CN109542452A - A kind of operation management method and system based on AI semantic analysis - Google Patents
A kind of operation management method and system based on AI semantic analysis Download PDFInfo
- Publication number
- CN109542452A CN109542452A CN201811376968.9A CN201811376968A CN109542452A CN 109542452 A CN109542452 A CN 109542452A CN 201811376968 A CN201811376968 A CN 201811376968A CN 109542452 A CN109542452 A CN 109542452A
- Authority
- CN
- China
- Prior art keywords
- answer
- inquiry
- input
- engine
- operation management
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/40—Transformation of program code
- G06F8/41—Compilation
- G06F8/42—Syntactic analysis
- G06F8/425—Lexical analysis
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of operation management method and system based on AI semantic analysis, this method comprises: the inquiry instruction of the personnel of acquisition input, the inquiry instruction includes to by the inquiry of the relevant information of the object of operation management, and the inquiry instruction is natural language text;The inquiry is instructed using AI engine and is parsed, answer is obtained;Primary data in the AI engine is outputting and inputting for the artificial operation/maintenance data of history;Operating process need to be executed using operation and maintenance tools determination according to the answer;It need to execute operating process according to described server sequentially executes on line.The present invention can be realized operation maintenance personnel and be not necessarily to be manually entered complicated order or parameter, it is only necessary to input natural language, i.e., automatable mapping simultaneously triggers O&M process and operated.
Description
Technical field
The present invention relates to field of artificial intelligence, more particularly to a kind of operation management method based on AI semantic analysis
And system.
Background technique
Modern Internet company often uses various O&M pipes to manage, safeguard various software and hardware resources on line
Reason method and tool.For example arrange O&M engineer festivals or holidays on duty on duty in company, it is desirable that O&M engineer is using remotely stepping on
Record tool logs on to machine on line, carries out manual operation maintenance etc. using order line.Although these traditional operation management thinkings
Enterprise is helped to realize resource management, but with business scale on enterprise's line, software deployment frequency, malfunction elimination number are at finger
Several levels increase, and operation maintenance personnel increasingly has to run around all the time wears him out, puts out a fire, these are also more and more obvious in the shortcomings that O&M method, mainly have
The following:
1, hand-manipulated, the degree of automation is low.Although having used some operation and maintenance tools, most of O&M engineer according to
Old needs: input account, password input order line, input various parameters, naked eyes resolve command row is as a result, perform the next step behaviour
Make.Change method due to largely manually entering, easily malfunctions, and efficiency is lower.The work many and diverse for some repetitions, without very
The progress of good automation, procedure.
2, territory restriction, mobile office are unfriendly.For most of enterprise, equipment, software that operation management is relied on etc.
In office space, though festivals or holidays be also required to O&M engineer handle official business it is on duty.These work for operation maintenance personnel extremely
It is boring, while also increasing the human cost of enterprise.
3, information island, operation maintenance personnel execute the process of operation management like a black box, these knowledge can not be good
Other staff are precipitated and are presented to, for example desired these experiences that pass on of operation maintenance personnel of new registration become extremely difficult.
4, the backwardness of responsibility and idea, traditional O&M method think that these work are to only belong to operation maintenance personnel.But it is right
In the various problems that the software of enterprise oneself exploitation occurs on line, developer oneself is finally still needed to go investigation that could determine
Position solves.O&M is not only the work of operation maintenance personnel, it should be the work executed together communicated with each other with developer.
5, simultaneously unnatural language is inconvenient to remember for O&M order.Such as linux order, traditional O&M method is needed in fortune
Dimension personnel voluntarily remember order, or are based on using the thing auxiliary of handbook etc, and efficiency rate is easy to forget.It can not utilize
The mode of natural language executes O&M operation.
Summary of the invention
The object of the present invention is to provide a kind of operation management method and system based on AI semantic analysis, to solve above-mentioned ask
Topic.
To achieve the above object, the present invention provides a kind of operation management method based on AI semantic analysis, the methods
Include:
The inquiry instruction of acquisition personnel input, the inquiry instruction includes to by the relevant information of the object of operation management
Inquiry, the inquiry instruction is natural language text;
The inquiry is instructed using AI engine and is parsed, answer is obtained;Primary data in the AI engine is history people
Labour movement dimension data is output and input;
Operating process need to be executed using operation and maintenance tools determination according to the answer;
It need to execute operating process according to described server sequentially executes on line.
Optionally, it is parsed in described instructed using AI engine to the inquiry, after obtaining answer, the method is also wrapped
It includes:
It stores the inquiry and instructs input text and the answer after corresponding parsing;
Using after the parsing input text and the answer analytic modell analytical model in the AI engine is trained.
Optionally, it is described according to it is described need to execute operating process server sequentially executes on line after, the method is also
Include:
Collect the implementing result that server sequentially executes on line;
Next step option of operation is mapped according to the implementing result;
According to the next step option of operation, repeating said steps " the inquiry instruction for obtaining personnel's input " to step " are pressed
It need to execute operating process according to described server sequentially executes on line ".
Optionally, described instructed using AI engine to the inquiry is parsed, and is obtained answer, is specifically included:
Inquiry instruction is segmented, part-of-speech tagging and syntactic analysis, the text after being parsed;
By in the analytic modell analytical model in AI engine described in the text input by after parsing, answer is obtained.
Optionally, the method for building up of the analytic modell analytical model is as follows:
Construct machine learning frame;
The training set as the machine learning frame is output and input to described using the artificial operation/maintenance data of the history
Machine learning frame is trained, and obtains analytic modell analytical model;
Or input text after parsing and answer corresponding with the input text after the parsing are as the engineering
The training set for practising frame is trained the machine learning frame, obtains analytic modell analytical model.
Optionally, described that inquiry instruction is segmented, it specifically includes:
Inquiry instruction is segmented using string matching algorithm;The string matching algorithm include it is positive most
Big matching method, reverse maximum matching method or minimum syncopation;
Or inquiry instruction is segmented using statistical method;The statistical method is that two adjacent words of statistics go out
Occurrence number, two words for determining that the number is more than given threshold are a word.
Optionally, it in the analytic modell analytical model by AI engine described in the text input by after parsing, is answered
After case, the method also includes:
According to statistical probability and feedback mechanism answer correction;
When text input after the parsing obtains multiple answers, the number that answer is selected is obtained;
It determines that the most answer of the number selected is model answer, is stored in the AI engine.
The present invention also provides a kind of operation management system based on AI semantic analysis, the system comprises:
Inquire instruction acquisition unit, for obtaining the inquiry instruction of personnel's input, the inquiry instruction includes to by O&M
The inquiry of the relevant information of the object of management, the inquiry instruction is natural language text;
Resolution unit is parsed for being instructed using AI engine to the inquiry, obtains answer;It is initial in the AI engine
Data are outputting and inputting for the artificial operation/maintenance data of history;
Operating process determination unit, for operating process need to be executed using operation and maintenance tools determination according to the answer;
Execution unit, for that need to execute operating process according to described server sequentially executes on line.
Optionally, the system also includes:
Storage unit instructs input text and the answer after corresponding parsing for storing the inquiry;
Update training unit, for using after the parsing input text and the answer to the solution in the AI engine
Analysis model is trained.
Optionally, the system also includes:
Implementing result collector unit, for collecting the implementing result that server sequentially executes on line;
Map unit, for mapping next step option of operation according to the implementing result;
Unit is repeated, for according to the next step option of operation, repeating said steps " to obtain the inquiry of personnel's input
Ask instruction " " it need to execute operating process according to described server sequentially executes on line " to step.
The specific embodiment provided according to the present invention, the invention discloses following technical effects:
1. chat type operates, high degree of automation: operation maintenance personnel is not necessarily to be manually entered complicated order or parameter, only needs
Natural language is inputted, i.e., automatable mapping simultaneously triggers O&M process and operated.
2. mobile office, region is unlimited: chat tool provide mobile device client end interface, can non-Administrative Area into
Row operation, without forcing the human attendance in place.
3. operation information is shared: the order initiation of O&M whole operation and result are presented to owner in chat, believe
Real-time synchronization is ceased to other people, both facilitates information sharing, is also able to allow O&M pass on knowledge.
4. developer also can use the self-service troubleshooting of chat tool, without waiting for operation maintenance personnel.Change developer to see
It reads, O&M is not only one of thing and developer's work of operation maintenance personnel.
5. the inquiry instruction of natural language can be inputted in chat tool, and non-critical program command term, by AI engine
The O&M operational order that natural language is handled, is analyzed and is finally needed to be implemented.AI engine can be according to input every time
And answer carries out repetition training, and the accuracy of answer is continuously improved.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the flow chart for the operation management method based on AI semantic analysis that the embodiment of the present invention provides;
Fig. 2 is the structural block diagram for the operation management system based on AI semantic analysis that the embodiment of the present invention provides.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
As shown in Figure 1, the operation management method provided in this embodiment based on AI semantic analysis includes:
Step 101: obtaining the inquiry instruction of personnel's input.Inquiry instruction is that operation maintenance personnel or other staff utilize and chat
What the client end interface of its tool was initiated, and read inquiry from client end interface by chat tool server-side or chat robots and refer to
It enables, and inquiry instruction is sent to AI engine.
The inquiry instruction includes to by the inquiry of the relevant information of the object of operation management, and the inquiry instruction is nature
Language text.Inquiry instruction can be Chinese (Han)language, is also possible to the natural language text of other every countries, needs here
To illustrate that inquiry instruction is using staff's routine work and used language of living.Be more convenient for personnel couple in this way
The management and execution of O&M reduce the requirement of personnel culture and knowledge expertise itself.The type of inquiry instruction may include looking into
It askes certain machine CPU and occupies highest situation, audit memory or network abnormal situation or certain business datum, log index
It is abnormal, such as refund data exception, relevant abnormal log number of withdrawing deposit increases etc..
Step 102: the inquiry being instructed using AI engine and is parsed, answer is obtained.
Primary data in the AI engine is outputting and inputting for the artificial operation/maintenance data of history.Specifically, in AI engine
Primary data derives from the existing artificial troubleshooting process related data of O&M, is divided into input and output, for example input is
" CPU occupies high ", output are then to inquire which process occupies high order " top ".Existing all artificial troubleshooting processes are equal
After being divided into input, output, as primary data typing AI engine.
Step 102 specifically includes:
Inquiry instruction is segmented, part-of-speech tagging and syntactic analysis, the text after being parsed;
By in the analytic modell analytical model in AI engine described in the text input by after parsing, answer is obtained.
Wherein, include: to the method for inquiring that instruction is segmented
Inquiry instruction is segmented using string matching algorithm;The string matching algorithm include it is positive most
Big matching method, reverse maximum matching method or minimum syncopation.
Or inquiry instruction is segmented using statistical method;The statistical method is that two adjacent words of statistics go out
Occurrence number, two words for determining that the number is more than given threshold are a word.
After step 102 further include:
It stores the inquiry and instructs input text and the answer after corresponding parsing;
Using after the parsing input text and the answer analytic modell analytical model in the AI engine is trained.This
Sample can guarantee the accuracy of language analysis, and improve answer according to the data in new inquiry instruction real-time update AI engine
Precision.
The method for building up of above-mentioned analytic modell analytical model is as follows:
Construct machine learning frame;
The training set as the machine learning frame is output and input to described using the artificial operation/maintenance data of the history
Machine learning frame is trained, and obtains analytic modell analytical model;It is marked off in no new data using the artificial operation/maintenance data of history defeated
Enter and export and be trained as training the set pair analysis model, the self study process and ability of model may be implemented.
After having new data input, often input is not corresponded with answer, it is possible that one-to-many situation, so
And how about from multiple answers determine that more accurate answer is relatively difficult to achieve.One-to-many feelings are realized by the following method in the present embodiment
The answer of condition corrects, and the specific method is as follows:
According to statistical probability and feedback mechanism answer correction;
When text input after the parsing obtains multiple answers, the number that answer is selected is obtained;
It determines that the most answer of the number selected is model answer, is stored in the AI engine.
Such as in training set, in read statement but all comprising " CPU " keyword, answer the inside necessarily includes " top "
Order is crucial.So after overfitting, a kind of association will be generated, i.e. " CPU "-> " top ".As long as being wrapped in inquiry command later
Containing " CPU " keyword, then will have maximum probability in the answer returned is exactly " top " order.In the case where one-to-many, return
Multiple answers are returned, system will affect the probability for generating answer as weight according to the number of each selection answer;It is most by selection
Secondary answer has very maximum probability that will be used as model answer.
In this way by the answer after correction it is corresponding with input after can be used as new training set to analytic modell analytical model re -training,
Input text and answer corresponding with the input text after the parsing i.e. after parsing is as the machine learning frame
Training set is trained the machine learning frame, obtains analytic modell analytical model.Data in this way in energy real-time update AI engine are simultaneously
Improve the accuracy of analytic modell analytical model.
Step 103: operating process need to be executed using operation and maintenance tools determination according to the answer.Answer in the step be from
It is transmitted to chat tool server-side or chat robots in AI engine, O&M is utilized by chat tool server-side or chat robots
Answer is mapped to by tool need to execute operating process.Operation and maintenance tools contain the workflow of layout, it is ensured that execute, execute exception
It interrupting and execute afterwards, exception information will return to chat tool server-side or chat robots, then re-enter to AI engine,
Redefine answer.
Step 104: need to execute operating process according to described server sequentially executes on line.
After step 104 further include:
Collect the implementing result that server sequentially executes on line;
Next step option of operation is mapped according to the implementing result;
According to the next step option of operation, repeating said steps 101 to step 104.
As shown in Fig. 2, the present embodiment additionally provides a kind of O&M based on AI semantic analysis corresponding with above-described embodiment
Management system, the system include:
Inquire instruction acquisition unit 201, for obtaining the inquiry instruction of personnel's input, it includes to being transported that the inquiry, which instructs,
The inquiry of the relevant information of the object of management is tieed up, the inquiry instruction is natural language text;
Resolution unit 202 is parsed for being instructed using AI engine to the inquiry, obtains answer;In the AI engine
Primary data is outputting and inputting for the artificial operation/maintenance data of history;
Operating process determination unit 203, for operating process need to be executed using operation and maintenance tools determination according to the answer;
Execution unit 204, for that need to execute operating process according to described server sequentially executes on line.
The system further includes with lower unit:
Storage unit instructs input text and the answer after corresponding parsing for storing the inquiry;
Update training unit, for using after the parsing input text and the answer to the solution in the AI engine
Analysis model is trained.
Implementing result collector unit, for collecting the implementing result that server sequentially executes on line;
Map unit, for mapping next step option of operation according to the implementing result;
Unit is repeated, for according to the next step option of operation, repeating said steps 101 to step 104.
Since this system is corresponding to method described in above-described embodiment, then the feature having is completely corresponding, generation
Technical effect is also identical.Details are not described herein.
Below with reference to a specific operation management case implementation process that the present invention will be described in detail:
01: O&M or developer initiate CPU querying command, such as: " CPU occupancy situation ";
02: after chat tool or robot reception, forwarding it to AI engine.AI engine parses the command, and obtains
Core keywords such as " CPU " " occupancy " after input model, obtain answer " top cpu on192.168.102.22 ", that is,
O&M operational order;
03: chat tool or robot receive answer;
04: answer is transmitted to operation and maintenance tools by chat tool or robot;
05: after operation and maintenance tools receive " top cpu on 192.168.102.22 ", mapping out the operation stream needed to be implemented
Journey, such as " inquiry specified machine CPU occupancy situation process ".Execute the process:
The process first carries out " top " order and finds out the higher several progress informations of CPU occupancy;
Progress information is formatted, and is each progress information addition next step operational order in the information, such as
" kill process number ";
Formatted information is returned into chat tool or robot, is finally returned that O&M or developer
After O&M or developer see process occupied information, it may be selected to operate in next step, for example kill process, i.e., again
The step of secondary initiation is ordered to chat tool or robot, and 01-05 is repeated.
Wherein, AI engine will can input every time text and answer as training sample and carry out self training.
For the system disclosed in the embodiment, since it is corresponded to the methods disclosed in the examples, so the ratio of description
Relatively simple, reference may be made to the description of the method.
Used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention;At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (10)
1. a kind of operation management method based on AI semantic analysis, which is characterized in that the described method includes:
The inquiry instruction of acquisition personnel input, the inquiry instruction includes to by the inquiry of the relevant information of the object of operation management
It asks, the inquiry instruction is natural language text;
The inquiry is instructed using AI engine and is parsed, answer is obtained;Primary data in the AI engine is that history is manually transported
Dimension data is output and input;
Operating process need to be executed using operation and maintenance tools determination according to the answer;
It need to execute operating process according to described server sequentially executes on line.
2. the operation management method according to claim 1 based on AI semantic analysis, which is characterized in that utilize AI described
Engine instructs the inquiry and parses, after obtaining answer, the method also includes:
It stores the inquiry and instructs input text and the answer after corresponding parsing;
Using after the parsing input text and the answer analytic modell analytical model in the AI engine is trained.
3. the operation management method according to claim 1 based on AI semantic analysis, which is characterized in that described according to described
After need to executing operating process server sequentially executing on line, the method also includes:
Collect the implementing result that server sequentially executes on line;
Next step option of operation is mapped according to the implementing result;
According to the next step option of operation, repeating said steps " the inquiry instruction for obtaining personnel's input " are to step " according to institute
Operating process need to be executed server sequentially executes on line by stating ".
4. the operation management method according to claim 1 based on AI semantic analysis, which is characterized in that described to be drawn using AI
It holds up to instruct the inquiry and parse, obtain answer, specifically include:
Inquiry instruction is segmented, part-of-speech tagging and syntactic analysis, the text after being parsed;
By in the analytic modell analytical model in AI engine described in the text input by after parsing, answer is obtained.
5. the operation management method according to claim 2 or 4 based on AI semantic analysis, which is characterized in that the parsing
The method for building up of model is as follows:
Construct machine learning frame;
The training set as the machine learning frame is output and input to the machine using the artificial operation/maintenance data of the history
Learning framework is trained, and obtains analytic modell analytical model;
Or input text after parsing and answer corresponding with the input text after the parsing are as the machine learning frame
The training set of frame is trained the machine learning frame, obtains analytic modell analytical model.
6. the operation management method according to claim 4 based on AI semantic analysis, which is characterized in that described to the inquiry
It asks that instruction is segmented, specifically includes:
Inquiry instruction is segmented using string matching algorithm;The string matching algorithm includes positive maximum
With method, reverse maximum matching method or minimum syncopation;
Or inquiry instruction is segmented using statistical method;The statistical method is that two adjacent words of statistics go out occurrence
Number, two words for determining that the number is more than given threshold are a word.
7. the operation management method according to claim 4 based on AI semantic analysis, which is characterized in that it is described will be described
By in the analytic modell analytical model in AI engine described in the text input after parsing, after obtaining answer, the method also includes:
According to statistical probability and feedback mechanism answer correction;
When text input after the parsing obtains multiple answers, the number that answer is selected is obtained;
It determines that the most answer of the number selected is model answer, is stored in the AI engine.
8. a kind of operation management system based on AI semantic analysis, which is characterized in that the system comprises:
Inquire instruction acquisition unit, for obtaining the inquiry instruction of personnel's input, the inquiry instruction includes to by operation management
Object relevant information inquiry, inquiry instruction is natural language text;
Resolution unit is parsed for being instructed using AI engine to the inquiry, obtains answer;Primary data in the AI engine
For outputting and inputting for the artificial operation/maintenance data of history;
Operating process determination unit, for operating process need to be executed using operation and maintenance tools determination according to the answer;
Execution unit, for that need to execute operating process according to described server sequentially executes on line.
9. the operation management system according to claim 8 based on AI semantic analysis, which is characterized in that the system is also wrapped
It includes:
Storage unit instructs input text and the answer after corresponding parsing for storing the inquiry;
Update training unit, for using after the parsing input text and the answer to the parsing mould in the AI engine
Type is trained.
10. the operation management system according to claim 8 based on AI semantic analysis, which is characterized in that the system is also
Include:
Implementing result collector unit, for collecting the implementing result that server sequentially executes on line;
Map unit, for mapping next step option of operation according to the implementing result;
Unit is repeated, for according to the next step option of operation, " inquiry of acquisition personnel input to refer to repeating said steps
Enable " " it need to execute operating process according to described server sequentially executes on line " to step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811376968.9A CN109542452A (en) | 2018-11-19 | 2018-11-19 | A kind of operation management method and system based on AI semantic analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811376968.9A CN109542452A (en) | 2018-11-19 | 2018-11-19 | A kind of operation management method and system based on AI semantic analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109542452A true CN109542452A (en) | 2019-03-29 |
Family
ID=65848380
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811376968.9A Pending CN109542452A (en) | 2018-11-19 | 2018-11-19 | A kind of operation management method and system based on AI semantic analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109542452A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110413308A (en) * | 2019-07-30 | 2019-11-05 | 深圳前海微众银行股份有限公司 | Software O&M method, apparatus, equipment and computer storage medium |
CN112348653A (en) * | 2020-12-03 | 2021-02-09 | 四川长虹电器股份有限公司 | Automatic test operation and maintenance system of financial cloud platform |
CN114730443A (en) * | 2019-11-06 | 2022-07-08 | 三菱电机楼宇解决方案株式会社 | Building information processing device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105206272A (en) * | 2015-09-06 | 2015-12-30 | 上海智臻智能网络科技股份有限公司 | Voice transmission control method and system |
US20170039039A1 (en) * | 2015-08-05 | 2017-02-09 | General Electric Company | System and method for model based technology and process for safety-critical software development |
CN107633079A (en) * | 2017-09-25 | 2018-01-26 | 重庆邮电大学 | A kind of vehicle device natural language human-machine interactions algorithm based on database and neutral net |
CN108170734A (en) * | 2017-12-15 | 2018-06-15 | 国网冀北电力有限公司信息通信分公司 | A kind of intelligence O&M robot |
-
2018
- 2018-11-19 CN CN201811376968.9A patent/CN109542452A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170039039A1 (en) * | 2015-08-05 | 2017-02-09 | General Electric Company | System and method for model based technology and process for safety-critical software development |
CN105206272A (en) * | 2015-09-06 | 2015-12-30 | 上海智臻智能网络科技股份有限公司 | Voice transmission control method and system |
CN107633079A (en) * | 2017-09-25 | 2018-01-26 | 重庆邮电大学 | A kind of vehicle device natural language human-machine interactions algorithm based on database and neutral net |
CN108170734A (en) * | 2017-12-15 | 2018-06-15 | 国网冀北电力有限公司信息通信分公司 | A kind of intelligence O&M robot |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110413308A (en) * | 2019-07-30 | 2019-11-05 | 深圳前海微众银行股份有限公司 | Software O&M method, apparatus, equipment and computer storage medium |
CN114730443A (en) * | 2019-11-06 | 2022-07-08 | 三菱电机楼宇解决方案株式会社 | Building information processing device |
CN112348653A (en) * | 2020-12-03 | 2021-02-09 | 四川长虹电器股份有限公司 | Automatic test operation and maintenance system of financial cloud platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ekanem et al. | Phoenix–a model-based human reliability analysis methodology: qualitative analysis procedure | |
US20160171050A1 (en) | Distributed Analytical Search Utilizing Semantic Analysis of Natural Language | |
CN112579707A (en) | Log data knowledge graph construction method | |
CN109542452A (en) | A kind of operation management method and system based on AI semantic analysis | |
KR20210047284A (en) | Recruitment position description text generation method, device, apparatus and medium | |
US20220358292A1 (en) | Method and apparatus for recognizing entity, electronic device and storage medium | |
CN114281968B (en) | Model training and corpus generation method, device, equipment and storage medium | |
CN110147544A (en) | A kind of instruction generation method, device and relevant device based on natural language | |
Saini et al. | Automated traceability for domain modelling decisions empowered by artificial intelligence | |
CN117633196B (en) | Question-answering model construction method and project question-answering method | |
Owda et al. | Information extraction for SQL query generation in the conversation-based interfaces to relational databases (C-BIRD) | |
US11550830B2 (en) | Systems and methods for multi-source reference class identification, base rate calculation, and prediction | |
CN115878818B (en) | Geographic knowledge graph construction method, device, terminal and storage medium | |
CN117522185A (en) | Flexibly configurable evaluation method, system and terminal | |
Setiawan et al. | Mobile visual programming apps for internet of things applications based on raspberry Pi 3 platform | |
US11036725B2 (en) | System and method for computerized data processing, analysis and display | |
Long et al. | 6G comprehensive intelligence: network operations and optimization based on Large Language Models | |
CN115269862A (en) | Electric power question-answering and visualization system based on knowledge graph | |
CN113377962B (en) | Intelligent process simulation method based on image recognition and natural language processing | |
Xiao et al. | Lightweight natural language driven intent translation mechanism for intent based networking | |
Zare | Enhancing maintenance strategies for elevators through fine-tuning large language models | |
Deppe et al. | AI-based assistance system for manufacturing | |
CN113963578A (en) | Self-adaptive training system and training method for knowledge service and skill drilling | |
Enders | Understanding and applying digital twins-results of selected studies | |
Ryabinin et al. | Ontology-driven data mining platform for fuzzy classification of mental maps |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |
|
RJ01 | Rejection of invention patent application after publication |