CN110807085B - Fault information query method and device, storage medium and electronic device - Google Patents
Fault information query method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN110807085B CN110807085B CN201910867099.8A CN201910867099A CN110807085B CN 110807085 B CN110807085 B CN 110807085B CN 201910867099 A CN201910867099 A CN 201910867099A CN 110807085 B CN110807085 B CN 110807085B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- information
- troubleshooting
- service
- target service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Animal Behavior & Ethology (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a fault information query method and device, a storage medium and an electronic device, wherein the method comprises the following steps: receiving service information of a target service; inquiring a knowledge graph of the target service in a cloud knowledge base according to the service information; when the knowledge graph of the target service exists in the cloud knowledge base, receiving troubleshooting factors of the target service; and generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script, and querying the fault information of the target service in the knowledge graph. The invention solves the technical problem that the business fault cannot be checked through the knowledge base in the related technology, and improves the problem checking efficiency.
Description
Technical Field
The invention relates to the field of big data, in particular to a fault information query method and device, a storage medium and an electronic device.
Background
In the related technology, when an online operation and maintenance worker handles the problem of the C end or the B end, the online operation and maintenance worker strongly depends on various query tools to solve and locate the problem, the problem is solved and located with certain efficiency, and the online operation and maintenance worker can only depend on the experience of the worker without data precipitation on the solution idea and the solution.
In the aspect of online operation and maintenance troubleshooting and positioning problems and providing solutions in the related art, at least the following problems exist: the on-line operation and maintenance work order checking thought is stored in office software in a document mode, the document amount is increased a lot along with the increase of the service volume, the searching and new building cost in the maintenance aspect is higher, and the feedback in the use aspect is more discrete; when the problems are solved, the tools are scattered at a plurality of places, the jumping among a plurality of platforms is carried out by depending on experience or documents, and the tools are lack of aggregation; throwing all the tools out of the brain can only cause information interference, but can reduce the efficiency; the use effects of the troubleshooting tools and the troubleshooting tools used in the problem solving process of the work order are currently fed back by human meat, and data precipitation of a platform is lacked; the mapping between problem descriptions in work orders currently provided by services to solutions is manually and empirically matched, lacking system support. The prior art with the application number of CN201811166796 discloses a fault information reporting method and device, which locate an equipment fault according to a reported fault location code, and also heavily depend on manual work to find the fault location of the equipment on site.
In view of the above problems in the related art, no effective solution has been found at present.
Disclosure of Invention
Embodiments of the present invention provide a method and an apparatus for querying fault information, a storage medium, and an electronic apparatus, so as to solve the above problems or at least partially solve the above problems.
According to an embodiment of the present invention, there is provided a method for querying fault information, including: receiving service information of a target service;
inquiring a knowledge graph of the target service in a cloud knowledge base according to the service information;
when the knowledge graph of the target service exists in the cloud knowledge base, receiving troubleshooting factors of the target service;
and generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script, and querying the fault information of the target service in the knowledge graph.
Optionally, querying, in a cloud knowledge base, a knowledge graph of the target service according to the service information includes:
acquiring access information from the service information based on a recall strategy;
extracting characteristic information of the parameter information;
searching a first knowledge graph matched with the characteristic information in the cloud knowledge base;
and sorting the matching degrees of the recall results in the first knowledge graph, and determining a plurality of recall results with the highest matching degrees as a second knowledge graph of the target service.
Optionally, the extracting the feature information of the parameter entry information includes:
extracting text features of the parameter information;
extracting word segmentation characteristics of the reference information based on a domain dictionary;
and extracting heat information of the parameter entering information.
Optionally, the recall policy is a knowledge recommendation rule, and obtaining the access information from the service information based on the recall policy includes:
acquiring a service portrait and/or keywords from the service information;
extracting preset service data of the service information from the service portrait and/or the keywords, wherein the preset service data comprises work order categories, work order titles, work order description information and work order result information;
and determining the preset service data as first access parameter information.
Optionally, the recall policy is a knowledge search rule, and obtaining the access information from the service information based on the recall policy includes:
acquiring a service portrait and/or keywords from the service information, and receiving search keywords related to the target service and search category information of the target service;
and determining the service portrait and/or the keyword, the search keyword and the search category information as second entry information.
Optionally, retrieving, in the cloud knowledge base, a first knowledge graph matched with the feature information includes:
and carrying out full-text search in the cloud knowledge base by using the characteristic information to obtain a knowledge tag, a knowledge title and a knowledge category which are matched with the characteristic information.
Optionally, the generating a tool troubleshooting script according to the troubleshooting element includes:
acquiring a knowledge node set of a troubleshooting process;
generating a tool investigation template according to the knowledge node set;
and replacing the entity content in the tool troubleshooting template by taking the troubleshooting element as a business entity to generate a tool troubleshooting script.
Optionally, the generating a tool troubleshooting template according to the knowledge node set includes:
analyzing a tool Uniform Resource Locator (URL), input and output of each knowledge node in the knowledge node set;
and after the analysis is finished, combining according to the logic sequence among the knowledge nodes to generate the tool troubleshooting template.
Optionally, the troubleshooting element includes at least one of: the store identification of the target service, the commodity identification of the target service and the coupon identification of the target service.
Optionally, after querying the knowledge graph of the target service in the cloud repository according to the service information, the method further includes:
when the knowledge map of the target service does not exist in the cloud end knowledge base, determining that the target service lacks knowledge support in the cloud end knowledge base;
receiving fault information of the target service, performing knowledge conversion on the fault information, and inputting a knowledge map of the target service; and setting a troubleshooting process according to the fault type of the fault information, and inputting a tool URL and troubleshooting elements matched with the troubleshooting process into the cloud knowledge base.
According to another embodiment of the present invention, there is provided an apparatus for querying fault information, including: the first receiving module is used for receiving the service information of the target service;
the first query module is used for querying the knowledge graph of the target service in a cloud knowledge base according to the service information;
the second receiving module is used for receiving troubleshooting factors of the target service when the knowledge graph of the target service exists in the cloud knowledge base;
and the second query module is used for generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script and querying the fault information of the target service in the knowledge graph.
Optionally, the first query module includes:
the acquisition unit is used for acquiring the access information from the service information based on the recall strategy;
the extraction unit is used for extracting the characteristic information of the parameter information;
the retrieval unit is used for retrieving a first knowledge graph matched with the characteristic information from the cloud knowledge base;
and the determining unit is used for sorting the matching degrees of the recall results in the first knowledge graph and determining a plurality of recall results with the highest matching degrees as a second knowledge graph of the target service.
Optionally, the second query module includes:
the acquisition unit is used for acquiring a knowledge node set of a troubleshooting process;
the generating unit is used for generating a tool troubleshooting template according to the knowledge node set;
and the replacing unit is used for replacing the entity content in the tool troubleshooting template by using the troubleshooting element as a business entity to generate a tool troubleshooting script.
Optionally, the generating unit includes:
the analysis subunit is used for analyzing the tool uniform resource locator URL, the input and the output of each knowledge node in the knowledge node set;
and the generating subunit is used for combining according to the logic sequence among the knowledge nodes after the analysis is finished, and generating the tool checking template.
According to a further embodiment of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
By the invention, the service information of the target service is received, then the knowledge map of the target service is inquired in the cloud knowledge base according to the service information, receiving troubleshooting factors of the target service when the knowledge map of the target service exists in the cloud knowledge base, generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script, the fault information of the target service is inquired in the knowledge map, the services of knowledge search and knowledge recommendation are provided in an intelligent matching mode, the knowledge map can be used for automatically analyzing the service information for knowledge recommendation, and a tool troubleshooting script for inquiring fault information is generated through the troubleshooting elements, so that the faults and troubleshooting problems can be quickly positioned, the processing timeliness of work orders is improved, the technical problem that the business faults cannot be debugged through a knowledge base in the related technology is solved, and the problem troubleshooting efficiency is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a block diagram of a computer terminal for querying fault information according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for querying fault information according to an embodiment of the present invention;
FIG. 3 is a logical block diagram of a knowledge base system of an embodiment of the present invention;
FIG. 4 is a flow chart of knowledge troubleshooting in accordance with an embodiment of the present invention;
FIG. 5 is a flow diagram of a knowledge search and knowledge recommendation process according to an embodiment of the invention;
FIG. 6 is a flow chart of a fault query using a tool template according to an embodiment of the present invention;
fig. 7 is a block diagram of a fault information query apparatus according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method provided by the first embodiment of the present application may be executed in a computer terminal, a server, or a similar computing device. Taking the example of running on a computer terminal, fig. 1 is a structural block diagram of a computer terminal for querying fault information according to an embodiment of the present invention. As shown in fig. 1, the computer terminal 10 may include one or more (only one shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and optionally, a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the computer terminal. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store a computer program, for example, a software program and a module of application software, such as a computer program corresponding to a method for querying fault information in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, so as to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In this embodiment, a method for querying fault information is provided, and fig. 2 is a flowchart of a method for querying fault information according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S202, receiving service information of a target service;
in the embodiment of the present application, the target service may be a service entity that needs to perform problem handling and fault query, such as a work order, a bill, and the like. And when the target service is the work order service, the service information is the work order information. The service information of the embodiment includes a service portrait, keywords, description information, and the like.
The embodiment receives the service information of the target service through modes of user input, service system sending and the like.
Step S204, inquiring a knowledge graph of the target service in a cloud knowledge base according to the service information;
the knowledge graph of the embodiment includes a plurality of information sets related to service information, a candidate set is established by inputting related information of a target service in advance, and the candidate set is stored in a knowledge base through a certain mapping relation and a certain structural relation.
In the embodiment of the present application, after receiving the service information of the target service, querying the knowledge graph of the target service in the cloud repository according to the service information includes:
s11, acquiring the access information from the service information based on the recall strategy;
the embodiment includes two scenarios, namely knowledge recommendation and knowledge search. The inner is algorithm implementation indistinguishable. The biggest difference is the difference between the reference values. Knowledge search is initiative of users, and the input parameters are keywords input by the users and other user-defined data such as selected categories and the like; knowledge recommendation is systematic and automatic, and the entries are obtained by analyzing the whole service data, for example, analyzing the work order service data, finding that the service data such as the work order category, title, problem description, processing conclusion and the like can influence the knowledge recommendation, and taking the data as the entries.
In an implementation scenario of this embodiment, the recall policy is a knowledge recommendation rule, and acquiring the access information from the service information based on the recall policy includes: acquiring a service portrait and/or keywords from the service information; extracting preset service data of service information from the service image and/or the keywords, wherein the preset service data comprises a work order category, a work order title, work order description information and work order result information; and determining the preset service data as the first access parameter information. The first reference information is used for recalling data recommended by the cloud knowledge base.
In an implementation scenario of this embodiment, the recall policy is a knowledge search rule, and acquiring the access information from the service information based on the recall policy includes: acquiring a service portrait and/or keywords from the service information, and receiving search keywords related to the target service and search category information of the target service; and determining the service portrait and/or the keyword, the search keyword and the search category information as second participation information. The first parameter information is used for recalling the data obtained by searching the cloud knowledge base.
S12, extracting the characteristic information of the parameter information;
the reference information of the present embodiment is an input parameter for searching the knowledge-graph. The parameter entering information comprises: text features, word segmentation features based on a domain dictionary, heat information and the like. The characteristic information for extracting the parameter information comprises the following steps: extracting text features of the access parameter information; extracting the word segmentation characteristics of the reference information based on the domain dictionary; and extracting heat information of the parameter information.
S13, searching a first knowledge graph matched with the characteristic information in the cloud knowledge base;
in the two scenarios of knowledge recommendation and knowledge search, the difference is that the knowledge search has no standard answer, and some test data needs to be set in advance because matching is performed according to the content input by the user. The test data is knowledge data marked by a business party, and the marked knowledge is knowledge which should be recalled theoretically if a user searches by using fixed search conditions. The final recall rate can be calculated by comparing and analyzing the data with the actual recall data. The knowledge recommendation is a mechanism capable of evaluating algorithm performance through recommendation coverage and recommendation accuracy, recall calculation is mainly based on knowledge recommendation evaluation, a user is required to evaluate the knowledge recommendation after a work order is processed, useful knowledge is selected more if the knowledge recommendation is useful, and useless reasons are selected more if the knowledge recommendation is useless. The evaluation data is analyzed to calculate a recall index. Therefore, after the recall result is fed back, feedback information of the user on the recall result can be received, and the knowledge graph of the target service is adjusted according to the feedback information.
The present embodiment may also calculate recall rates for knowledge searches and knowledge recommendations. Recalling knowledge search includes: the knowledge search data can be logged, and the recalling analysis mode is to compare the actual recalling data in the log with the theoretical recalling data in the test data and give the recall rate. The knowledge recommendation recall comprises: and the knowledge recommendation data can be logged, the knowledge recommendation evaluation data can be listed, and the recall analysis mode is to synthesize the recommendation data in the log and the evaluation data in the database to give the final recall rate.
In this embodiment of the application, retrieving the first knowledge graph matched with the feature information in the cloud knowledge base includes: and carrying out full text search in a cloud knowledge base by using the characteristic information to obtain a knowledge tag, a knowledge title and a knowledge category which are matched with the characteristic information.
And S14, sorting the recall results in the first knowledge graph according to the matching degree, and determining a plurality of recall results with the highest matching degree as a second knowledge graph of the target service.
The matching degree sorting in this embodiment is to perform fine sorting (secondary sorting) on the recall results, perform scoring sorting based on predetermined features and predetermined rules, and finally perform result returning of search recommendation.
Step S206, receiving troubleshooting factors of the target service when the knowledge graph of the target service exists in the cloud knowledge base;
in another aspect of this embodiment, after querying the knowledge graph of the target service in the cloud repository according to the service information, the method further includes: when the knowledge map of the target service does not exist in the cloud knowledge base, determining that the target service lacks knowledge support in the cloud knowledge base; receiving fault information of a target service, performing knowledge transformation on the fault information, and inputting a knowledge map of the target service; setting a troubleshooting process according to the fault type of the fault information, and inputting a Uniform Resource Locator (URL) and troubleshooting elements matched with the troubleshooting process in a cloud knowledge base.
And S208, generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script, and querying the fault information of the target service in the knowledge graph.
In an embodiment of the present application, generating a tool troubleshooting script according to the troubleshooting element includes:
s21, acquiring a knowledge node set of the troubleshooting process;
the knowledge nodes of the present embodiment are divided into three types: a start node, an intermediate node, and a result node. Each node judges whether the processing flow of the node is executed or not according to the processing result of the previous node. A solution step of acquiring specified knowledge for solving the problem and all nodes are required first.
S22, generating a tool checking template according to the knowledge node set;
in one embodiment of this embodiment, generating the tool troubleshooting template from the set of knowledge nodes comprises: analyzing tool URL, input and output of each knowledge node in the knowledge node set; and after the analysis is finished, combining according to the logic sequence among the knowledge nodes to generate a tool checking template.
S23, using the troubleshooting element as a business entity to replace the entity content in the tool troubleshooting template, and generating a tool troubleshooting script;
optionally, the troubleshooting element refers to some business entities related to tool troubleshooting, and the troubleshooting element includes at least one of the following: store identification of the target service, commodity identification of the target service and coupon identification of the target service. May be a consumption ticket, a membership ticket, etc.
In the embodiment of the application, the data query interface is called through the tool troubleshooting script, and the fault information of the target service is queried in the knowledge graph. And respectively carrying out troubleshooting and fault positioning on each troubleshooting element. And determining whether abnormal contents exist in the business information, such as whether the store name is correct, whether the commodity is on-line or off-line, whether the coupon is still valid, whether the use rule is met and the like.
Through the steps, the service information of the target service is received, then the knowledge map of the target service is inquired in the cloud knowledge base according to the service information, receiving troubleshooting factors of the target service when the knowledge map of the target service exists in the cloud knowledge base, generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script, the fault information of the target service is inquired in the knowledge map, the services of knowledge search and knowledge recommendation are provided in an intelligent matching mode, the knowledge map can be used for automatically analyzing the service information for knowledge recommendation, and a tool troubleshooting script for inquiring fault information is generated through the troubleshooting elements, so that the faults and troubleshooting problems can be quickly positioned, the processing timeliness of work orders is improved, the technical problem that the business faults cannot be debugged through a knowledge base in the related technology is solved, and the problem troubleshooting efficiency is improved.
Fig. 3 is a logical structure diagram of the knowledge base system according to the embodiment of the present invention, and as shown in fig. 3, the knowledge base is composed of at least three parts, namely, a basic data layer, a data processing layer, and a data output layer. The following is a detailed description:
and the basic data layer classifies the knowledge in the knowledge base into three categories, wherein the three categories are classified according to the validity period of the knowledge, the service type of the knowledge and the display mode of the knowledge. The knowledge can be divided into short-term knowledge and long-term knowledge according to the validity period and quality of the knowledge, divided into business knowledge and problem troubleshooting knowledge according to a solution mode, and divided into a QA (questions answers) mode and a SOP (Standard Operating procedure) mode according to a presentation mode.
And the data processing layer divides the problem processing process into three parts, namely pre-check, problem troubleshooting and post-processing, and matching technologies such as search recommendation, intelligent troubleshooting and the like are applied in the three parts of processing.
In this layer, the pre-check module and the post-processing module: the method is set for the knowledge of problem troubleshooting, and for the troubleshooting of a problem, the pre-verification means that some basic parameters are required for the troubleshooting of the problem, for example, relevant problems of a troubleshooting store, the store ID and relevant entity information are required, and if the pre-verification is not passed, the follow-up problem troubleshooting analysis cannot be performed. The post-processing is to judge the result of the problem investigation and to determine whether further work needs to be performed in combination with a processing strategy. Such as troubleshooting a store problem, and finally locating that the store is closed, further work such as store taking off shelves is required, which may be initiating a work order or a task.
A knowledge configuration module: the SOP, namely a standard operation program, describes the standard operation steps and requirements of a certain event in a uniform format to guide and standardize daily work. The method is often used for improving the working efficiency and the working efficiency.
The knowledge search and knowledge recommendation module: and respectively executing a knowledge search process and a knowledge recommendation process.
Tool + troubleshooting module: the method is used for executing a knowledge problem troubleshooting core and a tool intelligent troubleshooting process.
Category, label, classification management: management functions for the aspects of adding, deleting and modifying knowledge-related attributes are provided, and the attributes are used for the recommendation and search process of knowledge.
And the data output layer displays the results of the knowledge search recommendation, automatically generates tasks according to the results of the tool intelligent problem troubleshooting, and processes and issues the tasks according to the processing strategy. The method is a result of knowledge search and knowledge recommendation output, and the subsequent processing strategy output in a post-processing module of a data processing layer.
FIG. 4 is a flow chart of knowledge troubleshooting in accordance with an embodiment of the present invention. The knowledge base uses the business entities such as work orders which need knowledge to assist in problem processing in a scene. The problem troubleshooting process of the knowledge base comprises the following steps:
s402, firstly, carrying out knowledge search and knowledge recommendation according to the work order content or keywords input by a user;
fig. 5 is a schematic flow chart of the knowledge search and knowledge recommendation according to the embodiment of the present invention, as shown in fig. 5, including:
s502, firstly, a search engine of a knowledge base is constructed according to the existing knowledge base data, namely a knowledge candidate set containing knowledge core information, and then a data index and matching algorithm is provided for recommendation and search of knowledge. The knowledge information needs to be processed in advance, and the core information of each knowledge includes: knowledge title, knowledge state, knowledge category, knowledge label, knowledge usage times, etc.
S504, after the search engine is built, the search and recommendation of knowledge can be started. Firstly, acquiring input data of knowledge search and recommendation: the work order drawings/keywords are the work order information helpful for positioning the work order problem, and comprise data such as work order categories, work order descriptions and work order labels. In a search scenario, the user may also enter a search keyword.
S506, the system needs to match the work order portrait/keywords with knowledge data in a search engine, and firstly extracts features of the work order portrait/keywords and the knowledge data, wherein the features include text features of knowledge and work order information, word segmentation features of the knowledge and work order information based on a domain dictionary, knowledge popularity and the like.
S508, recalling according to knowledge recommendation and search rules, if knowledge search is carried out, full-text retrieval is carried out based on keywords, and information such as knowledge labels, titles and categories are mainly matched; and if the knowledge is recommended, performing word segmentation and extracting main key information based on the work order description information, and then performing full-text retrieval on the knowledge labels and the titles.
And S510, performing fine ranking (secondary ranking) on the recall results, and performing scoring ranking based on the characteristics and the rules. And finally, returning a result of searching recommendation.
S404, judging whether knowledge which can be used for solving the problem exists in the knowledge base or not according to the search recommendation result, if not, judging that the problem lacks knowledge support, automatically converting the work order problem, inputting a knowledge main body, setting a problem solving step according to the problem type, and inputting a corresponding tool URL and troubleshooting elements for tool intelligent problem troubleshooting.
S406, if corresponding knowledge exists in the knowledge base, problem troubleshooting elements need to be input, a tool is triggered to automatically troubleshoot after the input, and finally a tool troubleshooting result is given.
And if the knowledge search recommendation result shows that the problem can be solved by using the specified knowledge, starting a knowledge + tool automatic troubleshooting process. Fig. 6 is a flowchart of a fault query using a tool template according to an embodiment of the present invention, as shown in fig. 6, including:
s602, acquiring a knowledge solution step, wherein the knowledge solution step is composed of a plurality of knowledge nodes, and the knowledge nodes are mainly divided into three types: a start node, an intermediate node, and a result node. Each node judges whether the processing flow of the node is executed or not according to the processing result of the previous node. The first step is to first acquire the solution step and all nodes for the specified knowledge to solve the problem.
And S604, generating a tool troubleshooting template according to the solving step and all the nodes, wherein the tool troubleshooting template is generated by firstly analyzing tool URLs, inputs and outputs of all the nodes, then combining according to the relationship among the nodes and finally generating the tool troubleshooting template.
And S606, generating a tool troubleshooting script according to the problem troubleshooting elements, wherein the problem troubleshooting elements mainly refer to business entities related to tool troubleshooting, including store IDs, commodity IDs, coupon IDs and the like, and the entity contents in the tool troubleshooting template are replaced after the problem troubleshooting elements are obtained to generate the tool troubleshooting script.
And S608, generating a tool troubleshooting script, then calling a tool interface, wherein the calling mode can be SQL statements or data query interfaces of other business systems, and finally combining and converting according to query results and returning final troubleshooting results.
The problem troubleshooting method provides a unified solution for the problem troubleshooting at present, can realize the datamation and the online of the problem troubleshooting thought, and provides a more perfect management and maintenance strategy. Through the knowledge search and recommendation functions of the system and the embedding of the recommendation function into the work order, the work order information can be automatically analyzed for knowledge recommendation, and problems can be quickly located and eliminated. The tool and knowledge are combined, and according to the structured knowledge solution steps and the node combination tool, an automatic intelligent problem troubleshooting scheme of the knowledge and tool is provided, on one hand, certain carding and precipitation are carried out on tool data, and on the other hand, the problem troubleshooting efficiency is obviously improved.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In this embodiment, a device and a system for querying fault information are also provided, which are used to implement the foregoing embodiments and preferred embodiments, and are not described again after being described. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 7 is a block diagram of a fault information query apparatus according to an embodiment of the present invention, where the apparatus includes: a first receiving module 70, a first querying module 72, a second receiving module 74, and a second querying module 76.
A first receiving module 70, configured to receive service information of a target service;
a first query module 72, configured to query a knowledge graph of the target service in a cloud knowledge base according to the service information;
a second receiving module 74, configured to receive a troubleshooting element of the target service when the knowledge graph of the target service exists in the cloud knowledge base;
and a second query module 76, configured to generate a tool troubleshooting script according to the troubleshooting elements, and call a data query interface through the tool troubleshooting script to query the failure information of the target service in the knowledge graph.
Optionally, the first query module includes:
the acquisition unit is used for acquiring the access information from the service information based on the recall strategy;
the extraction unit is used for extracting the characteristic information of the parameter information;
the retrieval unit is used for retrieving a first knowledge graph matched with the characteristic information from the cloud knowledge base;
and the determining unit is used for sorting the matching degrees of the recall results in the first knowledge graph and determining a plurality of recall results with the highest matching degrees as a second knowledge graph of the target service.
Optionally, the second query module includes:
the acquisition unit is used for acquiring a knowledge node set of a troubleshooting process;
the generating unit is used for generating a tool troubleshooting template according to the knowledge node set;
and the replacing unit is used for replacing the entity content in the tool troubleshooting template by using the troubleshooting element as a business entity to generate a tool troubleshooting script.
Optionally, the generating unit includes:
the analysis subunit is used for analyzing the tool uniform resource locator URL, the input and the output of each knowledge node in the knowledge node set;
and the generating subunit is used for combining according to the logic sequence among the knowledge nodes after the analysis is finished, and generating the tool checking template.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Embodiments of the present invention also provide a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
Alternatively, in an aspect of the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
s1, receiving the service information of the target service;
s2, inquiring the knowledge graph of the target service in a cloud knowledge base according to the service information;
s3, receiving troubleshooting elements of the target service when the knowledge graph of the target service exists in the cloud knowledge base;
and S4, generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script, and querying the fault information of the target service in the knowledge graph.
Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in an aspect of this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, receiving the service information of the target service;
s2, inquiring the knowledge graph of the target service in a cloud knowledge base according to the service information;
s3, receiving troubleshooting elements of the target service when the knowledge graph of the target service exists in the cloud knowledge base;
and S4, generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script, and querying the fault information of the target service in the knowledge graph.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (12)
1. A method for inquiring fault information is characterized by comprising the following steps:
receiving service information of a target service;
inquiring a knowledge graph of the target service in a cloud knowledge base according to the service information;
when the knowledge graph of the target service exists in the cloud knowledge base, receiving troubleshooting factors of the target service;
generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script, and querying the fault information of the target service in the knowledge graph;
wherein generating a tool troubleshooting script according to the troubleshooting element comprises: acquiring a knowledge node set of a troubleshooting process; analyzing a tool Uniform Resource Locator (URL), input and output of each knowledge node in the knowledge node set; after the analysis is completed, combining according to the logic sequence among the knowledge nodes to generate a tool checking template; replacing the entity content in the tool troubleshooting template by taking the troubleshooting element as a business entity to generate a tool troubleshooting script; and the troubleshooting process is set according to the fault type of the fault information, and a tool URL and troubleshooting elements matched with the troubleshooting process are recorded in the cloud knowledge base.
2. The method of claim 1, wherein querying a cloud repository for the knowledge graph of the target service according to the service information comprises:
acquiring access information from the service information based on a recall strategy;
extracting characteristic information of the parameter information;
searching a first knowledge graph matched with the characteristic information in the cloud knowledge base;
and sorting the matching degrees of the recall results in the first knowledge graph, and determining a plurality of recall results with the highest matching degrees as a second knowledge graph of the target service.
3. The method of claim 2, wherein extracting feature information of the reference information comprises:
extracting text features of the parameter information;
extracting word segmentation characteristics of the reference information based on a domain dictionary;
and extracting heat information of the parameter entering information.
4. The method of claim 2, wherein the recall policy is a knowledge recommendation rule, and wherein obtaining the access information from the service information based on the recall policy comprises:
acquiring a service portrait and/or keywords from the service information;
extracting preset service data of the service information from the service portrait and/or the keywords, wherein the preset service data comprises work order categories, work order titles, work order description information and work order result information;
and determining the preset service data as first access parameter information.
5. The method of claim 2, wherein the recall policy is a knowledge search rule, and wherein obtaining the access information from the service information based on the recall policy comprises:
acquiring a service portrait and/or keywords from the service information, and receiving search keywords related to the target service and search category information of the target service;
and determining the service portrait and/or the keyword, the search keyword and the search category information as second entry information.
6. The method of claim 2, wherein retrieving the first knowledge graph in the cloud knowledge base that matches the feature information comprises:
and carrying out full-text search in the cloud knowledge base by using the characteristic information to obtain a knowledge tag, a knowledge title and a knowledge category which are matched with the characteristic information.
7. The method of claim 1, wherein the troubleshooting elements include at least one of: the store identification of the target service, the commodity identification of the target service and the coupon identification of the target service.
8. The method of claim 1, wherein after querying a cloud repository for the knowledge-graph of the target service according to the service information, the method further comprises:
when the knowledge map of the target service does not exist in the cloud end knowledge base, determining that the target service lacks knowledge support in the cloud end knowledge base;
receiving fault information of the target service, performing knowledge conversion on the fault information, and inputting a knowledge map of the target service; and setting a troubleshooting process according to the fault type of the fault information, and inputting a tool URL and troubleshooting elements matched with the troubleshooting process into the cloud knowledge base.
9. An apparatus for querying fault information, comprising:
the first receiving module is used for receiving the service information of the target service;
the first query module is used for querying the knowledge graph of the target service in a cloud knowledge base according to the service information;
the second receiving module is used for receiving troubleshooting factors of the target service when the knowledge graph of the target service exists in the cloud knowledge base;
the second query module is used for generating a tool troubleshooting script according to the troubleshooting elements, calling a data query interface through the tool troubleshooting script and querying the fault information of the target service in the knowledge graph; wherein generating a tool troubleshooting script according to the troubleshooting element comprises: acquiring a knowledge node set of a troubleshooting process; analyzing a tool Uniform Resource Locator (URL), input and output of each knowledge node in the knowledge node set; after the analysis is completed, combining according to the logic sequence among the knowledge nodes to generate a tool checking template; replacing the entity content in the tool troubleshooting template by taking the troubleshooting element as a business entity to generate a tool troubleshooting script; and the troubleshooting process is set according to the fault type of the fault information, and a tool URL and troubleshooting elements matched with the troubleshooting process are recorded in the cloud knowledge base.
10. The apparatus of claim 9, wherein the first query module comprises:
the acquisition unit is used for acquiring the access information from the service information based on the recall strategy;
the extraction unit is used for extracting the characteristic information of the parameter information;
the retrieval unit is used for retrieving a first knowledge graph matched with the characteristic information from the cloud knowledge base;
and the determining unit is used for sorting the matching degrees of the recall results in the first knowledge graph and determining a plurality of recall results with the highest matching degrees as a second knowledge graph of the target service.
11. A storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 8 when executed.
12. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910867099.8A CN110807085B (en) | 2019-09-12 | 2019-09-12 | Fault information query method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910867099.8A CN110807085B (en) | 2019-09-12 | 2019-09-12 | Fault information query method and device, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110807085A CN110807085A (en) | 2020-02-18 |
| CN110807085B true CN110807085B (en) | 2022-02-08 |
Family
ID=69487512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910867099.8A Active CN110807085B (en) | 2019-09-12 | 2019-09-12 | Fault information query method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110807085B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111694872B (en) * | 2020-04-29 | 2023-05-23 | 时时同云科技(成都)有限责任公司 | Method and device for providing service handling data scheme |
| CN111585809A (en) * | 2020-04-29 | 2020-08-25 | 北京润通丰华科技有限公司 | Method for auditing network equipment configuration by utilizing big data statistical analysis |
| CN113868427A (en) * | 2020-06-30 | 2021-12-31 | 中国移动通信集团天津有限公司 | Data processing method and device and electronic equipment |
| CN111813872B (en) * | 2020-07-08 | 2024-04-19 | 上海燕汐软件信息科技有限公司 | Method, device and equipment for generating fault troubleshooting model |
| CN112215501B (en) * | 2020-10-15 | 2021-11-26 | 拉扎斯网络科技（上海）有限公司 | Method and device for generating problem troubleshooting flow data |
| CN112348213A (en) * | 2020-11-27 | 2021-02-09 | 新华三大数据技术有限公司 | Operation and maintenance troubleshooting implementation method, device, medium and equipment |
| CN112786124B (en) * | 2020-12-30 | 2022-09-02 | 医渡云（北京）技术有限公司 | Problem troubleshooting method and device, storage medium and equipment |
| CN113327071B (en) * | 2021-08-04 | 2021-11-30 | 深圳市深水水务咨询有限公司 | 5G-based environment management method and device, computer equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241413A (en) * | 2018-08-20 | 2019-01-18 | 安徽智恒信科技有限公司 | A kind of the knowledge recommendation method and maintenance work platform of work order |
| CN109767081A (en) * | 2018-12-25 | 2019-05-17 | 云南电网有限责任公司信息中心 | Electric power work order table generating method and device |
| CN110135598A (en) * | 2019-05-16 | 2019-08-16 | 兰州交通大学 | A kind of high-speed railway electricity business maintenance auxiliary system of knowledge based service |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10019302B2 (en) * | 2016-02-16 | 2018-07-10 | T-Mobile Usa, Inc. | Workflow engine for troubleshooting user device issues |
| CN107623602B (en) * | 2017-10-12 | 2021-03-26 | 郑州市景安网络科技股份有限公司 | Automatic checking method and system |
| CN109343995A (en) * | 2018-10-25 | 2019-02-15 | 金税信息技术服务股份有限公司 | Intelligent O&M analysis system based on multi-source heterogeneous data fusion, machine learning and customer service robot |
-
2019
- 2019-09-12 CN CN201910867099.8A patent/CN110807085B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241413A (en) * | 2018-08-20 | 2019-01-18 | 安徽智恒信科技有限公司 | A kind of the knowledge recommendation method and maintenance work platform of work order |
| CN109767081A (en) * | 2018-12-25 | 2019-05-17 | 云南电网有限责任公司信息中心 | Electric power work order table generating method and device |
| CN110135598A (en) * | 2019-05-16 | 2019-08-16 | 兰州交通大学 | A kind of high-speed railway electricity business maintenance auxiliary system of knowledge based service |
Non-Patent Citations (3)
| Title |
|---|
| SOA-based platform implementing a structural modelling for large-scale system fault detection: Application to a board machine;A. Faghraoui 等;《2012 IEEE International Conference on Control Applications》;20121005;681-685 * |
| 支持多工具协同的流程管理系统的设计与实现;杨涛 等;《计算机应用》;20170710(第07期);2019-2026 * |
| 调度自动化系统知识图谱的构建与应用;李新鹏 等;《中国电力》;20190228;第52卷(第02期);70-77、157 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110807085A (en) | 2020-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110807085B (en) | Fault information query method and device, storage medium and electronic device | |
| CN109639771B (en) | Method and device for pushing service, computer equipment and storage medium | |
| US20130238375A1 (en) | Evaluating email information and aggregating evaluation results | |
| CN110502692B (en) | Information retrieval method, device, equipment and storage medium based on search engine | |
| CN108920607B (en) | Method and device for discovering field and electronic equipment | |
| CN110648172B (en) | Identity recognition method and system integrating multiple mobile devices | |
| CN104750760A (en) | Application software recommending method and device | |
| CN105096023A (en) | System and method for pushing data relevant to working standard | |
| CN110888985A (en) | Alarm information processing method and device, electronic equipment and storage medium | |
| CN110111796B (en) | Identity recognition method and device | |
| CN111353874B (en) | Intelligent service system of bank outlets | |
| CN115860548B (en) | SaaS one-stop platform management method, system and medium based on big data | |
| CN109902196B (en) | Trademark category recommendation method and device, computer equipment and storage medium | |
| CN109377391B (en) | Information tracking method, storage medium and server | |
| CN110647448A (en) | Mobile application operation log data real-time analysis method, server and system | |
| CN111124891A (en) | Access state detection method and device, storage medium and electronic device | |
| CN110472019A (en) | Public sentiment searching method and device | |
| CN114610689B (en) | Recording and analyzing method for request log in distributed environment | |
| CN108491506A (en) | Method for pushing problem answers combination | |
| CN110825609A (en) | Service testing method, device and system | |
| CN110471926B (en) | File establishing method and device | |
| CN113778831A (en) | Data application performance analysis method, device, equipment and medium | |
| CN106294433B (en) | Equipment information processing method and device | |
| CN110674386B (en) | Resource recommendation method, device and storage medium | |
| CN113191711A (en) | Express delivery sending strategy determining method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |