Application parameter management method and device based on knowledge graph, equipment and medium

Abstract

The invention discloses an application parameter management method and device based on a knowledge graph, equipment and a medium, and relates to the technical field of artificial intelligence. The method comprises the steps of obtaining a parameter information set corresponding to a target application; based on the data structure type of each piece of target parameter information in the parameter information set, performing knowledge extraction on the target parameter information to obtain basic knowledge content corresponding to the parameter information set, and based on a preset knowledge graph construction rule combination, processing the basic knowledge content to generate a knowledge graph corresponding to the target application; and performing analysis processing on the knowledge graph based on a preset recognition rule to obtain potential associated content corresponding to the target application, and performing combined processing on the knowledge graph and the potential associated content to obtain target knowledge content corresponding to the target application. By means of the technical scheme, information integration can be conducted on all parameters of the same application program on different platforms, and the efficiency and depth of data application are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and particularly to an application parameter management method, device, equipment and medium based on a knowledge graph. Background Art

[0002] With the gradual development of software technology, a large number of technical parameters are often involved in the software development process. Therefore, managing and analyzing each technical parameter is crucial for ensuring system stability and production safety.

[0003] In the prior art, the technical parameters corresponding to the same application program are usually scattered in multiple platforms, and the parameters within each platform are stored in isolation in a database in the form of a structured data table for technical parameter management. However, due to the increasing volume of technical parameters, the parameter content includes different parameter types, different levels of function and different uses, and parameter management is targeted at different groups such as designers, developers, testers or architects. If the parameter management method in the prior art is used, the parameter relationship will not be intuitive, reducing the efficiency of data application. In addition, the parameter table usually contains a large amount of text information such as parameter descriptions. If the parameter management method in the prior art is used, there is a lack of knowledge precipitation, which will result in a large amount of operation and maintenance work for technical parameters, an old and passive mode and a low degree of intelligence, reducing the depth of data application.

[0004] Therefore, how to integrate the information of each parameter of the same application program in different platforms, improve the efficiency and depth of data application, realize the management of technical parameters, and ensure system stability and production safety is an urgent problem to be solved at present. Summary of the Invention

[0005] The present invention provides an application parameter management method, device, equipment and medium based on a knowledge graph, which can solve the problem of low data application efficiency and depth of technical parameters in an application program.

[0006] According to one aspect of the present invention, an application parameter management method based on a knowledge graph is provided, including:

[0007] Obtaining a set of parameter information corresponding to a target application;

[0008] Performing knowledge extraction on the target parameter information based on the data structure type of each target parameter information in the parameter information set to obtain basic knowledge content corresponding to the parameter information set, and combining and processing the basic knowledge content based on a preset knowledge graph construction rule to generate a knowledge graph corresponding to the target application;

[0009] Analyze and process the knowledge graph based on a preset recognition rule to obtain potential associated content corresponding to the target application, and combine and process the knowledge graph and the potential associated content to obtain target knowledge content corresponding to the target application.

[0010] According to another aspect of the present invention, there is provided an application parameter management device based on a knowledge graph, including:

[0011] A data acquisition module, configured to acquire a set of parameter information corresponding to a target application;

[0012] A graph generation module, configured to perform knowledge extraction on the target parameter information based on the data structure type of each target parameter information in the set of parameter information to obtain basic knowledge content corresponding to the set of parameter information, and combine and process the basic knowledge content based on a preset knowledge graph construction rule to generate a knowledge graph corresponding to the target application;

[0013] A content determination module, configured to analyze and process the knowledge graph based on a preset recognition rule to obtain potential associated content corresponding to the target application, and combine and process the knowledge graph and the potential associated content to obtain target knowledge content corresponding to the target application.

[0014] According to another aspect of the present invention, there is provided an electronic device, the electronic device includes:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the application parameter management method based on a knowledge graph according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, there is provided a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the application parameter management method based on a knowledge graph according to any embodiment of the present invention when executed.

[0019] According to another aspect of the present invention, there is provided a computer program product, including a computer program, and the computer program implements the application parameter management method based on a knowledge graph according to any embodiment of the present invention when executed by a processor.

[0020] In the technical solution of the embodiment of the present invention, knowledge extraction is performed on the target parameter information through the data structure types of the respective target parameter information in the parameter information set corresponding to the target application, and the basic knowledge content corresponding to the parameter information set is obtained. Then, the basic knowledge content is processed by combining the preset knowledge graph construction rules to generate a knowledge graph corresponding to the target application. Furthermore, based on the preset recognition rules, the knowledge graph is analyzed and processed to obtain potential associated content corresponding to the target application, and the knowledge graph and the potential associated content are combined and processed to obtain target knowledge content corresponding to the target application. Since the various target parameter information in the parameter information set is integrated, and the potential associated content is mined using the integrated knowledge graph, the problem of low data application efficiency and depth of technical parameters in the application program is solved. It is possible to integrate the information of the respective parameters of the same application program on different platforms, improve the efficiency and depth of data application, realize the management of technical parameters, and ensure system stability and production safety.

[0021] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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.

[0023] Figure 1 is a flowchart of a method for managing application parameters based on a knowledge graph according to Embodiment 1 of the present invention;

[0024] Figure 2 is a flowchart of a method for managing application parameters based on a knowledge graph according to Embodiment 2 of the present invention;

[0025] Figure 3 is a schematic structural diagram of a device for managing application parameters based on a knowledge graph according to Embodiment 3 of the present invention;

[0026] Figure 4 is a schematic structural diagram of an electronic device for implementing the method for managing application parameters based on a knowledge graph of the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] 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 in conjunction with 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0028] It should be noted that the terms "target", "basis", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] It is worth noting that in the technical solution of this application, the collected information is information and data authorized by the user or fully authorized by all parties. Moreover, for the processing of relevant data such as collection, storage, use, processing, transmission, provision, disclosure, and application, all comply with the relevant laws, regulations, and standards of relevant countries and regions, necessary confidentiality measures are taken, it does not violate public order and good customs, and a corresponding operation entry is provided for the user to choose to authorize or refuse; if the user chooses to refuse, the expert decision-making process will be entered.

[0030] Embodiment 1

[0031] Figure 1 The following is a flowchart of a method for managing application parameters based on a knowledge graph provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of integrating information on various parameters of the same application program on different platforms. This method can be executed by a device for managing application parameters based on a knowledge graph, and the device for managing application parameters based on a knowledge graph can be implemented in the form of hardware and / or software, and the device for managing application parameters based on a knowledge graph can be configured in an electronic device. As Figure 1 shown, the method includes:

[0032] S110. Obtain a set of parameter information corresponding to the target application.

[0033] Among them, the target application can refer to a software application selected for technical parameter management. Exemplarily, the target application can be any software application included in the current operating system. The parameter information set can refer to a set containing all technical parameters of the target application on multiple platforms.

[0034] In an alternative embodiment, the parameter information set may include: a parameter information registration form, historical parameter management specifications, and historical production problems. Among them, the parameter information registration form can refer to a document or form used to record and summarize technical data related to the target application. Through the parameter information registration form, detailed information about the target application can be quickly obtained, facilitating management and use. The historical parameter management specifications can refer to rules standard-set for implementing the management of technical parameters. Exemplarily, the historical parameter management specifications can include various technical specifications and code scanning rules, etc. The historical production problems can refer to the problems generated by the target application during a historical time period. It should be noted that in the embodiments of the present invention, the parameter information registration form can be obtained from the registration records of daily application research and development, the historical parameter management specifications can be retrieved from a pre-constructed specification library, and the historical production problems can be retrieved from the production problem records. The embodiments of the present invention do not specifically limit this.

[0035] S120. Perform knowledge extraction on the target parameter information based on the data structure type of each target parameter information in the parameter information set, obtain the basic knowledge content corresponding to the parameter information set, and generate a knowledge graph corresponding to the target application by combining and processing the basic knowledge content based on a preset knowledge graph construction rule.

[0036] Among them, the target parameter information can refer to the parameter information selected for knowledge extraction in the parameter information set. Exemplarily, the target parameter information can be any parameter information in the parameter information set. Specifically, the target parameter information can be the parameter information registration form in the parameter information set, the historical parameter management specifications in the parameter information set, or the historical production problems in the parameter information set.

[0037] Among them, the data structure type can refer to a category used to classify the relationship logic and storage structure between data elements in the target parameter information. Exemplarily, the data structure type can include a structured type and can also include an unstructured type. Generally, the corresponding data structure type can be determined by the storage format of the target parameter information. Knowledge can refer to the understanding and comprehension after processing information, and is the result of refining and summarizing data and information. Generally, knowledge can include entities, concepts, relationships, and attributes. The basic knowledge content can refer to a set of knowledge results obtained by performing knowledge extraction on the target parameter information in the parameter information set.

[0038] Among them, the preset knowledge graph construction rules can refer to the rules preset for limiting the knowledge graph construction process. Exemplarily, the preset knowledge graph construction rules can include the connection methods of basic knowledge content. A knowledge graph can refer to a technical method that uses a graph model to describe knowledge and model the association relationships between all things in the world. Generally, a knowledge graph consists of nodes and edges. Nodes can be entities, such as a person or a book, etc., or can be abstract concepts, such as artificial intelligence or knowledge graph, etc. Edges can be attributes of entities, such as a name or a book title, or can be relationships between entities, such as friends. In the embodiments of the present invention, the knowledge graph can be the knowledge graph corresponding to the target application.

[0039] S130. Analyze and process the knowledge graph based on the preset recognition rules to obtain the potential associated content corresponding to the target application, and combine and process the knowledge graph and the potential associated content to obtain the target knowledge content corresponding to the target application.

[0040] Among them, the preset recognition rules can refer to the rules preset for recognizing the knowledge content that is not explicitly expressed. The potential associated content can refer to the content that exists in the knowledge graph but is not explicitly expressed. Exemplarily, the potential associated content can be the association relationship between entities that may exist but is not explicitly expressed in the knowledge graph, or can be the association relationship between an event and a production problem that may exist but is not explicitly expressed in the knowledge graph, etc. The target knowledge content can refer to the complete knowledge content obtained by merging the knowledge graph and the potential associated content.

[0041] The technical solution of the embodiments of the present invention extracts knowledge from the target parameter information through the data structure types of the target parameter information in the parameter information set corresponding to the target application to obtain the basic knowledge content corresponding to the parameter information set, and combines and processes the basic knowledge content based on the preset knowledge graph construction rules to generate the knowledge graph corresponding to the target application. Furthermore, based on the preset recognition rules, the knowledge graph is analyzed and processed to obtain the potential associated content corresponding to the target application, and the knowledge graph and the potential associated content are combined and processed to obtain the target knowledge content corresponding to the target application. Since the various target parameter information in the parameter information set is integrated, and the potential associated content is mined using the integrated knowledge graph, the problem of low data application efficiency and depth of technical parameters in the application program is solved. It can integrate the parameters of the same application program on different platforms, improve the efficiency and depth of data application, realize the management of technical parameters, and ensure system stability and production safety.

[0042] Embodiment Two

[0043] Figure 2The flowchart of an application parameter management method provided in the second embodiment of the present invention. This embodiment is refined based on the above-mentioned embodiment. Specifically, in this embodiment, the operation of extracting knowledge from the target parameter information according to the data structure type of each target parameter information in the parameter information set to obtain the basic knowledge content corresponding to the parameter information set is refined. Specifically, it may include: If the data structure type of the target parameter information in the parameter information set is a structured type, determine the relationship type content in the target parameter information based on a preset knowledge extraction task; if the data structure type of the target parameter information in the parameter information set is an unstructured type, determine the basic type content in the target parameter information based on a preset basic type recognition rule; combine and process the relationship type content and the basic type content to obtain the basic knowledge content corresponding to the parameter information set. As Figure 2 shown, the method includes:

[0044] S210. Obtain a parameter information set corresponding to a target application.

[0045] S220. If the data structure type of the target parameter information in the parameter information set is a structured type, determine the relationship type content in the target parameter information based on a preset knowledge extraction task.

[0046] Among them, the preset knowledge extraction task may refer to a preset knowledge content extraction task. Exemplarily, the preset knowledge extraction task may include entities corresponding to the current knowledge extraction task. Generally, the preset knowledge extraction task can be established by the user pre-selecting which information is used as an entity. The relationship type content may refer to the semantic relationship between entities, such as "located in" or "founded in", etc.

[0047] Specifically, if the target parameter information in the parameter information set is a structured type presented in a structured table form, for example, the parameter information registration form in the parameter information set. Then, the preset knowledge extraction task established by the user can be obtained. Furthermore, based on the preset knowledge extraction task, each entity in the parameter information registration form, that is, the relevant columns, can be determined. Further, determine the corresponding relationship between the entities as the relationship type content in the target parameter information. Thus, the determination of the relationship type content is realized, providing a basis for subsequent operations.

[0048] S230. If the data structure type of the target parameter information in the parameter information set is an unstructured type, determine the basic type content in the target parameter information based on a preset basic type recognition rule.

[0049] Among them, the basic content can refer to the remaining content except the relational content. In an optional implementation, the basic content can include: entity content, concept content, and event content. Entity content can refer to the objectively existing instances in the parameter management system. For example, applications, groups, nodes, or parameters, etc. Concept content can refer to the abstract overview of a class of entities. For example, parameters can be divided into database - type parameters and Network Operating System (NOS) - type parameters, etc. Generally, attaching a label to a class of entities becomes concept content. Event content can refer to events used to describe the dynamic changes of entities in time or space. For example, the addition and deletion of parameters, and historical production problem events, etc.

[0050] Among them, the preset basic - class recognition rule can refer to the rule for determining basic content set in advance. Exemplarily, the preset basic - class recognition rule can include a preset entity - content recognition rule, a preset concept - content recognition rule, and a preset event - content recognition rule. Specifically, the preset entity - content recognition rule can be a rule - based method, a statistical machine - learning method, a deep - learning method, etc. The preset concept - content recognition rule can be a template - based method and a supervised - learning method, such as a convolutional neural network, etc. The preset event - content recognition rule can be a keyword - based recognition method.

[0051] Specifically, if the target parameter information in the parameter information set is of an unstructured type presented in an unstructured text form, such as the historical parameter management specification and historical production problems in the parameter information set. Then, the preset basic - class recognition rule can be used to perform content recognition on the target parameter information to determine the basic content corresponding to the target parameter information, providing a basis for subsequent operations.

[0052] S240. Combine and process the relational content and the basic content to obtain the basic knowledge content corresponding to the parameter information set.

[0053] Specifically, after determining the relational content corresponding to the parameter information registration form in the parameter information set based on the preset knowledge extraction task, and determining each basic content corresponding to the historical parameter management specification and historical production problems in the parameter information set based on the preset basic - class recognition rule, the relational content and each basic content corresponding to the same parameter information set can be combined. Thus, the basic knowledge content corresponding to the parameter information set is obtained, providing an effective basis for subsequent construction of the knowledge graph.

[0054] S250. Combine and process the basic knowledge content based on the preset knowledge - graph construction rule to generate the knowledge graph corresponding to the target application.

[0055] Specifically, after obtaining the basic knowledge content, the entity content and concept content in the basic knowledge content can be used as nodes, the relationship content in the basic knowledge content can be used as edges, and the event content in the basic knowledge content can be represented in the form of nodes or subgraphs, including trigger words and event elements. Thus, a knowledge graph corresponding to the target application is generated.

[0056] It should be noted that in the embodiments of the present invention, the unique identifiers corresponding to the entity content and concept content are different, and different nodes in the knowledge graph can be distinguished by this unique identifier.

[0057] S260. Analyze and process the basic association relationships in the knowledge graph based on a preset link prediction algorithm to obtain the potential association relationships corresponding to the target application.

[0058] Among them, the potential association relationship can refer to the relationship content that may exist between nodes but is not shown in the knowledge graph. Exemplarily, if the effectiveness of parameter A depends on the configuration of parameter B, but the knowledge graph lacks the ledger information for the associated parameters, then the dependence of parameter A on parameter B can be used as a potential association relationship. The preset link prediction algorithm can refer to an algorithm preset for predicting missing facts based on the existing entities in the knowledge graph. Exemplarily, the preset link prediction algorithm can be a model based on tensor decomposition, a geometric model, a deep learning model, etc.

[0059] Specifically, after generating the knowledge graph corresponding to the target application, the relationship content in the knowledge graph can be input into the preset link prediction algorithm, and the preset link prediction algorithm can use information such as the similarity between nodes, common neighbors, path features, and node attributes to identify the potential association relationships between parameter entities.

[0060] S270. Analyze and process the basic events in the knowledge graph based on a preset potential problem identification rule to obtain the potential problems corresponding to the target application.

[0061] Among them, the potential problem can refer to a production problem that may exist but is not shown in the knowledge graph. The preset potential problem identification rule can refer to a strategy preset for limiting the potential problem identification process. Exemplarily, the preset potential problem identification rule can be to use machine learning methods to predict potential problems, or to determine potential problems based on historical production problems. For example, if there is an event of "problem E appears after making modification D to parameter C" in the historical production problems, and the basic events in the knowledge graph do not include the event of "modification D causing problem E", then "modification D causing problem E" can be used as a potential problem.

[0062] In an optional implementation, the basic events in the knowledge graph are analyzed and processed based on a preset potential problem identification rule to obtain the potential problems corresponding to the target application, including: transforming the features of the basic events in the knowledge graph based on a target machine learning algorithm to obtain the feature vectors corresponding to the basic events; inputting the feature vectors into a target decision model to obtain the potential problems corresponding to the target application; wherein, the target decision model is a decision model trained based on historical production problems and historical events.

[0063] Among them, the target machine learning algorithm may refer to a pre-trained selected machine learning algorithm for feature transformation. The feature vector may refer to the vector generated after feature transformation. Generally, one basic event corresponds to one feature vector. The target decision model may refer to a pre-trained selected decision tree for potential problem prediction. Through the target decision model, the rules can be automatically learned from the feature vectors and the potential problems can be accurately predicted. Specifically, before determining the potential problems corresponding to the target application, the selected decision model can be pre-trained using historical production problems and historical events to obtain the trained target decision model. Furthermore, the features of the basic events in the knowledge graph are transformed using the target machine learning algorithm to obtain the feature vectors corresponding to the basic events, and the feature vectors are input into the target decision model. Thus, the potential problems corresponding to the target application are obtained, improving the identification efficiency and accuracy of potential problems.

[0064] S280. Combine and process the potential association relationships and potential problems to obtain the potential associated content corresponding to the target application.

[0065] Specifically, after generating the potential association relationships and potential problems corresponding to the target application respectively, the potential association relationships and potential problems corresponding to the same target application can be summarized. Thus, the potential associated content corresponding to the target application is obtained, providing an effective basis for subsequent operations.

[0066] S290. Combine and process the knowledge graph and the potential associated content to obtain the target knowledge content corresponding to the target application.

[0067] Specifically, after generating the potential associated content corresponding to the target application, the potential associated content corresponding to the target application can be combined with the knowledge graph to obtain the target knowledge content corresponding to the target application. Thus, the target knowledge content can cover work such as data collection, data processing, data analysis, relationship visualization, parameter governance, and parameter operation and maintenance in the parameter field, providing an effective basis for complex association analysis, statistical analysis functions, decision analysis, and truly empowering work such as parameter design, development, and operation and maintenance.

[0068] S2100. Obtain the current working parameters corresponding to the target application.

[0069] Among them, the current working parameter may refer to the operation state parameter of the target application at the current moment. Exemplarily, the current working parameter may be the parameter being modified currently.

[0070] S2110. Determine the current associated content corresponding to the current working parameter in the target knowledge content based on the parameter name of the current working parameter.

[0071] Among them, the current associated content may refer to the content in the target knowledge content that is associated with the current working parameter. Exemplarily, the current associated content may be an associated event or an associated parameter, etc.

[0072] S2120. Generate a parameter adjustment strategy corresponding to the target application based on the current operation content and the current associated content of the current working parameter.

[0073] Among them, the current operation content may refer to the operation result of the current working parameter. Exemplarily, the current operation content may be the modified content of the current working parameter. The parameter adjustment strategy may refer to a parameter operation plan generated based on the current operation content and the current associated content.

[0074] Specifically, taking the current working parameter as parameter F and the current operation content of the current working parameter as "making a G modification to parameter F" as an example, parameter matching can be performed using parameter F in the target knowledge content to determine the associated parameter or associated event corresponding to parameter F as the current associated content. If the current associated content is associated parameter H, then "testing the associated parameter H" is used as the parameter adjustment strategy corresponding to the target application. If the current associated content is associated event I, then "evaluating production problems for the current operation content based on the associated event I" is used as the parameter adjustment strategy corresponding to the target application.

[0075] In the technical solution of the embodiment of the present invention, by obtaining a set of parameter information corresponding to a target application, if the data structure type of the target parameter information in the set of parameter information is a structured type, the relationship content in the target parameter information is determined based on a preset knowledge extraction task. If the data structure type of the target parameter information in the set of parameter information is an unstructured type, the basic content in the target parameter information is determined based on a preset basic class recognition rule. Furthermore, the relationship content and the basic content are combined and processed to obtain the basic knowledge content corresponding to the set of parameter information, and the basic knowledge content is combined and processed based on a preset knowledge graph construction rule to generate a knowledge graph corresponding to the target application. Further, based on a preset link prediction algorithm, the basic association relationships in the knowledge graph are analyzed and processed to obtain potential association relationships corresponding to the target application. Based on a preset potential problem recognition rule, the basic events in the knowledge graph are analyzed and processed to obtain potential problems corresponding to the target application. And the potential association relationships and the potential problems are combined and processed to obtain potential association content corresponding to the target application, and the knowledge graph and the potential association content are combined and processed to obtain target knowledge content corresponding to the target application. Finally, the current working parameters corresponding to the target application are obtained, the current association content corresponding to the current working parameters is determined in the target knowledge content based on the parameter names of the current working parameters, and a parameter adjustment strategy corresponding to the target application is generated based on the current operation content and the current association content of the current working parameters. Since the various target parameter information in the set of parameter information is integrated, and the potential association content is mined using the integrated knowledge graph, the problem of low data application efficiency and depth of technical parameters in the application program is solved. It is possible to integrate the information of the various parameters of the same application program on different platforms, improve the efficiency and depth of data application, realize the management of technical parameters, and ensure system stability and production safety.

[0076] Embodiment III

[0077] Figure 3 FIG. is a schematic structural diagram of an application parameter management device based on a knowledge graph provided in Embodiment III of the present invention. As Figure 3 shown, the device includes: a data acquisition module 310, a graph generation module 320, and a content determination module 330;

[0078] Among them, the data acquisition module 310 is configured to acquire a set of parameter information corresponding to a target application;

[0079] The graph generation module 320 is configured to perform knowledge extraction on the target parameter information based on the data structure type of each target parameter information in the set of parameter information to obtain the basic knowledge content corresponding to the set of parameter information, and combine and process the basic knowledge content based on a preset knowledge graph construction rule to generate a knowledge graph corresponding to the target application;

[0080] A content determination module 330, configured to analyze and process the knowledge graph based on a preset recognition rule, obtain potential associated content corresponding to the target application, and combine and process the knowledge graph and the potential associated content to obtain target knowledge content corresponding to the target application.

[0081] In the technical solution of the embodiment of the present invention, knowledge extraction is performed on target parameter information through the data structure types of the target parameter information in the parameter information set corresponding to the target application to obtain basic knowledge content corresponding to the parameter information set, and the basic knowledge content is combined and processed based on a preset knowledge graph construction rule to generate a knowledge graph corresponding to the target application. Furthermore, based on a preset recognition rule, the knowledge graph is analyzed and processed to obtain potential associated content corresponding to the target application, and the knowledge graph and the potential associated content are combined and processed to obtain target knowledge content corresponding to the target application. Since each target parameter information in the parameter information set is integrated, and the integrated knowledge graph is used to mine potential associated content, the problem of low data application efficiency and depth of technical parameters in the application program is solved. It can integrate the parameters of the same application program on different platforms, improve the efficiency and depth of data application, realize the management of technical parameters, and ensure system stability and production safety.

[0082] Optionally, the parameter information set may include: a parameter information registration form, a historical parameter management specification, and historical production problems.

[0083] Optionally, the graph generation module 320 may specifically be configured to:

[0084] If the data structure type of the target parameter information in the parameter information set is a structured type, determine the relationship type content in the target parameter information based on a preset knowledge extraction task;

[0085] If the data structure type of the target parameter information in the parameter information set is an unstructured type, determine the basic type content in the target parameter information based on a preset basic type recognition rule;

[0086] Combine and process the relationship type content and the basic type content to obtain basic knowledge content corresponding to the parameter information set.

[0087] Optionally, the basic type content may include: entity type content, concept type content, and event type content.

[0088] Optionally, the content determination module 330 may specifically be configured to:

[0089] Analyze and process the basic association relationships in the knowledge graph based on a preset link prediction algorithm to obtain potential association relationships corresponding to the target application;

[0090] Analyze and process the basic events in the knowledge graph based on the preset potential problem recognition rules to obtain the potential problems corresponding to the target application;

[0091] Combine and process the potential association relationships and potential problems to obtain the potential associated content corresponding to the target application.

[0092] Optionally, the content determination module 330 can specifically be used for:

[0093] Perform feature transformation on the basic events in the knowledge graph based on the target machine learning algorithm to obtain the feature vectors corresponding to the basic events;

[0094] Input the feature vectors into the target decision model to obtain the potential problems corresponding to the target application; wherein, the target decision model is a decision model trained based on historical production problems and historical events.

[0095] Optionally, the application parameter management device based on the knowledge graph may further include: a post-processing module, configured to, after combining and processing the knowledge graph and the potential associated content to obtain the target knowledge content corresponding to the target application, obtain the current working parameters corresponding to the target application;

[0096] Determine the current associated content corresponding to the current working parameters in the target knowledge content based on the parameter names of the current working parameters;

[0097] Generate a parameter adjustment strategy corresponding to the target application based on the current operation content and the current associated content of the current working parameters.

[0098] The application parameter management device based on the knowledge graph provided by the embodiments of the present invention can execute the application parameter management method based on the knowledge graph provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0099] Embodiment 4

[0100] Figure 4 FIG. shows a schematic structural diagram of an electronic device 410 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0101] AsFigure 4 As shown in the figure, the electronic device 410 includes at least one processor 420, and a memory communicatively connected to the at least one processor 420, such as a read-only memory (ROM) 430, a random access memory (RAM) 440, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 420 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 430 or the computer program loaded from the storage unit 490 into the random access memory (RAM) 440. In the RAM 440, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 420, the ROM 430, and the RAM 440 are connected to each other through a bus 450. The input / output (I / O) interface 460 is also connected to the bus 450.

[0102] Multiple components in the electronic device 410 are connected to the I / O interface 460, including: an input unit 470, such as a keyboard, a mouse, etc.; an output unit 480, such as various types of displays, speakers, etc.; a storage unit 490, such as a disk, an optical disc, etc.; and a communication unit 4100, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 4100 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0103] The processor 420 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 420 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 420 executes the various methods and processes described above, such as the application parameter management method based on a knowledge graph.

[0104] The method includes:

[0105] Obtaining a set of parameter information corresponding to a target application;

[0106] Performing knowledge extraction on the target parameter information based on the data structure type of each target parameter information in the parameter information set, obtaining basic knowledge content corresponding to the parameter information set, and combining and processing the basic knowledge content based on a preset knowledge graph construction rule to generate a knowledge graph corresponding to the target application;

[0107] Performing analysis and processing on the knowledge graph based on a preset recognition rule, obtaining potential associated content corresponding to the target application, and combining and processing the knowledge graph and the potential associated content to obtain target knowledge content corresponding to the target application.

[0108] In some embodiments, the method for managing application parameters based on a knowledge graph can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 490. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 410 via the ROM 430 and / or the communication unit 4100. When the computer program is loaded into the RAM 440 and executed by the processor 420, one or more steps of the method for managing application parameters based on a knowledge graph described above can be performed. Alternatively, in other embodiments, the processor 420 can be configured to execute the method for managing application parameters based on a knowledge graph by any other suitable means (e.g., by means of firmware).

[0109] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0113] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0114] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs that run on corresponding computers and have a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0115] The embodiments of the present application also disclose a computer program product, which includes a computer program that, when executed by a processor, implements the method for managing application parameters based on a knowledge graph provided in any embodiment of the present application. This program product and the method for managing application parameters based on a knowledge graph disclosed in each embodiment of the present application belong to the same inventive concept, so details are not described herein.

[0116] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0117] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for managing application parameters based on a knowledge graph, characterized in that Including: Obtain a set of parameter information corresponding to the target application; Based on the data structure types of the target parameter information in the set of parameter information, perform knowledge extraction on the target parameter information to obtain the basic knowledge content corresponding to the set of parameter information, and based on a preset knowledge graph construction rule, combine and process the basic knowledge content to generate a knowledge graph corresponding to the target application; Based on a preset recognition rule, analyze and process the knowledge graph to obtain potential associated content corresponding to the target application, and combine and process the knowledge graph and the potential associated content to obtain target knowledge content corresponding to the target application.

2. The method according to claim 1, wherein The set of parameter information includes: a parameter information registration form, a historical parameter management specification, and historical production problems.

3. The method according to claim 1, wherein The performing knowledge extraction on the target parameter information based on the data structure types of the target parameter information in the set of parameter information to obtain the basic knowledge content corresponding to the set of parameter information includes: If the data structure type of the target parameter information in the set of parameter information is a structured type, determine the relationship type content in the target parameter information based on a preset knowledge extraction task; If the data structure type of the target parameter information in the set of parameter information is an unstructured type, determine the basic type content in the target parameter information based on a preset basic type recognition rule; Combine and process the relationship type content and the basic type content to obtain the basic knowledge content corresponding to the set of parameter information.

4. The method according to claim 3, characterized in that, The basic type content includes: entity type content, concept type content, and event type content.

5. The method according to claim 1, characterized in that, The analyzing and processing the knowledge graph based on a preset recognition rule to obtain potential associated content corresponding to the target application includes: Based on a preset link prediction algorithm, analyze and process the basic association relationships in the knowledge graph to obtain potential association relationships corresponding to the target application; Based on a preset potential problem recognition rule, analyze and process the basic events in the knowledge graph to obtain potential problems corresponding to the target application; Combine and process the potential association relationships and the potential problems to obtain potential associated content corresponding to the target application.

6. The method according to claim 5, characterized in that, The analyzing and processing the basic events in the knowledge graph based on a preset potential problem recognition rule to obtain potential problems corresponding to the target application includes: Based on a target machine learning algorithm, perform feature transformation on the basic events in the knowledge graph to obtain feature vectors corresponding to the basic events; Input the feature vectors into a target decision model to obtain potential problems corresponding to the target application; wherein, the target decision model is a decision model trained based on historical production problems and historical events.

7. The method according to claim 1, characterized in that, After the combining and processing the knowledge graph and the potential associated content to obtain the target knowledge content corresponding to the target application, it further includes: Obtain the current working parameters corresponding to the target application; Based on the parameter names of the current working parameters, determine the current associated content corresponding to the current working parameters in the target knowledge content; Generate a parameter adjustment strategy corresponding to the target application based on the current operation content and the current associated content of the current working parameters.

8. An application parameter management device based on a knowledge graph, characterized in that, Including: A data acquisition module for obtaining a set of parameter information corresponding to the target application; A graph generation module, configured to perform knowledge extraction on the target parameter information based on the data structure types of the target parameter information in the parameter information set, obtain the basic knowledge content corresponding to the parameter information set, and generate a knowledge graph corresponding to the target application by combining and processing the basic knowledge content based on a preset knowledge graph construction rule; A content determination module, configured to analyze and process the knowledge graph based on a preset recognition rule, obtain potential associated content corresponding to the target application, and combine and process the knowledge graph and the potential associated content to obtain target knowledge content corresponding to the target application.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the knowledge graph-based application parameter management method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the processor to implement the knowledge graph-based application parameter management method according to any one of claims 1-7 when executed.

11. A computer program product, including a computer program, where the computer program, when executed by a processor, implements the knowledge graph-based application parameter management method according to any one of claims 1-7.

Images