Information query method and device, computer equipment, storage medium and computer program product

Abstract

The embodiment of the invention provides an information query method and device, computer equipment, a storage medium and a computer program product, and relates to the technical field of data processing. The method comprises the steps of receiving a configuration information query request triggered by a target object and sent by a query terminal, and obtaining to-be-queried text information according to the configuration information query request; obtaining an initial information query result corresponding to the configuration information query request according to the to-be-queried text information; obtaining object feature information of the target object; obtaining a target information query result corresponding to the configuration information query request by utilizing a large language model and a first cue word according to the initial information query result and the object feature information; the first cue word is used for guiding the large language model to obtain a target information query result; sending the target information query result to a query terminal; the query terminal is used for displaying the target information query result. According to the method, the accuracy of configuration information query is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an information query method, device, computer equipment, storage medium and computer program product. Background Art

[0002] For a data configuration system, for example, a configuration management database, a query service can usually be provided to users, and users can query the configuration management database for information technology configuration related information.

[0003] The current configuration management database mainly uses predefined rules and scripts to automatically update and manage data, and then provides query services to the outside world through pages and interfaces. When users make queries, they must first be routed to the specified resource page before they can retrieve as needed, which is cumbersome and inefficient. Summary of the invention

[0004] Based on this, it is necessary to provide an information query method, device, computer equipment, storage medium and computer program product to address the above technical issues.

[0005] In a first aspect, the present application provides an information query method. The method comprises:

[0006] Receiving a configuration information query request triggered by a target object sent by a query terminal, and acquiring text information to be queried according to the configuration information query request;

[0007] According to the text information to be queried, obtaining an initial information query result corresponding to the configuration information query request;

[0008] Acquire object feature information of the target object;

[0009] Using the large language model and the first prompt word, according to the initial information query result and the object feature information, obtaining the target information query result corresponding to the configuration information query request; the first prompt word is used to guide the large language model to obtain the target information query result;

[0010] The target information query result is sent to the query terminal; the query terminal is used to display the target information query result.

[0011] In one of the embodiments, obtaining the initial information query result corresponding to the configuration information query request based on the text information to be queried includes: using the large language model and the second prompt word to obtain an information query statement for the configuration information query request based on the text information to be queried; the second prompt word is used to guide the large language model to obtain the information query statement; according to the information query statement, obtaining the initial information query result corresponding to the configuration information query request in an information query database corresponding to a data configuration system; the data configuration system is used to manage configuration information of a target business system; and the information query database is used to store configuration information of the data configuration system.

[0012] In one of the embodiments, the use of the large language model and the second prompt word to obtain an information query statement for the configuration information query request according to the text information to be queried includes: using the large language model and the second prompt word to convert the initial data format of the text information to be queried into a target data format adapted to the information query database to obtain the information query statement; the second prompt word is used to guide the large language model to perform data format conversion on the text information to be queried to obtain the information query statement.

[0013] In one of the embodiments, the obtaining of the object feature information of the target object includes: obtaining basic object information and object interaction information of the target object from multiple associated data sources associated with the information query system; using the large language model and a third prompt word to obtain multiple query indicator feature information of the target object according to the object interaction information; the third prompt word is used to guide the large language model to obtain the multiple query indicator feature information of the target object according to the object interaction information; and obtaining the object feature information of the target object according to the basic object information and the multiple query indicator feature information.

[0014] In one of the embodiments, obtaining multiple query indicator feature information of the target object based on the object interaction information includes: determining multiple query indicators corresponding to the target object based on the object interaction information; fusing the object interaction information to obtain the query indicator information corresponding to each query indicator; and obtaining the multiple query indicator feature information of the target object based on the multiple query indicators and the query indicator information corresponding to each query indicator.

[0015] In one of the embodiments, the method further includes: acquiring system data of a data configuration system; performing data preprocessing on the system data to obtain optimized system data; converting a first data format of the optimized system data into a second data format adapted to a graph database according to preset data conversion rules to obtain synchronous system data corresponding to the optimized system data; synchronizing the synchronous system data to an information query database corresponding to the data configuration system; the database type of the information query database is a graph database.

[0016] In a second aspect, the present application provides an information query device. The device comprises:

[0017] A request receiving module, used for receiving a configuration information query request triggered by a target object sent by a query terminal, and obtaining text information to be queried according to the configuration information query request;

[0018] A first query result acquisition module, configured to acquire an initial information query result corresponding to the configuration information query request according to the text information to be queried;

[0019] An acquisition module, used to acquire object feature information of the target object;

[0020] A second query result acquisition module is used to obtain a target information query result corresponding to the configuration information query request according to the initial information query result and the object feature information by using a large language model and a first prompt word; the first prompt word is used to guide the large language model to obtain the target information query result;

[0021] The result display module is used to send the target information query result to the query terminal; the query terminal is used to display the target information query result.

[0022] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0023] Receiving a configuration information query request triggered by a target object sent by a query terminal, and acquiring text information to be queried according to the configuration information query request;

[0024] According to the text information to be queried, obtaining an initial information query result corresponding to the configuration information query request;

[0025] Acquire object feature information of the target object;

[0026] Using the large language model and the first prompt word, according to the initial information query result and the object feature information, obtaining the target information query result corresponding to the configuration information query request; the first prompt word is used to guide the large language model to obtain the target information query result;

[0027] The target information query result is sent to the query terminal; the query terminal is used to display the target information query result.

[0028] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0029] Receiving a configuration information query request triggered by a target object sent by a query terminal, and acquiring text information to be queried according to the configuration information query request;

[0030] According to the text information to be queried, obtaining an initial information query result corresponding to the configuration information query request;

[0031] Acquire object feature information of the target object;

[0032] Using the large language model and the first prompt word, according to the initial information query result and the object feature information, obtaining the target information query result corresponding to the configuration information query request; the first prompt word is used to guide the large language model to obtain the target information query result;

[0033] The target information query result is sent to the query terminal; the query terminal is used to display the target information query result.

[0034] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0035] Receiving a configuration information query request triggered by a target object sent by a query terminal, and acquiring text information to be queried according to the configuration information query request;

[0036] According to the text information to be queried, obtaining an initial information query result corresponding to the configuration information query request;

[0037] Acquire object feature information of the target object;

[0038] Using the large language model and the first prompt word, according to the initial information query result and the object feature information, obtaining the target information query result corresponding to the configuration information query request; the first prompt word is used to guide the large language model to obtain the target information query result;

[0039] The target information query result is sent to the query terminal; the query terminal is used to display the target information query result.

[0040] In the above-mentioned information query method, device, computer equipment, storage medium and computer program product, first, a configuration information query request triggered by a target object sent by a query terminal can be received, and the text information to be queried can be obtained according to the configuration information query request; next, the initial information query result corresponding to the configuration information query request can be obtained according to the text information to be queried; the object feature information of the target object can be obtained; further, the large language model and the first prompt word can be used to obtain the target information query result corresponding to the configuration information query request according to the initial information query result and the object feature information; the first prompt word is used to guide the large language model to obtain the target information query result; the target information query result is sent to the query terminal; the query terminal is used to display the target information query result. In the method provided by the embodiment of the present application, a large language model is introduced in the configuration information query process of the target object, and the large language model can be used to obtain the initial information query result corresponding to the configuration information query request according to the text information to be queried, which can improve the efficiency and accuracy of the configuration information query. Further, the preliminary information query result can be improved and optimized in combination with the object feature information of the target object to obtain the target information query result, which further improves the accuracy of the configuration information query. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 A flowchart of an information query method provided in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of a process for obtaining initial information query results provided in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of a process for obtaining object feature information provided in an embodiment of the present application;

[0045] Figure 4 A schematic diagram of a process for obtaining multi-query index feature information provided in an embodiment of the present application;

[0046] Figure 5A schematic diagram of a data synchronization process provided in an embodiment of the present application;

[0047] Figure 6 A structural block diagram of an information query device provided in an embodiment of the present application;

[0048] Figure 7 An internal structure diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] In an exemplary embodiment, Figure 1 As shown, an information query method is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0051] Step 102: receiving a configuration information query request triggered by a target object sent by a query terminal, and acquiring text information to be queried according to the configuration information query request.

[0052] Among them, the information query method provided by the present application can be applied to an information query system, and the information query system may include a data configuration system, an information query database corresponding to the data configuration system, a query terminal and a query server. In a possible implementation, the data configuration system may be a configuration management database (CMDB), which is a logical database that may contain information about the entire life cycle of configuration items and the relationships between configuration items, such as physical relationships, real-time communication relationships, non-real-time communication relationships, and dependencies. The configuration management database may store the configuration information of the enterprise's information technology (IT), and may include configuration information of IT configuration items (e.g., servers, network devices, applications, etc.) and their relationships. CMDB may include the following features: centralized storage and management: including hardware, software, network devices, servers, applications, documents, etc., to provide a comprehensive and accurate view. Relationship management: determine and define various relationships between configuration items. Data model design: create relevant tables and fields to store configuration items, attributes, and relationship information. Unification and standardization of equipment information: improve the maintainability and query efficiency of information. Visualization relationship: display the relationship between configuration items through a logical relationship diagram or a network diagram. Fast query and update: supports fast device information query and update. Based on ITIL standards: is a core component of the ITIL standard system. Dynamic scalability: can flexibly add configuration items, attributes and relationships, etc. Permission management: supports fine-grained data permission control. Open API service: facilitates integration and data sharing with other systems. In addition, the system data in the CMDB can be periodically synchronized to the information query database. The database type of the information query database can be a graph database. Specifically, first, the data conversion rules can be specified. The data conversion rules can include but are not limited to the synchronization type, synchronization cycle and synchronization format. The synchronization type can include full synchronization and incremental synchronization. The full synchronization may cover all data in the entire CMDB system, which is used to initialize the graph database or ensure the integrity of the data when the data structure changes significantly. Incremental synchronization focuses on the data that has been added, modified or deleted since the last synchronization to reduce the amount of data transmission and synchronization time, and improve system efficiency. For the synchronization cycle, a reasonable synchronization cycle can be set, such as daily, weekly or real-time synchronization. If the real-time requirement is high and the data is updated frequently, the synchronization period can be set as real-time synchronization to ensure that the data in the information query database remains up to date; if the system performance and resource requirements are high, the synchronization period can be set as daily or weekly. For the synchronization format, the first data structure and the first data format adapted to the CMDB system can be converted into the second data structure and the second data format adapted to the graph database.Next, the system data of the CMDB system may be cleansed, and further, the cleaned system data of the CMDB system may be converted into the data structure and data format of the adaptation graph database, and then, the system data of the CMDB system may be synchronized to the information query database.

[0053] The query terminal may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices and portable wearable devices. IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The query server may be a server for equipment operation and maintenance in the financial business system. The query server may be implemented by an independent server or a server cluster consisting of multiple servers. The query terminal may communicate with the query server through a network. The target object may be an information query person, who may register and log in to the information query system on the query terminal. The query terminal displays a configuration information query page in response to a login operation triggered by the information query person; the information query person may trigger a configuration information query request on the configuration information query page. The configuration information query request may contain text information to be queried; the text information to be queried may be in the form of keywords (e.g., configuration type), natural language (e.g., querying detailed information of a server named Server01) and / or entity-relationship structure.

[0054] Step 104: Obtain an initial information query result corresponding to the configuration information query request according to the text information to be queried.

[0055] Among them, in this step, the text information to be queried can be a natural language sentence. The query terminal can send the configuration information query request to the query server in response to the configuration information query request triggered by the information query personnel. The query server can obtain the information query statement corresponding to the text information to be queried according to the text information to be queried contained in the configuration information query request and the structure and data characteristics of the graph database, and obtain the initial information query result corresponding to the configuration information query request in the information query database corresponding to the CMDB system according to the information query statement.

[0056] Step 106: Obtain object feature information of the target object.

[0057] Among them, the target object may be an information query person, and the object feature information may be used to construct a user profile of the information query person. First, the object basic information and object interaction information of the target object may be obtained from multiple associated data sources associated with the information query system; the object basic information may be the user basic information of the information query person, such as user name, email address, department and position, etc., and the object interaction information may be the interaction information between the information query person and the information query system, and the associated system, such as the natural language query statement proposed by the user, the feedback on the query result (such as query evaluation and query demand, etc.), the dialogue content with the system, and the user's operation log in the CMDB system (such as login time, query frequency and operation type, etc.). Next, the object feature information of the target object may be obtained based on the object basic information and object interaction information, and the user profile of the information query person may be constructed based on the object feature information.

[0058] Step 108 , using the large language model and the first prompt word, according to the initial information query result and the object feature information, obtain the target information query result corresponding to the configuration information query request.

[0059] The first prompt word is used to guide the large language model to obtain the target information query result. In this step, the initial information query result for the configuration information query request and the user portrait of the information query person can be input into the large language model. Under the guidance of the first prompt word, the large language model can optimize the initial information query result according to the user portrait to obtain the target information query result.

[0060] Step 110, sending the target information query result to the query terminal; the query terminal is used to display the target information query result.

[0061] The query server obtains the target information query result for the configuration information query request, and may send the target information query result to the query terminal, and the query terminal may display the target information query result through a result display page.

[0062] In the method of this embodiment, first, a configuration information query request triggered by a target object sent by a query terminal can be received, and the text information to be queried can be obtained according to the configuration information query request; next, the initial information query result corresponding to the configuration information query request can be obtained according to the text information to be queried; the object feature information of the target object can be obtained; further, the target information query result corresponding to the configuration information query request can be obtained according to the initial information query result and the object feature information using a large language model and a first prompt word; the first prompt word is used to guide the large language model to obtain the target information query result; the target information query result is sent to the query terminal; the query terminal is used to display the target information query result. In the method provided by the embodiment of the present application, a large language model is introduced in the configuration information query process of the target object, and the large language model can be used to obtain the initial information query result corresponding to the configuration information query request according to the text information to be queried, which can improve the efficiency and accuracy of the configuration information query. Further, the preliminary information query result can be improved and optimized in combination with the object feature information of the target object to obtain the target information query result, thereby further improving the accuracy of the configuration information query.

[0063] In an exemplary embodiment, Figure 2 As shown, step 104 may include steps 202 to 204. Among them:

[0064] Step 202: using the large language model and the second prompt word, according to the text information to be queried, obtain an information query statement for the configuration information query request.

[0065] The second prompt word is used to guide the large language model to obtain the information query sentence.

[0066] Step 204: According to the information query statement, an initial information query result corresponding to the configuration information query request is obtained in the information query database corresponding to the data configuration system.

[0067] The data configuration system is used to manage the configuration information of the target business system; the information query database is used to store the configuration information of the data configuration system.

[0068] In an exemplary embodiment, step 202 may include: using a large language model and a second prompt word to convert the initial data format of the text information to be queried into a target data format adapted to the information query database to obtain an information query statement; the second prompt word is used to guide the large language model to perform data format conversion on the text information to be queried to obtain an information query statement.

[0069] The query server can input the text information to be queried contained in the configuration information query request into the large language model. Under the guidance of the second prompt word, the large language model can perform semantic understanding and analysis on the text information to be queried, and identify the query intention, for example, querying configuration objects (for example, servers and applications, etc.), query conditions (for example, running specific applications) and query purposes (for example, configuration information of configuration objects). Furthermore, the information query statement corresponding to the text information to be queried can be obtained in combination with the structure and data characteristics of the graph database, and the initial information query result corresponding to the configuration information query request can be obtained in the information query database corresponding to the CMDB system according to the information query statement; the data configuration system is used to manage the configuration information of the target business system; the information query database is used to store the configuration information of the data configuration system. In a possible implementation, the large language model and the second prompt word can be used to convert the initial data format of the text information to be queried into the target data format adapted to the information query database to obtain the information query statement, and the second prompt word is used to guide the large language model to convert the data format of the text information to be queried to obtain the information query statement. For example, the information query statement can be a Cypher statement. Cypher is the query language of the graph database Neo4j, which is used to retrieve and operate data in the graph. For example, for the above user query, the Cypher statement that may be generated is: "MATCH(s:Server)-[:RUNS]->(a:Application{name:'X'})RETURNs.configuration", which means to find the server node with a "RUNS" relationship with the application named "X" in the graph database and return its configuration information. Next, based on the query server, the information query statement generated by the large language model can be syntax checked and semantically verified to obtain the verified information query statement. Then, the information query statement can be used to traverse and search in the information query database, that is, the graph database, to obtain the initial information query result corresponding to the configuration information query request. For example, the graph database traverses and searches in the stored graph data structure according to the instructions of the Cypher statement, finds the nodes and relationships that meet the query conditions, and obtains the corresponding data.

[0070] In the method of this embodiment, a large language model can be used to convert the natural language input by the information query personnel into information query statements adapted to the graph database, which facilitates subsequent configuration information query in the information query database and improves the efficiency and accuracy of configuration information query.

[0071] In an exemplary embodiment, Figure 3 As shown, step 106 may include steps 302 to 306. Among them:

[0072] Step 302: Obtain basic object information and object interaction information of the target object from multiple associated data sources associated with the information query system.

[0073] Among them, the object basic information can be the user basic information of the information query person, such as user name, email, department and position, etc., and the object interaction information can be the interaction information between the information query person and the information query system, and related systems, such as natural language query statements proposed by the user, feedback on the query results (such as query evaluation and query requirements, etc.), dialogue content with the system, and user operation logs in the CMDB system (such as login time, query frequency and operation type, etc.).

[0074] Step 304 : using the large language model and the third prompt word, and according to the object interaction information, obtain multi-query index feature information of the target object.

[0075] Among them, multiple query indicators for the current query are pre-set, and then, based on the object interaction information, query indicator information corresponding to each of the multiple query indicators can be obtained. Then, based on the basic information of the object and the query indicator information corresponding to each of the multiple query indicators, a large language model and a third prompt word can be used to obtain multiple query indicator feature information of the target object.

[0076] Step 306: Obtain object feature information of the target object according to the object basic information and the multi-query index feature information.

[0077] Among them, a user portrait of the information query person can be constructed based on the object feature information.

[0078] In the method of this embodiment, a large language model can be used to construct a user profile of the information query person, thereby improving the efficiency and accuracy of user profile construction.

[0079] In an exemplary embodiment, Figure 4 As shown, step 304 may include steps 402 to 406. Among them:

[0080] Step 402: Determine multiple query indices corresponding to the target object based on the object interaction information.

[0081] Among them, the object interaction information can be divided into multi-dimensional indicators, and the query indicator information corresponding to each of the multiple query indicators can be extracted from the object interaction information. The multiple indicators can include but are not limited to configuration query information (for example, the application types frequently queried by users, the number of queries related to specific applications, etc.), business module information (for example, the query status of IT assets involved in the business processes or modules that users are concerned about), cluster and namespace information associated with cluster resources (for example, the user's query frequency for specific cluster resources, the query distribution under different namespaces, etc.), query time distribution (for example, the user's query activity in different time periods, judging the user's work habits and business peak periods) and query keyword distribution (analyzing the query keywords commonly used by users to understand the key IT assets or problem types that users are concerned about), etc.

[0082] Step 404: fuse the object interaction information to obtain query index information corresponding to each query index.

[0083] The object interaction information may come from multiple associated data sources, the data obtained from the multiple associated data sources may be integrated and fused, and the indicator data of each query indicator from different associated data sources may be integrated together to obtain query indicator information corresponding to each query indicator.

[0084] Step 406: Obtain multi-query index feature information of the target object according to the multiple query indexes and the query index information corresponding to each query index.

[0085] Among them, the basic information of the object of the information query person, multiple indicators and query indicator information of each indicator can be input into the large language model. Under the guidance of the third prompt word, the large language model fuses the object interaction information to obtain the query indicator information corresponding to each query indicator; according to the multiple query indicators and the query indicator information corresponding to each query indicator, the multi-query indicator feature information of the target object is obtained. The query indicator information under each query indicator may include multiple indicator values. For example, the large language model can process according to certain rules (for example, similarity, dimension, etc.). For some similar or repeated indicator values, the large language model determines whether they can be merged. If it is judged to be consistent, the records are merged, the number of times is added, and the new records after the merger and the list of merged old records (for clearing redundant data) are output. For example, if a user uses similar but not completely the same keywords in multiple queries to query the same type of IT assets, the large language model can identify the similarity of these keywords and merge the relevant query times. In addition, the large language model can also determine whether the person in charge of the configuration item is the information query person. If the person in charge of the configuration item is the information query person, a certain number of times will be added to highlight the user's attention and operation frequency of the configuration item he is responsible for. In this way, resources with a large number of queries and related to the person in charge will be given a higher priority in subsequent queries, which can better reflect the core needs and work priorities of the user. Thus, the large language model can output the query indicator feature information of each query indicator in the multiple query indicators of the information query person, and the query indicator feature information can include multiple indicator values. In a possible implementation method, the query indicator feature information under each query indicator can be screened out to find the indicator value that meets the preset data volume, for example, 10 types are taken from the resource types that users frequently query, and 10 query times are taken from the query time distribution. Finally, according to the basic information of the object of the information query person and the multi-query indicator feature information, the object feature information of the target object is obtained, and the user portrait of the information query person is constructed according to the object feature information.

[0086] In the method of this embodiment, a large language model can be used to construct a user profile of the information query person, thereby improving the efficiency and accuracy of user profile construction.

[0087] In an exemplary embodiment, Figure 5 As shown, before step 102, steps 502 to 508 may also be included. Among them:

[0088] Step 502: Acquire system data of the data configuration system.

[0089] The system data may be configuration information in the CMDB system, and may include configuration information of IT configuration items (e.g., servers, network devices, applications, etc.) and their relationships.

[0090] Step 504: preprocess the system data to obtain optimized system data.

[0091] Among them, the data preprocessing can include data cleaning, which can be performed on the system data of the CMDB system to obtain optimized system data, for example, to handle inconsistencies in the data, such as unifying naming specifications, standardizing asset names and attribute values ​​in different formats or with spelling errors, etc.; to handle missing values, you can choose to fill in default values, use mean / median (for numerical data) or infer and supplement based on related data. For example, for the missing server IP address field, if it can be reasonably inferred based on the subnet range where the server is located and the IP rules of other configured servers, it will be supplemented; otherwise, it can be temporarily marked as "unknown" or use a specific placeholder value to avoid the impact of missing data on subsequent analysis and queries.

[0092] Step 506: According to a preset data conversion rule, the first data format of the optimized system data is converted into the second data format of the adaptation graph database to obtain the synchronous system data corresponding to the optimized system data.

[0093] The preset data conversion rules may include data format conversion rules, data structure conversion rules and data synchronization strategies. The data format conversion rules and data structure conversion rules may be used to convert the optimized system data of the cleaned CMDB system to adapt to the data structure and data format of the graph database, that is, to convert the first data format of the optimized system data into the second data format adapted to the graph database, and obtain the synchronized system data corresponding to the optimized system data. Convert the relational data in the CMDB system into graph structure data. Determine the node type and attributes in the graph database, for example, map servers, network devices, etc. as nodes, and the node attributes may include device name, model, IP address, operating system version, etc. Define the relationship type between nodes, such as "connected", "running on", "belonging to", etc., to accurately represent the logical relationship between IT assets. For example, the record representing the association between an application and a server in the CMDB is converted into a "running on" relationship between an application node and a server node in the graph database, and may contain relationship attributes, such as startup time, port number, etc., to describe more details of the relationship. Through reasonable data conversion, ensure that data can be stored and queried in a suitable structure in the graph database.

[0094] Step 508, synchronizing the synchronization system data to the information query database corresponding to the data configuration system; the database type of the information query database is a graph database.

[0095] Among them, the synchronization tool can be used to synchronize the system data of the CMDB system in full and / or incrementally to the information query database according to the data synchronization strategy included in the data conversion rule.

[0096] In the method of this embodiment, the system data in the CMDB can be periodically synchronized to the information query database, and the database type of the information query database can be a graph database, which improves the simplicity and efficiency of information query.

[0097] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0098] Based on the same inventive concept, the embodiment of the present application also provides an information query device for implementing the above-mentioned information query method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more information query device embodiments provided below can refer to the limitations on the information query method above, and will not be repeated here.

[0099] In one embodiment, Figure 6 As shown, an information query device is provided, including: a request receiving module 602, a first query result obtaining module 604, an obtaining module 606, a second query result obtaining module 608 and a result display module 610, wherein:

[0100] The request receiving module 602 is used to receive a configuration information query request triggered by a target object sent by a query terminal, and obtain the text information to be queried according to the configuration information query request;

[0101] A first query result acquisition module 604 is used to acquire an initial information query result corresponding to the configuration information query request according to the text information to be queried;

[0102] An acquisition module 606 is used to acquire object feature information of the target object;

[0103] A second query result acquisition module 608 is used to obtain a target information query result corresponding to the configuration information query request according to the initial information query result and the object feature information by using a large language model and a first prompt word; the first prompt word is used to guide the large language model to obtain the target information query result;

[0104] The result display module 610 is used to send the target information query result to the query terminal; the query terminal is used to display the target information query result.

[0105] In one embodiment, the first query result acquisition module 604 is also used to: use the large language model and the second prompt word to obtain an information query statement for the configuration information query request according to the text information to be queried; the second prompt word is used to guide the large language model to obtain the information query statement; according to the information query statement, obtain the initial information query result corresponding to the configuration information query request in the information query database corresponding to the data configuration system; the data configuration system is used to manage the configuration information of the target business system; the information query database is used to store the configuration information of the data configuration system.

[0106] In one embodiment, the first query result acquisition module 604 is also used to: use the large language model and the second prompt word to convert the initial data format of the text information to be queried into a target data format adapted to the information query database to obtain the information query statement; the second prompt word is used to guide the large language model to perform data format conversion on the text information to be queried to obtain the information query statement.

[0107] In one embodiment, the acquisition module 606 is further used to: acquire basic object information and object interaction information of the target object from multiple associated data sources associated with the information query system; acquire multi-query indicator feature information of the target object according to the object interaction information using the large language model and the third prompt word; the third prompt word is used to guide the large language model to acquire the multi-query indicator feature information of the target object according to the object interaction information; and acquire the object feature information of the target object according to the object basic information and the multi-query indicator feature information.

[0108] In one embodiment, the acquisition module 606 is also used to: determine multiple query indicators corresponding to the target object based on the object interaction information; fuse the object interaction information to obtain the query indicator information corresponding to each query indicator; and obtain the multiple query indicator feature information of the target object based on the multiple query indicators and the query indicator information corresponding to each query indicator.

[0109] In one embodiment, the request receiving module 602 is also used to: obtain system data of the data configuration system; perform data preprocessing on the system data to obtain optimized system data; according to preset data conversion rules, convert the first data format of the optimized system data into a second data format adapted to the graph database to obtain synchronous system data corresponding to the optimized system data; synchronize the synchronous system data to the information query database corresponding to the data configuration system; the database type of the information query database is a graph database.

[0110] Each module in the above information query device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0111] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store information query related data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an information query method is implemented.

[0112] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0113] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0114] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0115] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0116] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0117] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0118] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0119] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An information query method, characterized in that: The method comprises: Receiving a configuration information query request triggered by a target object sent by a query terminal, and acquiring text information to be queried according to the configuration information query request; According to the text information to be queried, obtaining an initial information query result corresponding to the configuration information query request; Acquire object feature information of the target object; Using the large language model and the first prompt word, according to the initial information query result and the object feature information, obtaining the target information query result corresponding to the configuration information query request; the first prompt word is used to guide the large language model to obtain the target information query result; The target information query result is sent to the query terminal; the query terminal is used to display the target information query result.

2. The method according to claim 1, characterized in that The obtaining, according to the text information to be queried, an initial information query result corresponding to the configuration information query request includes: Using the large language model and the second prompt word, according to the text information to be queried, an information query sentence for the configuration information query request is obtained; the second prompt word is used to guide the large language model to obtain the information query sentence; According to the information query statement, the initial information query result corresponding to the configuration information query request is obtained in the information query database corresponding to the data configuration system; the data configuration system is used to manage the configuration information of the target business system; the information query database is used to store the configuration information of the data configuration system.

3. The method according to claim 2, characterized in that The method of using the large language model and the second prompt word to obtain an information query statement for the configuration information query request according to the text information to be queried includes: Using the large language model and the second prompt word, the initial data format of the text information to be queried is converted into a target data format adapted to the information query database to obtain the information query statement; the second prompt word is used to guide the large language model to convert the data format of the text information to be queried to obtain the information query statement.

4. The method according to claim 1, characterized in that The acquiring the object feature information of the target object includes: Acquire basic object information and object interaction information of the target object from a plurality of associated data sources associated with the information query system; Using the large language model and the third prompt word, according to the object interaction information, multiple query index feature information of the target object is obtained; the third prompt word is used to guide the large language model to obtain the multiple query index feature information of the target object according to the object interaction information; The object feature information of the target object is acquired according to the object basic information and the multi-query index feature information.

5. The method according to claim 4, characterized in that The acquiring, according to the object interaction information, multi-query index feature information of the target object includes: Based on the object interaction information, determining a plurality of query indicators corresponding to the target object; Fusing the object interaction information to obtain the query index information corresponding to each query index; The multiple query indicator feature information of the target object is obtained according to the multiple query indicators and the query indicator information corresponding to each query indicator.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Get system data of data configuration system; Performing data preprocessing on the system data to obtain optimized system data; According to a preset data conversion rule, the first data format of the optimized system data is converted into a second data format of the adaptation graph database to obtain the synchronization system data corresponding to the optimized system data; The synchronization system data is synchronized to the information query database corresponding to the data configuration system; the database type of the information query database is a graph database.

7. An information query device, characterized in that: The device comprises: A request receiving module, used for receiving a configuration information query request triggered by a target object sent by a query terminal, and obtaining text information to be queried according to the configuration information query request; A first query result acquisition module, used to acquire an initial information query result corresponding to the configuration information query request according to the text information to be queried; An acquisition module, used to acquire object feature information of the target object; A second query result acquisition module is used to obtain a target information query result corresponding to the configuration information query request according to the initial information query result and the object feature information by using a large language model and a first prompt word; the first prompt word is used to guide the large language model to obtain the target information query result; The result display module is used to send the target information query result to the query terminal; the query terminal is used to display the target information query result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images