CN112925895A - Natural language software operation and maintenance method and device - Google Patents
Natural language software operation and maintenance method and deviceDownload PDFInfo
- Publication number
- CN112925895A CN112925895ACN202110332002.0ACN202110332002ACN112925895ACN 112925895 ACN112925895 ACN 112925895ACN 202110332002 ACN202110332002 ACN 202110332002ACN 112925895 ACN112925895 ACN 112925895A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- natural language
- preset
- strategy
- user
- 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.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The application relates to the field of software operation and maintenance, can also be used in the field of finance, and particularly relates to a natural language software operation and maintenance method and device.
Background
The intelligent operation and maintenance robot or the intelligent operation and maintenance robot based on machine learning generally comprises a background processing end, an operation and maintenance database and a plurality of operation and maintenance robots, the database is updated through a learning strategy or rules are specified manually, and when a fault signal is output to a back end, the back end triggers fault recovery according to the maintained rules.
Chat operation and maintenance (chatops) generally manages operation and maintenance work by means of a group chat room, and operation and maintenance personnel can communicate with a robot in the chat room to trigger execution of some operation and maintenance rules, scripts and the like which are maintained in advance, complete environment change, acquire some basic information of the environment and realize a series of operation and maintenance actions such as the like.
The inventor finds that the intelligent operation and maintenance robot is mainly a back-end program, lacks of human-computer interaction, and users are basically operation and maintenance experts and operation and maintenance personnel. The traditional chat operation and maintenance has foreground pages with rich contents, but the background function is single, and the function realization depends on detailed configuration. The operation and maintenance personnel have better effect when using the device by themselves, but the accuracy is low when the non-operation and maintenance personnel use the device.
Disclosure of Invention
Aiming at the problems in the prior art, the application provides a method and a device for operating and maintaining natural language software, which can reduce the maintenance and use threshold through simple configuration and more accurately realize the operation and maintenance requirements of users.
In order to solve at least one of the above problems, the present application provides the following technical solutions:
in a first aspect, the present application provides a natural language software operation and maintenance method, including:
receiving a natural language operation and maintenance request sent by a user, and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to a set rule;
acquiring corresponding operation and maintenance environment information from a preset configuration management database according to the operation and maintenance strategy, and sending the operation and maintenance strategy and the operation and maintenance environment information to corresponding micro-service clusters so that the micro-service clusters execute the operation and maintenance strategy according to the operation and maintenance environment information;
and receiving the operation and maintenance execution result returned by the micro service cluster and feeding back the operation and maintenance execution result to the user.
Further, the receiving a natural language operation and maintenance request sent by a user, and determining an operation and maintenance policy corresponding to the natural language operation and maintenance request according to a set rule includes:
receiving a natural language operation and maintenance request sent by a user in a chat group corresponding to the current application, and performing natural language analysis on the natural language operation and maintenance request;
retrieving the natural language analysis result according to a preset inverted index, a semantic index and a semantic representation neural network model to obtain a preset operation and maintenance strategy, wherein the similarity between the preset operation and maintenance strategy and the natural language operation and maintenance request is higher than a threshold value;
according to a preset semantic similarity neural network model, carrying out similarity analysis on the preset operation and maintenance strategy with the similarity higher than a threshold value and the natural language operation and maintenance request;
and performing regression analysis on the result of the similarity analysis according to a preset linear regression model and a gradient lifting model, and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to the result of the regression analysis.
Further, the performing natural language analysis on the natural language operation and maintenance request includes:
and carrying out named entity recognition on the natural language operation and maintenance request according to the entity type, the time type and the number type, and carrying out natural language cutting according to the recognition result of the named entity.
Further, before the retrieving the result of the natural language analysis according to the preset reverse index, the semantic index and the semantic representation neural network model, the method includes:
extracting key words in a preset demand set, and establishing an inverted index according to the positions of the key words in a preset operation and maintenance strategy;
and clustering key words in a preset operation and maintenance strategy, and establishing semantic indexes according to the clustered key words.
In a second aspect, the present application provides a natural language software operation and maintenance device, including:
the operation and maintenance strategy determination module is used for receiving a natural language operation and maintenance request sent by a user and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to a set rule;
the strategy scheduling execution module is used for acquiring corresponding operation and maintenance environment information from a preset configuration management database according to the operation and maintenance strategy and sending the operation and maintenance strategy and the operation and maintenance environment information to a corresponding micro-service cluster so that the micro-service cluster executes the operation and maintenance strategy according to the operation and maintenance environment information;
and the operation and maintenance result feedback module is used for receiving the operation and maintenance execution result returned by the micro service cluster and feeding the operation and maintenance execution result back to the user.
Further, the operation and maintenance strategy determination module comprises:
the natural language analysis unit is used for receiving a natural language operation and maintenance request sent by a user in a chat group corresponding to the current application and carrying out natural language analysis on the natural language operation and maintenance request;
the indexing unit is used for retrieving the natural language analysis result according to a preset inverted index, a semantic index and a semantic representation neural network model to obtain a preset operation and maintenance strategy, wherein the similarity between the preset operation and maintenance strategy and the natural language operation and maintenance request is higher than a threshold value;
the similarity analysis unit is used for carrying out similarity analysis on the preset operation and maintenance strategy with the similarity higher than a threshold value and the natural language operation and maintenance request according to a preset semantic similarity neural network model;
and the reordering unit is used for performing regression analysis on the result of the similarity analysis according to a preset linear regression model and a gradient lifting model, and determining the operation and maintenance strategy corresponding to the natural language operation and maintenance request according to the result of the regression analysis.
Further, the natural language analysis unit includes:
and the entity identification and segmentation subunit is used for carrying out named entity identification on the natural language operation and maintenance request according to an entity type, a time type and a number type and carrying out natural language segmentation according to the named entity identification result.
Further, still include:
the inverted index building unit is used for extracting key words in a preset demand set and building an inverted index according to the positions of the key words in a preset operation and maintenance strategy;
and the semantic index construction unit is used for clustering key words in the preset operation and maintenance strategy and establishing a semantic index according to the clustered key words.
In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the natural language software operation and maintenance method when executing the program.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the natural language software operation and maintenance method.
According to the technical scheme, the method and the device for the operation and maintenance of the natural language software are characterized in that a natural language operation and maintenance request sent by a user is analyzed to determine a corresponding operation and maintenance strategy, corresponding operation and maintenance environment information is automatically obtained from a preset configuration management database, and the operation and maintenance strategy and the operation and maintenance environment information are sent to a corresponding micro-service cluster, so that the micro-service cluster executes the operation and maintenance strategy according to the operation and maintenance environment information, and therefore maintenance and use thresholds are reduced through simple configuration, and the operation and maintenance requirements of the user are more accurately met.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flowchart illustrating a natural language software operation and maintenance method according to an embodiment of the present application;
FIG. 2 is a second flowchart illustrating a natural language software operation and maintenance method according to an embodiment of the present application;
FIG. 3 is a third schematic flowchart of a natural language software operation and maintenance method in an embodiment of the present application;
FIG. 4 is a diagram of one of the structures of the natural language software operation and maintenance device in the embodiment of the present application;
FIG. 5 is a second block diagram of the natural language software operation and maintenance device in the embodiment of the present application;
FIG. 6 is a third block diagram of the natural language software operation and maintenance device in the embodiment of the present application;
FIG. 7 is a fourth block diagram of the natural language software operation and maintenance device in the embodiment of the present application;
FIG. 8 is a diagram illustrating the overall operation and maintenance process of the natural language software according to an embodiment of the present application;
FIG. 9 is a schematic diagram of an intelligent customer service operation process according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Considering that the intelligent operation and maintenance robot in the prior art is mainly a back-end program and lacks man-machine interaction, users are basically operation and maintenance experts and operation and maintenance personnel, the traditional chatting operation and maintenance has foreground pages with rich content, but the background function is single, the function implementation depends on detailed configuration, the operation and maintenance personnel have better effect when using the robot, but the accuracy of the operation and maintenance personnel is low when using the robot, the application provides a natural language software operation and maintenance method and device, the natural language operation and maintenance request sent by the users is analyzed, the corresponding operation and maintenance strategy is determined, the corresponding operation and maintenance environment information is automatically obtained from the preset configuration management database, and the operation and maintenance strategy and the operation and maintenance environment information are sent to the corresponding micro-service cluster, so that the micro-service cluster executes the operation and maintenance strategy according to the operation and maintenance environment information, thereby the maintenance and use thresholds are reduced through simple configuration, and the operation and maintenance requirements of the user are realized more accurately.
In order to reduce maintenance and use thresholds through simple configuration and more accurately realize the operation and maintenance requirements of users, the application provides an embodiment of a natural language software operation and maintenance method, and referring to fig. 1, the natural language software operation and maintenance method specifically includes the following contents:
step S101: receiving a natural language operation and maintenance request sent by a user, and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to a set rule.
Optionally, the natural language operation and maintenance request may be an operation and maintenance requirement provided by an operation and maintenance person in a natural language manner, and may be sent in a chat group (e.g., a chat room) of a specific application, and the application may be used as an intelligent customer service in the chat group to obtain the natural language operation and maintenance request.
Optionally, in the chat room group, each application has its own independent chat room, the user groups are distinguished according to the application, and users of the same group can master the latest test environment information and operation and maintenance operation dynamics in the chat room. The chat room is implemented using node.
Optionally, the user may trigger interaction with the intelligent customer service of the present application in the @ intelligent customer service manner, and further initiate an operation and maintenance request, where the request content is in a natural language, and the request types may be various, and the chat room background of the present application may send the content input by the user to the intelligent customer service cluster in a http request manner for processing, and after the natural language operation and maintenance request of the user is analyzed and understood, the present application may determine a corresponding operation and maintenance policy from preset operation and maintenance policies.
Step S102: and acquiring corresponding operation and maintenance environment information from a preset configuration management database according to the operation and maintenance strategy, and sending the operation and maintenance strategy and the operation and maintenance environment information to a corresponding micro-service cluster so that the micro-service cluster executes the operation and maintenance strategy according to the operation and maintenance environment information.
Step S103: and receiving the operation and maintenance execution result returned by the micro service cluster and feeding back the operation and maintenance execution result to the user.
Optionally, after the operation and maintenance policy is determined, the application may obtain corresponding operation and maintenance environment information from a preset Configuration Management Database (CMDB) according to the operation and maintenance policy, and send the operation and maintenance policy and the operation and maintenance environment information to the corresponding micro service cluster.
Optionally, a Configuration Management Database (CMDB) is used to summarize environment information of multiple statistical dimensions, in a large-scale multi-type test environment, code contents of multiple applications and different production time points are deployed at the same time, in the CMDB, each set of environment of each application is registered according to a production time sequence, each set of environment is divided into multiple nodes according to a minimum service granularity, and the multiple nodes include an application server, an Oracle database, a Mysql database, a batch server, and the like, and each service node includes type information of the node, operating system information, a server ip address, server user information, and other various kinds of element information.
Optionally, after receiving the specific operation and maintenance policy and the operation and maintenance environment information sent by the intelligent customer service, the micro-service cluster executes the operation and maintenance policy in the corresponding server and waits for a processing result, and then feeds the result back to the back end of the chat room, and finally displays the result in the chat room to the user.
As can be seen from the above description, the operation and maintenance method for natural language software provided in this embodiment of the present application can determine a corresponding operation and maintenance policy by analyzing a natural language operation and maintenance request sent by a user, automatically obtain corresponding operation and maintenance environment information from a preset configuration management database, and send the operation and maintenance policy and the operation and maintenance environment information to a corresponding micro-service cluster, so that the micro-service cluster executes the operation and maintenance policy according to the operation and maintenance environment information, thereby reducing maintenance and use thresholds through simple configuration, and more accurately implementing user operation and maintenance requirements.
In order to determine the corresponding operation and maintenance policy accurately according to the natural language request, in an embodiment of the natural language software operation and maintenance method of the present application, referring to fig. 2, the step S101 may further include the following steps:
step S201: and receiving a natural language operation and maintenance request sent by a user in a chat group corresponding to the current application, and performing natural language analysis on the natural language operation and maintenance request.
Optionally, the natural language operation and maintenance request may be an operation and maintenance requirement provided by an operation and maintenance person in a natural language manner, and may be sent in a chat group (e.g., a chat room) of a specific application, and the application may be used as an intelligent customer service in the chat group to obtain the natural language operation and maintenance request.
Optionally, the natural language analysis may be to identify and cut the natural language operation and maintenance request according to three types (entity type, time type, and number type) of named entities.
Step S202: and retrieving the natural language analysis result according to a preset inverted index, a semantic index and a semantic representation neural network model to obtain a preset operation and maintenance strategy, wherein the similarity between the preset operation and maintenance strategy and the natural language operation and maintenance request is higher than a threshold value.
Optionally, in the application, a user is required to maintain a precise natural language form requirement and execution strategy set, then an inverted index and a semantic index are respectively established for the requirement set, and the inverted index part is responsible for extracting key words and word positions in the requirement set to form a key word-strategy matrix, that is, an index is established for the positions of the key words in a specific strategy. The semantic indexing is to cluster key words in the strategy and build indexes for words with semantic relevance. The ANN (approximate nearest neighbor search) implemented by Python runs the process. In addition, the method and the device can also preset a proper noun dictionary aiming at the financial software operation and maintenance field, can pertinently establish indexes, and avoid excessive cutting of sentences when the indexes are generated.
Optionally, the present application may also train the neural network model in advance: the semantic representation model and the semantic similarity model are used for model training, and a large amount of natural language data and an accurate operation and maintenance requirement set are used. The semantic representation model uses BOW (bag of words), CNN (convolutional neural network), and the semantic similarity model uses MatchPyramid (construction matching matrix), all of which are realized by Python.
Optionally, the generated index and semantic representation model may be used to retrieve information after natural language analysis processing, and retrieve all preset operation and maintenance policies that are the same as and/or similar to (i.e., higher than) the user natural language operation and maintenance request.
Step S203: and according to a preset semantic similarity neural network model, carrying out similarity analysis on the preset operation and maintenance strategy with the similarity higher than a threshold value and the natural language operation and maintenance request.
Optionally, the similarity evaluation scoring can be performed on the retrieved preset operation and maintenance strategy and the natural language operation and maintenance request sent by the user.
In one embodiment, the user sends a request: "DDBA pipeline creation". It is assumed that DDBA is a commonly used persistent integration platform for users, which is maintained as a special named entity into a domain-specific noun dictionary.
The tokenizer first breaks down the request into: [ DDBA, length: 4, begin: 0, weight: 0.333333, [ pipeline, length: 9, begin: 4, weight: 0.333333, [ Create, length: 6, begin: 13, weight: 0.333333].
Because of the existence of the proper noun DDBA, the search only returns the preset strategy related to the DDBA platform, and the result is as follows:
and (5) when the id is 91, the DDBA pipeline creates a JENKINS task.
And d, 88, locking and unlocking the DDBA pipeline.
And (5) establishing a DDBA pipeline when id is 190.
id 207, DDBA pipeline application.
And id is 49, and the DDBA pipeline is used for supporting personnel on duty.
id 124, DDBA pipeline log view.
And id 38, how the DDBA hand-off production line is used.
id 192, the DDBA pipeline configures the issue scope and node.
id 233, DDBA pipeline soar scan trigger.
And d, 225, applying DDBA change pipeline authority.
A large number of DDBA platform assembly line related strategies exist in the preset operation and maintenance strategies, the semantic representation model processes all returned results, and the comprehensive grading of the part of speech, phrase sequence, length and the like formed by sentences is carried out:
and (5) the DDBA pipeline creates a JENKINS task with id being 91 and socre being 0.560519.
And id is 88, the DDBA pipeline is blocked and unlocked, socre is 0.552531.
190, establishing a DDBA pipeline, socre: 0.582507.
id 207, DDBA pipeline application, socre 0.596339.
id 49, DDBA pipeline on-duty support personnel, socre 0.537818.
id 124, DDBA pipeline log view, socre 0.452070.
id 38, how the DDBA hand-off production line is used, socre 0.356850.
id 192, DDBA pipeline configuration issue scope and node, socre 0.364970.
id 233, DDBA pipeline soar scan trigger, socre 0.355371.
id 225, DDBA change pipeline filing application, socre 0.324169.
It can be seen from the above returned results that the score of the preset strategy DDBA pipeline application is slightly higher than that of the new DDBA pipeline from the semantic representation model comparing the characteristics of part of speech, phrase sequence, length, etc.
After semantic representation calculation, the semantic similarity neural network model compares the similarity and difference between the request and a preset sample according to the components of the sentence, the meaning of the vocabulary and the like, and calculates a score, wherein the result is as follows:
91, the DDBA pipeline creates JENKINS task 0.428571.
88, DDBA pipeline stuck unlock 0.500000.
190, and the DDBA pipeline 0.714286 is newly built.
id 207, DDBA pipeline application 0.500000.
id 49, DDBA pipeline attendant support 0.333333.
id 124, DDBA pipeline log view 0.333333.
And id 38, how the DDBA hand-off production line uses 0.285714.
192, the DDBA pipeline configures the issue range and node 0.266667.
id 233, DDBA pipeline soar scan trigger 0.307692.
225, DDBA change pipeline privilege filing application 0.222222.
The semantic representation model and the semantic similarity neural network model are all used as the data set to be processed in step S204.
Step S204: and performing regression analysis on the result of the similarity analysis according to a preset linear regression model and a gradient lifting model, and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to the result of the regression analysis.
Optionally, a Python-packaged linear regression model and a GBDT (gradient lifting) are used to perform regression analysis on the operation and maintenance strategy set after the similarity calculation, the scores of the documents are adjusted according to a certain weight, and finally a strategy closest to the user request is selected.
In order to accurately analyze the natural language request, in an embodiment of the natural language software operation and maintenance method of the present application, the step S201 may further include the following steps:
and carrying out named entity recognition on the natural language operation and maintenance request according to the entity type, the time type and the number type, and carrying out natural language cutting according to the recognition result of the named entity.
In order to accurately perform index query on the natural language request, in an embodiment of the natural language software operation and maintenance method of the present application, referring to fig. 3, before the step S202, the following contents may be further included:
step S301: extracting key words in a preset demand set, and establishing an inverted index according to the positions of the key words in a preset operation and maintenance strategy.
Step S302: and clustering key words in a preset operation and maintenance strategy, and establishing semantic indexes according to the clustered key words.
In order to reduce the maintenance and use thresholds through simple configuration and more accurately implement the operation and maintenance requirements of the user, the application provides an embodiment of a natural language software operation and maintenance device for implementing all or part of the contents of the natural language software operation and maintenance method, and referring to fig. 4, the natural language software operation and maintenance device specifically includes the following contents:
and the operation and maintenancestrategy determination module 10 is configured to receive a natural language operation and maintenance request sent by a user, and determine an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to a set rule.
And the policyscheduling execution module 20 is configured to obtain corresponding operation and maintenance environment information from a preset configuration management database according to the operation and maintenance policy, and send the operation and maintenance policy and the operation and maintenance environment information to a corresponding micro service cluster, so that the micro service cluster executes the operation and maintenance policy according to the operation and maintenance environment information.
And the operation and maintenance resultfeedback module 30 is configured to receive the operation and maintenance execution result returned by the micro service cluster and feed the operation and maintenance execution result back to the user.
As can be seen from the above description, the operation and maintenance device for natural language software provided in this embodiment of the present application can determine a corresponding operation and maintenance policy by analyzing a natural language operation and maintenance request sent by a user, automatically obtain corresponding operation and maintenance environment information from a preset configuration management database, and send the operation and maintenance policy and the operation and maintenance environment information to a corresponding micro-service cluster, so that the micro-service cluster executes the operation and maintenance policy according to the operation and maintenance environment information, thereby reducing maintenance and use thresholds through simple configuration, and more accurately implementing user operation and maintenance requirements.
In order to determine the corresponding operation and maintenance policy accurately according to the natural language request, in an embodiment of the operation and maintenance device of the natural language software of the present application, referring to fig. 5, the operation and maintenancepolicy determining module 10 includes:
and the natural language analysis unit 11 is configured to receive a natural language operation and maintenance request sent by a user in a chat group corresponding to the current application, and perform natural language analysis on the natural language operation and maintenance request.
And theindexing unit 12 is configured to retrieve the result of the natural language analysis according to a preset inverted index, a semantic index and a semantic representation neural network model, and obtain a preset operation and maintenance strategy in which the similarity between the preset operation and maintenance strategy and the natural language operation and maintenance request is higher than a threshold.
And thesimilarity analysis unit 13 is configured to perform similarity analysis on the preset operation and maintenance policy with the similarity higher than the threshold and the natural language operation and maintenance request according to a preset semantic similarity neural network model.
And thereordering unit 14 is configured to perform regression analysis on the result of the similarity analysis according to a preset linear regression model and a gradient lifting model, and determine an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to the result of the regression analysis.
In order to accurately analyze the natural language request, in an embodiment of the natural language software operation and maintenance device of the present application, referring to fig. 6, the natural language analysis unit 11 includes:
and the entity identification andsegmentation subunit 111 is configured to perform named entity identification on the natural language operation and maintenance request according to an entity type, a time type, and a number type, and perform natural language segmentation according to the named entity identification result.
In order to accurately perform index query on the natural language request, in an embodiment of the natural language software operation and maintenance device of the present application, referring to fig. 7, the following contents are further included:
the invertedindex constructing unit 41 is configured to extract a key word in the preset requirement set, and establish an inverted index according to a position of the key word in the preset operation and maintenance policy.
And the semanticindex constructing unit 42 is configured to perform clustering processing on the key words in the preset operation and maintenance strategy, and establish a semantic index according to the clustered key words.
In order to further explain the present solution, the present application further provides a specific application example of implementing the natural language software operation and maintenance method by using the natural language software operation and maintenance device, which specifically includes the following contents:
referring to fig. 8, 4 modules are included: 1) a chat room group directly facing users (chat rooms applying 1-N), 2) an intelligent robot cluster (also called an intelligent customer service cluster) capable of understanding the natural language of the users, 3) a micro-service cluster capable of executing various strategies, and 4) a CMDB module for managing large-scale multi-type environment information.
In a chat room group, each application has its own independent chat room. The user groups are differentiated by application. The users in the same group can master the latest test environment information and operation and maintenance operation dynamics in the chat room. The chat room is implemented using node.
The intelligent customer service robot resides in the chat room. The user triggers interaction with the customer service in an intelligent customer service mode, and then initiates an operation and maintenance request. The request content is in natural language, and the request type can be various. The background of the chat room sends the content input by the user to the intelligent customer service cluster for processing in an http request mode. After the intelligent customer service analyzes and understands the natural language request of the user, an execution strategy is selected, necessary environment information is extracted from the CMDB system, and a corresponding micro-service execution strategy is called.
The CMDB module aggregates environmental information for a plurality of statistical dimensions. In a large-scale multi-type test environment, code contents of a plurality of applications and different production time points are deployed at the same time. The CMDB first registers the respective sets of environments for each application in order of production time. Each set of environment is subdivided into a plurality of nodes according to the minimum service granularity, and the nodes comprise an application server, an Oracle database, a Mysql database, a batch server and the like. Each service node also contains the type information, the operating system information, the ip address of the server, the user information of the server and other various element information of the node.
And after receiving the specific execution strategy and parameter information sent by the intelligent customer service, the micro-service cluster module executes the strategy on the corresponding server and waits for processing the result, and then feeds the result back to the back end of the chat room and finally displays the result to the user in the chat room.
In the complete user requirement realization process, the intelligent customer service is responsible for decision making and overall planning. The intelligent customer service cluster module is shown in fig. 9, and the intelligent customer service cluster module is composed of 7 modules: 1) a natural language analysis module; 2, an index generating module; 3) a model training module; 4) a retrieval module; 5) a similarity calculation module; 6) a reordering module; 7) a domain specific noun dictionary.
The natural language analysis module is composed of a series of jar packages compiled in advance, processes the request of a user at first, and is responsible for identifying and cutting the named entities of the natural language according to three categories (entity category, time category and digital category).
The index generation module requires the user to first maintain a precise set of requirements and execution policies in natural language form. And then respectively establishing an inverted index and a semantic index for the demand set. The inverted index part is responsible for extracting key words and word positions in the requirement set to form a key word-strategy matrix, namely, an index is established for the positions of the key words in a specific strategy. The semantic indexing is to cluster key words in the strategy and build indexes for words with semantic relevance. The ANN (approximate nearest neighbor search) implemented by Python runs the process. In addition, a special noun dictionary aiming at the financial software operation and maintenance field is specially manufactured, so that indexes can be built in a targeted mode, and excessive cutting of sentences during index generation is avoided.
The model training module needs to train 2 models, namely a semantic representation model and a semantic similarity model. Model training uses a large amount of natural language data and an accurate set of operation and maintenance requirements. The semantic representation model uses BOW (bag of words), CNN (convolutional neural network), and the semantic similarity model uses MatchPyramid (construction matching matrix), all of which are realized by Python.
The retrieval module is composed of jar packets, the information processed by the module 1 is retrieved by using the indexes and semantic representation models which are generated in the module 2 and the module 3, all documents which are the same as or similar to the user request are retrieved, and are transmitted to the next module in a list form.
And the similarity calculation module performs similarity evaluation scoring on the searched documents and the request sent by the user. The semantic similarity calculation calls the model generated by the module 3, and the term similarity calculation uses Jaccard (Jaccard similarity coefficient). The domain-specific noun dictionary of module 7 is applied here to improve the score of a particular vocabulary.
And the reordering module performs regression analysis on the document set after similarity calculation by using a Python-packaged linear regression model and GBDT (gradient lifting), adjusts the score of each document according to a certain weight, and finally selects a strategy closest to the user request.
The domain-specific noun dictionary of module 7 is maintained by the user. The dictionary comprises proper nouns in the financial software operation and maintenance field and the word habits of the user, and is used by the modules 2 and 4.
As can be seen from the above, the present application can achieve at least the following technical effects:
1. the chat room group fully isolates user groups with different applications and different environments, locks a single communication channel of the same user group, reduces information difference among users, and improves communication efficiency and processing efficiency of operation and maintenance matters.
2. The concept of dimension, namely chat, is to finish various tasks of daily operation and maintenance, including environment monitoring, warning and early warning, demand change, resource coordination and the like, in a natural language mode. The user use threshold is reduced.
3. And (5) optimizing natural language processing. The domain specific noun dictionary comprises specific vocabularies in the financial software operation and maintenance domain and user habit vocabularies, and the comprehension capability of intelligent customer service in a specific scene is obviously improved. A user and an operation and maintenance expert designate a certain number of demand-strategy sets for model generation, and the hit rate of the accurate operation and maintenance strategy is improved.
4. Safe, compliant and efficient operation and maintenance. The operation and maintenance strategy is maintained by a user, operation and maintenance experts further abstract, optimize and comply, and finally user manual operations such as operation and maintenance, testing and development are replaced by a micro-service scheduling mode of the intelligent robot, so that the working efficiency is improved, the operation safety compliance is guaranteed, and the labor cost is saved.
In order to reduce the maintenance and use thresholds and more accurately realize the operation and maintenance requirements of the user through simple configuration in a hardware level, the application provides an embodiment of an electronic device for realizing all or part of contents in the natural language software operation and maintenance method, where the electronic device specifically includes the following contents:
a processor (processor), a memory (memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the communication interface is used for realizing information transmission between the natural language software operation and maintenance device and relevant equipment such as a core service system, a user terminal, a relevant database and the like; the logic controller may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the logic controller may be implemented with reference to the embodiment of the natural language software operation and maintenance method and the embodiment of the natural language software operation and maintenance device in the embodiment, and the contents thereof are incorporated herein, and repeated details are not repeated.
It is understood that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), an in-vehicle device, a smart wearable device, and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..
In practical applications, part of the natural language software operation and maintenance method may be executed on the electronic device side as described above, or all operations may be completed in the client device. The selection may be specifically performed according to the processing capability of the client device, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. The client device may further include a processor if all operations are performed in the client device.
The client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.
Fig. 10 is a schematic block diagram of a system configuration of anelectronic device 9600 according to an embodiment of the present application. As shown in fig. 10, theelectronic device 9600 can include acentral processor 9100 and amemory 9140; thememory 9140 is coupled to thecentral processor 9100. Notably, this fig. 10 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.
In one embodiment, the natural language software operation and maintenance method function may be integrated into thecentral processor 9100. Thecentral processor 9100 may be configured to control as follows:
step S101: receiving a natural language operation and maintenance request sent by a user, and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to a set rule.
Step S102: and acquiring corresponding operation and maintenance environment information from a preset configuration management database according to the operation and maintenance strategy, and sending the operation and maintenance strategy and the operation and maintenance environment information to a corresponding micro-service cluster so that the micro-service cluster executes the operation and maintenance strategy according to the operation and maintenance environment information.
Step S103: and receiving the operation and maintenance execution result returned by the micro service cluster and feeding back the operation and maintenance execution result to the user.
As can be seen from the above description, according to the electronic device provided in the embodiment of the present application, a natural language operation and maintenance request sent by a user is analyzed, a corresponding operation and maintenance policy is determined, corresponding operation and maintenance environment information is automatically obtained from a preset configuration management database, and the operation and maintenance policy and the operation and maintenance environment information are sent to a corresponding micro-service cluster, so that the micro-service cluster executes the operation and maintenance policy according to the operation and maintenance environment information.
In another embodiment, the natural language software operation and maintenance device may be configured separately from thecentral processor 9100, for example, the natural language software operation and maintenance device may be configured as a chip connected to thecentral processor 9100, and the function of the natural language software operation and maintenance method may be implemented by the control of the central processor.
As shown in fig. 10, theelectronic device 9600 may further include: acommunication module 9110, aninput unit 9120, anaudio processor 9130, adisplay 9160, and apower supply 9170. It is noted that theelectronic device 9600 also does not necessarily include all of the components shown in fig. 10; in addition, theelectronic device 9600 may further include components not shown in fig. 10, which can be referred to in the prior art.
As shown in fig. 10, acentral processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, whichcentral processor 9100 receives input and controls the operation of the various components of theelectronic device 9600.
Thememory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And thecentral processing unit 9100 can execute the program stored in thememory 9140 to realize information storage or processing, or the like.
Theinput unit 9120 provides input to thecentral processor 9100. Theinput unit 9120 is, for example, a key or a touch input device.Power supply 9170 is used to provide power toelectronic device 9600. Thedisplay 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.
Thememory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. Thememory 9140 could also be some other type of device.Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). Thememory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of theelectronic device 9600 by thecentral processor 9100.
Thememory 9140 can also include adata store 9143, thedata store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. Thedriver storage portion 9144 of thememory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).
Thecommunication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via anantenna 9111. The communication module (transmitter/receiver) 9110 is coupled to thecentral processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality ofcommunication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to aspeaker 9131 and amicrophone 9132 via anaudio processor 9130 to provide audio output via thespeaker 9131 and receive audio input from themicrophone 9132, thereby implementing ordinary telecommunications functions. Theaudio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, theaudio processor 9130 is also coupled to thecentral processor 9100, thereby enabling recording locally through themicrophone 9132 and enabling locally stored sounds to be played through thespeaker 9131.
The embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the natural language software operation and maintenance method in which the execution subject in the above embodiment is the server or the client, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements all the steps in the natural language software operation and maintenance method in which the execution subject in the above embodiment is the server or the client, for example, when the processor executes the computer program, the processor implements the following steps:
step S101: receiving a natural language operation and maintenance request sent by a user, and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to a set rule.
Step S102: and acquiring corresponding operation and maintenance environment information from a preset configuration management database according to the operation and maintenance strategy, and sending the operation and maintenance strategy and the operation and maintenance environment information to a corresponding micro-service cluster so that the micro-service cluster executes the operation and maintenance strategy according to the operation and maintenance environment information.
Step S103: and receiving the operation and maintenance execution result returned by the micro service cluster and feeding back the operation and maintenance execution result to the user.
As can be seen from the above description, the computer-readable storage medium provided in this embodiment of the present application determines a corresponding operation and maintenance policy by analyzing a natural language operation and maintenance request sent by a user, automatically obtains corresponding operation and maintenance environment information from a preset configuration management database, and sends the operation and maintenance policy and the operation and maintenance environment information to a corresponding micro-service cluster, so that the micro-service cluster executes the operation and maintenance policy according to the operation and maintenance environment information, thereby reducing maintenance and usage thresholds through simple configuration and more accurately implementing user operation and maintenance requirements.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A natural language software operation and maintenance method is characterized by comprising the following steps:
receiving a natural language operation and maintenance request sent by a user, and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to a set rule;
acquiring corresponding operation and maintenance environment information from a preset configuration management database according to the operation and maintenance strategy, and sending the operation and maintenance strategy and the operation and maintenance environment information to corresponding micro-service clusters so that the micro-service clusters execute the operation and maintenance strategy according to the operation and maintenance environment information;
and receiving the operation and maintenance execution result returned by the micro service cluster and feeding back the operation and maintenance execution result to the user.
2. The method for operating and maintaining natural language software according to claim 1, wherein the receiving a natural language operation and maintenance request sent by a user and determining an operation and maintenance policy corresponding to the natural language operation and maintenance request according to a set rule includes:
receiving a natural language operation and maintenance request sent by a user in a chat group corresponding to the current application, and performing natural language analysis on the natural language operation and maintenance request;
retrieving the natural language analysis result according to a preset inverted index, a semantic index and a semantic representation neural network model to obtain a preset operation and maintenance strategy, wherein the similarity between the preset operation and maintenance strategy and the natural language operation and maintenance request is higher than a threshold value;
according to a preset semantic similarity neural network model, carrying out similarity analysis on the preset operation and maintenance strategy with the similarity higher than a threshold value and the natural language operation and maintenance request;
and performing regression analysis on the result of the similarity analysis according to a preset linear regression model and a gradient lifting model, and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to the result of the regression analysis.
3. The method according to claim 2, wherein the performing natural language analysis on the natural language operation request comprises:
and carrying out named entity recognition on the natural language operation and maintenance request according to the entity type, the time type and the number type, and carrying out natural language cutting according to the recognition result of the named entity.
4. The method for operating and maintaining natural language software according to claim 2, wherein before the retrieving the result of the natural language analysis according to the preset inverted index, the semantic index and the semantic representation neural network model, the method comprises:
extracting key words in a preset demand set, and establishing an inverted index according to the positions of the key words in a preset operation and maintenance strategy;
and clustering key words in a preset operation and maintenance strategy, and establishing semantic indexes according to the clustered key words.
5. A natural language software operation and maintenance device is characterized by comprising:
the operation and maintenance strategy determination module is used for receiving a natural language operation and maintenance request sent by a user and determining an operation and maintenance strategy corresponding to the natural language operation and maintenance request according to a set rule;
the strategy scheduling execution module is used for acquiring corresponding operation and maintenance environment information from a preset configuration management database according to the operation and maintenance strategy and sending the operation and maintenance strategy and the operation and maintenance environment information to a corresponding micro-service cluster so that the micro-service cluster executes the operation and maintenance strategy according to the operation and maintenance environment information;
and the operation and maintenance result feedback module is used for receiving the operation and maintenance execution result returned by the micro service cluster and feeding the operation and maintenance execution result back to the user.
6. The natural language software operation and maintenance device according to claim 5, wherein the operation and maintenance strategy determination module comprises:
the natural language analysis unit is used for receiving a natural language operation and maintenance request sent by a user in a chat group corresponding to the current application and carrying out natural language analysis on the natural language operation and maintenance request;
the indexing unit is used for retrieving the natural language analysis result according to a preset inverted index, a semantic index and a semantic representation neural network model to obtain a preset operation and maintenance strategy, wherein the similarity between the preset operation and maintenance strategy and the natural language operation and maintenance request is higher than a threshold value;
the similarity analysis unit is used for carrying out similarity analysis on the preset operation and maintenance strategy with the similarity higher than a threshold value and the natural language operation and maintenance request according to a preset semantic similarity neural network model;
and the reordering unit is used for performing regression analysis on the result of the similarity analysis according to a preset linear regression model and a gradient lifting model, and determining the operation and maintenance strategy corresponding to the natural language operation and maintenance request according to the result of the regression analysis.
7. The natural language software operation and maintenance device according to claim 6, wherein the natural language analysis unit comprises:
and the entity identification and segmentation subunit is used for carrying out named entity identification on the natural language operation and maintenance request according to an entity type, a time type and a number type and carrying out natural language segmentation according to the named entity identification result.
8. The natural language software operation and maintenance device according to claim 6, further comprising:
the inverted index building unit is used for extracting key words in a preset demand set and building an inverted index according to the positions of the key words in a preset operation and maintenance strategy;
and the semantic index construction unit is used for clustering key words in the preset operation and maintenance strategy and establishing a semantic index according to the clustered key words.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the natural language software operation and maintenance method according to any one of claims 1 to 4 are implemented when the processor executes the program.
10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the natural language software operation and maintenance method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110332002.0ACN112925895A (en) | 2021-03-29 | 2021-03-29 | Natural language software operation and maintenance method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110332002.0ACN112925895A (en) | 2021-03-29 | 2021-03-29 | Natural language software operation and maintenance method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112925895Atrue CN112925895A (en) | 2021-06-08 |
Family
ID=76176340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110332002.0APendingCN112925895A (en) | 2021-03-29 | 2021-03-29 | Natural language software operation and maintenance method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112925895A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114721952A (en)* | 2022-04-07 | 2022-07-08 | 平安科技（深圳）有限公司 | Synchronous deployment method, device, equipment and storage medium for multiple sets of test environments |
| WO2022267874A1 (en)* | 2021-06-24 | 2022-12-29 | 中兴通讯股份有限公司 | Troubleshooting method and system, electronic device, and computer readable storage medium |
| CN117389843A (en)* | 2023-12-13 | 2024-01-12 | 广州嘉为科技有限公司 | Intelligent operation and maintenance system, method, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653706A (en)* | 2015-12-31 | 2016-06-08 | 北京理工大学 | Multilayer quotation recommendation method based on literature content mapping knowledge domain |
| CN109190008A (en)* | 2018-07-26 | 2019-01-11 | 挖财网络技术有限公司 | Automate operation management method |
| CN109542452A (en)* | 2018-11-19 | 2019-03-29 | 万惠投资管理有限公司 | A kind of operation management method and system based on AI semantic analysis |
| CN110399385A (en)* | 2019-06-24 | 2019-11-01 | 厦门市美亚柏科信息股份有限公司 | A kind of semantic analysis and system for small data set |
| CN111611355A (en)* | 2019-02-25 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Dialog reply method, device, server and storage medium |
| CN111737543A (en)* | 2019-05-27 | 2020-10-02 | 北京京东尚科信息技术有限公司 | A method, device, device and storage medium for extracting question-answer pairs |
- 2021
- 2021-03-29CNCN202110332002.0Apatent/CN112925895A/enactivePending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653706A (en)* | 2015-12-31 | 2016-06-08 | 北京理工大学 | Multilayer quotation recommendation method based on literature content mapping knowledge domain |
| CN109190008A (en)* | 2018-07-26 | 2019-01-11 | 挖财网络技术有限公司 | Automate operation management method |
| CN109542452A (en)* | 2018-11-19 | 2019-03-29 | 万惠投资管理有限公司 | A kind of operation management method and system based on AI semantic analysis |
| CN111611355A (en)* | 2019-02-25 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Dialog reply method, device, server and storage medium |
| CN111737543A (en)* | 2019-05-27 | 2020-10-02 | 北京京东尚科信息技术有限公司 | A method, device, device and storage medium for extracting question-answer pairs |
| CN110399385A (en)* | 2019-06-24 | 2019-11-01 | 厦门市美亚柏科信息股份有限公司 | A kind of semantic analysis and system for small data set |
Non-Patent Citations (1)
| Title |
|---|
| 颜廷吉: "Java架构之完美设计：实战经典", 31 August 2019, 机械工业出版社, pages: 299 - 300* |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022267874A1 (en)* | 2021-06-24 | 2022-12-29 | 中兴通讯股份有限公司 | Troubleshooting method and system, electronic device, and computer readable storage medium |
| CN114721952A (en)* | 2022-04-07 | 2022-07-08 | 平安科技（深圳）有限公司 | Synchronous deployment method, device, equipment and storage medium for multiple sets of test environments |
| CN117389843A (en)* | 2023-12-13 | 2024-01-12 | 广州嘉为科技有限公司 | Intelligent operation and maintenance system, method, electronic equipment and storage medium |
| CN117389843B (en)* | 2023-12-13 | 2024-04-09 | 广州嘉为科技有限公司 | Intelligent operation and maintenance system, method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240419659A1 (en) | Method and system of classification in a natural language user interface | |
| KR102842345B1 (en) | Predictive Similarity Scoring Subsystem in a Natural Language Understanding (NLU) Framework | |
| CN114503115B (en) | Generating rich action items | |
| CN110334347B (en) | Information processing method based on natural language recognition, related equipment and storage medium | |
| CN116521841B (en) | Method, device, equipment and medium for generating reply information | |
| WO2021121198A1 (en) | Semantic similarity-based entity relation extraction method and apparatus, device and medium | |
| CN116541536B (en) | Knowledge-enhanced content generation system, data generation method, device, and medium | |
| CN112925895A (en) | Natural language software operation and maintenance method and device | |
| KR102285142B1 (en) | Apparatus and method for recommending learning data for chatbots | |
| WO2021063089A1 (en) | Rule matching method, rule matching apparatus, storage medium and electronic device | |
| CN116955561A (en) | Question answering method, question answering device, electronic equipment and storage medium | |
| CN117421398A (en) | Man-machine interaction method, device, equipment and storage medium | |
| CN118227868B (en) | Text processing method, device, electronic equipment and storage medium | |
| CN117992601B (en) | Document generation method and device based on artificial intelligence | |
| CN111538817B (en) | Man-machine interaction method and device | |
| CN117312521A (en) | Processing method for intelligent customer service dialogue and related products | |
| CN117033540A (en) | Report generation method, report generation device, electronic equipment and medium | |
| WO2025130162A1 (en) | Multimedia information processing method, system, and electronic device | |
| CN115858748A (en) | Question answer processing method, device, computer equipment and storage medium | |
| CN111798118B (en) | Enterprise operation risk monitoring method and device | |
| CN117313670A (en) | Document generation method, device, electronic equipment and storage medium | |
| EP3893143A1 (en) | Corpus processing method, apparatus and storage medium | |
| CN113326363A (en) | Searching method and device, prediction model training method and device, and electronic device | |
| JP2025124738A (en) | Human-machine interaction method, device, equipment, and storage medium based on conversation history | |
| CN114461749B (en) | Data processing method and device for conversation content, electronic equipment and 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 |