CN118690026A - Operation and maintenance data processing method, device and server - Google Patents

Abstract

The specification provides a processing method, a processing device and a server for operation and maintenance data, and is applied to the field of artificial intelligence. Before specific implementation, a dynamic operation and maintenance map aiming at a target network system is constructed by comprehensively utilizing a digital twin technology and a knowledge graph; and in the idle time period, a data modeling layer of the dynamic operation and maintenance map is utilized to call a target operation and maintenance simulation model, and a corresponding operation and maintenance query result is obtained according to the hot spot operation and maintenance query problem in the current time period and is cached. When the method is implemented, after a target operation and maintenance data query request initiated by an operation and maintenance terminal based on a dynamic operation and maintenance map is received, a target operation and maintenance query problem is extracted; detecting whether the target operation and maintenance query problem exists in the cache hot spot problem list in the current time period; if the target operation and maintenance query result exists, the query is performed through routing to a cache module according to a preset routing rule, so that the target operation and maintenance query result is quickly found out and fed back to the operation and maintenance terminal. Therefore, the corresponding target operation and maintenance query result can be determined and fed back more efficiently and accurately.

Description

Operation and maintenance data processing method, device and server

Technical Field

This specification belongs to the field of artificial intelligence technology, and in particular to a method, device and server for processing operation and maintenance data.

Background Art

In financial business scenarios, large network systems such as bank transaction service platforms are mostly complex and changeable in structure, and involve a large number of managed devices. Accordingly, the operation and maintenance management of the above network systems usually involves a relatively large amount of data processing. Based on existing methods, when operation and maintenance personnel perform operation and maintenance management on the above network systems (for example, querying and locating faulty equipment in the network system, etc.), they mostly need to rely on operation and maintenance personnel to manually perform a large amount of verification and testing, which has the problems of low processing efficiency, long processing time, and easy error.

To address the above problems, no effective solution has been proposed yet.

Summary of the invention

The present specification provides a method, device and server for processing operation and maintenance data, which can efficiently and accurately determine and feedback a target operation and maintenance query result corresponding to a target operation and maintenance data query request, effectively reducing the user's waiting time.

This specification provides a method for processing operation and maintenance data, which is applied to a server and includes:

Receive a target operation and maintenance data query request initiated by an operation and maintenance terminal based on a dynamic operation and maintenance map; wherein the dynamic operation and maintenance map is an operation and maintenance knowledge graph tool for a target network system; the dynamic operation and maintenance map comprises at least a data collection layer and a data modeling layer; the data collection layer is used to collect device parameters of managed devices in the connected target network system; the data modeling layer is used to construct a target operation and maintenance simulation model for the target network system based on digital twins and knowledge graphs using the device parameters of the managed devices;

According to the preset instantiation processing rules, by processing the target operation and maintenance data query request, a target operation and maintenance query question that meets the requirements is extracted;

Detect whether the target operation and maintenance query problem exists in the cache hot problem list of the current time period; wherein the cache hot problem list of the current time period includes the hot operation and maintenance query problem of the current time period; the cache hot problem list of the current time period is associated with a cache module; the cache module is responsible for storing the operation and maintenance query results corresponding to the hot operation and maintenance query problem of the current time period; the operation and maintenance query results are obtained by calling and running the target operation and maintenance simulation model based on the hot operation and maintenance query problem of the current time period by the server in the idle time period;

When it is determined that the target operation and maintenance query problem exists in the cache hot problem list of the current time period, the target operation and maintenance data query request carrying the target operation and maintenance query problem is routed to the cache module for data query according to the preset routing rules;

Obtain a target operation and maintenance query result corresponding to the target operation and maintenance query question fed back by the cache module; and send the target operation and maintenance query result to the operation and maintenance terminal; wherein the operation and maintenance terminal is an initiating terminal for the target operation and maintenance data query request.

In one embodiment, the dynamic operation and maintenance map further includes: a business function layer; wherein the business function layer is connected to the operation and maintenance terminal; the business function layer supports users to initiate operation and maintenance data query requests of various business types through the operation and maintenance terminal;

The operation and maintenance data query requests of the multiple business types include: a faulty equipment location query request, a connection path navigation query request, and a connection path road condition query request.

In one embodiment, the dynamic operation and maintenance map also includes: a maintenance management layer; wherein the maintenance management layer is used to monitor the health status of the target network system according to the simulation calculation results output by the data modeling layer; when an abnormality is detected in the health status of the target network system, an operation and maintenance strategy for the target network system is generated according to the simulation calculation results.

In one embodiment, according to a preset instantiation processing rule, by processing the target operation and maintenance data query request, a target operation and maintenance query question that meets the requirements is extracted, including:

According to the preset instantiation processing rules, the initial question is extracted from the target operation and maintenance data query request;

Match the questions according to the preset reference question list and the initial question to obtain the corresponding matching results;

According to the matching result, when it is determined that the matching fails, semantic recognition is performed on the initial question to obtain a corresponding semantic recognition result;

Performing word segmentation processing on the semantic recognition result; and extracting question keywords based on the semantic recognition result after word segmentation processing;

Based on the question keywords, multiple pending questions are obtained by querying the knowledge graph associated with the target network system;

From the multiple pending questions, select target operation and maintenance query questions that meet the requirements.

In one embodiment, after matching questions according to the preset reference question list and the initial question to obtain corresponding matching results, the method further includes:

According to the matching result, when it is determined that the match is successful, a reference question matching the initial question is determined from a preset reference question list as the target operation and maintenance query question.

In one embodiment, after detecting whether the target operation and maintenance query problem exists in the cache hotspot problem list in the current time period, the method further includes:

When it is determined that the target operation and maintenance query problem does not exist in the cache hot problem list of the current time period, the target operation and maintenance data query request carrying the target operation and maintenance query problem is routed to the data modeling layer according to the preset routing rules, so as to call the target operation and maintenance simulation model to perform simulation calculation based on the target operation and maintenance query problem;

Obtain the target simulation calculation result output by the data modeling layer; and send the target simulation calculation result to the operation and maintenance terminal.

In one embodiment, calling the target operation and maintenance simulation model to perform simulation calculation based on the target operation and maintenance query problem includes:

According to the target operation and maintenance query question, by querying the knowledge graph associated with the target network system, the starting device, the ending device, and the associated device are determined; wherein the associated device includes a directly associated device and/or an indirectly associated device;

Obtain and use the link address of the starting device, the link address of the ending device, and the link address of the associated device to construct a target link address matrix;

According to the attribute information of the device area, the target link address matrix is split into a plurality of sub-link address matrices;

Calling the target operation and maintenance simulation model to perform parallel simulation operations according to multiple sub-link address matrices to obtain multiple sub-simulation operation results;

According to the attribute information of the device area, multiple sub-simulation operation results are combined to obtain the target simulation operation result.

In one embodiment, after extracting a target operation and maintenance query question that meets the requirements by processing the target operation and maintenance data query request according to a preset instantiation processing rule, the method further includes:

The target operation and maintenance query question and the query time corresponding to the target operation and maintenance query question are recorded in the query log.

In one embodiment, the method further comprises:

At preset time intervals, obtain the operation and maintenance query problem records of the current time period based on the query log;

According to the operation and maintenance query problem records, the query popularity value of the operation and maintenance query problem in the current time period is obtained by statistics;

Filter out hot O&M issues in the current time period based on the query popularity of the O&M query issues in the current time period;

According to the hot operation and maintenance problems in the current time period, the cache hot problem list of the previous time period is updated to obtain the cache hot problem list of the current time period.

In one embodiment, the method further comprises:

Check whether the current idle time period meets the preset trigger conditions;

When it is determined that the current idle time period meets the preset triggering condition, the target operation and maintenance simulation model is called through the data modeling layer to process the unmarked hot issues in the cache hot issue list of the current time period;

Obtain the simulation calculation results for the hot issue output by the data modeling layer; and mark the hot issue accordingly in the cached hot issue list of the current time period;

The simulation results of the hot issue are sent to the cache module for caching.

In one embodiment, the cache module is connected to a SQL database and a graph database;

Correspondingly, after receiving the simulation operation result, the cache module determines the data format type of the simulation operation result; and stores the simulation operation result in a matching database according to the data format type of the simulation operation result.

In one embodiment, after obtaining the target operation and maintenance query result corresponding to the target operation and maintenance query question fed back by the cache module, the method further includes:

According to the target operation and maintenance query result, query the knowledge graph associated with the target network system to obtain target associated data related to the target operation and maintenance query result;

Generate visual display data based on the target operation and maintenance query results and target related data;

The visualized result display data is sent to the operation and maintenance terminal.

This specification also provides a device for processing operation and maintenance data, including:

A receiving module is used to receive a target operation and maintenance data query request initiated by an operation and maintenance terminal based on a dynamic operation and maintenance map; wherein the dynamic operation and maintenance map is an operation and maintenance knowledge graph tool for a target network system; the dynamic operation and maintenance map comprises at least a data acquisition layer and a data modeling layer; the data acquisition layer is used to acquire device parameters of managed devices in the connected target network system; the data modeling layer is used to construct a target operation and maintenance simulation model for the target network system based on digital twins and knowledge graphs using the device parameters of the managed devices;

An extraction module is used to extract target operation and maintenance query questions that meet the requirements by processing the target operation and maintenance data query request according to a preset instantiation processing rule;

A detection module is used to detect whether the target operation and maintenance query problem exists in the cache hot problem list of the current time period; wherein the cache hot problem list of the current time period includes the hot operation and maintenance query problem of the current time period; the cache hot problem list of the current time period is associated with a cache module; the cache module is responsible for storing the operation and maintenance query results corresponding to the hot operation and maintenance query problem of the current time period; the operation and maintenance query results are obtained by calling and running the target operation and maintenance simulation model based on the hot operation and maintenance query problem of the current time period by the server in the idle time period;

A routing module is used to route the target operation and maintenance data query request carrying the target operation and maintenance query question to the cache module for data query according to a preset routing rule when it is determined that the target operation and maintenance query question exists in the cache hotspot question list in the current time period;

The feedback module is used to obtain the target operation and maintenance query result corresponding to the target operation and maintenance query question fed back by the cache module; and send the target operation and maintenance query result to the operation and maintenance terminal; wherein the operation and maintenance terminal is the initiating terminal of the target operation and maintenance data query request.

The present specification also provides a server, comprising a processor and a memory for storing processor executable instructions, wherein the processor implements relevant steps of the method for processing operation and maintenance data when executing the instructions.

The present specification also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the relevant steps of the method for processing operation and maintenance data are implemented.

Based on the operation and maintenance data processing method, device and server provided in this specification, before specific implementation, the digital twin technology and knowledge graph can be used to construct a dynamic operation and maintenance map for the target network system; wherein, the dynamic operation and maintenance map at least includes a data modeling layer and a data acquisition layer; the data acquisition layer is used to collect the equipment parameters of the managed devices in the connected target network system; the data modeling layer is used to use the equipment parameters of the managed devices to construct a target operation and maintenance simulation model for the target network system based on the digital twin technology and knowledge graph; wherein, the target operation and maintenance simulation model is associated with the knowledge graph of the target network system. Further, the server will also regularly update the hot operation and maintenance query problems in the cached hot problem list of the current time period; and in the idle time period, without affecting the normal business data processing, the target operation and maintenance simulation model is called through the data modeling layer to perform simulation calculations in advance according to the hot operation and maintenance query problems of the current time period to obtain the corresponding simulation calculation results as the corresponding operation and maintenance query results; and then introduce a cache mechanism to send the above operation and maintenance query results to the cache module for caching for subsequent retrieval and use. In specific implementation, after receiving the target operation and maintenance data query request initiated by the operation and maintenance terminal based on the dynamic operation and maintenance map, the server can first extract the target operation and maintenance query problem that meets the requirements according to the preset instantiation processing rules; then detect whether the target operation and maintenance query problem exists in the cache hot problem list of the current time period; if so, according to the preset routing rules, the target operation and maintenance data query request carrying the target operation and maintenance query problem is preferentially routed to the cache module for data query, avoiding the on-site call of the target operation and maintenance simulation model for online simulation calculation, and quickly find the corresponding target operation and maintenance query result from the cache database and feedback it to the operation and maintenance terminal. In this way, the corresponding target operation and maintenance query result can be determined and fed back more efficiently and accurately, effectively reducing the waiting time of users.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

FIG1 is a flow chart of a method for processing operation and maintenance data provided by an embodiment of the present specification;

FIG2 is a schematic diagram of an embodiment of a method for processing operation and maintenance data provided by an embodiment of this specification in a scenario example;

FIG3 is a schematic diagram of an embodiment of a method for processing operation and maintenance data provided by an embodiment of this specification in a scenario example;

FIG4 is a schematic diagram of an embodiment of a method for processing operation and maintenance data provided by an embodiment of this specification in a scenario example;

FIG5 is a schematic diagram of an embodiment of a method for processing operation and maintenance data provided by an embodiment of this specification in a scenario example;

FIG6 is a schematic diagram of an embodiment of a method for processing operation and maintenance data provided by an embodiment of this specification in a scenario example;

FIG7 is a schematic diagram of an embodiment of a method for processing operation and maintenance data provided by an embodiment of this specification in a scenario example;

FIG8 is a schematic diagram of the structure of a server provided by an embodiment of the present specification;

FIG9 is a schematic diagram of the structure of a device for processing operation and maintenance data provided by an embodiment of the present specification;

FIG10 is a schematic diagram of an embodiment of a method for processing operation and maintenance data provided in an embodiment of this specification, in a scenario example.

DETAILED DESCRIPTION

In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be described clearly and completely below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

Referring to FIG. 1 , an embodiment of the present specification provides a method for processing operation and maintenance data. The method is specifically applied to the server side. When implemented, the method may include the following contents:

S101: Receive a target operation and maintenance data query request initiated by an operation and maintenance terminal based on a dynamic operation and maintenance map; wherein the dynamic operation and maintenance map is an operation and maintenance knowledge graph tool for a target network system; the dynamic operation and maintenance map comprises at least a data acquisition layer and a data modeling layer; the data acquisition layer is used to acquire device parameters of managed devices in the connected target network system; the data modeling layer is used to construct a target operation and maintenance simulation model for the target network system based on digital twins and knowledge graphs using the device parameters of the managed devices;

S102: extracting target operation and maintenance query questions that meet the requirements by processing the target operation and maintenance data query request according to a preset instantiation processing rule;

S103: Detect whether the target operation and maintenance query problem exists in the cache hot problem list of the current time period; wherein the cache hot problem list of the current time period includes the hot operation and maintenance query problem of the current time period; the cache hot problem list of the current time period is associated with a cache module; the cache module is responsible for storing the operation and maintenance query results corresponding to the hot operation and maintenance query problem of the current time period; the operation and maintenance query results are obtained by calling and running the target operation and maintenance simulation model based on the hot operation and maintenance query problem of the current time period by the server in the idle time period;

S104: When it is determined that the target operation and maintenance query problem exists in the cache hot problem list of the current time period, the target operation and maintenance data query request carrying the target operation and maintenance query problem is routed to the cache module for data query according to a preset routing rule;

S105: Obtain a target operation and maintenance query result corresponding to the target operation and maintenance query question fed back by the cache module; and send the target operation and maintenance query result to the operation and maintenance terminal; wherein the operation and maintenance terminal is an initiating terminal of the target operation and maintenance data query request.

Based on the above embodiments, on the one hand, digital twin technology and knowledge graph technology are introduced and utilized to construct a dynamic operation and maintenance map for the target network system; wherein, the dynamic operation and maintenance map at least includes a data modeling layer and a data acquisition layer; the data acquisition layer is used to automatically acquire and update the device parameters of the corresponding managed devices in the target network system; the data modeling layer is used to use the device parameters of the managed devices to construct a target operation and maintenance simulation model for the target network system; at the same time, the target operation and maintenance simulation model is also associated with the knowledge graph of the target network system. Based on the above dynamic operation and maintenance map, the server can use the target operation and maintenance simulation model in combination with the knowledge graph, and accurately obtain the corresponding operation and maintenance query results through simulation calculations to meet the user's diverse operation and maintenance query needs. On the other hand, a cache mechanism is also introduced, and the server regularly updates the hot operation and maintenance query problems in the cache hot problem list of the current time period; and in the idle time period, without affecting the normal business data processing, the target operation and maintenance simulation model is called to perform simulation calculations in advance according to the hot operation and maintenance query problems in the current time period to obtain the corresponding operation and maintenance query results; and then the above operation and maintenance query results are sent to the cache module for caching for subsequent use. Based on the above-mentioned cache mechanism, after receiving the target operation and maintenance data query request and extracting the corresponding target operation and maintenance query question, the server can first search whether the question exists in the cache hot question list of the current time period; if it does, there is no need to call the target operation and maintenance simulation model on site to perform simulation calculations with huge amounts of data. Instead, it can be directly routed to the cache module according to the preset routing rules, and the corresponding target operation and maintenance query results can be quickly queried and fed back to the operation and maintenance terminal in a timely manner, thereby effectively reducing the user's waiting time and improving the overall processing efficiency.

In some embodiments, the above-mentioned operation and maintenance data processing method can be specifically applied to the server side, wherein the server can specifically be an operation and maintenance server of the transaction service platform.

Specifically, the server may include a background server capable of realizing functions such as data transmission and data processing. Specifically, the server may be, for example, an electronic device having data calculation, storage and network interaction functions. Alternatively, the server may also be a software program running in the electronic device to provide support for data processing, storage and network interaction. In this embodiment, the number of the servers is not specifically limited. The server may be one server, or several servers, or a server cluster formed by several servers.

The target network system may specifically be a backend data processing system of a transaction service platform. Specifically, the target network system may be connected to a plurality of managed devices, such as ATM machines, servers, teller machines, surveillance cameras, computers, routers, switches, etc. Further, the managed devices included in the target network system may be divided into a plurality of business function areas based on the attribute information of the device area (e.g., business function attributes, etc.), such as a database area, a security area, a settlement area, etc.

The above-mentioned dynamic operation and maintenance map can be specifically understood as an operation and maintenance knowledge graph tool constructed for the target network system by using digital twin technology and knowledge graph technology in advance.

Among them, the above-mentioned digital twin technology can specifically refer to a simulation technology that makes full use of physical models, monitoring data updates, operation history and other data, integrates multi-disciplinary, multi-physical quantities, multi-scales, and multi-probabilities. Based on the above-mentioned digital twin technology, it can complete the mapping of the target network system in the virtual space, and then accurately and finely reflect the full life cycle operation process of each managed device corresponding to the target network system.

The above-mentioned knowledge graph can specifically refer to a structured semantic knowledge base, which is used to describe concepts and their relationships in the physical world in symbolic form. Its basic component unit is the "entity-relationship-entity" triple, as well as the entity and its related attribute-value pairs. Entities are connected to each other through relationships to form a network knowledge structure.

The above-mentioned operation and maintenance knowledge graph tool can be specifically understood as a tool software suitable for operation and maintenance scenarios, which is configured with a knowledge graph corresponding to the target network system, and can realize operation and maintenance data query and operation and maintenance status management of the target network system based on the knowledge graph and combined with digital twin technology.

Among them, the knowledge graph of the target network system can at least include the attribute information of each managed device in the target network system, as well as the connection relationship between different managed devices. Specifically, each node in the knowledge graph of the target network system corresponds to a managed device, and the edges between different nodes correspond to the connection relationship between different managed devices. Furthermore, the device identification and attribute information of the corresponding managed device can be marked at the node position in the knowledge graph; the attribute information of the corresponding connection relationship can also be marked at the edge position.

Specifically, referring to FIG. 2 , the above-mentioned dynamic operation and maintenance map at least includes a data collection layer and a data modeling layer.

The data collection layer may be connected to each managed device in the target network system in a wired or wireless manner. Furthermore, the data collection layer may deploy monitoring threads on each connected managed device.

Accordingly, the data collection layer can obtain the configuration parameters of the managed devices through the data connection with the managed devices, such as the device identification, physical address, CPU model, routing table entries, arp table entries, mac table entries, etc. of the managed devices; in addition, the data collection layer can also obtain the operating parameters of the managed devices through real-time or scheduled collection of monitoring threads, such as the CPU occupancy rate of the managed devices, the network communication speed of the managed devices, the response time of the managed devices, etc. The data collection layer can then combine the basic information and operating parameters of the managed devices to obtain the device parameters of the managed devices.

The data modeling layer can be specifically connected to the data acquisition layer. The data modeling layer can use the device parameters of the managed devices of the target network system collected by the data acquisition layer, based on the digital twin technology, combined with the knowledge graph of the target network system, to construct a target operation and maintenance simulation model for the target network system and associated with the knowledge graph of the target network system.

Among them, the above-mentioned target operation and maintenance simulation model can utilize the device parameters of the managed devices in the target network system, simulate the actual network between the managed devices in the target network system, and related network behaviors, and perform simulation operations to accurately determine the current operation status of the target network system, or predict the future operation status of the target network system.

Furthermore, the above-mentioned data modeling layer can also support calling the target operation and maintenance simulation model to simulate part of the structure or all of the structure in the target network system based on the device parameters of the relevant managed devices.

In some embodiments, as shown in FIG. 2 , the dynamic operation and maintenance map may further include a business function layer (or core capability layer); wherein the business function layer may be specifically connected to the operation and maintenance terminal; and the business function layer supports users to initiate operation and maintenance data query requests of various business types through the operation and maintenance terminal;

The operation and maintenance data query requests of the multiple business types may specifically include: a faulty equipment location query request, a connection path navigation query request, a connection path road condition query request, and the like.

The above-mentioned path navigation can be specifically understood as the navigation of the data interaction connection path between the specified managed devices that the user is concerned about. The above-mentioned connection path traffic status can specifically include the operation status of the connection path itself (for example, whether the connection path is currently congested), and the operation status of other managed devices involved in the connection path (for example, the operation status of the server passed by the connection path).

Of course, it should be noted that the operation and maintenance data query request listed above is only an illustrative description. In specific implementation, according to specific business scenarios and processing requirements, the above operation and maintenance data query request may also include other types of operation and maintenance data query requests. This specification does not limit this.

Based on the above embodiments, users can connect to the business function layer through the operation and maintenance terminal, use the corresponding business functions in the business function layer, and perform diversified operation and maintenance data queries to meet the user's diverse operation and maintenance query needs.

Specifically, the business function layer is also connected to the knowledge graph of the target network system. The business function layer can be connected to the data modeling layer.

In specific implementation, a data interface connected to the above-mentioned business function layer can be established by installing a client APP of a dynamic operation and maintenance map on the operation and maintenance terminal. Accordingly, the user can enter the above-mentioned business function layer through the data interface and initiate a corresponding operation and maintenance data query request to the server to query the operation and maintenance data of interest. At the same time, the business function layer can also combine the knowledge graph to visualize the queried operation and maintenance data to obtain visualized data similar to an electronic map; and then display it to the user through the operation and maintenance terminal. This allows users to have a better interactive experience.

The above-mentioned operation and maintenance terminal may specifically include a front end applied to the user (e.g., the operation and maintenance personnel of the target network system) side, which can realize functions such as data collection and data transmission. Specifically, the operation and maintenance terminal may be, for example, an electronic device such as a desktop computer, a tablet computer, a laptop computer, a smart phone, etc. Alternatively, the operation and maintenance terminal may also be a software application that can be run in the above-mentioned electronic devices.

In some embodiments, referring to FIG. 2 , the dynamic operation and maintenance map may further include: a maintenance management layer (or upper application layer); wherein the maintenance management layer may be specifically used to monitor the health status of the target network system according to the simulation calculation results output by the data modeling layer; when an abnormality is detected in the health status of the target network system, an operation and maintenance strategy for the target network system is generated according to the simulation calculation results.

Based on the above embodiments, the maintenance management layer can be used to automatically monitor the health status of the target network system in real time or at a scheduled time. When it is determined that there is an abnormality in the health status of the target network system, a corresponding operation and maintenance strategy can be automatically generated so that the abnormality can be eliminated in time based on the operation and maintenance strategy to improve the stability and health of the target network system.

The maintenance management layer is specifically configured with at least a preset anomaly detection model, and may also be configured with a preset policy set.

The above-mentioned preset anomaly detection model can be specifically understood as a neural network model that is pre-trained based on artificial intelligence technology using the historical maintenance records of the target network system and the target operation and maintenance simulation model, and can analyze and determine whether the network system is abnormal and the specific type of abnormality based on the operation and maintenance simulation results of the input network system. The above-mentioned preset strategy set can specifically include multiple preset template operation and maintenance strategies; each preset template operation and maintenance strategy corresponds to an abnormality type.

In specific implementation, the maintenance management layer can periodically call the preset anomaly detection model to process the system simulation operation results output by the data modeling layer for the target network system as a whole; then use the preset anomaly detection model to process the system simulation operation results to obtain the corresponding anomaly detection results; according to the anomaly detection results, determine whether there is an anomaly in the health status of the target network system, and when it is determined that there is an anomaly in the health status of the target network system, further determine the anomaly type according to the anomaly detection results; then retrieve the preset policy set to determine the preset template operation and maintenance policy that matches the anomaly type as the operation and maintenance policy for the target network system. Then, the operation and maintenance policy can be displayed to the user, or executed within a certain authority to eliminate the anomaly in the target network system. In this way, the target network system can be automatically maintained to operate normally.

Before specific implementation, the historical operation and maintenance records of the target network system can be obtained, and the equipment parameters and sample equipment parameters of the relevant managed equipment in the relevant target network system can be extracted from the historical operation and maintenance records; the sample equipment parameters are then processed by the target operation and maintenance simulation model to obtain the corresponding sample operation simulation results as sample data; the sample data is labeled (including abnormality labeling and abnormality type labeling) according to the abnormal record information in the historical operation and maintenance records corresponding to the sample data to obtain labeled sample data; the labeled sample data is then used to train the initial classification model to obtain a preset anomaly detection model that meets the requirements.

Before specific implementation, the historical operation and maintenance records of the target network system can be obtained, and the historical operation and maintenance records with abnormalities in the abnormal record information can be screened out from the historical operation and maintenance records to obtain abnormal historical operation and maintenance records, and the abnormal type of the abnormal historical operation and maintenance records can be determined according to the abnormal record information. Operation and maintenance operation records are extracted from the abnormal historical operation and maintenance records; and the operation and maintenance operation records are spliced with the abnormal type to obtain sample abnormal operation records. In addition, considering that the proportion of real abnormal historical operation and maintenance records in the historical operation and maintenance records is relatively small, further, the remaining normal historical operation and maintenance records in the historical operation and maintenance records can be modified and adjusted to obtain modified historical operation and maintenance records; then the target operation and maintenance simulation model and the preset abnormality detection model are used to process the above-mentioned modified historical operation and maintenance records in turn to screen out the historical operation and maintenance records with abnormalities as expanded abnormal operation and maintenance records, as well as the abnormal type of the expanded abnormal operation and maintenance records; then expert experience is used to generate operation and maintenance operation records for the expanded abnormal operation and maintenance records based on the expanded abnormal operation and maintenance records and the corresponding abnormal type; and the operation and maintenance operation records are spliced with the abnormal type to obtain the expanded abnormal operation record. The expanded abnormal operation records and the sample abnormal operation records are then mixed, and the mixed abnormal operation records are clustered to obtain a combination of multiple groups of abnormal operation steps corresponding to multiple different abnormal types, as corresponding multiple preset template operation and maintenance strategies; and then a preset strategy set is established.

In some embodiments, referring to FIG. 3 , the above-mentioned target operation and maintenance query questions meeting the requirements are extracted by processing the target operation and maintenance data query request according to the preset instantiation processing rules. When implemented specifically, the following contents may be included:

S1: extracting the initial question from the target operation and maintenance data query request according to the preset instantiation processing rules;

S2: Matching questions according to the preset reference question list and the initial question to obtain corresponding matching results;

S3: Based on the matching result, if it is determined that the matching fails, semantic recognition is performed on the initial question to obtain a corresponding semantic recognition result;

S4: performing word segmentation processing on the semantic recognition result; and extracting question keywords based on the semantic recognition result after word segmentation processing;

S5: Based on the question keywords, multiple pending questions are obtained by querying the knowledge graph associated with the target network system;

S6: Filter out target operation and maintenance query questions that meet the requirements from the multiple pending questions.

Based on the above embodiment, the server can automatically and accurately extract from the target operation and maintenance data query request questions that the server can recognize and can characterize the user's operation and maintenance query demands in a standardized form as target operation and maintenance query questions that meet the requirements, so as to facilitate subsequent specific use and further data processing.

In specific implementation, the server may locate a specified question field in the target operation and maintenance data query request according to the format template of the query request, and then extract the initial question based on the question field.

Next, the initial question may be used to perform feature vector matching in a preset reference question list to obtain a corresponding matching result. The preset reference question list may specifically include a plurality of common reference questions that meet standard requirements.

According to the results, when it is determined that the match is successful, the reference question in the preset reference question list that matches the initial question is determined as the target operation and maintenance query question. On the contrary, when it is determined that the match fails, the initial question can be semantically recognized to obtain the corresponding semantic recognition result; through word segmentation processing, based on the semantic recognition result after word segmentation processing, combined with specific grammatical rules and keyword library, the required question keywords are extracted. Furthermore, according to the question keywords, combined with the preset reference question list, multiple pending questions can be obtained by querying the knowledge graph of the target network system. Then, the feature distance between each pending question and the initial question is calculated respectively, and the pending question with the smallest feature distance is selected as the target operation and maintenance query question that meets the requirements.

In some embodiments, after matching questions according to the preset reference question list and the initial question to obtain corresponding matching results, the method may further include the following when implemented:

According to the matching result, when it is determined that the match is successful, a reference question matching the initial question is determined from a preset reference question list as the target operation and maintenance query question.

Based on the above embodiment, a preset reference question list can be used to quickly determine target operation and maintenance query questions that meet the requirements through question matching.

In some embodiments, when it is determined that the target operation and maintenance query problem exists in the cache hot problem list of the current time period, the server can add the target operation and maintenance query problem to the target operation and maintenance data query request according to the preset routing rules; and then route the target operation and maintenance data query request carrying the target operation and maintenance query problem to the cache module. The cache module receives and responds to the target operation and maintenance data query request, retrieves the connected cache database according to the target operation and maintenance query problem carried, and finds the target operation and maintenance query result corresponding to the target operation and maintenance query problem in combination with the correspondence between the problems stored in the cache database and the simulation operation results, and returns the target operation and maintenance query result to the server. The server can then feed back the above-mentioned target operation and maintenance query result to the operation and maintenance terminal. Among them, the cache database can specifically include: an SQL database and a graph database. The above-mentioned SQL database is used to cache simulation operation results of structured format types, and the above-mentioned graph database is used to cache simulation operation results of unstructured format types.

In some embodiments, after detecting whether the target operation and maintenance query problem exists in the cache hotspot problem list in the current time period, the method may further include the following contents when implemented:

S1: When it is determined that the target operation and maintenance query problem does not exist in the cache hot problem list of the current time period, the target operation and maintenance data query request carrying the target operation and maintenance query problem is routed to the data modeling layer according to the preset routing rules, so as to call the target operation and maintenance simulation model to perform simulation calculation based on the target operation and maintenance query problem;

S2: Obtain the target simulation calculation result output by the data modeling layer; and send the target simulation calculation result to the operation and maintenance terminal.

Based on the above embodiment, when it is determined that the target operation and maintenance query problem does not exist in the cache hot problem list of the current time period, it can be judged that the cache module has not previously cached the corresponding target simulation operation result; accordingly, the server can route the target operation and maintenance data query request carrying the target operation and maintenance query problem to the data modeling layer according to the preset routing rules, so as to call the target operation and maintenance simulation model through the data modeling layer according to the target operation and maintenance query problem to perform relevant simulation operations online, so as to obtain the target simulation operation result as the corresponding target operation and maintenance query result, and feed it back to the operation and maintenance terminal.

In some embodiments, referring to FIG. 4 , the above-mentioned calling of the target operation and maintenance simulation model to perform simulation calculation based on the target operation and maintenance query problem may include the following contents during specific implementation:

S1: According to the target operation and maintenance query question, determine the starting device, the ending device, and the associated device by querying the knowledge graph associated with the target network system; wherein the associated device includes a directly associated device and/or an indirectly associated device;

S2: Obtain and use the link address of the starting device, the link address of the ending device, and the link address of the associated device to construct a target link address matrix;

S3: splitting the target link address matrix into multiple sub-link address matrices according to the attribute information of the device area;

S4: calling the target operation and maintenance simulation model to perform parallel simulation operations according to multiple sub-link address matrices to obtain multiple sub-simulation operation results;

S5: According to the attribute information of the device area, multiple sub-simulation operation results are combined to obtain the target simulation operation result.

Based on the above embodiment, the server can call the target operation and maintenance simulation model through the data modeling layer to perform online simulation calculations based on the target operation and maintenance query questions to obtain more accurate target simulation calculation results.

The link address may be an IP address. In addition, when the target link address matrix is split into multiple sub-link address matrices, it is also possible to detect whether the amount of data contained in the sub-link address matrix is greater than the maximum tolerable amount of data during the current single operation of the target operation and maintenance simulation model; when it is determined that the amount of data contained in the sub-link address matrix is greater than the maximum tolerable amount of data, the sub-link address matrix may be further split until the amount of data contained in the sub-link address matrix is less than the maximum tolerable amount of data.

In specific implementation, the data modeling layer receives and responds to the target operation and maintenance query request, and determines the starting device and the ending device associated with the problem according to the target operation and maintenance query question; further, the knowledge graph of the target network system can be queried to retrieve the nodes directly or indirectly connected to the node corresponding to the starting device and the node corresponding to the ending device through the connection edge, so as to determine the associated device. Then, by querying the attribute information marked on the node in the knowledge graph, the link address of the starting device, the link address of the ending device, and the link address of the associated device can be quickly obtained; and according to the link address of the starting device, the link address of the ending device, the link address of the associated device, and the edge relationship between the devices, the corresponding target link address matrix is constructed; then, according to the attribute information of the device area, the target link address matrix is split into multiple sub-link address matrices; wherein each sub-link address matrix corresponds to a device area; and then, multiple threads can be started at the same time, and the target operation and maintenance simulation model can be called to synchronously perform parallel simulation operations according to multiple sub-link address matrices to quickly obtain multiple corresponding sub-simulation operation results; then, according to the attribute information of the device area, multiple sub-simulation operation results are combined to obtain a complete target simulation operation result. Therefore, the required target simulation calculation results can be obtained through calculation simulation in a shorter time and more efficiently.

In some embodiments, after extracting a target operation and maintenance query question that meets the requirements by processing the target operation and maintenance data query request according to a preset instantiation processing rule, the method may further include the following contents when implemented:

The target operation and maintenance query question and the query time corresponding to the target operation and maintenance query question are recorded in the query log.

Based on the above embodiment, the subsequent server can accurately update the hotspot operation and maintenance issues according to the historical operation and maintenance query issues recorded in the query log.

In some embodiments, referring to FIG5 , the method may further include the following contents when implemented:

S1: At preset time intervals, obtain the operation and maintenance query problem records of the current time period according to the query log;

S2: According to the operation and maintenance query problem records, the query popularity value of the operation and maintenance query problem in the current time period is obtained by statistics;

S3: Filter out hot operation and maintenance issues in the current time period according to the query popularity value of the operation and maintenance query issues in the current time period;

S4: According to the hot operation and maintenance issues in the current time period, the cache hot issue list of the previous time period is updated to obtain the cache hot issue list of the current time period.

Based on the above embodiment, the server can accurately determine the hot operation and maintenance issues in the current time period by counting and according to the query heat values of the operation and maintenance query questions at preset time intervals, so as to update the cache hot issue list of the current time period with relatively good effect and high reference value.

During specific implementation, the server can count the query frequency of operation and maintenance query problems in the current time period based on the operation and maintenance query problem records, and determine the problem type of the operation and maintenance query problem, as well as the equipment area involved; at the same time, the server will also collect error feedback in the current time period, and determine the weight parameters for different problem types and different equipment areas in the current time period based on the error feedback; and then perform weighted operations based on the query frequency of operation and maintenance query problems in the current time period, as well as the weight parameters of the problem type of the operation and maintenance query problem and the weight parameters of the equipment area involved, to obtain the corresponding weighted operation result as the query heat value of the operation and maintenance query problem.

During specific implementation, the server can query your bureau to arrange the operation and maintenance query issues in the current time period in order of popularity value from high to low, and select a preset number of operation and maintenance query issues with the highest ranking as the hot operation and maintenance issues in the current time period.

In some embodiments, referring to FIG6 , the method may further include the following contents when it is implemented:

S1: Check whether the current idle time period meets the preset trigger condition;

S2: When it is determined that the current idle time period meets the preset triggering condition, the target operation and maintenance simulation model is called through the data modeling layer to process the unmarked hot issues in the cache hot issue list of the current time period;

S3: Obtain the simulation calculation results for the hot issue output by the data modeling layer; and mark the hot issue accordingly in the cached hot issue list of the current time period;

S4: Send the simulation result of the hot issue to the cache module for caching.

Based on the above embodiments, the server can use the introduced cache mechanism and the data processing resources in the idle time period to call the target operation and maintenance simulation model through the data modeling layer, without affecting the normal business data processing of the target network system, to obtain in advance through simulation operations the operation and maintenance query results that subsequent users are likely to query and correspond to the hot operation and maintenance query issues in the current time period, and cache them through the cache module, so that when the user queries related issues later, the corresponding operation and maintenance query results can be directly fed back to the user through the cache module.

The idle time period may be a non-working time period, for example, from 11:00 pm to 2:00 am, etc. The unmarked hot issues may be understood as hot query issues for which the cache module has not cached the corresponding simulation operation results.

In specific implementation, the server can detect whether there is a service carrying a key service tag in the target network system at the current time point in the idle time period in the execution state; when it is determined that there is no such service in the execution state, it is determined that the preset trigger condition is met.

In some embodiments, the cache module can be specifically connected to an SQL database and a graph database; wherein the SQL database is used to cache simulation operation results of structured data format types; and the graph database is used to cache simulation operation results of unstructured data format types.

Correspondingly, after receiving the simulation operation result, the cache module determines the data format type of the simulation operation result; and stores the simulation operation result in a matching database according to the data format type of the simulation operation result.

Based on the above embodiments, by introducing and utilizing two different cache databases to cache simulation calculation results of different data format types respectively, the reading and writing efficiency of the simulation calculation results in the cache database can be effectively improved, thereby further improving the processing efficiency of subsequent queries to obtain corresponding simulation calculation results, and further shortening the user's waiting time.

In some embodiments, after obtaining the target operation and maintenance query result corresponding to the target operation and maintenance query question fed back by the cache module, referring to FIG. 7 , the method may further include the following contents when it is specifically implemented:

S1: According to the target operation and maintenance query result, query the knowledge graph associated with the target network system to obtain target associated data related to the target operation and maintenance query result;

S2: Generate visual display data based on the target operation and maintenance query results and target related data;

S3: Send the visualized result display data to the operation and maintenance terminal.

Based on the above embodiment, the server can combine the knowledge graph of the target network system to convert the target operation and maintenance query results into corresponding visual result display data and feed it back to the operation and maintenance terminal, so that users can conveniently and intuitively understand the specific content involved in the target operation and maintenance query results, thereby improving the user's interactive experience.

During specific implementation, the server can use the knowledge graph of the target network system to obtain image data such as nodes and connection edges related to the target operation and maintenance query results as target associated data; then, based on the target operation and maintenance query results and the target associated data, the server can imitate the electronic map to construct corresponding visualization result display data.

Specifically, for example, a query request for locating a faulty device. The generated visualization result display data may specifically include a knowledge graph of a local network system containing a faulty device; the faulty device and the cause of the fault are marked in the knowledge graph; further, the associated devices associated with the faulty device, as well as the connection edges involved in the faulty device and the associated devices are marked in the knowledge graph, so that the user can accurately and efficiently determine the faulty device and the cause of the fault based on the above knowledge graph, and can also conveniently and meticulously sort out the affected device area range and the affected mode caused by the faulty device based on the above faulty device; thus, the above faulty device and other devices within the affected device area can be better targeted for operation and maintenance repair to eliminate the fault.

As can be seen from the above, based on the processing method of operation and maintenance data provided by the embodiment of this specification, before specific implementation, the digital twin technology and knowledge graph technology can be comprehensively utilized to construct a dynamic operation and maintenance map for the target network system; wherein, the dynamic operation and maintenance map at least includes a data modeling layer and a data acquisition layer; the data acquisition layer is used to collect the equipment parameters of the managed devices in the connected target network system; the data modeling layer is used to use the equipment parameters of the managed devices to construct a target operation and maintenance simulation model for the target network system based on digital twins and knowledge graphs; wherein, the target operation and maintenance simulation model is associated with the knowledge graph of the target network system. Furthermore, the server will also regularly update the hot operation and maintenance query issues in the cached hot issue list of the current time period; and in the idle time period, without affecting the normal business data processing, the target operation and maintenance simulation model is called through the data modeling layer to perform simulation operations in advance according to the hot operation and maintenance query issues of the current time period to obtain the corresponding operation and maintenance query results; and then introduce a cache mechanism to send the above operation and maintenance query results to the cache module for caching for subsequent use. In specific implementation, after receiving the target operation and maintenance data query request initiated by the operation and maintenance terminal based on the dynamic operation and maintenance map, the server can first extract the target operation and maintenance query questions that meet the requirements according to the preset instantiation processing rules; then detect whether the target operation and maintenance query question exists in the cache hotspot question list of the current time period; if so, according to the preset routing rules, the target operation and maintenance data query request carrying the target operation and maintenance query question is routed to the cache module for data query, so as to quickly find the corresponding target operation and maintenance query results from the cache database and feedback them to the operation and maintenance terminal. In this way, the corresponding target operation and maintenance query results can be determined and fed back more efficiently and accurately, effectively reducing the waiting time of users.

The embodiment of this specification also provides a server, as shown in Figure 8. The server includes a network communication port 801, a processor 802 and a memory 803, and the above structures are connected through internal cables so that each structure can perform specific data interaction.

Among them, the network communication port 801 can be specifically used to receive a target operation and maintenance data query request initiated by the operation and maintenance terminal based on a dynamic operation and maintenance map; wherein the dynamic operation and maintenance map is an operation and maintenance knowledge graph tool for the target network system; the dynamic operation and maintenance map at least includes a data acquisition layer and a data modeling layer; the data acquisition layer is used to collect device parameters of managed devices in the connected target network system; the data modeling layer is used to use the device parameters of the managed devices to construct a target operation and maintenance simulation model for the target network system based on digital twins and knowledge graphs;

The processor 802 can be specifically used to extract the target operation and maintenance query problem that meets the requirements by processing the target operation and maintenance data query request according to the preset instantiation processing rules; detect whether the target operation and maintenance query problem exists in the cache hot problem list of the current time period; wherein the cache hot problem list of the current time period contains the hot operation and maintenance query problem of the current time period; the cache hot problem list of the current time period is associated with the cache module; the cache module is responsible for storing the operation and maintenance query results corresponding to the hot operation and maintenance query problem of the current time period; the operation and maintenance query result is obtained by calling and running the target operation and maintenance simulation model based on the hot operation and maintenance query problem of the current time period in the idle time period by the server; when it is determined that the target operation and maintenance query problem exists in the cache hot problem list of the current time period, according to the preset routing rules, the target operation and maintenance data query request carrying the target operation and maintenance query problem is routed to the cache module for data query; obtain the target operation and maintenance query result corresponding to the target operation and maintenance query problem fed back by the cache module; and send the target operation and maintenance query result to the operation and maintenance terminal; wherein the operation and maintenance terminal is the initiating terminal of the target operation and maintenance data query request;

The memory 803 may be specifically used to store corresponding instruction programs.

In this embodiment, the network communication port 801 can be a virtual port that is bound to different communication protocols so that different data can be sent or received. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. In addition, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it can also be a Bluetooth chip.

In this embodiment, the processor 802 may be implemented in any appropriate manner. For example, the processor may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) executable by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc. This specification does not limit this.

In this embodiment, the memory 803 may include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function that has no physical form is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

The embodiment of this specification also provides a computer-readable storage medium based on the above-mentioned operation and maintenance data processing method, and the computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed, the following steps are implemented: receiving a target operation and maintenance data query request initiated by an operation and maintenance terminal based on a dynamic operation and maintenance map; wherein the dynamic operation and maintenance map is an operation and maintenance knowledge graph tool for the target network system; the dynamic operation and maintenance map includes at least a data acquisition layer and a data modeling layer; the data acquisition layer is used to collect device parameters of managed devices in the connected target network system; the data modeling layer is used to use the device parameters of the managed devices to construct a target operation and maintenance simulation model for the target network system based on digital twins and knowledge graphs; according to preset instantiation processing rules, by processing the target operation and maintenance data query request, extract the target operation and maintenance query questions that meet the requirements; detect the cache hot problem list for the current time period whether the target operation and maintenance query problem exists in the cache hot problem list of the current time period; wherein, the cache hot problem list of the current time period includes the hot operation and maintenance query problem of the current time period; the cache hot problem list of the current time period is associated with the cache module; the cache module is responsible for storing the operation and maintenance query results corresponding to the hot operation and maintenance query problems of the current time period; the operation and maintenance query results are obtained by calling and running the target operation and maintenance simulation model based on the hot operation and maintenance query problems of the current time period in the idle time period by the server; when it is determined that the target operation and maintenance query problem exists in the cache hot problem list of the current time period, according to the preset routing rules, the target operation and maintenance data query request carrying the target operation and maintenance query problem is routed to the cache module for data query; the target operation and maintenance query result corresponding to the target operation and maintenance query problem fed back by the cache module is obtained; and the target operation and maintenance query result is sent to the operation and maintenance terminal; wherein, the operation and maintenance terminal is the initiating terminal of the target operation and maintenance data query request.

In this embodiment, the storage medium includes but is not limited to a random access memory (RAM), a read-only memory (ROM), a cache, a hard disk (HDD) or a memory card. The memory may be used to store computer program instructions. The network communication unit may be an interface for network connection communication set in accordance with the standard specified by the communication protocol.

In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other implementations and will not be described in detail here.

Referring to FIG. 9 , at the software level, the embodiment of this specification further provides a device for processing operation and maintenance data, which may specifically include the following structural modules:

The receiving module 901 can be specifically used to receive a target operation and maintenance data query request initiated by the operation and maintenance terminal based on a dynamic operation and maintenance map; wherein the dynamic operation and maintenance map is an operation and maintenance knowledge graph tool for the target network system; the dynamic operation and maintenance map at least includes a data acquisition layer and a data modeling layer; the data acquisition layer is used to collect device parameters of managed devices in the connected target network system; the data modeling layer is used to use the device parameters of the managed devices to construct a target operation and maintenance simulation model for the target network system based on digital twins and knowledge graphs;

The extraction module 902 may be specifically configured to extract target operation and maintenance query questions that meet the requirements by processing the target operation and maintenance data query request according to a preset instantiation processing rule;

The detection module 903 can be specifically used to detect whether the target operation and maintenance query problem exists in the cache hot problem list of the current time period; wherein the cache hot problem list of the current time period includes the hot operation and maintenance query problem of the current time period; the cache hot problem list of the current time period is associated with the cache module; the cache module is responsible for storing the operation and maintenance query results corresponding to the hot operation and maintenance query problem of the current time period; the operation and maintenance query results are obtained by calling and running the target operation and maintenance simulation model based on the hot operation and maintenance query problem of the current time period in the idle time period by the server;

The routing module 904 may be specifically configured to route the target operation and maintenance data query request carrying the target operation and maintenance query question to the cache module for data query according to a preset routing rule when it is determined that the target operation and maintenance query question exists in the cache hotspot question list in the current time period;

The feedback module 905 can be specifically used to obtain the target operation and maintenance query result corresponding to the target operation and maintenance query question fed back by the cache module; and send the target operation and maintenance query result to the operation and maintenance terminal; wherein the operation and maintenance terminal is the initiating terminal of the target operation and maintenance data query request.

In some embodiments, the dynamic operation and maintenance map may further include: a business function layer; wherein the business function layer is connected to the operation and maintenance terminal; the business function layer supports users to initiate operation and maintenance data query requests of various business types through the operation and maintenance terminal;

The operation and maintenance data query requests of the multiple business types include: a faulty equipment location query request, a connection path navigation query request, and a connection path road condition query request.

In some embodiments, the dynamic operation and maintenance map may further specifically include: a maintenance management layer; wherein the maintenance management layer is used to monitor the health status of the target network system according to the simulation calculation results output by the data modeling layer; when an abnormality is detected in the health status of the target network system, an operation and maintenance strategy for the target network system is generated according to the simulation calculation results.

In some embodiments, when the above-mentioned extraction module 902 is implemented, it can be implemented in the following manner according to preset instantiation processing rules, by processing the target operation and maintenance data query request, to extract the target operation and maintenance query question that meets the requirements: according to the preset instantiation processing rules, extract the initial question from the target operation and maintenance data query request; according to the preset reference question list and the initial question, perform question matching to obtain the corresponding matching result; according to the matching result, when it is determined that the match fails, perform semantic recognition on the initial question to obtain the corresponding semantic recognition result; perform word segmentation processing on the semantic recognition result; and based on the semantic recognition result after word segmentation processing, extract question keywords; according to the question keywords, obtain multiple pending questions by querying the knowledge graph associated with the target network system; and screen out the target operation and maintenance query question that meets the requirements from the multiple pending questions.

In some embodiments, after matching questions according to a preset reference question list and the initial question to obtain corresponding matching results, the device, when implemented specifically, can also be used to: based on the matching results, when it is determined that the match is successful, determine a reference question that matches the initial question from the preset reference question list as the target operation and maintenance query question.

In some embodiments, after detecting whether the target operation and maintenance query problem exists in the cache hot spot problem list of the current time period, the device can also be used when it is specifically implemented to: when it is determined that the target operation and maintenance query problem does not exist in the cache hot spot problem list of the current time period, according to preset routing rules, route the target operation and maintenance data query request carrying the target operation and maintenance query problem to the data modeling layer to call the target operation and maintenance simulation model to perform simulation operations based on the target operation and maintenance query problem; obtain the target simulation operation results output by the data modeling layer; and send the target simulation operation results to the operation and maintenance terminal.

In some embodiments, when the device is implemented, the target operation and maintenance simulation model can be called to perform simulation operations based on the target operation and maintenance query problem in the following manner: according to the target operation and maintenance query problem, the starting device, the ending device, and the associated devices are determined by querying the knowledge graph associated with the target network system; wherein the associated devices include directly associated devices and/or indirectly associated devices; the link address of the starting device, the link address of the ending device, and the link address of the associated device are obtained and used to construct a target link address matrix; according to the attribute information of the device area, the target link address matrix is split into multiple sub-link address matrices; the target operation and maintenance simulation model is called to perform parallel simulation operations based on the multiple sub-link address matrices to obtain multiple sub-simulation operation results; according to the attribute information of the device area, multiple sub-simulation operation results are combined to obtain the target simulation operation result.

In some embodiments, after extracting a target operation and maintenance query question that meets the requirements by processing the target operation and maintenance data query request according to a preset instantiation processing rule, the device, when implemented specifically, can also be used to: record the target operation and maintenance query question and the query time corresponding to the target operation and maintenance query question into a query log.

In some embodiments, when the device is implemented, it can also be used to: obtain the operation and maintenance query problem record of the current time period according to the query log at every preset time interval; obtain the query heat value of the operation and maintenance query problem of the current time period according to the operation and maintenance query problem record; filter out the hot operation and maintenance problems of the current time period according to the query heat value of the operation and maintenance query problem of the current time period; update the cached hot problem list of the previous time period according to the hot operation and maintenance problems of the current time period, and obtain the cached hot problem list of the current time period.

In some embodiments, when the device is implemented, it can also be used to: detect whether the current idle time period meets the preset trigger conditions; when it is determined that the current idle time period meets the preset trigger conditions, call the target operation and maintenance simulation model through the data modeling layer to process the unmarked hot issues in the cache hot issue list of the current time period; obtain the simulation operation results for the hot issue output by the data modeling layer; and mark the hot issue accordingly in the cache hot issue list of the current time period; send the simulation operation results of the hot issue to the cache module for caching.

In some embodiments, the cache module may be specifically connected to a SQL database and a graph database;

Correspondingly, after receiving the simulation operation result, the cache module can determine the data format type of the simulation operation result; and store the simulation operation result in a matching database according to the data format type of the simulation operation result.

In some embodiments, after obtaining the target operation and maintenance query results corresponding to the target operation and maintenance query questions fed back by the cache module, the device can also be used, when implemented, to: query the knowledge graph associated with the target network system based on the target operation and maintenance query results, and obtain target-related data related to the target operation and maintenance query results; generate visual result display data based on the target operation and maintenance query results and the target-related data; and send the visual result display data to the operation and maintenance terminal.

It should be noted that the units, devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by functions divided into various modules. Of course, when implementing this specification, the functions of each module can be implemented in the same or more software and/or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

It can be seen from the above that the operation and maintenance data processing device provided in the embodiments of this specification can more efficiently and accurately determine and feedback the corresponding target operation and maintenance query results, effectively reducing the waiting time of users.

In a specific scenario example, the operation and maintenance data processing method provided in this specification can be applied to optimize and improve network simulation forwarding path query in system operation and maintenance scenarios. The specific implementation includes the following contents.

S1: Combine digital twin technology and dynamic operation and maintenance map to build a simulation model (e.g., target operation and maintenance simulation model);

S2: Build a cache mechanism;

S3: Optimizes and improves the query efficiency of the simulated forwarding path based on the cache mechanism of S2.

In specific implementation, for S1, as shown in FIG10, the dynamic operation and maintenance map can be an application tool based on the operation and maintenance knowledge graph, which can be divided into a data collection layer (marked as 1), a data modeling layer (marked as 2), a core capability layer (e.g., a business function layer, marked as 3), and an upper application layer (e.g., a maintenance management layer, marked as 4) in terms of architecture. The data collection layer is responsible for source data access. In order to build a complete map for the IT infrastructure environment, it is necessary to collect data of different dimensions such as equipment, network, system, cloud platform, and application (e.g., equipment parameters); the data modeling layer is responsible for integrating and pulling data into an operation and maintenance graph (e.g., a knowledge graph of the target network system); and further constructing a simulation model (e.g., a target operation and maintenance simulation model); the core capability layer refers to the digital map in life and builds capabilities such as "search positioning", "path navigation", and "road condition display" on the operation and maintenance graph; the application layer serves specific business scenarios based on core capabilities.

Furthermore, the simulation model is partially optimized. The simulation model is based on the network device configuration information, routing table entries, arp table entries, and mac table entries provided by the data collection layer, combined with digital twin technology, and uses mathematical methods to simulate real networks and network behaviors. The optimization point is to improve the efficiency and coverage of the simulation model's external output results.

For S2, a cache mechanism is introduced, and the idea of "trading space for time" is used to query hot issues (for example, hot query issues in the current time period) in full when the system is idle at night (for example, idle time period) for efficient use the next day. First, a problem identification module needs to be built. This module first realizes hot issue statistics and secondly, routes the query. If the query matches the hot issue, it is routed to the cache library (for example, cache module) to obtain the result; otherwise, it is routed to the simulation system for calculation. Secondly, a problem instantiation module needs to be built, which realizes the full instance enumeration of hot issues, and the enumeration is based on the full data of the operation and maintenance map. For example, if the network forwarding path is a hot issue (the input of the issue is the IP address of two servers, and the output is the link of each network device through which the two servers communicate), the IP matrix should be enumerated and constructed in this module to cover all source and destination combinations, and the full IP address is obtained from the operation and maintenance map. Finally, the scheduled query module is triggered at night based on the enumeration of all instances, and queries the simulation model in full. Based on the data format of the query results, different results are saved in different databases. If the result is structured data, it is stored in a SQL database. If the result is unstructured data, it is stored in a graph database.

For S3, the efficiency of forwarding path query is optimized. First, according to the server access information in the operation and maintenance map, the IP matrix constructed in S2 is simplified into a matrix from switch i to switch j. Secondly, according to the network area information in the operation and maintenance map, the matrix from switch i to switch j is split, and a sub-matrix (for example, a sub-link address matrix) is constructed for switches in every n areas, where n is limited by the number of devices that can be managed by the simulation model at one time. Finally, for areas with multiple sub-matrices, the simulation model is pulled up batch by batch, and the path from switch i to switch j is calculated. The design is stored in the database based on the results of S2, and the results are saved and updated on a daily basis.

Furthermore, when providing path query services to the outside, the saved results are combined with the server access information to provide services. In this way, on the one hand, the forwarding path can be provided to the upper-layer application scenarios quickly and with high concurrency, such as in the fault location scenario, where the paths between multiple pairs of server IPs can be obtained at one time, without serial query waiting to affect the location efficiency, or only doing location analysis on one path with the problem of local perspective; on the other hand, it can overcome the problem of a small number of devices managed by the simulation model, query the network block by block (several areas together) and ensure that the query is in this block at one time.

Based on the above scenario examples, the operation and maintenance data processing method provided in this manual is verified. Through the combination of dynamic maps and digital twin technology, the network is simulated and modeled, and accurate queries based on simulation operations are realized; by introducing and building a cache mechanism, the query efficiency of simulation results is improved; by adopting relevant routing rules, the query efficiency of network forwarding paths is specially optimized. In addition, the query efficiency and equipment coverage of the simulation model when providing external services are improved, thereby improving the operation and maintenance efficiency and accuracy, and effectively predicting abnormal conditions such as faults.

Although the present specification provides method operation steps as described in the embodiments or flow charts, more or less operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the order of many steps, and does not represent the only execution order. When the device or client product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. The first, second, etc. words are used to represent the name, and do not represent any particular order.

Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

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

Although the present specification is described through embodiments, those skilled in the art will appreciate that there are many modifications and changes to the present specification without departing from the spirit of the present specification, and it is intended that the appended claims include these modifications and changes without departing from the spirit of the present specification.

Claims (15)

1. A method for processing operation and maintenance data, characterized in that it is applied to a server and comprises: Receive a target operation and maintenance data query request initiated by an operation and maintenance terminal based on a dynamic operation and maintenance map; wherein the dynamic operation and maintenance map is an operation and maintenance knowledge graph tool for a target network system; the dynamic operation and maintenance map comprises at least a data collection layer and a data modeling layer; the data collection layer is used to collect device parameters of managed devices in the connected target network system; the data modeling layer is used to construct a target operation and maintenance simulation model for the target network system based on digital twins and knowledge graphs using the device parameters of the managed devices; According to the preset instantiation processing rules, by processing the target operation and maintenance data query request, a target operation and maintenance query question that meets the requirements is extracted; Detect whether the target operation and maintenance query problem exists in the cache hot problem list of the current time period; wherein the cache hot problem list of the current time period includes the hot operation and maintenance query problem of the current time period; the cache hot problem list of the current time period is associated with a cache module; the cache module is responsible for storing the operation and maintenance query results corresponding to the hot operation and maintenance query problem of the current time period; the operation and maintenance query results are obtained by calling and running the target operation and maintenance simulation model based on the hot operation and maintenance query problem of the current time period by the server in the idle time period; When it is determined that the target operation and maintenance query problem exists in the cache hot problem list of the current time period, the target operation and maintenance data query request carrying the target operation and maintenance query problem is routed to the cache module for data query according to the preset routing rules; The target operation and maintenance query result corresponding to the target operation and maintenance query question fed back by the cache module is obtained; and the target operation and maintenance query result is sent to the operation and maintenance terminal. 2. The method according to claim 1 is characterized in that the dynamic operation and maintenance map further comprises: a business function layer; wherein the business function layer is connected to the operation and maintenance terminal; the business function layer supports users to initiate operation and maintenance data query requests of various business types through the operation and maintenance terminal; The operation and maintenance data query requests of the multiple business types include: a faulty equipment location query request, a connection path navigation query request, and a connection path road condition query request. 3. The method according to claim 1 is characterized in that the dynamic operation and maintenance map also includes: a maintenance management layer; wherein the maintenance management layer is used to monitor the health status of the target network system according to the simulation calculation results output by the data modeling layer; when an abnormality is detected in the health status of the target network system, an operation and maintenance strategy for the target network system is generated according to the simulation calculation results. 4. The method according to claim 1 is characterized in that, according to a preset instantiation processing rule, by processing the target operation and maintenance data query request, a target operation and maintenance query question that meets the requirements is extracted, comprising: According to the preset instantiation processing rules, the initial question is extracted from the target operation and maintenance data query request; Match the questions according to the preset reference question list and the initial question to obtain the corresponding matching results; According to the matching result, when it is determined that the matching fails, semantic recognition is performed on the initial question to obtain a corresponding semantic recognition result; Performing word segmentation processing on the semantic recognition result; and extracting question keywords based on the semantic recognition result after word segmentation processing; Based on the question keywords, multiple pending questions are obtained by querying the knowledge graph associated with the target network system; From the multiple pending questions, select target operation and maintenance query questions that meet the requirements. 5. The method according to claim 4, characterized in that after matching the questions according to the preset reference question list and the initial question to obtain the corresponding matching results, the method further comprises: According to the matching result, when it is determined that the match is successful, a reference question matching the initial question is determined from a preset reference question list as the target operation and maintenance query question. 6. The method according to claim 4, characterized in that after detecting whether the target operation and maintenance query problem exists in the cache hot problem list in the current time period, the method further comprises: When it is determined that the target operation and maintenance query problem does not exist in the cache hot problem list of the current time period, the target operation and maintenance data query request carrying the target operation and maintenance query problem is routed to the data modeling layer according to the preset routing rules, so as to call the target operation and maintenance simulation model to perform simulation calculation based on the target operation and maintenance query problem; Obtain the target simulation calculation result output by the data modeling layer; and send the target simulation calculation result to the operation and maintenance terminal. 7. The method according to claim 6, characterized in that calling the target operation and maintenance simulation model to perform simulation calculation based on the target operation and maintenance query problem comprises: According to the target operation and maintenance query question, by querying the knowledge graph associated with the target network system, the starting device, the ending device, and the associated device are determined; wherein the associated device includes a directly associated device and/or an indirectly associated device; Obtain and use the link address of the starting device, the link address of the ending device, and the link address of the associated device to construct a target link address matrix; According to the attribute information of the device area, the target link address matrix is split into a plurality of sub-link address matrices; Calling the target operation and maintenance simulation model to perform parallel simulation operations according to multiple sub-link address matrices to obtain multiple sub-simulation operation results; According to the attribute information of the device area, multiple sub-simulation operation results are combined to obtain the target simulation operation result. 8. The method according to claim 1 is characterized in that, after extracting the target operation and maintenance query question that meets the requirements by processing the target operation and maintenance data query request according to the preset instantiation processing rules, the method further comprises: The target operation and maintenance query question and the query time corresponding to the target operation and maintenance query question are recorded in the query log. 9. The method according to claim 8, characterized in that the method further comprises: At preset time intervals, obtain the operation and maintenance query problem records of the current time period based on the query log; According to the operation and maintenance query problem records, the query popularity value of the operation and maintenance query problem in the current time period is obtained by statistics; Filter out hot O&M issues in the current time period based on the query popularity of the O&M query issues in the current time period; According to the hot operation and maintenance problems in the current time period, the cache hot problem list of the previous time period is updated to obtain the cache hot problem list of the current time period. 10. The method according to claim 9, characterized in that the method further comprises: Check whether the current idle time period meets the preset trigger conditions; When it is determined that the current idle time period meets the preset triggering condition, the target operation and maintenance simulation model is called through the data modeling layer to process the unmarked hot issues in the cache hot issue list of the current time period; Obtain the simulation calculation results for the hot issue output by the data modeling layer; and mark the hot issue accordingly in the cached hot issue list of the current time period; The simulation results of the hot issue are sent to the cache module for caching. 11. The method according to claim 10, characterized in that the cache module is connected to a SQL database and a graph database; Correspondingly, after receiving the simulation operation result, the cache module determines the data format type of the simulation operation result; and stores the simulation operation result in a matching database according to the data format type of the simulation operation result. 12. The method according to claim 1, characterized in that after obtaining the target operation and maintenance query result corresponding to the target operation and maintenance query question fed back by the cache module, the method further comprises: According to the target operation and maintenance query result, query the knowledge graph associated with the target network system to obtain target associated data related to the target operation and maintenance query result; Generate visual display data based on the target operation and maintenance query results and target related data; The visualized result display data is sent to the operation and maintenance terminal. 13. A device for processing operation and maintenance data, comprising: A receiving module is used to receive a target operation and maintenance data query request initiated by an operation and maintenance terminal based on a dynamic operation and maintenance map; wherein the dynamic operation and maintenance map is an operation and maintenance knowledge graph tool for a target network system; the dynamic operation and maintenance map comprises at least a data acquisition layer and a data modeling layer; the data acquisition layer is used to collect device parameters of managed devices in the connected target network system; the data modeling layer is used to use the device parameters of the managed devices to construct a target operation and maintenance simulation model for the target network system based on digital twins and knowledge graphs; An extraction module is used to extract target operation and maintenance query questions that meet the requirements by processing the target operation and maintenance data query request according to a preset instantiation processing rule; A detection module is used to detect whether the target operation and maintenance query problem exists in the cache hot problem list of the current time period; wherein the cache hot problem list of the current time period includes the hot operation and maintenance query problem of the current time period; the cache hot problem list of the current time period is associated with a cache module; the cache module is responsible for storing the operation and maintenance query results corresponding to the hot operation and maintenance query problem of the current time period; the operation and maintenance query results are obtained by calling and running the target operation and maintenance simulation model based on the hot operation and maintenance query problem of the current time period by the server in an idle time period; A routing module is used to route the target operation and maintenance data query request carrying the target operation and maintenance query question to the cache module for data query according to a preset routing rule when it is determined that the target operation and maintenance query question exists in the cache hotspot question list in the current time period; The feedback module is used to obtain the target operation and maintenance query result corresponding to the target operation and maintenance query question fed back by the cache module; and send the target operation and maintenance query result to the operation and maintenance terminal. 14. A server, characterized in that it comprises a processor and a memory for storing processor-executable instructions, wherein the processor implements the steps of the method according to any one of claims 1 to 12 when executing the instructions. 15. A computer-readable storage medium, characterized in that computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.