 601, and the processor 602 reads the information in the memory 601 and in combination with its hardware performs the functions that the unit comprised by the temperature measuring device of the present application needs to perform, for example, the steps/functions of the embodiments shown in fig. 3 or fig. 4 can be performed.

The communication interface 603 may enable communication between the apparatus 600 and other devices or communication networks using, but is not limited to, a transceiver-like transceiver.

A bus 604 may include a path to transfer information between elements of the apparatus 600 (e.g., the memory 601, the processor 602, the communication interface 603).

It should be understood that the apparatus 600 shown in the embodiment of the present application may be an electronic device, or may be a chip configured in an electronic device.

It should be appreciated that the processor in embodiments of the present application may be a central processing unit (central processing unit, CPU), which may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application Specific Integrated Circuits (ASICs), off-the-shelf programmable gate arrays (field programmable GATE ARRAY, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It should also be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an erasable programmable ROM (erasable PROM), an electrically erasable programmable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as external cache memory. By way of example, and not limitation, many forms of random access memory (random access memory, RAM) are available, such as static random access memory (STATIC RAM, SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (double DATA RATE SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (direct rambus RAM, DR RAM).

The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.

It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.

In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.

It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for configuring system parameters, comprising:

Acquiring configuration information of a target system, wherein the configuration information is used for indicating a value range of at least one configuration parameter of the target system;

outputting M parameter value ranges based on the configuration information by using a parameter configuration rule system, wherein the M parameter value ranges are in one-to-one correspondence with M configuration parameters of the target system, and M is a positive integer;

using a machine learning system to output N first parameter value ranges based on the configuration information, wherein the N first parameter value ranges are in one-to-one correspondence with N configuration parameters of the target system, N is a positive integer greater than or equal to M, and the N configuration parameters comprise the M configuration parameters;

Determining a target value range of each of the N configuration parameters according to the M parameter value ranges and the N first parameter value ranges, wherein the target value range of the first configuration parameter of the N configuration parameters comprises all or part of the parameter value ranges corresponding to the first configuration parameter of the M parameter value ranges and the parameter value ranges corresponding to the first configuration parameter of the N first parameter value ranges;

And configuring the target system according to the target value range of each configuration parameter in the N configuration parameters.

2. The method of claim 1, wherein configuring the target system according to the target range of values for each of the N configuration parameters comprises:

Outputting N second parameter value ranges based on the performance of the target system and the configuration information by using the machine learning system;

The target value range of each configuration parameter in the N configuration parameters is redetermined according to the M parameter value ranges and the N second parameter value ranges, wherein the target value range of the first configuration parameter in the N configuration parameters comprises all or part of the value ranges, which are overlapped, of the parameter value ranges corresponding to the first configuration parameter in the M parameter value ranges and the parameter value ranges corresponding to the first configuration parameter in the N second parameter value ranges;

3. The method according to claim 1 or 2, wherein configuring the target system according to the target value range of each of the N configuration parameters comprises:

And if the performance of the target system exceeds a performance threshold, configuring the target system according to the default value range of the N configuration parameters.

4. The method of claim 1, wherein the target range of values for a second configuration parameter of the N configuration parameters includes a third range of values for parameters of the N first ranges of values corresponding to the second configuration parameter, the third range of values including all or a portion of the M ranges of values for parameters of the M corresponding to the second configuration parameter and the N first ranges of values for parameters of the N corresponding to the second configuration parameter.

5. The method according to claim 1, wherein the target value range of any one of the N configuration parameters other than the first configuration parameter is all or part of the value ranges of the M parameter value ranges corresponding to the any one configuration parameter and the N first parameter value ranges overlapping with the value range of the parameter corresponding to the any one configuration parameter.

6. The method of claim 1, wherein the machine learning system is implemented based on a bayesian algorithm, a genetic algorithm, or a particle swarm algorithm.

7. A system parameter configuration apparatus, comprising:

the system comprises an acquisition module, a configuration module and a control module, wherein the acquisition module is used for acquiring configuration information of a target system, and the configuration information is used for indicating a value range of at least one configuration parameter of the target system;

The first parameter output module is used for outputting M parameter value ranges based on the configuration information by using a parameter configuration rule system, wherein the M parameter value ranges are in one-to-one correspondence with M configuration parameters of the target system, and M is a positive integer;

The second parameter output module is used for outputting N first parameter value ranges based on the configuration information by using a machine learning system, the N first parameter value ranges are in one-to-one correspondence with N configuration parameters of the target system, N is a positive integer greater than or equal to M, and the N configuration parameters comprise the M configuration parameters;

The processing module is used for determining a target value range of each configuration parameter in the N configuration parameters according to the M parameter value ranges and the N first parameter value ranges, wherein the target value range of the first configuration parameter in the N configuration parameters comprises all or part of the parameter value ranges corresponding to the first configuration parameter in the M parameter value ranges and the parameter value ranges corresponding to the first configuration parameter in the N first parameter value ranges;

and the configuration module is used for configuring the target system according to the target value range of each configuration parameter in the N configuration parameters.

8. The apparatus of claim 7, wherein the second parameter output module is further configured to: outputting N second parameter value ranges based on the performance of the target system and the configuration information by using the machine learning system;

The processing module is further configured to: the target value range of each configuration parameter in the N configuration parameters is redetermined according to the M parameter value ranges and the N second parameter value ranges, wherein the target value range of the first configuration parameter in the N configuration parameters comprises all or part of the value ranges, which are overlapped, of the parameter value ranges corresponding to the first configuration parameter in the M parameter value ranges and the parameter value ranges corresponding to the first configuration parameter in the N second parameter value ranges;

The configuration module is further configured to: and configuring the target system according to the target value range redetermined for each configuration parameter in the N configuration parameters.

9. The apparatus of claim 7 or 8, wherein the configuration module is further configured to:

10. The apparatus of claim 7, wherein the target range of values for a second configuration parameter of the N configuration parameters comprises a third range of values for parameters of the N first ranges of values corresponding to the second configuration parameter, the third range of values comprising all or a portion of the M ranges of values for parameters of the M corresponding to the second configuration parameter and the N first ranges of values for parameters of the N corresponding to the second configuration parameter.

11. The apparatus of claim 7, wherein the target range of any one of the N configuration parameters other than the first configuration parameter is all or part of the range of values of the M parameters corresponding to the any one configuration parameter and the range of values of the N first parameters corresponding to the any one configuration parameter.

12. The apparatus of claim 7, wherein the machine learning system is implemented based on a bayesian algorithm, a genetic algorithm, or a particle swarm algorithm.

13. A system parameter configuration apparatus, comprising: a memory and a processor;

The memory is used for storing program instructions;

the processor is configured to invoke program instructions in the memory to perform the method of any of claims 1 to 6.

14. A chip comprising at least one processor and a communication interface, the communication interface and the at least one processor being interconnected by wires, the at least one processor being configured to execute a computer program or instructions to perform the method of any of claims 1-6.

15. A computer readable medium, characterized in that the computer readable medium stores a program code for computer execution, the program code comprising instructions for performing the method of any of claims 1 to 6.