CN110059830A - A kind of skilled work post industry pattern training technique based on artificial intelligence technology - Google Patents
A kind of skilled work post industry pattern training technique based on artificial intelligence technology Download PDFInfo
- Publication number
- CN110059830A CN110059830A CN201910483695.6A CN201910483695A CN110059830A CN 110059830 A CN110059830 A CN 110059830A CN 201910483695 A CN201910483695 A CN 201910483695A CN 110059830 A CN110059830 A CN 110059830A
- Authority
- CN
- China
- Prior art keywords
- data
- discrimination
- work post
- artificial intelligence
- skilled work
- 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
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The present invention provides a kind of skilled work post industry pattern training technique based on artificial intelligence technology, and the skilled work post industry pattern training technique is the following steps are included: data acquisition, data prediction, model training, machine learning, data identification, database preparation.A kind of skilled work post industry pattern training technique based on artificial intelligence technology of the present invention is combined by artificial correction with machine learning, the accuracy of the data for model training can greatly be improved, and can effectively improve data it is less in the case where model training efficiency, the accuracy of lift scheme training, saves model training cost.
Description
Technical field
The invention belongs to model training technical field, in particular to a kind of skilled work post industry based on artificial intelligence technology
Model training technology.
Background technique
Artificial intelligence is a branch of computer science, it attempts to understand essence of intelligence, and is produced a kind of new
The intelligence machine that can be made a response in such a way that human intelligence is similar, the research in the field include robot, language identification, image
Identification, natural language processing and expert system etc..Artificial intelligence is since the birth, and theory and technology is increasingly mature, application field
Also constantly expand, it is contemplated that the following artificial intelligence bring sci-tech product, and the realization of artificial intelligence be unable to do without engineering
It practises, the learning behavior that the mankind were simulated or realized to computer how is specialized in machine learning, to obtain new knowledge or skills, weight
The existing structure of knowledge is newly organized to be allowed to constantly improve the performance of itself, the practice of present industrial expansion and artificial intelligence technology
It is increasingly closer, and the foundation of various industry patterns has great importance for the intelligence of industry, still, for just at
For vertical company, data volume is zero-based or seldom, if they will use common model training method build
If vertical industry pattern, because the accuracy rate of model will be very low without historical data, can there are problems that cold start-up, be
This, the present invention proposes a kind of skilled work post industry pattern training technique based on artificial intelligence technology.
Summary of the invention
It is of the existing technology in order to solve the problems, such as, the skilled work post based on artificial intelligence technology that the present invention provides a kind of
Industry pattern training technique is combined with machine learning by artificial correction, can greatly improve the number for model training
According to accuracy, and can effectively improve data it is less in the case where model training efficiency, lift scheme training
Accuracy saves model training cost.
To achieve the goals above, the present invention is to realize by the following technical solutions: one kind is based on artificial intelligence skill
The skilled work post industry pattern training technique of art, the skilled work post industry pattern training technique the following steps are included:
Step 1: data acquisition；According to the acquisition for needing to carry out data sample of model training, data are known after acquiring
Rate does not judge, then judges whether discrimination is greater than 95%, if it is not, then continuing step 2, if it is, directly carrying out
Step 6；
Step 2: data prediction；The worker of skilled work post is rule of thumb first to the abnormal data in the data sample of acquisition
Pretreatment amendment is carried out, data sample correct, that quality is high is obtained, then carries out discrimination calculating, calculated discrimination
Old discrimination is replaced and as the discrimination recycled next time；
Step 3: model training；Model training is carried out using the high data sample of correct, quality；
Step 4: machine learning；The mode, type and correction amount for correcting data to the worker of work post skilled in step 2 carry out machine
Tool study, learns the relationship between each data, establishes modified feature database, and the result of machine learning is stored in feature database；
Step 5: data identification；Circulation terminates, after circulation carries out the acquisition of step 1 data again, first according in step 3
Feature database carries out data identification, and the data in data with same or similar problem are identified and are identified, are recycled into
The data prediction of row step 2；
Step 6: database preparation；After discrimination is greater than 95%, according to the mode of the amendment data of machine learning, type and repair
Positive quantity carries out the relationship between rote learning and each data, is modified automatically to the data of acquisition, then return step
Three carry out model training, and then circulation carries out Step 1: step 6 and step 3.
Discrimination calculation formula as a kind of preferred embodiment of the invention, in the step 2 are as follows: discrimination=identify
Data/always correct data.
As a kind of preferred embodiment of the invention, the step is a kind of, and when first time data acquire, initial identification rate is 0.
As a kind of preferred embodiment of the invention, when discrimination judges in the step 1, discrimination standard being capable of basis
It needs to set, practical discrimination being capable of timing or not timing selective examination amendment.
The invention has the benefit that
1, a kind of skilled work post industry pattern training technique based on artificial intelligence technology of the present invention passes through artificial correction and machine
Study combines, and can greatly improve the accuracy of the data for model training, and can effectively improve data compared with
The efficiency of model training in the case where few, the accuracy of lift scheme training, saves model training cost.
2, for the company just set up, data volume be it is zero-based or seldom, if they to use it is general
If logical model training method establishes industry pattern, because the accuracy rate of model will be very low, meeting without historical data
There are problems that cold start-up, can be good at solving the problems, such as this using the present invention.
3, a kind of skilled work post industry pattern training technique step based on artificial intelligence technology of the present invention is succinct, later period energy
It is enough that automatically data are carried out to correct to reach the automatic quality for improving data, it is suitble to promote.
Detailed description of the invention
Fig. 1 is a kind of skilled work post industry pattern training technique flow chart of steps based on artificial intelligence technology.
Specific embodiment
To be easy to understand the technical means, the creative features, the aims and the efficiencies achieved by the present invention, below with reference to
Specific embodiment, the present invention is further explained.
Referring to Fig. 1, the present invention provides a kind of technical solution: a kind of skilled work post industry mould based on artificial intelligence technology
Type training technique, the skilled work post industry pattern training technique the following steps are included:
Step 1: data acquisition；According to the acquisition for needing to carry out data sample of model training, data are known after acquiring
Rate does not judge, then judges whether discrimination is greater than 95%, if it is not, then continuing step 2, if it is, directly carrying out
Step 6；
Step 2: data prediction；The worker of skilled work post is rule of thumb first to the abnormal data in the data sample of acquisition
Pretreatment amendment is carried out, data sample correct, that quality is high is obtained, then carries out discrimination calculating, calculated discrimination
Old discrimination is replaced and as the discrimination recycled next time；
Step 3: model training；Model training is carried out using the high data sample of correct, quality；
Step 4: machine learning；The mode, type and correction amount for correcting data to the worker of work post skilled in step 2 carry out machine
Tool study, learns the relationship between each data, establishes modified feature database, and the result of machine learning is stored in feature database；
Step 5: data identification；Circulation terminates, after circulation carries out the acquisition of step 1 data again, first according in step 3
Feature database carries out data identification, and the data in data with same or similar problem are identified and are identified, are recycled into
The data prediction of row step 2；
Step 6: database preparation；After discrimination is greater than 95%, according to the mode of the amendment data of machine learning, type and repair
Positive quantity carries out the relationship between rote learning and each data, is modified automatically to the data of acquisition, then return step
Three carry out model training, and then circulation carries out Step 1: step 6 and step 3.
Discrimination calculation formula as a kind of preferred embodiment of the invention, in the step 2 are as follows: discrimination=identify
Data/always correct data.
As a kind of preferred embodiment of the invention, the step is a kind of, and when first time data acquire, initial identification rate is 0.
As a kind of preferred embodiment of the invention, when discrimination judges in the step 1, discrimination standard being capable of basis
It needs to set, practical discrimination being capable of timing or not timing selective examination amendment.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention, for this field skill
For art personnel, it is clear that invention is not limited to the details of the above exemplary embodiments, and without departing substantially from spirit of the invention or
In the case where essential characteristic, the present invention can be realized in other specific forms.Therefore, in all respects, should all incite somebody to action
Embodiment regards exemplary as, and is non-limiting, the scope of the present invention by appended claims rather than on state
Bright restriction, it is intended that including all changes that fall within the meaning and scope of the equivalent elements of the claims in the present invention
It is interior.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (4)
1. a kind of skilled work post industry pattern training technique based on artificial intelligence technology, which is characterized in that the skilled work post
Industry pattern training technique the following steps are included:
Step 1: data acquisition；According to the acquisition for needing to carry out data sample of model training, data are known after acquiring
Rate does not judge, then judges whether discrimination is greater than 95%, if it is not, then continuing step 2, if it is, directly carrying out
Step 6；
Step 2: data prediction；The worker of skilled work post is rule of thumb first to the abnormal data in the data sample of acquisition
Pretreatment amendment is carried out, data sample correct, that quality is high is obtained, then carries out discrimination calculating, calculated discrimination
Old discrimination is replaced and as the discrimination recycled next time；
Step 3: model training；Model training is carried out using the high data sample of correct, quality；
Step 4: machine learning；The mode, type and correction amount for correcting data to the worker of work post skilled in step 2 carry out machine
Tool study, learns the relationship between each data, establishes modified feature database, and the result of machine learning is stored in feature database；
Step 5: data identification；Circulation terminates, after circulation carries out the acquisition of step 1 data again, first according in step 3
Feature database carries out data identification, and the data in data with same or similar problem are identified and are identified, are recycled into
The data prediction of row step 2；
Step 6: database preparation；After discrimination is greater than 95%, according to the mode of the amendment data of machine learning, type and repair
Positive quantity carries out the relationship between rote learning and each data, is modified automatically to the data of acquisition, then return step
Three carry out model training, and then circulation carries out Step 1: step 6 and step 3.
2. a kind of skilled work post industry pattern training technique based on artificial intelligence technology according to claim 1, special
Sign is that the discrimination calculation formula in the step 2 are as follows: discrimination=data identified/always corrects data.
3. a kind of skilled work post industry pattern training technique based on artificial intelligence technology according to claim 1, special
Sign is that the step is a kind of, and when first time data acquire, initial identification rate is 0.
4. a kind of skilled work post industry pattern training technique based on artificial intelligence technology according to claim 1, special
Sign is, when discrimination judges in the step 1, discrimination standard can be set as needed, and practical discrimination being capable of timing
Or not timing selective examination amendment.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910099948X | 2019-01-31 | ||
| CN201910099948 | 2019-01-31 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110059830A true CN110059830A (en) | 2019-07-26 |
Family
ID=67325593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910483695.6A Pending CN110059830A (en) | 2019-01-31 | 2019-06-05 | A kind of skilled work post industry pattern training technique based on artificial intelligence technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059830A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580385A (en) * | 2019-08-21 | 2019-12-17 | 南京博阳科技有限公司 | data processing method, device and equipment for underground pipeline and computer storage medium |
| CN112819757A (en) * | 2021-01-19 | 2021-05-18 | 上海华野模型有限公司 | New industrial model planning method |
-
2019
- 2019-06-05 CN CN201910483695.6A patent/CN110059830A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580385A (en) * | 2019-08-21 | 2019-12-17 | 南京博阳科技有限公司 | data processing method, device and equipment for underground pipeline and computer storage medium |
| CN112819757A (en) * | 2021-01-19 | 2021-05-18 | 上海华野模型有限公司 | New industrial model planning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876163B (en) | Transient state power angle stability rapid evaluation method integrating causal analysis and machine learning | |
| CN108736465A (en) | A kind of future-state electric network model construction method and device | |
| CN110059830A (en) | A kind of skilled work post industry pattern training technique based on artificial intelligence technology | |
| CN109782124B (en) | Main distribution integrated fault positioning method and system based on gradient descent algorithm | |
| CN103020743A (en) | Ultra-short-term wind speed forecasting method for wind power plant | |
| CN110009135A (en) | A kind of wind power forecasting method based on width study | |
| CN109087215A (en) | More Power Output for Wind Power Field joint probability density prediction techniques | |
| CN104346839A (en) | Electronic employee attendance system based on local area network | |
| CN115374091A (en) | Distributed new energy output data quality improving method and system | |
| CN113869633A (en) | Power distribution network multi-source data quality control method | |
| CN110994613B (en) | Power plant load scheduling system and scheduling method thereof | |
| CN105373446B (en) | It is a kind of based on the system self-repairing method drilled automatically and device | |
| CN110674460B (en) | E-Seq2Seq technology-based data driving type unit combination intelligent decision method | |
| CN111737402A (en) | Question bank intelligent knowledge point marking system | |
| CN106405271A (en) | Monitoring data-based transformer state expert diagnosis method | |
| CN111091292A (en) | Real-time risk dynamic modeling analysis system for nuclear power station | |
| CN115422844A (en) | Power system operation scene identification method and system based on artificial intelligence identification | |
| CN111859783B (en) | Water pressure prediction method, system, storage medium, equipment and urban water supply system | |
| CN107506867B (en) | Photovoltaic output prediction method based on dynamic modeling | |
| CN109685242B (en) | Photovoltaic ultra-short term combined prediction method based on Adaboost algorithm | |
| CN112101608A (en) | Offshore wind farm site selection method and device | |
| CN110717694A (en) | Energy storage configuration random decision method and device based on new energy consumption expected value | |
| CN109726365A (en) | A kind of method and apparatus of load forecast | |
| CN106447062A (en) | Online optimization simulation system for complex distribution network | |
| Su et al. | Combined-LSTM based user electricity consumption prediction in a smart grid system |
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: 20190726 |
|
| RJ01 | Rejection of invention patent application after publication |