System optimization method, device, equipment and storage medium

Abstract

The present invention relates to artificial intelligence, and provides a system optimization method, device, equipment and storage medium. When receiving a system maintenance request, the method obtains the system problems of the system to be optimized according to the system maintenance request; obtains the system technical documents of the system to be optimized, and obtains the user behavior data of the system to be optimized; extracts the key information of the document in the system technical documents; inputs the key information of the document and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized; matches the solution of the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problems; optimizes the system to be optimized based on the solution to improve the optimization efficiency. In addition, the present invention also relates to blockchain technology, and the solution can be stored in the blockchain.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a system optimization method, device, equipment and storage medium. Background Art

[0002] At present, the technical capabilities of software system developers vary widely, which leads to frequent system problems such as freezing in some developed software systems in the later stages, making such software systems difficult to dimension. When such systems have problems, operation and maintenance users are usually required to analyze and troubleshoot system problems one by one to find a suitable solution, which leads to low system optimization efficiency and is not conducive to system dimensioning. Summary of the invention

[0003] In view of the above, it is necessary to provide a system optimization method, device, equipment and storage medium that can improve the system optimization efficiency.

[0004] In one aspect, the present invention provides a system optimization method, the system optimization method comprising:

[0005] When a system maintenance request is received, obtaining a system problem of the system to be optimized according to the system maintenance request;

[0006] Obtaining system technical documents of the system to be optimized, and obtaining user behavior data of the system to be optimized;

[0007] Extracting key document information from the system technical document;

[0008] Inputting the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized;

[0009] Matching a solution for the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problems;

[0010] The system to be optimized is optimized based on the solution.

[0011] According to a preferred embodiment of the present invention, obtaining the system problem of the system to be optimized according to the system maintenance request includes:

[0012] Locating a request triggering interface for the system maintenance request;

[0013] Identify the interface prompt position in the request trigger interface based on a preset prompt box;

[0014] The information at the interface prompt position is obtained as the system problem.

[0015] According to a preferred embodiment of the present invention, before inputting the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized, the method further includes:

[0016] Obtain design documents of the historical system from a preset website, and obtain historical operation and maintenance problems of the historical system and the time when the historical operation and maintenance problems occurred;

[0017] identifying a plurality of functional modules of the historical system from the design document;

[0018] Classify the historical operation and maintenance problems to obtain module problems corresponding to each functional module;

[0019] Calculate the frequency of the module problem occurring within a preset time period based on the problem occurrence time;

[0020] The pre-trained trend prediction model is constructed according to the multiple functional modules, the preset time period, the multiple module questions and the question frequency.

[0021] According to a preferred embodiment of the present invention, the pre-trained trend prediction model includes a module prediction network for each functional module, the module prediction network includes a prediction curve graph for each module problem in the functional module, and the document key information and the user behavior data are input into the pre-trained trend prediction model to obtain the system development trend of the system to be optimized, including:

[0022] Based on the key information of the document, a module prediction network matching the system to be optimized is identified as a target prediction network;

[0023] Identifying a prediction curve graph matching the user behavior data from the target prediction network as a system trend graph;

[0024] Identifying the system investment time of the system to be optimized according to the user behavior data;

[0025] Obtaining module problems from the system trend graph as target problems, and obtaining problem frequencies corresponding to the system investment time from the system trend graph as target frequencies;

[0026] The target problem and the target frequency are determined as the system development trend.

[0027] According to a preferred embodiment of the present invention, extracting key document information from the system technical document includes:

[0028] Extracting requirement module information from the system technical document, wherein the requirement module information includes a plurality of vocabulary information;

[0029] Acquire module identification information of the plurality of functional modules from the design document;

[0030] Calculating the information similarity between each vocabulary information and the module identification information;

[0031] If the information similarity is greater than a preset similarity threshold, the vocabulary information is determined as the document key information.

[0032] According to a preferred embodiment of the present invention, matching the solution of the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problem includes:

[0033] Determine the target problem whose target frequency is greater than a preset frequency threshold as a problem to be processed;

[0034] Acquire a processing method matching the problem to be processed from the preset operation and maintenance shared library as a first method, and acquire a processing method matching the system problem from the preset operation and maintenance shared library as a second method;

[0035] Detecting whether the first method conflicts with the second method;

[0036] If the first method does not conflict with the second method, the first method and the second method are combined as the solution.

[0037] According to a preferred embodiment of the present invention, the optimizing process of the system to be optimized based on the solution includes:

[0038] Obtaining solution code information corresponding to the solution;

[0039] The solution code information is run to perform an optimization process on the system to be optimized.

[0040] On the other hand, the present invention further provides a system optimization device, the system optimization device comprising:

[0041] an acquisition unit, configured to acquire the system problem of the system to be optimized according to the system maintenance request when receiving the system maintenance request;

[0042] The acquisition unit is further used to acquire system technical documents of the system to be optimized and to acquire user behavior data of the system to be optimized;

[0043] An extraction unit, used for extracting key document information from the system technical document;

[0044] An input unit, used to input the key information of the document and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized;

[0045] A matching unit, configured to match a solution of the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problem;

[0046] An optimization unit is used to optimize the system to be optimized based on the solution.

[0047] On the other hand, the present invention further provides an electronic device, comprising:

[0048] a memory storing computer readable instructions; and

[0049] A processor executes the computer-readable instructions stored in the memory to implement the system optimization method.

[0050] On the other hand, the present invention further proposes a computer-readable storage medium, in which computer-readable instructions are stored. The computer-readable instructions are executed by a processor in an electronic device to implement the system optimization method.

[0051] It can be seen from the above technical solutions that the present invention can predict the development trend of the system by extracting the key information of the document in the system technical document, and using the key information of the document, which not only avoids the interference of the interference information in the system technical document on the development trend of the system, but also improves the prediction efficiency of the system development trend because the pre-trained trend prediction model does not need to analyze the entire system technical document, and then accurately predicts the system development trend of the system to be optimized by combining the key information of the document and the user behavior data. Furthermore, the solution can be matched from the preset operation and maintenance shared library in combination with the system development trend and the system problem, and then the system to be optimized can be optimized based on the solution, and the system problem can be solved. Since the present invention does not need to adapt solutions one by one, it can improve the optimization efficiency of the system to be optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart of a preferred embodiment of the system optimization method of the present invention.

[0053] Figure 2 It is a functional module diagram of a preferred embodiment of the system optimization device of the present invention.

[0054] Figure 3 It is a schematic diagram of the structure of an electronic device of a preferred embodiment of the system optimization method of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0056] like Figure 1 FIG. 1 is a flow chart of a preferred embodiment of the system optimization method of the present invention. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted.

[0057] The system optimization method can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0058] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0059] The system optimization method is applied to one or more electronic devices, which are devices that can automatically perform numerical calculations and / or information processing according to pre-set or stored computer-readable instructions, and whose hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0060] The electronic device may be any electronic product that can perform human-computer interaction with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.

[0061] The electronic device may include a network device and / or a user device. The network device includes, but is not limited to, a single network electronic device, an electronic device group consisting of multiple network electronic devices, or a cloud consisting of a large number of hosts or network electronic devices based on cloud computing.

[0062] The network where the electronic device is located includes, but is not limited to: the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0063] S10: When a system maintenance request is received, system problems of the system to be optimized are obtained according to the system maintenance request.

[0064] In at least one embodiment of the present invention, the system maintenance request is a request triggered when a user fails to perform an operation on the system to be optimized. The system maintenance request carries an interface identifier corresponding to the interface that triggers the request to be generated.

[0065] The system to be optimized refers to a system that needs to be optimized.

[0066] The system problem refers to a problem generated when a user performs an operation on the system to be optimized. For example, the system problem may be a freeze or other problem.

[0067] In at least one embodiment of the present invention, the electronic device obtaining the system problem of the system to be optimized according to the system maintenance request includes:

[0068] Locating a request triggering interface for the system maintenance request;

[0069] Identify the interface prompt position in the request trigger interface based on a preset prompt box;

[0070] The information at the interface prompt position is obtained as the system problem.

[0071] The system problem is stored in the preset prompt box, and the preset prompt box may be a prompt box pre-designed by a developer of the system to be optimized.

[0072] The request triggering interface can be accurately located through the system maintenance request, and the interface prompt position can be quickly located through the preset prompt box, thereby improving the accuracy of the system problem.

[0073] Specifically, the electronic device parses the message of the system maintenance request to obtain data information carried in the message, extracts the interface identifier from the data information, and determines the interface corresponding to the interface identifier as the request triggering interface.

[0074] Specifically, the electronic device captures the position of the preset prompt box in the request trigger interface as the interface prompt position.

[0075] S11, obtaining system technical documents of the system to be optimized, and obtaining user behavior data of the system to be optimized.

[0076] In at least one embodiment of the present invention, the system technical document refers to the research and development requirement document of the system to be optimized, and the system technical document includes information such as the functional module diagram of the system to be optimized and the implementation code of each module.

[0077] The user behavior data includes information such as the operation of the operating user on a module in the system to be optimized.

[0078] In at least one embodiment of the present invention, the electronic device obtains the system technical document from a document library based on the system identification of the system to be optimized.

[0079] In at least one embodiment of the present invention, the electronic device acquiring the user behavior data of the system to be optimized includes:

[0080] Obtaining a system log corresponding to the system to be optimized from a preset log library;

[0081] Information corresponding to a preset behavior tag is extracted from the system log as the user behavior data.

[0082] The preset behavior label is used to indicate the user's operation behavior.

[0083] S12, extracting key document information from the system technical document.

[0084] In at least one embodiment of the present invention, the document key information includes vocabulary information corresponding to the system modules in the system to be optimized, and the document key information is stored in the requirement module information in the system technical document.

[0085] In at least one embodiment of the present invention, the electronic device extracting key document information from the system technical document includes:

[0086] Extracting requirement module information from the system technical document, wherein the requirement module information includes a plurality of vocabulary information;

[0087] Obtain module identification information of multiple functional modules from design documents;

[0088] Calculating the information similarity between each vocabulary information and the module identification information;

[0089] If the information similarity is greater than a preset similarity threshold, the vocabulary information is determined as the document key information.

[0090] The multiple vocabulary information is used to indicate the system modules in the system to be optimized.

[0091] The preset similarity threshold may be set according to actual needs. For example, the preset similarity threshold may be 90%.

[0092] The design document refers to a research and development requirement document of the historical system, and the multiple functional modules refer to historical system modules of the historical system.

[0093] By calculating the information similarity, it is possible to avoid the inability to accurately extract the key information of the document due to differences in the identification of the system modules.

[0094] S13, inputting the key information of the document and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized.

[0095] In at least one embodiment of the present invention, the pre-trained trend prediction model can be used to predict problems and problem frequencies that may occur in system modules in the system to be optimized during a preset period of time.

[0096] In at least one embodiment of the present invention, before inputting the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized, the method further includes:

[0097] Obtain design documents of the historical system from a preset website, and obtain historical operation and maintenance problems of the historical system and the time when the historical operation and maintenance problems occurred;

[0098] identifying a plurality of functional modules of the historical system from the design document;

[0099] Classify the historical operation and maintenance problems to obtain module problems corresponding to each functional module;

[0100] Calculate the frequency of the module problem occurring within a preset time period based on the problem occurrence time;

[0101] The pre-trained trend prediction model is constructed according to the multiple functional modules, the preset time period, the multiple module questions and the question frequency.

[0102] Among them, the preset websites share a large number of system R&D requirement documents.

[0103] The historical operation and maintenance problem may refer to a large amount of BUG information that appeared in the historical system, and the problem occurrence time refers to the time difference between the time when the historical operation and maintenance problem appeared and the time when the historical system was put into production.

[0104] For example, the multiple functional modules include module A, and the module problems corresponding to module A include problem 1, wherein problem 1 occurs 200 times, the time of problem occurrence corresponding to 50 times of problem 1 is 1 month, and the time of problem occurrence corresponding to 150 times of problem 1 is 2 months. Then, the frequency of problem A occurring in module A within the first month is 50, and the frequency of problem A occurring in module A within the second month is 150.

[0105] Through the above implementation, the frequency of problems in each module in the multiple functional modules can be accurately calculated, so that the trend prediction model can be accurately constructed.

[0106] In at least one embodiment of the present invention, the pre-trained trend prediction model includes a module prediction network for each functional module, the module prediction network includes a prediction curve graph for each module problem in the functional module, and the electronic device inputs the document key information and the user behavior data into the pre-trained trend prediction model to obtain the system development trend of the system to be optimized, including:

[0107] Based on the key information of the document, a module prediction network matching the system to be optimized is identified as a target prediction network;

[0108] Identifying a prediction curve graph matching the user behavior data from the target prediction network as a system trend graph;

[0109] Identifying the system investment time of the system to be optimized according to the user behavior data;

[0110] Obtaining module problems from the system trend graph as target problems, and obtaining problem frequencies corresponding to the system investment time from the system trend graph as target frequencies;

[0111] The target problem and the target frequency are determined as the system development trend.

[0112] The target prediction network refers to a module prediction network of a system module in the system to be optimized.

[0113] The system trend graph refers to a prediction curve graph corresponding to the operation module matching the user behavior data. If the operation module matching the user behavior data includes multiple module problems, the system trend graph includes multiple prediction curve graphs.

[0114] By combining the key information of the document and the user behavior data, the target problem and the target frequency can be accurately identified from the pre-trained trend prediction model, thereby improving the accuracy of the system development trend.

[0115] S14, matching a solution for the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problem.

[0116] It should be emphasized that in order to further ensure the privacy and security of the above solution, the above solution can also be stored in a node of a blockchain.

[0117] In at least one embodiment of the present invention, the preset operation and maintenance shared library shares a plurality of operation and maintenance problems and corresponding problem-solving codes.

[0118] The solution refers to specific code information that can solve the system problem.

[0119] In at least one embodiment of the present invention, the electronic device matches a solution for the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problem, including:

[0120] Determine the target problem whose target frequency is greater than a preset frequency threshold as a problem to be processed;

[0121] Acquire a processing method matching the problem to be processed from the preset operation and maintenance shared library as a first method, and acquire a processing method matching the system problem from the preset operation and maintenance shared library as a second method;

[0122] Detecting whether the first method conflicts with the second method;

[0123] If the first method does not conflict with the second method, the first method and the second method are combined as the solution.

[0124] The preset frequency threshold may be set according to user requirements. For example, the preset frequency threshold may be 1000 times.

[0125] For example, the first method is: setting the value of indicator A to be less than 50, and the second method is: setting the value of indicator B to be greater than 50, then it is determined that the first method conflicts with the second method.

[0126] By comparing the target frequency with the preset frequency threshold, the problem that needs to be optimized for the system can be customized according to user needs, thereby avoiding the problem from occurring in subsequent operations of the user. By detecting whether the first method conflicts with the second method, it can be determined whether the problem to be processed and the system problem cannot be solved due to the conflict between the first method and the second method, thereby improving the accuracy of system optimization.

[0127] In other embodiments, if the first method conflicts with the second method, an alarm message is generated.

[0128] S15: Optimize the system to be optimized based on the solution.

[0129] In at least one embodiment of the present invention, the electronic device optimizing the system to be optimized based on the solution includes:

[0130] Obtaining solution code information corresponding to the solution;

[0131] The solution code information is run to perform an optimization process on the system to be optimized.

[0132] Through the above implementation, the solution code information can be directly called to perform optimization processing on the system to be optimized, thereby improving the optimization efficiency of the system to be optimized.

[0133] It can be seen from the above technical solutions that the present invention can predict the development trend of the system by extracting the key information of the document in the system technical document, and using the key information of the document, which not only avoids the interference of the interference information in the system technical document on the development trend of the system, but also improves the prediction efficiency of the system development trend because the pre-trained trend prediction model does not need to analyze the entire system technical document, and then accurately predicts the system development trend of the system to be optimized by combining the key information of the document and the user behavior data. Furthermore, the solution can be matched from the preset operation and maintenance shared library in combination with the system development trend and the system problem, and then the system to be optimized can be optimized based on the solution, and the system problem can be solved. Since the present invention does not need to adapt solutions one by one, it can improve the optimization efficiency of the system to be optimized.

[0134] like Figure 2As shown, it is a functional module diagram of a preferred embodiment of the system optimization device of the present invention. The system optimization device 11 includes an acquisition unit 110, an extraction unit 111, an input unit 112, a matching unit 113, an optimization unit 114, an identification unit 115, a classification unit 116, a calculation unit 117 and a construction unit 118. The module / unit referred to in the present invention refers to a series of computer-readable instruction segments that can be acquired by the processor 13 and can complete a fixed function, which is stored in the memory 12. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0135] When receiving a system maintenance request, the acquisition unit 110 acquires the system problem of the system to be optimized according to the system maintenance request.

[0136] In at least one embodiment of the present invention, the system maintenance request is a request triggered when a user fails to perform an operation on the system to be optimized. The system maintenance request carries an interface identifier corresponding to the interface that triggers the request to be generated.

[0137] The system to be optimized refers to a system that needs to be optimized.

[0138] The system problem refers to a problem generated when a user performs an operation on the system to be optimized. For example, the system problem may be a freeze or other problem.

[0139] In at least one embodiment of the present invention, the acquiring unit 110 acquires the system problem of the system to be optimized according to the system maintenance request, including:

[0140] Locating a request triggering interface for the system maintenance request;

[0141] Identify the interface prompt position in the request trigger interface based on a preset prompt box;

[0142] The information at the interface prompt position is obtained as the system problem.

[0143] The system problem is stored in the preset prompt box, and the preset prompt box may be a prompt box pre-designed by a developer of the system to be optimized.

[0144] The request triggering interface can be accurately located through the system maintenance request, and the interface prompt position can be quickly located through the preset prompt box, thereby improving the accuracy of the system problem.

[0145] Specifically, the acquisition unit 110 parses the message of the system maintenance request to obtain data information carried in the message, extracts the interface identifier from the data information, and determines the interface corresponding to the interface identifier as the request triggering interface.

[0146] Specifically, the acquisition unit 110 captures the position of the preset prompt box in the request triggering interface as the interface prompt position.

[0147] The acquisition unit 110 acquires system technical documents of the system to be optimized, and acquires user behavior data of the system to be optimized.

[0148] In at least one embodiment of the present invention, the system technical document refers to the research and development requirement document of the system to be optimized, and the system technical document includes information such as the functional module diagram of the system to be optimized and the implementation code of each module.

[0149] The user behavior data includes information such as the operation of the operating user on a module in the system to be optimized.

[0150] In at least one embodiment of the present invention, the acquisition unit 110 acquires the system technical document from a document library based on the system identifier of the system to be optimized.

[0151] In at least one embodiment of the present invention, the acquiring unit 110 acquires the user behavior data of the system to be optimized, including:

[0152] Obtaining a system log corresponding to the system to be optimized from a preset log library;

[0153] Information corresponding to a preset behavior tag is extracted from the system log as the user behavior data.

[0154] The preset behavior label is used to indicate the user's operation behavior.

[0155] The extraction unit 111 extracts key document information from the system technical document.

[0156] In at least one embodiment of the present invention, the document key information includes vocabulary information corresponding to the system modules in the system to be optimized, and the document key information is stored in the requirement module information in the system technical document.

[0157] In at least one embodiment of the present invention, the extracting unit 111 extracts the key document information from the system technical document, including:

[0158] Extracting requirement module information from the system technical document, wherein the requirement module information includes a plurality of vocabulary information;

[0159] Obtain module identification information of multiple functional modules from design documents;

[0160] Calculating the information similarity between each vocabulary information and the module identification information;

[0161] If the information similarity is greater than a preset similarity threshold, the vocabulary information is determined as the document key information.

[0162] The multiple vocabulary information is used to indicate the system modules in the system to be optimized.

[0163] The preset similarity threshold may be set according to actual needs. For example, the preset similarity threshold may be 90%.

[0164] The design document refers to a research and development requirement document of the historical system, and the multiple functional modules refer to historical system modules of the historical system.

[0165] By calculating the information similarity, it is possible to avoid the inability to accurately extract the key information of the document due to differences in the identification of the system modules.

[0166] The input unit 112 inputs the key information of the document and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized.

[0167] In at least one embodiment of the present invention, the pre-trained trend prediction model can be used to predict problems and problem frequencies that may occur in system modules in the system to be optimized during a preset period of time.

[0168] In at least one embodiment of the present invention, before inputting the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized, the acquisition unit 110 acquires the design document of the historical system from a preset website, and acquires the historical operation and maintenance problems of the historical system and the problem occurrence time of the historical operation and maintenance problems;

[0169] The identification unit 115 identifies a plurality of functional modules of the historical system from the design document;

[0170] The classification unit 116 classifies the historical operation and maintenance problems to obtain module problems corresponding to each functional module;

[0171] The calculation unit 117 calculates the problem frequency of the module problem occurring within a preset time period based on the problem occurrence time;

[0172] The construction unit 118 constructs the pre-trained trend prediction model according to the multiple functional modules, the preset time period, the multiple module questions and the question frequency.

[0173] Among them, the preset websites share a large number of system R&D requirement documents.

[0174] The historical operation and maintenance problem may refer to a large amount of BUG information that appeared in the historical system, and the problem occurrence time refers to the time difference between the time when the historical operation and maintenance problem appeared and the time when the historical system was put into production.

[0175] For example, the multiple functional modules include module A, and the module problems corresponding to module A include problem 1, wherein problem 1 occurs 200 times, the time of problem occurrence corresponding to 50 times of problem 1 is 1 month, and the time of problem occurrence corresponding to 150 times of problem 1 is 2 months. Then, the frequency of problem A occurring in module A within the first month is 50, and the frequency of problem A occurring in module A within the second month is 150.

[0176] Through the above implementation, the frequency of problems in each module in the multiple functional modules can be accurately calculated, so that the trend prediction model can be accurately constructed.

[0177] In at least one embodiment of the present invention, the pre-trained trend prediction model includes a module prediction network for each functional module, and the module prediction network includes a prediction curve graph for each module problem in the functional module. The input unit 112 inputs the document key information and the user behavior data into the pre-trained trend prediction model, and the system development trend of the system to be optimized is obtained, including:

[0178] Based on the key information of the document, a module prediction network matching the system to be optimized is identified as a target prediction network;

[0179] Identifying a prediction curve graph matching the user behavior data from the target prediction network as a system trend graph;

[0180] Identifying the system investment time of the system to be optimized according to the user behavior data;

[0181] Obtaining module problems from the system trend graph as target problems, and obtaining problem frequencies corresponding to the system investment time from the system trend graph as target frequencies;

[0182] The target problem and the target frequency are determined as the system development trend.

[0183] The target prediction network refers to a module prediction network of a system module in the system to be optimized.

[0184] The system trend graph refers to a prediction curve graph corresponding to the operation module matching the user behavior data. If the operation module matching the user behavior data includes multiple module problems, the system trend graph includes multiple prediction curve graphs.

[0185] By combining the key information of the document and the user behavior data, the target problem and the target frequency can be accurately identified from the pre-trained trend prediction model, thereby improving the accuracy of the system development trend.

[0186] The matching unit 113 matches a solution for the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problem.

[0187] It should be emphasized that in order to further ensure the privacy and security of the above solution, the above solution can also be stored in a node of a blockchain.

[0188] In at least one embodiment of the present invention, the preset operation and maintenance shared library shares a plurality of operation and maintenance problems and corresponding problem-solving codes.

[0189] The solution refers to specific code information that can solve the system problem.

[0190] In at least one embodiment of the present invention, the matching unit 113 matches the solution of the system to be optimized from the preset operation and maintenance shared library based on the system development trend and the system problem, including:

[0191] Determine the target problem whose target frequency is greater than a preset frequency threshold as a problem to be processed;

[0192] Acquire a processing method matching the problem to be processed from the preset operation and maintenance shared library as a first method, and acquire a processing method matching the system problem from the preset operation and maintenance shared library as a second method;

[0193] Detecting whether the first method conflicts with the second method;

[0194] If the first method does not conflict with the second method, the first method and the second method are combined as the solution.

[0195] The preset frequency threshold may be set according to user requirements. For example, the preset frequency threshold may be 1000 times.

[0196] For example, the first method is: setting the value of indicator A to be less than 50, and the second method is: setting the value of indicator B to be greater than 50, then it is determined that the first method conflicts with the second method.

[0197] By comparing the target frequency with the preset frequency threshold, the problem that needs to be optimized for the system can be customized according to user needs, thereby avoiding the problem from occurring in subsequent operations of the user. By detecting whether the first method conflicts with the second method, it can be determined whether the problem to be processed and the system problem cannot be solved due to the conflict between the first method and the second method, thereby improving the accuracy of system optimization.

[0198] In other embodiments, if the first method conflicts with the second method, an alarm message is generated.

[0199] The optimization unit 114 optimizes the system to be optimized based on the solution.

[0200] In at least one embodiment of the present invention, the optimization unit 114 optimizes the system to be optimized based on the solution, including:

[0201] Obtaining solution code information corresponding to the solution;

[0202] The solution code information is run to perform an optimization process on the system to be optimized.

[0203] Through the above implementation, the solution code information can be directly called to perform optimization processing on the system to be optimized, thereby improving the optimization efficiency of the system to be optimized.

[0204] It can be seen from the above technical solutions that the present invention can predict the development trend of the system by extracting the key information of the document in the system technical document, and using the key information of the document, which not only avoids the interference of the interference information in the system technical document on the development trend of the system, but also improves the prediction efficiency of the system development trend because the pre-trained trend prediction model does not need to analyze the entire system technical document, and then accurately predicts the system development trend of the system to be optimized by combining the key information of the document and the user behavior data. Furthermore, the solution can be matched from the preset operation and maintenance shared library in combination with the system development trend and the system problem, and then the system to be optimized can be optimized based on the solution, and the system problem can be solved. Since the present invention does not need to adapt solutions one by one, it can improve the optimization efficiency of the system to be optimized.

[0205] like Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device of a preferred embodiment of the system optimization method of the present invention.

[0206] In one embodiment of the present invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and computer-readable instructions stored in the memory 12 and executable on the processor 13, such as a system optimization program.

[0207] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation on the electronic device 1. The electronic device 1 may include more or fewer components than shown in the diagram, or a combination of certain components, or different components. For example, the electronic device 1 may also include input and output devices, network access devices, buses, etc.

[0208] The processor 13 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 13 is the computing core and control center of the electronic device 1, and uses various interfaces and lines to connect various parts of the entire electronic device 1, and executes the operating system of the electronic device 1 and various installed applications, program codes, etc.

[0209] Exemplarily, the computer-readable instructions may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of completing specific functions, which are used to describe the execution process of the computer-readable instructions in the electronic device 1. For example, the computer-readable instructions may be divided into an acquisition unit 110, an extraction unit 111, an input unit 112, a matching unit 113, an optimization unit 114, a recognition unit 115, a classification unit 116, a calculation unit 117, and a construction unit 118.

[0210] The memory 12 can be used to store the computer-readable instructions and / or modules, and the processor 13 implements various functions of the electronic device 1 by running or executing the computer-readable instructions and / or modules stored in the memory 12, and calling the data stored in the memory 12. The memory 12 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device, etc. The memory 12 can include non-volatile and volatile memories, such as: a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other storage devices.

[0211] The memory 12 may be an external memory and / or an internal memory of the electronic device 1. Furthermore, the memory 12 may be a memory in a physical form, such as a memory stick, a TF card (Trans-flash Card), and the like.

[0212] If the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also instruct the relevant hardware to complete it through computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed by the processor, the steps of the above-mentioned various method embodiments can be implemented.

[0213] The computer-readable instructions include computer-readable instruction codes, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer-readable instruction code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM).

[0214] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed system optimization, point-to-point transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0215] Combination Figure 1 The memory 12 in the electronic device 1 stores computer-readable instructions to implement a system optimization method, and the processor 13 can execute the computer-readable instructions to implement:

[0216] When a system maintenance request is received, obtaining a system problem of the system to be optimized according to the system maintenance request;

[0217] Obtaining system technical documents of the system to be optimized, and obtaining user behavior data of the system to be optimized;

[0218] Extracting key document information from the system technical document;

[0219] Inputting the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized;

[0220] Matching a solution for the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problems;

[0221] The system to be optimized is optimized based on the solution.

[0222] Specifically, the specific implementation method of the processor 13 for the above-mentioned computer readable instructions can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0223] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0224] The computer-readable storage medium stores computer-readable instructions, wherein the computer-readable instructions are used to implement the following steps when executed by the processor 13:

[0225] When a system maintenance request is received, obtaining a system problem of the system to be optimized according to the system maintenance request;

[0226] Obtaining system technical documents of the system to be optimized, and obtaining user behavior data of the system to be optimized;

[0227] Extracting key document information from the system technical document;

[0228] Inputting the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized;

[0229] Matching a solution for the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problems;

[0230] The system to be optimized is optimized based on the solution.

[0231] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0232] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0233] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0234] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices mentioned can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0235] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A system optimization method, characterized in that: The system optimization method comprises: When a system maintenance request is received, obtaining a system problem of the system to be optimized according to the system maintenance request; Obtaining system technical documents of the system to be optimized, and obtaining user behavior data of the system to be optimized; Extracting key document information from the system technical document; Input the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized, the pre-trained trend prediction model includes a module prediction network for each functional module, and the module prediction network includes a prediction curve diagram for each module problem in the functional module. The inputting the document key information and the user behavior data into the pre-trained trend prediction model to obtain the system development trend of the system to be optimized includes: identifying a module prediction network matching the system to be optimized as a target prediction network based on the document key information; identifying a prediction curve diagram matching the user behavior data from the target prediction network as a system trend diagram; identifying the system investment time of the system to be optimized according to the user behavior data; obtaining module problems from the system trend diagram as target problems, and obtaining the problem frequency corresponding to the system investment time from the system trend diagram as the target frequency; determining the target problem and the target frequency as the system development trend; Matching a solution for the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problems; Optimizing the system to be optimized based on the solution; Before inputting the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized, the method further includes: Obtain design documents of the historical system from a preset website, and obtain historical operation and maintenance problems of the historical system and the time when the historical operation and maintenance problems occurred; identifying a plurality of functional modules of the historical system from the design document; Classify the historical operation and maintenance problems to obtain module problems corresponding to each functional module; Calculate the frequency of the module problem occurring within a preset time period based on the problem occurrence time; The pre-trained trend prediction model is constructed according to the multiple functional modules, the preset time period, the multiple module questions and the question frequency.

2. The system optimization method according to claim 1, characterized in that: The obtaining of the system problem of the system to be optimized according to the system maintenance request comprises: Locating a request triggering interface for the system maintenance request; Identify the interface prompt position in the request trigger interface based on a preset prompt box; The information at the interface prompt position is obtained as the system problem.

3. The system optimization method according to claim 1, characterized in that: The extracting of key document information from the system technical document includes: Extracting requirement module information from the system technical document, wherein the requirement module information includes a plurality of vocabulary information; Acquire module identification information of the plurality of functional modules from the design document; Calculating the information similarity between each vocabulary information and the module identification information; If the information similarity is greater than a preset similarity threshold, the vocabulary information is determined as the document key information.

4. The system optimization method according to claim 1, characterized in that: The matching of the solution of the system to be optimized from the preset operation and maintenance shared library based on the system development trend and the system problem includes: Determine the target problem whose target frequency is greater than a preset frequency threshold as a problem to be processed; Acquire a processing method matching the problem to be processed from the preset operation and maintenance shared library as a first method, and acquire a processing method matching the system problem from the preset operation and maintenance shared library as a second method; Detecting whether the first method conflicts with the second method; If the first method does not conflict with the second method, the first method and the second method are combined as the solution.

5. The system optimization method according to claim 1, characterized in that: The optimizing process of the system to be optimized based on the solution includes: Obtaining solution code information corresponding to the solution; The solution code information is run to perform an optimization process on the system to be optimized.

6. A system optimization device, characterized in that: The system optimization device comprises: an acquisition unit, configured to acquire the system problem of the system to be optimized according to the system maintenance request when receiving the system maintenance request; The acquisition unit is further used to acquire system technical documents of the system to be optimized and to acquire user behavior data of the system to be optimized; An extraction unit, used for extracting key document information from the system technical document; An input unit is used to input the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized, the pre-trained trend prediction model includes a module prediction network for each functional module, and the module prediction network includes a prediction curve diagram for each module problem in the functional module. The inputting the document key information and the user behavior data into the pre-trained trend prediction model to obtain the system development trend of the system to be optimized includes: identifying a module prediction network matching the system to be optimized as a target prediction network based on the document key information; identifying a prediction curve diagram matching the user behavior data from the target prediction network as a system trend diagram; identifying the system investment time of the system to be optimized according to the user behavior data; obtaining module problems from the system trend diagram as target problems, and obtaining the problem frequency corresponding to the system investment time from the system trend diagram as the target frequency; determining the target problem and the target frequency as the system development trend; A matching unit, configured to match a solution of the system to be optimized from a preset operation and maintenance shared library based on the system development trend and the system problem; An optimization unit, configured to optimize the system to be optimized based on the solution; Before inputting the document key information and the user behavior data into a pre-trained trend prediction model to obtain the system development trend of the system to be optimized, the device further includes: The acquisition unit is further used to acquire the design documents of the historical system from a preset website, and acquire the historical operation and maintenance problems of the historical system and the time when the historical operation and maintenance problems occurred; an identification unit, configured to identify a plurality of functional modules of the historical system from the design document; A classification unit, used to classify the historical operation and maintenance problems to obtain module problems corresponding to each functional module; A calculation unit, used for calculating the frequency of occurrence of the module problem within a preset time period based on the problem occurrence time; A construction unit is used to construct the pre-trained trend prediction model according to the multiple functional modules, the preset time period, the multiple module problems and the problem frequency.

7. An electronic device, characterized in that: The electronic device comprises: a memory storing computer-readable instructions; and A processor executes computer-readable instructions stored in the memory to implement the system optimization method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions are executed by a processor in an electronic device to implement the system optimization method as described in any one of claims 1 to 5.

Images