Chip Configuration Method and System Based on Server Task Prediction

Abstract

The present invention discloses a chip configuration method and system based on server task prediction. The method includes: obtaining in real time the server type, current task load, server device parameters, predicted task plan, and data transmission record of a target storage server; determining the attack probability of the target storage server according to the current task load and the data transmission record based on a data matching prediction rule; determining the predicted service quality of the target storage server according to the server device parameters and the predicted task plan based on a server parameter evaluation rule; and determining the configuration necessity and configuration strategy corresponding to the processor chip of the target storage server based on a preset configuration policy rule according to the attack probability and the predicted service quality. The present invention can effectively improve the intelligence level of server chip configuration, improve the working safety and working efficiency of the server, and achieve a more secure and efficient storage service.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a chip configuration method and system based on server task prediction. Background Art

[0002] Distributed storage systems have been widely used in fields such as IT enterprises, cloud computing, big data, and virtualization. At the same time, with the rapid growth of business in these fields, higher requirements are put forward for the intelligent services of storage servers. However, in the existing distributed storage technologies, the service configuration of storage servers is generally configured only according to preset configuration logics and the types of servers, without fully considering the security and service quality of the servers for real-time configuration. Therefore, the chip configuration effect is poor, and neither the service quality of the servers nor the security of the system can be guaranteed. It can be seen that there are defects in the existing technology and it is urgent to be solved. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a chip configuration method and system based on server task prediction, which can effectively improve the intelligent degree of server chip configuration, improve the working security and working efficiency of the server, and realize a more secure and efficient storage service.

[0004] To solve the above technical problem, in the first aspect of the present invention, a chip configuration method based on server task prediction is disclosed, and the method includes:

[0005] Obtain in real time the server type, current task load, server device parameters, predicted task plan, and data transmission record of the target storage server;

[0006] Based on the data matching prediction rule, determine the attack probability of the target storage server according to the current task load and the data transmission record;

[0007] Based on the server parameter evaluation rule, determine the predicted service quality of the target storage server according to the server device parameters and the predicted task plan;

[0008] According to the attack probability and the predicted service quality, based on the preset configuration policy rule, determine the configuration necessity and configuration policy corresponding to the processor chip of the target storage server; the configuration policy is used to configure the service of the target storage server when the configuration necessity is higher than the preset necessity threshold.

[0009] As an optional implementation manner, in the first aspect of the present invention, the server type includes one or more of a newly extended server, a management server, a server with a computing task, a pure storage server, a server with a transfer task, and a server with a redistribution task.

[0010] As an optional implementation, in the first aspect of the present invention, the determining the probability of the target storage server being attacked based on the data matching prediction rule according to the current task load and the data transmission record includes:

[0011] Input the current task load into the data transmission prediction neural network model corresponding to the target storage server to obtain the predicted transmission data corresponding to the target storage server;

[0012] Calculate the record similarity between the data transmission record and the predicted transmission data;

[0013] Based on the preset attack character recognition rule, calculate the proportion of the records in the data transmission record that conform to the attack character recognition rule in all the records to obtain the attack record proportion;

[0014] Calculate a first parameter that is inversely proportional to the record similarity;

[0015] Calculate a second parameter that is directly proportional to the attack record proportion;

[0016] Calculate the product of the first parameter and the second parameter to obtain the probability of the target storage server being attacked.

[0017] As an optional implementation, in the first aspect of the present invention, the determining the predicted service quality of the target storage server based on the server parameter evaluation rule according to the server device parameters and the predicted task plan includes:

[0018] According to the multiple recently executed tasks in the predicted task plan whose time difference between the task execution time and the current time point is less than the preset first time difference threshold;

[0019] According to the task requirement parameters of each of the recently executed tasks and the preset corresponding relationship between the requirement parameters and the device parameters, determine the device requirement parameters corresponding to each of the recently executed tasks;

[0020] Summarize the device requirement parameters corresponding to all the recently executed tasks to obtain a set of device requirement parameters;

[0021] For multiple device requirement parameters belonging to the same arbitrary parameter type in the set of device requirement parameters, calculate the average value between the multiple device requirement parameters of this parameter type to obtain the requirement parameter corresponding to this parameter type, and replace the multiple device requirement parameters of this parameter type with the requirement parameter;

[0022] Determine the set of device requirement parameters after replacement as the overall device requirement parameters corresponding to all the recently executed tasks;

[0023] Calculate the predicted quality of service of the target storage server according to the server device parameters and the overall device requirement parameters.

[0024] As an optional implementation manner, in the first aspect of the present invention, the calculating the predicted quality of service of the target storage server according to the server device parameters and the overall device requirement parameters includes:

[0025] Determine a plurality of matching server device parameters corresponding to any parameter type of the overall device requirement parameters in the server device parameters;

[0026] Calculate the parameter difference obtained by subtracting the requirement parameter of the corresponding parameter type in the overall device requirement parameters from each of the matching server device parameters; the parameter difference retains the positive and negative signs;

[0027] Calculate the weighted sum value of all the parameter differences to obtain the predicted quality of service of the target storage server; wherein, the weight corresponding to each parameter difference includes a first weight and a second weight; the first weight is proportional to the number of requirement parameters of the same parameter type in the corresponding device requirement parameter set; the second weight is proportional to the difference parameter corresponding to the parameter difference; the difference parameter is the difference between the parameter difference and a preset difference threshold.

[0028] As an optional implementation manner, in the first aspect of the present invention, the determining the configuration necessity and configuration strategy corresponding to the processor chip of the target storage server according to the attack probability and the predicted quality of service based on a preset configuration policy rule includes:

[0029] Determine the benchmark security probability and benchmark quality of service corresponding to the server type according to the corresponding relationship between the preset server type and the benchmark security probability and the benchmark quality of service;

[0030] Calculate the probability difference between the attack probability and the server benchmark probability;

[0031] Calculate the quality difference between the predicted quality of service and the benchmark quality of service;

[0032] Calculate the weighted sum average of the probability difference and the quality difference to obtain the configuration necessity corresponding to the target storage server;

[0033] Determine the set of security configuration policies corresponding to the probability difference according to the corresponding relationship between the preset probability difference and the security configuration policies;

[0034] Determine a set of service configuration policies corresponding to the quality difference and the server type according to the corresponding relationship between the preset quality difference, server type, and data service configuration policy;

[0035] Based on the dynamic programming algorithm, preset policy conflict rules, and policy effect prediction model, calculate the optimal configuration policy corresponding to the set of security configuration policies and the set of service configuration policies; the set of security configuration policies includes multiple policies for configuring the security protection rules of the target storage server; the set of service configuration policies includes multiple policies for configuring the server service functions of the target storage server.

[0036] As an optional implementation manner, in the first aspect of the present invention, the calculating the optimal configuration policy corresponding to the set of security configuration policies and the set of service configuration policies based on the dynamic programming algorithm, preset policy conflict rules, and policy effect prediction model includes:

[0037] According to the preset policy conflict rules, eliminate the service configuration policies in the set of service configuration policies that conflict with any security configuration policy in the set of security configuration policies;

[0038] Set the objective function to include that the sum of the running efficiencies after configuration corresponding to all configuration policies in the configuration scheme reaches the maximum, the sum of the configuration costs corresponding to all configuration policies reaches the minimum, and the total number of all configuration policies reaches the minimum;

[0039] Set the constraint conditions to include that the sum of the security effects after configuration corresponding to all security configuration policies in the configuration scheme is greater than the preset effect threshold; the running efficiency after configuration and the security effect after configuration are both obtained by predicting the configuration policy through a trained policy effect prediction model; the policy effect prediction model is trained by a training data set including multiple training configuration policies and corresponding running efficiency annotations, configuration cost annotations, and security effect annotations after configuration; the configuration cost includes configuration time cost and configuration energy consumption cost;

[0040] Based on the dynamic programming algorithm, calculate according to the objective function and the constraint conditions to obtain the configuration policy corresponding to the optimal configuration scheme.

[0041] As an optional implementation manner, in the first aspect of the present invention, the method further includes:

[0042] Judge whether the configuration necessity is greater than the necessity threshold to obtain a first judgment result;

[0043] Determine whether the remaining time difference between the execution time point of the task closest to the current time point in the predicted task plan and the current time point is greater than a preset second time difference threshold, to obtain a second judgment result;

[0044] Determine whether the difference between the sum of the configuration time costs corresponding to the configuration policy and the remaining time difference is less than a preset parameter threshold, to obtain a third judgment result;

[0045] When the first judgment result, the second judgment result, and the third judgment result are all yes, configure the target storage server according to the configuration policy.

[0046] A second aspect of the embodiments of the present invention discloses a chip configuration system based on server task prediction, and the system includes:

[0047] An acquisition module, configured to acquire in real time the server type, current task load, server device parameters, predicted task plan, and data transmission record of the target storage server;

[0048] A first determination module, configured to determine the attack probability of the target storage server based on a data matching prediction rule according to the current task load and the data transmission record;

[0049] A second determination module, configured to determine the predicted service quality of the target storage server based on a server parameter evaluation rule according to the server device parameters and the predicted task plan;

[0050] A third determination module, configured to determine the configuration necessity and configuration policy corresponding to the processor chip of the target storage server based on a preset configuration policy rule according to the attack probability and the predicted service quality; the configuration policy is used to configure the service of the target storage server when the configuration necessity is higher than a preset necessity threshold.

[0051] As an optional implementation manner, in the second aspect of the present invention, the server type includes one or more of a newly extended server, a management server, a server with a computing task, a pure storage server, a server with a transfer task, and a server with a redistribution task.

[0052] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the first determination module determines the attack probability of the target storage server based on a data matching prediction rule according to the current task load and the data transmission record includes:

[0053] Input the current task load into the data transmission prediction neural network model corresponding to the target storage server to obtain the predicted transmission data corresponding to the target storage server;

[0054] Calculate the record similarity between the data transmission record and the predicted transmission data;

[0055] Based on a preset attack character recognition rule, calculate the proportion of records in the data transmission record that conform to the attack character recognition rule among all records to obtain the attack record proportion;

[0056] Calculate a first parameter that is inversely proportional to the record similarity;

[0057] Calculate a second parameter that is directly proportional to the attack record proportion;

[0058] Calculate the product of the first parameter and the second parameter to obtain the attacked probability of the target storage server.

[0059] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the second determination module determines the predicted service quality of the target storage server based on the server parameter evaluation rule according to the server device parameter and the predicted task plan includes:

[0060] According to multiple recently executed tasks in the predicted task plan where the time difference between the task execution time and the current time point is less than a preset first time difference threshold;

[0061] According to the task requirement parameters of each of the recently executed tasks and the corresponding relationship between the preset requirement parameters and the device parameters, determine the device requirement parameters corresponding to each of the recently executed tasks;

[0062] Summarize the device requirement parameters corresponding to all the recently executed tasks to obtain a set of device requirement parameters;

[0063] For multiple device requirement parameters belonging to the same arbitrary parameter type in the set of device requirement parameters, calculate the average value between the multiple device requirement parameters of this parameter type to obtain the requirement parameter corresponding to this parameter type, and replace the multiple device requirement parameters of this parameter type with the requirement parameter;

[0064] Determine the set of device requirement parameters after replacement as the overall device requirement parameters corresponding to all the recently executed tasks;

[0065] Calculate the predicted service quality of the target storage server according to the server device parameter and the overall device requirement parameter.

[0066] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the second determination module calculates the predicted service quality of the target storage server according to the server device parameters and the overall device requirement parameters includes:

[0067] Determine a plurality of matching server device parameters in the server device parameters corresponding to any parameter type of the overall device requirement parameters;

[0068] Calculate the parameter difference obtained by subtracting the requirement parameter of the corresponding parameter type in the overall device requirement parameters from each of the matching server device parameters; the parameter difference retains the positive and negative signs;

[0069] Calculate the weighted sum value of all the parameter differences to obtain the predicted service quality of the target storage server; wherein, the weight corresponding to each parameter difference includes a first weight and a second weight; the first weight is proportional to the number of requirement parameters of the same parameter type in the corresponding device requirement parameter set; the second weight is proportional to the difference parameter corresponding to the parameter difference; the difference parameter is the difference between the parameter difference and a preset difference threshold.

[0070] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the third determination module determines the configuration necessity and configuration policy corresponding to the processor chip of the target storage server according to the attack probability and the predicted service quality based on a preset configuration policy rule includes:

[0071] Determine the benchmark security probability and benchmark service quality corresponding to the server type according to the corresponding relationship between the preset server type and the benchmark security probability and the benchmark service quality;

[0072] Calculate the probability difference between the attack probability and the server benchmark probability;

[0073] Calculate the quality difference between the predicted service quality and the benchmark service quality;

[0074] Calculate the weighted sum average of the probability difference and the quality difference to obtain the configuration necessity corresponding to the target storage server;

[0075] Determine the set of security configuration policies corresponding to the probability difference according to the corresponding relationship between the preset probability difference and the security configuration policies;

[0076] Determine the set of service configuration policies corresponding to the quality difference and the server type according to the corresponding relationship between the preset quality difference and the server type and the data service configuration policies;

[0077] Based on the dynamic programming algorithm, the preset policy conflict rules, and the policy effect prediction model, calculate the optimal configuration policies corresponding to the security configuration policy set and the service configuration policy set; the security configuration policy set includes multiple policies for configuring the security protection rules of the target storage server; the service configuration policy set includes multiple policies for configuring the server service functions of the target storage server.

[0078] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the third determination module calculates the optimal configuration policies corresponding to the security configuration policy set and the service configuration policy set based on the dynamic programming algorithm, the preset policy conflict rules, and the policy effect prediction model includes:

[0079] According to the preset policy conflict rules, eliminate the service configuration policies in the service configuration policy set that conflict with any security configuration policy in the security configuration policy set;

[0080] Set the objective function to include that the sum of the post-configuration operation efficiencies corresponding to all configuration policies in the configuration plan reaches the maximum, the sum of the configuration costs corresponding to all configuration policies reaches the minimum, and the total number of all configuration policies reaches the minimum;

[0081] Set the constraint conditions to include that the sum of the post-configuration security effects corresponding to all security configuration policies in the configuration plan is greater than the preset effect threshold; the post-configuration operation efficiency and the post-configuration security effect are both obtained by predicting the configuration policies through the trained policy effect prediction model; the policy effect prediction model is trained through a training data set including multiple training configuration policies and the corresponding post-configuration operation efficiency annotations, configuration cost annotations, and post-configuration security effect annotations; the configuration cost includes configuration time cost and configuration energy consumption cost;

[0082] Based on the dynamic programming algorithm, perform calculations according to the objective function and the constraint conditions to obtain the configuration policies corresponding to the optimal configuration plan.

[0083] As an optional implementation manner, in the second aspect of the present invention, the system is further configured to perform the following steps:

[0084] Judge whether the configuration necessity is greater than the necessity threshold to obtain a first judgment result;

[0085] Judge whether the remaining time difference between the execution time point of the task closest to the current time point in the predicted task plan and the current time point is greater than the preset second time difference threshold to obtain a second judgment result;

[0086] Determine whether the difference between the sum of the configuration time costs corresponding to the configuration policy and the remaining time difference is less than a preset parameter threshold to obtain a third judgment result;

[0087] When the first judgment result, the second judgment result, and the third judgment result are all yes, configure the target storage server according to the configuration policy.

[0088] The third aspect of the present invention discloses another chip configuration system based on server task prediction, and the system includes:

[0089] A memory storing executable program code;

[0090] A processor coupled to the memory;

[0091] The processor calls the executable program code stored in the memory and executes some or all of the steps in the chip configuration method based on server task prediction disclosed in the first aspect of the present invention.

[0092] The fourth aspect of the present invention discloses a computer storage medium, and the computer storage medium stores computer instructions, which are used to execute some or all of the steps in the chip configuration method based on server task prediction disclosed in the first aspect of the present invention when called.

[0093] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0094] The present invention can analyze and determine the attack probability and service quality of the server based on multiple parameters and records of the server, and calculate the configuration necessity and configuration policy based on this, so as to effectively improve the intelligence level of server chip configuration, improve the working safety and working efficiency of the server, and realize a more secure and efficient storage service. Description of the Drawings

[0095] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0096] Figure 1 It is a flowchart of a chip configuration method based on server task prediction disclosed in an embodiment of the present invention.

[0097] Figure 2 It is a structural diagram of a chip configuration system based on server task prediction disclosed in an embodiment of the present invention.

[0098] Figure 3 It is a schematic structural diagram of another chip configuration system based on server task prediction disclosed in an embodiment of the present invention. Specific embodiments

[0099] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0100] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0101] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment may be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0102] The present invention discloses a chip configuration method and system based on server task prediction, which can analyze and determine the attack probability and service quality of the server according to multiple parameters and records of the server, and calculate the configuration necessity and configuration strategy based on this, so as to effectively improve the intelligence level of server chip configuration, improve the working safety and working efficiency of the server, and realize a more secure and efficient storage service. The following will be described in detail respectively.

[0103] Embodiment 1

[0104] Please refer to Figure 1 , Figure 1 It is a schematic flowchart of a chip configuration method based on server task prediction disclosed in an embodiment of the present invention. Among them, Figure 1The described chip configuration method based on server task prediction can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 1 shown, the chip configuration method based on server task prediction may include the following operations:

[0105] 101. Obtain the server type, current task load, server device parameters, expected task plan, and data transmission record of the target storage server in real time.

[0106] 102. Based on the data matching prediction rule, determine the attack probability of the target storage server according to the current task load and data transmission record.

[0107] 103. Based on the server parameter evaluation rule, determine the predicted service quality of the target storage server according to the server device parameters and expected task plan.

[0108] 104. According to the attack probability and predicted service quality, based on the preset configuration policy rule, determine the configuration necessity and configuration policy corresponding to the processor chip of the target storage server.

[0109] Optionally, the configuration policy is used to configure the service of the target storage server when the configuration necessity is higher than the preset necessity threshold.

[0110] It can be seen that the above-mentioned invention embodiments can analyze and determine the attack probability and service quality of the server according to multiple parameters and records of the server, and calculate the configuration necessity and configuration policy based on this, so as to effectively improve the intelligence level of server chip configuration, improve the working safety and working efficiency of the server, and realize a more secure and efficient storage service.

[0111] As an optional embodiment, in the above steps, the server type includes one or more of a newly extended server, a management server, a server with computing tasks, a pure storage server, a server with transfer tasks, and a server with redistribution tasks.

[0112] It can be seen that through the above optional embodiment, the server type is defined, which can effectively represent the type of the server, facilitate the subsequent determination of the configuration policy, assist in improving the intelligence level of server chip configuration, improve the working safety and working efficiency of the server, and realize a more secure and efficient storage service.

[0113] As an optional embodiment, in the above steps, based on the data matching prediction rule, determining the attack probability of the target storage server according to the current task load and data transmission record includes:

[0114] Input the current task load into the data transfer prediction neural network model corresponding to the target storage server to obtain the predicted transfer data corresponding to the target storage server;

[0115] Calculate the record similarity between the data transfer record and the predicted transfer data;

[0116] Based on the preset attack character recognition rule, calculate the proportion of records in the data transfer record that conform to the attack character recognition rule in all records to obtain the attack record proportion;

[0117] Calculate the first parameter that is inversely proportional to the record similarity;

[0118] Calculate the second parameter that is directly proportional to the attack record proportion;

[0119] Calculate the product of the first parameter and the second parameter to obtain the attack probability of the target storage server.

[0120] It can be seen that through the above optional embodiments, it is possible to predict the attack probability of the server based on the calculation of the record similarity and the attack character recognition ratio, which is convenient for determining the configuration strategy subsequently, assisting in improving the intelligence level of the server chip configuration, enhancing the working security and working efficiency of the server, and realizing a more secure and efficient storage service.

[0121] As an optional embodiment, in the above steps, based on the server parameter evaluation rule, according to the server device parameters and the expected task plan, determine the predicted service quality of the target storage server, including:

[0122] According to multiple recently executed tasks in the expected task plan where the time difference between the task execution time and the current time point is less than the preset first time difference threshold;

[0123] According to the task requirement parameters of each recently executed task and the preset corresponding relationship between the requirement parameters and the device parameters, determine the device requirement parameters corresponding to each recently executed task;

[0124] Summarize the device requirement parameters corresponding to all recently executed tasks to obtain a set of device requirement parameters;

[0125] For multiple device requirement parameters belonging to the same arbitrary parameter type in the set of device requirement parameters, calculate the average value between the multiple device requirement parameters of this parameter type to obtain the requirement parameter corresponding to this parameter type, and replace the multiple device requirement parameters of this parameter type with the requirement parameter;

[0126] Determine the set of overall device requirement parameters corresponding to all recently executed tasks after the replacement is completed;

[0127] Calculate the predicted service quality of the target storage server according to the server device parameters and the overall device requirement parameters.

[0128] It can be seen that through the above optional embodiments, it is possible to predict the service quality of the server based on the calculation of the task execution time difference and the overall device requirement parameters, which is convenient for subsequent determination of the configuration strategy, assisting in improving the intelligence level of the server chip configuration, enhancing the working safety and efficiency of the server, and realizing a more secure and efficient storage service.

[0129] As an optional embodiment, in the above steps, calculating the predicted service quality of the target storage server according to the server device parameters and the overall device requirement parameters includes:

[0130] Determine multiple matching server device parameters corresponding to any parameter type of the overall device requirement parameters in the server device parameters;

[0131] Calculate the parameter difference obtained by subtracting the requirement parameter of the corresponding parameter type in the overall device requirement parameters from each matching server device parameter; optionally, the parameter difference retains the positive or negative sign;

[0132] Calculate the weighted sum value of all parameter differences to obtain the predicted service quality of the target storage server; optionally, among them, the weight corresponding to each parameter difference includes a first weight and a second weight; the first weight is proportional to the number of requirement parameters of the same parameter type in the corresponding device requirement parameter set; the second weight is proportional to the difference parameter corresponding to the parameter difference; the difference parameter is the difference between the parameter difference and the preset difference threshold.

[0133] It can be seen that through the above optional embodiments, it is possible to determine the service quality of the server based on the weighted sum calculation of the parameter differences, which is convenient for subsequent determination of the configuration strategy, assisting in improving the intelligence level of the server chip configuration, enhancing the working safety and efficiency of the server, and realizing a more secure and efficient storage service.

[0134] As an optional embodiment, in the above steps, determining the configuration necessity and configuration strategy corresponding to the processor chip of the target storage server based on the attack probability and the predicted service quality according to the preset configuration strategy rules includes:

[0135] Determine the reference security probability and reference service quality corresponding to the server type according to the corresponding relationship between the preset server type and the reference security probability and reference service quality;

[0136] Calculate the probability difference between the attack probability and the server reference probability;

[0137] Calculate the quality difference between the predicted service quality and the reference service quality;

[0138] Calculate the weighted sum average of the probability difference and the quality difference to obtain the configuration necessity corresponding to the target storage server;

[0139] According to the corresponding relationship between the preset probability difference and the security configuration policy, determine the set of security configuration policies corresponding to the probability difference;

[0140] According to the corresponding relationship between the preset quality difference, the server type, and the data service configuration policy, determine the set of service configuration policies corresponding to the quality difference and the server type;

[0141] Based on the dynamic programming algorithm, the preset policy conflict rule, and the policy effect prediction model, calculate the optimal configuration policy corresponding to the set of security configuration policies and the set of service configuration policies; Optionally, the set of security configuration policies includes multiple policies for configuring the security protection rules of the target storage server; the set of service configuration policies includes multiple policies for configuring the server service functions of the target storage server.

[0142] It can be seen that through the above optional embodiments, it is possible to determine the configuration necessity based on the calculation of the probability difference and the quality difference, and based on the corresponding relationship between the probability difference and the security configuration policy and the corresponding relationship between the quality difference, the server type, and the data service configuration policy, determine the optimal configuration policy based on the dynamic programming algorithm model, thereby improving the intelligent degree of the server chip configuration, improving the working security and working efficiency of the server, and realizing a more secure and efficient storage service.

[0143] As an optional embodiment, in the above steps, based on the dynamic programming algorithm, the preset policy conflict rule, and the policy effect prediction model, calculating the optimal configuration policy corresponding to the set of security configuration policies and the set of service configuration policies includes:

[0144] According to the preset policy conflict rule, eliminate the service configuration policies in the set of service configuration policies that conflict with any security configuration policy in the set of security configuration policies;

[0145] Set the objective function to include that the sum of the running efficiencies after configuration corresponding to all configuration policies in the configuration plan reaches the maximum, the sum of the configuration costs corresponding to all configuration policies reaches the minimum, and the total number of all configuration policies reaches the minimum;

[0146] The set constraints include that the sum of the corresponding post-configuration security effects of all security configuration policies in the configuration plan is greater than a preset effect threshold; optionally, the post-configuration operation efficiency and the post-configuration security effect are both obtained by predicting the configuration policy through a trained policy effect prediction model; the policy effect prediction model is trained through a training data set including multiple training configuration policies and the corresponding post-configuration operation efficiency annotations, configuration cost annotations, and post-configuration security effect annotations; the configuration cost includes configuration time cost and configuration energy consumption cost;

[0147] Based on the dynamic programming algorithm, perform calculations according to the objective function and the limiting conditions to obtain the configuration policy corresponding to the optimal configuration plan.

[0148] It can be seen that through the above optional embodiments, it is possible to first eliminate conflicting policies through the preset policy conflict rules, and then determine the optimal configuration policy based on the dynamic programming algorithm model according to the objective function and the limiting conditions, thereby improving the intelligence level of server chip configuration, enhancing the working security and working efficiency of the server, and realizing a more secure and efficient storage service.

[0149] As an optional embodiment, in the above steps, the method further includes:

[0150] Judge whether the configuration necessity is greater than the necessity threshold to obtain a first judgment result;

[0151] Judge whether the remaining time difference between the execution time point of the task closest to the current time point in the predicted task plan and the current time point is greater than a preset second time difference threshold to obtain a second judgment result;

[0152] Judge whether the difference between the sum of the configuration time costs corresponding to the configuration policy and the remaining time difference is less than a preset parameter threshold to obtain a third judgment result;

[0153] When the first judgment result, the second judgment result, and the third judgment result are all yes, configure the target storage server according to the configuration policy.

[0154] It can be seen that through the above optional embodiments, it is possible to determine the specific server configuration timing based on the preset threshold judgment and difference judgment rules, and more precisely configure the server when it is necessary, the time is sufficient, and the time cost is low enough, thereby improving the intelligence level of server chip configuration, enhancing the working security and working efficiency of the server, and realizing a more secure and efficient storage service.

[0155] Embodiment 2

[0156] Please refer to Figure 2 , Figure 2It is a schematic structural diagram of a chip configuration system based on server task prediction disclosed in an embodiment of the present invention. Among them, Figure 2 The described chip configuration system based on server task prediction can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 2 shown, the chip configuration system based on server task prediction may include:

[0157] An acquisition module 201, configured to acquire in real time the server type, current task load, server device parameters, predicted task plan, and data transmission record of the target storage server.

[0158] A first determination module 202, configured to determine the attack probability of the target storage server based on a data matching prediction rule according to the current task load and the data transmission record.

[0159] A second determination module 203, configured to determine the predicted service quality of the target storage server based on a server parameter evaluation rule according to the server device parameters and the predicted task plan.

[0160] A third determination module 204, configured to determine the configuration necessity and configuration strategy corresponding to the processor chip of the target storage server based on a preset configuration policy rule according to the attack probability and the predicted service quality.

[0161] Optionally, the configuration strategy is used to configure the service of the target storage server when the configuration necessity is higher than a preset necessity threshold.

[0162] It can be seen that the above-mentioned invention embodiments can analyze and determine the attack probability and service quality of the server based on multiple parameters and records of the server, and calculate the configuration necessity and configuration strategy based on this, so as to effectively improve the intelligence level of server chip configuration, improve the working security and working efficiency of the server, and achieve a more secure and efficient storage service.

[0163] As an optional embodiment, the server type includes one or more of a newly extended server, a management server, a server with computing tasks, a pure storage server, a server with transfer tasks, and a server with redistribution tasks.

[0164] It can be seen that through the above optional embodiment, the server type is defined, which can effectively represent the type of the server, facilitate the subsequent determination of the configuration strategy, assist in improving the intelligence level of server chip configuration, improve the working security and working efficiency of the server, and achieve a more secure and efficient storage service.

[0165] As an alternative embodiment, the specific manner in which the first determination module determines the attack probability of the target storage server based on the data matching prediction rule according to the current task load and the data transmission record includes:

[0166] Input the current task load into the data transmission prediction neural network model corresponding to the target storage server to obtain the predicted transmission data corresponding to the target storage server;

[0167] Calculate the record similarity between the data transmission record and the predicted transmission data;

[0168] Based on the preset attack character recognition rule, calculate the proportion of the records in the data transmission record that conform to the attack character recognition rule in all the records to obtain the attack record proportion;

[0169] Calculate the first parameter that is inversely proportional to the record similarity;

[0170] Calculate the second parameter that is directly proportional to the attack record proportion;

[0171] Calculate the product of the first parameter and the second parameter to obtain the attack probability of the target storage server.

[0172] It can be seen that through the above alternative embodiment, it is possible to predict the attack probability of the server based on the calculation of the record similarity and the attack character recognition ratio, which is convenient for subsequent determination of the configuration strategy, assisting in improving the intelligence level of the server chip configuration, enhancing the working safety and working efficiency of the server, and realizing a more secure and efficient storage service.

[0173] As an alternative embodiment, the specific manner in which the second determination module determines the predicted service quality of the target storage server based on the server parameter evaluation rule according to the server device parameters and the expected task plan includes:

[0174] According to multiple recently executed tasks in the expected task plan where the time difference between the task execution time and the current time point is less than the preset first time difference threshold;

[0175] According to the task requirement parameters of each recently executed task and the preset corresponding relationship between the requirement parameters and the device parameters, determine the device requirement parameters corresponding to each recently executed task;

[0176] Summarize the device requirement parameters corresponding to all the recently executed tasks to obtain a set of device requirement parameters;

[0177] For multiple device requirement parameters belonging to the same arbitrary parameter type in the set of device requirement parameters, calculate the average value between the multiple device requirement parameters of this parameter type to obtain the requirement parameter corresponding to this parameter type, and replace the multiple device requirement parameters of this parameter type with the requirement parameter;

[0178] Determine the set of device requirement parameters after replacement completion as the overall device requirement parameters corresponding to all recently executed tasks;

[0179] Calculate the predicted service quality of the target storage server based on the server device parameters and the overall device requirement parameters.

[0180] It can be seen that through the above optional embodiments, it is possible to predict the service quality of the server based on the calculation of the task execution time difference and the overall device requirement parameters, which is convenient for subsequent determination of the configuration strategy, helps to improve the intelligence level of the server chip configuration, improves the working safety and working efficiency of the server, and realizes a more secure and efficient storage service.

[0181] As an optional embodiment, the specific manner in which the second determination module calculates the predicted service quality of the target storage server based on the server device parameters and the overall device requirement parameters includes:

[0182] Determine multiple matching server device parameters in the server device parameters corresponding to any parameter type of the overall device requirement parameters;

[0183] Calculate the parameter difference obtained by subtracting the requirement parameter of the corresponding parameter type in the overall device requirement parameters from each matching server device parameter; optionally, the parameter difference retains the positive and negative signs;

[0184] Calculate the weighted sum value of all parameter differences to obtain the predicted service quality of the target storage server; optionally, among them, the weight corresponding to each parameter difference includes a first weight and a second weight; the first weight is proportional to the number of requirement parameters of the same parameter type in the corresponding device requirement parameter set; the second weight is proportional to the difference parameter corresponding to the parameter difference; the difference parameter is the difference between the parameter difference and a preset difference threshold.

[0185] It can be seen that through the above optional embodiments, it is possible to determine the service quality of the server based on the weighted sum calculation of the parameter differences, which is convenient for subsequent determination of the configuration strategy, helps to improve the intelligence level of the server chip configuration, improves the working safety and working efficiency of the server, and realizes a more secure and efficient storage service.

[0186] As an optional embodiment, the specific manner in which the third determination module determines the configuration necessity and configuration strategy corresponding to the processor chip of the target storage server based on the attack probability and the predicted service quality according to the preset configuration strategy rules includes:

[0187] Determine the reference security probability and reference service quality corresponding to the server type according to the corresponding relationship between the preset server type and the reference security probability and the reference service quality;

[0188] Calculate the probability difference between the attacked probability and the server benchmark probability;

[0189] Calculate the quality difference between the predicted service quality and the benchmark service quality;

[0190] Calculate the weighted sum average of the probability difference and the quality difference to obtain the configuration necessity corresponding to the target storage server;

[0191] According to the corresponding relationship between the preset probability difference and the security configuration policy, determine the set of security configuration policies corresponding to the probability difference;

[0192] According to the corresponding relationship between the preset quality difference and the server type and the data service configuration policy, determine the set of service configuration policies corresponding to the quality difference and the server type;

[0193] Based on the dynamic programming algorithm and the preset policy conflict rules and policy effect prediction model, calculate the optimal configuration policy corresponding to the set of security configuration policies and the set of service configuration policies; Optionally, the set of security configuration policies includes multiple policies for configuring the security protection rules of the target storage server; the set of service configuration policies includes multiple policies for configuring the server service functions of the target storage server.

[0194] It can be seen that through the above optional embodiments, it is possible to determine the configuration necessity based on the calculation of the probability difference and the quality difference, and based on the corresponding relationship between the probability difference and the security configuration policy and the corresponding relationship between the quality difference and the server type and the data service configuration policy, and determine the optimal configuration policy based on the dynamic programming algorithm model, thereby improving the intelligent degree of the server chip configuration, improving the working security and working efficiency of the server, and realizing a more secure and efficient storage service.

[0195] As an optional embodiment, the specific manner in which the third determination module calculates the optimal configuration policy corresponding to the set of security configuration policies and the set of service configuration policies based on the dynamic programming algorithm and the preset policy conflict rules and policy effect prediction model includes:

[0196] According to the preset policy conflict rules, eliminate the service configuration policies in the set of service configuration policies that conflict with any security configuration policy in the set of security configuration policies;

[0197] Set the objective function to include that the sum of the running efficiencies after configuration corresponding to all configuration policies in the configuration plan reaches the maximum, the sum of the configuration costs corresponding to all configuration policies reaches the minimum, and the total number of all configuration policies reaches the minimum;

[0198] The set constraints include that the sum of the corresponding post-configuration security effects of all security configuration policies in the configuration plan is greater than a preset effect threshold; optionally, the post-configuration operation efficiency and the post-configuration security effect are both obtained by predicting the configuration policy through a trained policy effect prediction model; the policy effect prediction model is trained through a training data set including multiple training configuration policies and the corresponding post-configuration operation efficiency annotations, configuration cost annotations, and post-configuration security effect annotations; the configuration cost includes configuration time cost and configuration energy consumption cost;

[0199] Based on the dynamic programming algorithm, perform calculations according to the objective function and the limiting conditions to obtain the configuration policy corresponding to the optimal configuration plan.

[0200] It can be seen that through the above optional embodiments, it is possible to first eliminate conflicting policies through the preset policy conflict rules, and then determine the optimal configuration policy based on the dynamic programming algorithm model according to the objective function and the limiting conditions, thereby improving the intelligent level of server chip configuration, enhancing the working security and working efficiency of the server, and realizing a more secure and efficient storage service.

[0201] As an optional embodiment, the system is further configured to perform the following steps:

[0202] Judge whether the configuration necessity is greater than the necessity threshold to obtain a first judgment result;

[0203] Judge whether the remaining time difference between the execution time point of the task closest to the current time point in the predicted task plan and the current time point is greater than a preset second time difference threshold to obtain a second judgment result;

[0204] Judge whether the difference between the sum of the configuration time costs corresponding to the configuration policy and the remaining time difference is less than a preset parameter threshold to obtain a third judgment result;

[0205] When the first judgment result, the second judgment result, and the third judgment result are all yes, configure the target storage server according to the configuration policy.

[0206] It can be seen that through the above optional embodiments, it is possible to determine the specific server configuration timing based on the preset threshold judgment and difference judgment rules, and more accurately configure the server when it is necessary, the time is sufficient, and the time cost is low enough, thereby improving the intelligent level of server chip configuration, enhancing the working security and working efficiency of the server, and realizing a more secure and efficient storage service.

[0207] Embodiment III

[0208] Please refer to Figure 3 , Figure 3 which is another chip configuration system based on server task prediction disclosed in the embodiments of the present invention.Figure 3 The described chip configuration system based on server task prediction is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). As Figure 3 shown, the chip configuration system based on server task prediction may include:

[0209] A memory 301 storing executable program code;

[0210] A processor 302 coupled to the memory 301;

[0211] Wherein, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the chip configuration method based on server task prediction described in Embodiment 1.

[0212] Embodiment 4

[0213] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the chip configuration method based on server task prediction described in Embodiment 1.

[0214] Embodiment 5

[0215] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the chip configuration method based on server task prediction described in Embodiment 1.

[0216] The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily have to be performed in the specific order or continuous order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0217] The systems, devices, modules, or units illustrated in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0218] For the sake of convenience in description, when describing the above device, it is divided into various units according to functions for separate description. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0219] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0220] This specification is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0221] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0222] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0223] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0224] Memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0225] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transitory media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0226] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0227] This specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0228] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the description in the method embodiment.

[0229] Finally, it should be noted that what is disclosed in a chip configuration method and system based on server task prediction disclosed in the embodiments of the present invention is only the preferred embodiments of the present invention, which are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A chip configuration method based on server task prediction, characterized in that, The method includes: Obtaining the server type, current task load, server device parameters, predicted task plan, and data transmission record of the target storage server in real time; Based on the data matching prediction rule, determining the attack probability of the target storage server according to the current task load and the data transmission record, including: Inputting the current task load into the data transmission prediction neural network model corresponding to the target storage server to obtain the predicted transmission data corresponding to the target storage server; Calculating the record similarity between the data transmission record and the predicted transmission data; Based on the preset attack character recognition rule, calculating the proportion of the records in the data transmission record that conform to the attack character recognition rule in all records to obtain the attack record proportion; Calculating a first parameter inversely proportional to the record similarity; Calculating a second parameter proportional to the attack record proportion; Calculating the product of the first parameter and the second parameter to obtain the attack probability of the target storage server; Based on the server parameter evaluation rule, determining the predicted service quality of the target storage server according to the server device parameters and the predicted task plan, including: Determining multiple recently executed tasks in the predicted task plan whose time difference between the task execution time and the current time point is less than a preset first time difference threshold; According to the task requirement parameters of each of the recently executed tasks and the corresponding relationship between the preset requirement parameters and the device parameters, determining the device requirement parameters corresponding to each of the recently executed tasks; Summarizing the device requirement parameters corresponding to all the recently executed tasks to obtain a set of device requirement parameters; For multiple device requirement parameters belonging to the same arbitrary parameter type in the set of device requirement parameters, calculating the average value between the multiple device requirement parameters of this parameter type to obtain the requirement parameter corresponding to this parameter type, and replacing the multiple device requirement parameters of this parameter type with the requirement parameter; Determining the set of device requirement parameters after replacement as the overall device requirement parameters corresponding to all the recently executed tasks; Determining multiple matching server device parameters corresponding to any parameter type of the overall device requirement parameters in the server device parameters; Calculating the parameter difference obtained by subtracting the requirement parameter corresponding to the corresponding parameter type in the overall device requirement parameters from each of the matching server device parameters; the parameter difference retains the positive and negative signs; Calculating the weighted sum value of all the parameter differences to obtain the predicted service quality of the target storage server; wherein, the weight corresponding to each parameter difference includes a first weight and a second weight; the first weight is proportional to the number of requirement parameters of the same parameter type in the corresponding set of device requirement parameters; the second weight is proportional to the difference parameter corresponding to the parameter difference; the difference parameter is the difference between the parameter difference and a preset difference threshold; According to the attack probability and the predicted service quality, based on the preset configuration policy rule, determining the configuration necessity and configuration policy corresponding to the processor chip of the target storage server, including: Determine the baseline security probability and baseline service quality corresponding to the server type according to the correspondence between the preset server type and the baseline security probability and baseline service quality; Calculate the probability difference between the probability of being attacked and the baseline probability of the server; Calculate the quality difference between the predicted service quality and the baseline service quality; Calculate the weighted sum average of the probability difference and the quality difference to obtain the configuration necessity corresponding to the target storage server; Determine the set of security configuration policies corresponding to the probability difference according to the correspondence between the preset probability difference and the security configuration policies; Determine the set of service configuration policies corresponding to the quality difference and the server type according to the correspondence between the preset quality difference and the server type and the data service configuration policies; Based on the dynamic programming algorithm and the preset policy conflict rules and policy effect prediction model, calculate the optimal configuration policies corresponding to the set of security configuration policies and the set of service configuration policies; the set of security configuration policies includes multiple policies for configuring the security protection rules of the target storage server; the set of service configuration policies includes multiple policies for configuring the server service functions of the target storage server; the configuration policies are used to configure the services of the target storage server when the configuration necessity is higher than the preset necessity threshold.

2. The chip configuration method based on server task prediction according to claim 1, wherein The server type includes one or more of a newly extended server, a management server, a server with computing tasks, a pure storage server, a server with transfer tasks, and a server with redistribution tasks.

3. The chip configuration method based on server task prediction according to claim 1, wherein The calculating the optimal configuration policies corresponding to the set of security configuration policies and the set of service configuration policies based on the dynamic programming algorithm and the preset policy conflict rules and policy effect prediction model includes: According to the preset policy conflict rules, eliminate the service configuration policies in the set of service configuration policies that conflict with any security configuration policy in the set of security configuration policies; Set the objective function to include that the sum of the post-configuration operation efficiencies corresponding to all configuration policies in the configuration plan reaches the maximum, the sum of the configuration costs corresponding to all configuration policies reaches the minimum, and the total number of all configuration policies reaches the minimum; Set the constraint conditions to include that the sum of the post-configuration security effects corresponding to all security configuration policies in the configuration plan is greater than the preset effect threshold; the post-configuration operation efficiency and the post-configuration security effect are both obtained by predicting the configuration policies through the trained policy effect prediction model; the policy effect prediction model is trained by a training data set including multiple training configuration policies and corresponding post-configuration operation efficiency annotations, configuration cost annotations, and post-configuration security effect annotations; the configuration cost includes configuration time cost and configuration energy consumption cost; Based on the dynamic programming algorithm, calculate according to the objective function and the constraint conditions to obtain the configuration policies corresponding to the optimal configuration plan.

4. The chip configuration method based on server task prediction according to claim 3, wherein, The method further includes: Judge whether the configuration necessity is greater than the necessity threshold to obtain a first judgment result; Determine whether the remaining time difference between the execution time point of the task closest to the current time point in the predicted task plan and the current time point is greater than a preset second time difference threshold, and obtain a second judgment result; Determine whether the difference between the sum of the configuration time costs corresponding to the configuration policy and the remaining time difference is less than a preset parameter threshold, and obtain a third judgment result; When the first judgment result, the second judgment result, and the third judgment result are all yes, configure the target storage server according to the configuration policy.

5. A chip configuration system based on server task prediction, characterized in that, The system includes: An acquisition module, configured to acquire in real time the server type, current task load, server device parameters, predicted task plan, and data transmission record of the target storage server; A first determination module, configured to determine the attack probability of the target storage server based on a data matching prediction rule according to the current task load and the data transmission record, including: Input the current task load into the data transmission prediction neural network model corresponding to the target storage server to obtain the predicted transmission data corresponding to the target storage server; Calculate the record similarity between the data transmission record and the predicted transmission data; Based on a preset attack character recognition rule, calculate the proportion of records in the data transmission record that conform to the attack character recognition rule in all records to obtain an attack record proportion; Calculate a first parameter that is inversely proportional to the record similarity; Calculate a second parameter that is directly proportional to the attack record proportion; Calculate the product of the first parameter and the second parameter to obtain the attack probability of the target storage server; A second determination module, configured to determine the predicted service quality of the target storage server based on a server parameter evaluation rule according to the server device parameters and the predicted task plan, including: According to the multiple recently executed tasks in the predicted task plan whose time difference between the task execution time and the current time point is less than a preset first time difference threshold; According to the task requirement parameters of each of the recently executed tasks and the corresponding relationship between the preset requirement parameters and the device parameters, determine the device requirement parameters corresponding to each of the recently executed tasks; Summarize the device requirement parameters corresponding to all the recently executed tasks to obtain a set of device requirement parameters; For multiple device requirement parameters belonging to the same arbitrary parameter type in the set of device requirement parameters, calculate the average value between the multiple device requirement parameters of this parameter type to obtain the requirement parameter corresponding to this parameter type, and replace the multiple device requirement parameters of this parameter type with the requirement parameter; Determine the set of device requirement parameters after replacement as the overall device requirement parameters corresponding to all the recently executed tasks; Determine multiple matching server device parameters corresponding to any parameter type of the overall device requirement parameters in the server device parameters; Calculate the parameter difference obtained by subtracting the requirement parameter corresponding to the corresponding parameter type in the overall device requirement parameters from each of the matching server device parameters; the parameter difference retains the positive and negative signs; Calculate the weighted sum value of all the parameter differences to obtain the predicted service quality of the target storage server; wherein, the weight corresponding to each parameter difference includes a first weight and a second weight; the first weight is proportional to the number of required parameters of the same parameter type in the corresponding device requirement parameter set; the second weight is proportional to the difference parameter corresponding to the parameter difference; the difference parameter is the difference between the parameter difference and a preset difference threshold. A third determination module, configured to determine the configuration necessity and configuration policy corresponding to the processor chip of the target storage server based on a preset configuration policy rule according to the attack probability and the predicted service quality, including: Determine the benchmark security probability and benchmark service quality corresponding to the server type according to the corresponding relationship between the preset server type and the benchmark security probability and benchmark service quality. Calculate the probability difference between the attack probability and the server benchmark probability. Calculate the quality difference between the predicted service quality and the benchmark service quality. Calculate the weighted sum average of the probability difference and the quality difference to obtain the configuration necessity corresponding to the target storage server. Determine the set of security configuration policies corresponding to the probability difference according to the corresponding relationship between the preset probability difference and the security configuration policy. Determine the set of service configuration policies corresponding to the quality difference and the server type according to the corresponding relationship between the preset quality difference and the server type and the data service configuration policy. Based on the dynamic programming algorithm and the preset policy conflict rule and policy effect prediction model, calculate the optimal configuration policy corresponding to the set of security configuration policies and the set of service configuration policies; the set of security configuration policies includes multiple policies for configuring the security protection rules of the target storage server; the set of service configuration policies includes multiple policies for configuring the server service functions of the target storage server; the configuration policy is used to configure the service of the target storage server when the configuration necessity is higher than a preset necessity threshold.

6. A chip configuration system based on server task prediction, characterized in that, The system includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory and executes the chip configuration method based on server task prediction according to any one of claims 1-4.

Images