CN109284298A - A kind of contents production system handled based on machine learning and big data - Google Patents
A kind of contents production system handled based on machine learning and big data Download PDFInfo
- Publication number
- CN109284298A CN109284298A CN201811332021.8A CN201811332021A CN109284298A CN 109284298 A CN109284298 A CN 109284298A CN 201811332021 A CN201811332021 A CN 201811332021A CN 109284298 A CN109284298 A CN 109284298A
- Authority
- CN
- China
- Prior art keywords
- data
- machine learning
- feature
- model
- template
- 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
- 238000010801 machine learning Methods 0.000 title claims abstract description 42
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000007726 management method Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims abstract description 8
- 238000013523 data management Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 8
- 238000012986 modification Methods 0.000 claims description 7
- 230000004048 modification Effects 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012550 audit Methods 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000014759 maintenance of location Effects 0.000 claims description 3
- 239000011265 semifinished product Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Abstract
The invention discloses a kind of contents production systems handled based on machine learning and big data, the system includes user management module, system function requirement module, data management module, machine learning system, feature collection system, analysis process system and Hadoop big data first floor system, wherein user management module is made of user management and user's checking, wherein system function requirement module is by template library, result's management and recycle bin, and wherein data management is by data source and system bottom data.The system has broken the production method of conventional contents, based on mass data processing ability, realized by the model algorithm operation of machine learning content from produce, while the continuous iteration of machine learning with adaptively will be so that content achievement be more accurate.The generation of the system will greatly discharge traditional labour, and any content for having a little curing mold formula can realize intelligent automatic production, greatly improve society and economical production efficiency.
Description
Technical field
The present invention relates to a kind of production systems, raw more particularly, to a kind of content handled based on machine learning and big data
Production system.
Background technique
The production method application field of traditional content is narrow, and needs a large amount of traditional labour.
The essence of the system is to support the integrated big data machine of machine learning algorithm design and large-scale data processing
Learning system.The data mining of model, training, precision problem and big data processing aspect in terms of including machine learning divides
The factors such as cloth storage, parallelization calculating, network communication, locality calculating, task schedule, system administration.
The system is intended to automatically carry out data acquisition, identification, clear using AI machine learning and big data processing technique
It washes, process, analyzing, model calculation and Intellectual power output, to realize the automated production of content, final output achievement had both included knot
Structure data present, again include text and hypertext class content achievement.
Summary of the invention
The technical problem to be solved by the present invention is to the production method application field of existing traditional content is narrow, and
A large amount of traditional labour is needed, therefore a kind of contents production system handled based on machine learning and big data is provided, thus
It solves the above problems.
To achieve the above object, the invention provides the following technical scheme: a kind of handled based on machine learning and big data
Contents production system, which is characterized in that the system include user management module, system function requirement module, data management module,
Machine learning system, feature collection system, analysis process system and Hadoop big data first floor system, wherein user management module
It is made of user management and user's checking, wherein system function requirement module is by template library, result's management and recycle bin, wherein counting
According to management by data source and system bottom data.
As a preferred technical solution of the present invention, user management include this system user setting primary account number and sub- account
Number two ranks, primary account number, which possesses, to be uploaded template, modification template, checks and manage production results, and manages the power of sub- account
Limit；Sub- account, which possesses, checks production results, and the operating right for the corresponding task assigned by primary account number；User's checking: if any
It needs, the permission login authentication for further progress data source platform.
As a preferred technical solution of the present invention, template library includes:
1) template library is to generate early period in content, needs to study and develops the sample database completed, wherein being integrated with model algorithm, number
According to source, processing logic, algorithm logic, model logic, text logic etc.；
2) according to different content type and customer type, different templates will be generated, template will store in systems, selective
Property call；
3) template of completion has been developed for system, administrator possesses upload template, and the permission of modification template；
4) template that completely new needs are developed, open application module, the system that can be committed to carry out judge to audit whether into
Row is developed in next step.
As a preferred technical solution of the present invention, result's management includes:
1) create content tasks: selection template library and data source input parameter, click a key and generate, content achievement generates, manually
Online check and correction and editor support to save, and assign the operation such as other users editor, are finally completed achievement export；
2) task in carrying out: refer to that the last time preserves, it is also necessary to which the semi-finished product for continuing editor can be clicked herein after sequeling
It collects until completing；
3) achievement is completed: to being completed and derived content can update, can also delete.
As a preferred technical solution of the present invention, recycle bin includes:
1) the content achievement cancelled for temporarily storing history；
2) longest retention cycle is automatic permanent removing after 30 days, 30 days；
3) manual permanent delet is supported.
As a preferred technical solution of the present invention, data source is set according to different data sources and different algorithm models
Meter carries out the access of different dimensions to data source and calculates bottom-layer design.
As a preferred technical solution of the present invention, system bottom data include MySQL: the processing of service database,
Hadoop: Real-time data interface, file system: the processing for report file and text etc. are provided.
As a preferred technical solution of the present invention, machine learning system includes core algorithm library, core algorithm inventory
The data such as algorithm model configuration item are stored up, guarantee the more perfect of core algorithm library by constantly optimizing and being promoted；
Step 1: selection data source, and training data, verify data and test data；
Step 2: it model data: constructs according to the feature of training data using computation model；
Step 3: verifying model: verify data access model is verified, and is continued to optimize according to result；
Step 4: it test model: using the performance for the model that test data inspection is verified, and is continued to optimize according to result；
Step 5: it uses model: doing calculating analysis in target data using complete trained model；
Step 6: tuning model: in continuous application practice, come according to more data and different features or adjusted parameter
Boosting algorithm performance.
As a preferred technical solution of the present invention, feature collection system is the continuous updating according to business datum, number
Constantly cumulative according to source, characteristic index is enriched constantly and is promoted perfect, and deposits in queue processing, then classification storage；
Step 1: according to the feature database of data source in the metadata got extraction feature index；
Step 2: and update the characteristic index newly extracted to feature database；
Step 3: classification storage and expansion；
As a preferred technical solution of the present invention, analysis process system includes:
A, it is outputted results in operation system according to input data, discriminatory analysis and decision；
B, discriminatory analysis principle of decision-making: use bottom data feature as dependence condition；
Hadoop big data first floor system includes:
A, as data warehouse, the bottom data for machine learning supports hadoop big data bottom, is mainly used for magnanimity number
According to cleaning, analysis and data characteristics and data summarization processing；
B, after the completion of data processing, data classification processing is carried out using data classification model.
Compared with current technology, the beneficial effects of the present invention are: the system has broken the production method of conventional contents, with sea
Based on measuring data-handling capacity, producing certainly for content, while engineering are realized by the model algorithm operation of machine learning
Practise continuous iteration with adaptively will be so that content achievement be more accurate.The generation of the system will greatly discharge traditional labour
Power, any content for having a little curing mold formula can realize intelligent automatic production, can be widely applied to marketing activity, consult
The fields such as industry, capital market, industry research, government-invested project are ask, society and economical production efficiency are greatlyd improve.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example to be used to explain the present invention together, not be construed as limiting the invention.In the accompanying drawings:
Fig. 1 is that system data of the invention handles illustraton of model；
Fig. 2 is this big bright machine learning system flow chart；
Fig. 3 is feature collection system flow chart of the invention.
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, 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.
As shown in Figure 1-3, a kind of contents production system handled based on machine learning and big data, which includes user
Management module, system function requirement module, data management module, machine learning system, feature collection system, analysis process system
With Hadoop big data first floor system, wherein user management module is made of user management and user's checking, wherein system function
Demand module is by template library, result's management and recycle bin, and wherein data management is by data source and system bottom data.
As a preferred technical solution of the present invention, user management include this system user setting primary account number and sub- account
Number two ranks, primary account number, which possesses, to be uploaded template, modification template, checks and manage production results, and manages the power of sub- account
Limit；Sub- account, which possesses, checks production results, and the operating right for the corresponding task assigned by primary account number；User's checking: if any
It needs, the permission login authentication for further progress data source platform.
Template library includes:
1) template library is to generate early period in content, needs to study and develops the sample database completed, wherein being integrated with model algorithm, number
According to source, processing logic, algorithm logic, model logic, text logic etc.；
2) according to different content type and customer type, different templates will be generated, template will store in systems, selective
Property call；
3) template of completion has been developed for system, administrator possesses upload template, and the permission of modification template；
4) template that completely new needs are developed, open application module, the system that can be committed to carry out judge to audit whether into
Row is developed in next step.
Result's management includes:
1) create content tasks: selection template library and data source input parameter, click a key and generate, content achievement generates, manually
Online check and correction and editor support to save, and assign the operation such as other users editor, are finally completed achievement export；
2) task in carrying out: refer to that the last time preserves, it is also necessary to which the semi-finished product for continuing editor can be clicked herein after sequeling
It collects until completing；
3) achievement is completed: to being completed and derived content can update, can also delete.
Recycle bin includes:
1) the content achievement cancelled for temporarily storing history；
2) longest retention cycle is automatic permanent removing after 30 days, 30 days；
3) manual permanent delet is supported.
Data source is designed according to different data sources and different algorithm models, and the access of different dimensions is carried out to data source
With calculating bottom-layer design.
System bottom data include MySQL: the processing of service database, Hadoop: providing Real-time data interface, file system
System: the processing for report file and text etc..
Machine learning system includes core algorithm library, and core algorithm library stores the data such as algorithm model configuration item, by not
Disconnected optimization and promotion guarantees the more perfect of core algorithm library, as shown in Figure 2；
Step 1: selection data source, and training data, verify data and test data；
Step 2: it model data: constructs according to the feature of training data using computation model；
Step 3: verifying model: verify data access model is verified, and is continued to optimize according to result；
Step 4: it test model: using the performance for the model that test data inspection is verified, and is continued to optimize according to result；
Step 5: it uses model: doing calculating analysis in target data using complete trained model；
Step 6: tuning model: in continuous application practice, come according to more data and different features or adjusted parameter
Boosting algorithm performance.
Feature collection system is the continuous updating according to business datum, and data source is constantly cumulative, and characteristic index is enriched constantly
And promoted perfect, and queue processing is deposited in, then classification storage, as shown in Figure 3；
Step 1: according to the feature database of data source in the metadata got extraction feature index；
Step 2: and update the characteristic index newly extracted to feature database；
Step 3: classification storage and expansion；
Analysis process system includes:
A, it is outputted results in operation system according to input data, discriminatory analysis and decision；
B, discriminatory analysis principle of decision-making: use bottom data feature as dependence condition；
Hadoop big data first floor system includes:
A, as data warehouse, the bottom data for machine learning supports hadoop big data bottom, is mainly used for magnanimity number
According to cleaning, analysis and data characteristics and data summarization processing；
B, after the completion of data processing, data classification processing is carried out using data classification model.
Referring to Fig. 1, data processing model basic logic is as follows:
(1) user click data source generates, and input will generate all kinds of parameters of content: template parameter, analysis image parameter etc.；
(2) system carries out Verification and whether data source successfully transfers judgement；
(3) after verifying and judge successfully, it is a series of to start progress data acquisition, identification, cleaning, processing, analysis, model calculation etc.
Operation；
(4) until operation is completed, PRELIMINARY RESULTS is exported；
(5) user carries out necessary verification editor to content results；
(6) can the result of generation be distributed and is assigned towards different role user after；
(7) after confirmation is errorless, editor is completed, and clicks export, and end result content file, which exports, to be completed.
The system has broken the production method of conventional contents, based on mass data processing ability, passes through machine learning
Model algorithm operation come realize content from producing, while the continuous iteration of machine learning and it is adaptive will be so that content achievement
More precisely.The generation of the system will greatly discharge traditional labour, and any content for having a little curing mold formula can be real
Existing intelligent automatic production, can be widely applied to marketing activity, consulting industry, capital market, industry research, government-invested project etc.
Field greatlys improve society and economical production efficiency.
The present invention is directed to build a set of content handled based on machine learning and big data from production system, the system nature
It is the innovative integrated frame building the processing of mass data cluster and machine learning collateral action and capable of reaching from iteration optimization
Construction system realizes that Machine self-learning with adaptively, is finally realized in content production field in the case where the framework is constantly applied and practiced
Automation, the production of wisdom, high standard, high quality.
The core meaning of the system is that the landingization by AI technical application on industry service chain is practiced, with Hadoop
Big data bottom and processing technique are support, through the realization of system architecture, guarantee machine learning or even deep learning algorithm
It continues to optimize and iteration, so as to realize the self-service presentation of digitization and text intelligence double contents, and in application practice
Wisdom degree is constantly promoted through Machine self-learning, to maximumlly save the resource inputs such as person property, changes tradition
Industry production mode realizes that social value maximizes to innovate kinetic energy.
The realization of the project include machine learning model call, training, amendment and data mining, distributed storage, simultaneously
The data bottom core technologies such as rowization calculating, network communication, locality calculating, task schedule, system administration.System implementation process
Concentrate on machine learning algorithm and big data processing technique automatically carry out data acquisition, identification, cleaning, processing, analysis,
Algorithm call with self study, model optimization, wisdomization output etc. links, final output achievement both included structural data present,
It again include text and hypertext class content achievement.
System features:
(1) machine learning is the core of the system, it is ensured that system can be held under continuous application practice with self study with adaptively
The continuous wisdomization that promoted is horizontal, so that content generation result is more intelligent, precision.
(2) searching and managing of the extraction of training data and feature, the design of collateral learning algorithm, training pattern and parameter,
Distribution training calculating process, self-learning optimization iteration etc., are all integrated in the system platform and complete.
(3) a variety of parallel training modes are provided, support different machine learning model and algorithm.
(4) it provides and first floor system is abstracted, to realize the support to bottom general big data processing engine, and provide number
According to programming language interface (API) common in science.
(5) possess ecology open and abundant, be widely applied and quick evolvability
Finally, it should be noted that the foregoing is only a preferred embodiment of the present invention, it is not intended to restrict the invention, although
Present invention has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, still can be right
Technical solution documented by foregoing embodiments is modified or equivalent replacement of some of the technical features, it is all
Within the spirit and principles in the present invention, any modification, equivalent replacement, improvement and so on should be included in protection of the invention
Within the scope of.
Claims (9)
1. a kind of contents production system handled based on machine learning and big data, which is characterized in that the system includes user's pipe
Manage module, system function requirement module, data management module, machine learning system, feature collection system, analysis process system and
Hadoop big data first floor system, wherein user management module is made of user management and user's checking, and wherein system function needs
Modulus block is by template library, result's management and recycle bin, and wherein data management is by data source and system bottom data.
2. a kind of contents production system handled based on machine learning and big data according to claim 1, feature are existed
In user management includes two ranks of user setting primary account number and sub- account of this system, and primary account number, which possesses, uploads template, modification
Production results, and the permission of the sub- account of management are checked and managed to template；Sub- account, which possesses, checks production results, and by leading
The operating right of the corresponding task of account number assignment；User's checking: if it is desired, being used for the permission of further progress data source platform
Login authentication.
3. a kind of contents production system handled based on machine learning and big data according to claim 1, feature are existed
In template library includes:
1) template library is to generate early period in content, needs to study and develops the sample database completed, wherein being integrated with model algorithm, number
According to source, processing logic, algorithm logic, model logic, text logic etc.；
2) according to different content type and customer type, different templates will be generated, template will store in systems, selective
Property call；
3) template of completion has been developed for system, administrator possesses upload template, and the permission of modification template；
4) template that completely new needs are developed, open application module, the system that can be committed to carry out judge to audit whether into
Row is developed in next step.
4. a kind of contents production system handled based on machine learning and big data according to claim 1, feature are existed
In result's management includes:
1) create content tasks: selection template library and data source input parameter, click a key and generate, content achievement generates, manually
Online check and correction and editor support to save, and assign the operation such as other users editor, are finally completed achievement export；
2) task in carrying out: refer to that the last time preserves, it is also necessary to which the semi-finished product for continuing editor can be clicked herein after sequeling
It collects until completing；
3) achievement is completed: to being completed and derived content can update, can also delete.
5. a kind of contents production system handled based on machine learning and big data according to claim 1, feature are existed
In recycle bin includes:
1) the content achievement cancelled for temporarily storing history；
2) longest retention cycle is automatic permanent removing after 30 days, 30 days；
3) manual permanent delet is supported.
6. a kind of contents production system handled based on machine learning and big data according to claim 1, feature are existed
In data source is designed according to different data sources and different algorithm models, and access and the meter of different dimensions are carried out to data source
Bottom-layer design is calculated, system bottom data include MySQL: the processing of service database, Hadoop: Real-time data interface, text are provided
Part system: the processing for report file and text etc..
7. a kind of contents production system handled based on machine learning and big data according to claim 1, feature are existed
In machine learning system includes core algorithm library, and core algorithm library stores the data such as algorithm model configuration item, by continuous excellent
Change and is promoted to guarantee the more perfect of core algorithm library；
Step 1: selection data source, and training data, verify data and test data；
Step 2: it model data: constructs according to the feature of training data using computation model；
Step 3: verifying model: verify data access model is verified, and is continued to optimize according to result；
Step 4: it test model: using the performance for the model that test data inspection is verified, and is continued to optimize according to result；
Step 5: it uses model: doing calculating analysis in target data using complete trained model；
Step 6: tuning model: in continuous application practice, come according to more data and different features or adjusted parameter
Boosting algorithm performance.
8. a kind of contents production system handled based on machine learning and big data according to claim 1, feature are existed
In feature collection system is the continuous updating according to business datum, and data source is constantly cumulative, and characteristic index is enriched constantly and promoted
It is perfect, and deposit in queue processing, then classification storage；
Step 1: according to the feature database of data source in the metadata got extraction feature index；
Step 2: and update the characteristic index newly extracted to feature database；
Step 3: classification storage and expansion.
9. a kind of contents production system handled based on machine learning and big data according to claim 1, feature are existed
In analysis process system includes:
A, it is outputted results in operation system according to input data, discriminatory analysis and decision；
B, discriminatory analysis principle of decision-making: use bottom data feature as dependence condition；
Hadoop big data first floor system includes:
A, as data warehouse, the bottom data for machine learning supports hadoop big data bottom, is mainly used for magnanimity number
According to cleaning, analysis and data characteristics and data summarization processing；
B, after the completion of data processing, data classification processing is carried out using data classification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811332021.8A CN109284298A (en) | 2018-11-09 | 2018-11-09 | A kind of contents production system handled based on machine learning and big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811332021.8A CN109284298A (en) | 2018-11-09 | 2018-11-09 | A kind of contents production system handled based on machine learning and big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109284298A true CN109284298A (en) | 2019-01-29 |
Family
ID=65175497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811332021.8A Pending CN109284298A (en) | 2018-11-09 | 2018-11-09 | A kind of contents production system handled based on machine learning and big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109284298A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109992662A (en) * | 2019-04-12 | 2019-07-09 | 上海晏鼠计算机技术股份有限公司 | A kind of Innovation Process method that intelligent text automation generates |
| CN111177238A (en) * | 2019-12-13 | 2020-05-19 | 北京航天云路有限公司 | Data set generation method based on user definition |
| CN111309378A (en) * | 2020-02-25 | 2020-06-19 | 电子科技大学 | Machine learning model life cycle management system and method |
| CN111339375A (en) * | 2020-03-19 | 2020-06-26 | 中国海洋石油集团有限公司 | Universal big data model configuration and analysis method |
| CN111695734A (en) * | 2020-06-12 | 2020-09-22 | 中国科学院重庆绿色智能技术研究院 | Multi-process planning comprehensive evaluation system and method based on digital twin and deep learning |
| CN112446526A (en) * | 2019-09-05 | 2021-03-05 | 美商讯能集思智能科技股份有限公司台湾分公司 | Production scheduling system and method |
| CN113177040A (en) * | 2021-04-29 | 2021-07-27 | 东北大学 | Full-process big data cleaning and analyzing method for aluminum/copper plate strip production |
| CN113485694A (en) * | 2021-07-06 | 2021-10-08 | 算话信息科技(上海)有限公司 | Variable data intelligent middle station system of algorithm |
| CN115577646A (en) * | 2022-12-08 | 2023-01-06 | 北京领雁科技股份有限公司 | Data modeling method, device, equipment and medium based on multi-source heterogeneous data |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955502A (en) * | 2014-04-24 | 2014-07-30 | 科技谷（厦门）信息技术有限公司 | Visualized on-line analytical processing (OLAP) application realizing method and system |
| US20160232456A1 (en) * | 2015-02-06 | 2016-08-11 | Box, Inc. | Method and system for implementing machine learning analysis of documents |
| CN106250987A (en) * | 2016-07-22 | 2016-12-21 | 无锡华云数据技术服务有限公司 | A kind of machine learning method, device and big data platform |
| US20170078621A1 (en) * | 2015-09-16 | 2017-03-16 | Intel Corporation | Facilitating personal assistance for curation of multimedia and generation of stories at computing devices |
| CN106803218A (en) * | 2017-03-17 | 2017-06-06 | 西安优盛信息技术有限公司 | A kind of big data tutoring system based on virtualization and cloud computing |
| CN106991161A (en) * | 2017-03-31 | 2017-07-28 | 北京字节跳动科技有限公司 | A kind of method for automatically generating open-ended question answer |
| CN107102976A (en) * | 2017-03-23 | 2017-08-29 | 北京大学 | Entertainment newses autocreating technology and system based on microblogging |
| CN107291680A (en) * | 2017-05-09 | 2017-10-24 | 毛姗婷 | A kind of system and implementation method that automatically generate composition based on template |
| US20170371856A1 (en) * | 2016-06-22 | 2017-12-28 | Sas Institute Inc. | Personalized summary generation of data visualizations |
| US20180032861A1 (en) * | 2016-07-29 | 2018-02-01 | Splunk, Inc. | Automated data-generation for event-based system |
| CN108121742A (en) * | 2016-11-30 | 2018-06-05 | 中国移动通信集团广东有限公司 | The generation method and device of user's disaggregated model |
| CN108447534A (en) * | 2018-05-18 | 2018-08-24 | 灵玖中科软件（北京）有限公司 | A kind of electronic health record data quality management method based on NLP |
| CN108563620A (en) * | 2018-04-13 | 2018-09-21 | 上海财梵泰传媒科技有限公司 | The automatic writing method of text and system |
| CN108710625A (en) * | 2018-03-16 | 2018-10-26 | 电子科技大学成都研究院 | A kind of special topic knowledge automatic mining system and method |
-
2018
- 2018-11-09 CN CN201811332021.8A patent/CN109284298A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955502A (en) * | 2014-04-24 | 2014-07-30 | 科技谷（厦门）信息技术有限公司 | Visualized on-line analytical processing (OLAP) application realizing method and system |
| US20160232456A1 (en) * | 2015-02-06 | 2016-08-11 | Box, Inc. | Method and system for implementing machine learning analysis of documents |
| US20170078621A1 (en) * | 2015-09-16 | 2017-03-16 | Intel Corporation | Facilitating personal assistance for curation of multimedia and generation of stories at computing devices |
| US20170371856A1 (en) * | 2016-06-22 | 2017-12-28 | Sas Institute Inc. | Personalized summary generation of data visualizations |
| CN106250987A (en) * | 2016-07-22 | 2016-12-21 | 无锡华云数据技术服务有限公司 | A kind of machine learning method, device and big data platform |
| US20180032861A1 (en) * | 2016-07-29 | 2018-02-01 | Splunk, Inc. | Automated data-generation for event-based system |
| CN108121742A (en) * | 2016-11-30 | 2018-06-05 | 中国移动通信集团广东有限公司 | The generation method and device of user's disaggregated model |
| CN106803218A (en) * | 2017-03-17 | 2017-06-06 | 西安优盛信息技术有限公司 | A kind of big data tutoring system based on virtualization and cloud computing |
| CN107102976A (en) * | 2017-03-23 | 2017-08-29 | 北京大学 | Entertainment newses autocreating technology and system based on microblogging |
| CN106991161A (en) * | 2017-03-31 | 2017-07-28 | 北京字节跳动科技有限公司 | A kind of method for automatically generating open-ended question answer |
| CN107291680A (en) * | 2017-05-09 | 2017-10-24 | 毛姗婷 | A kind of system and implementation method that automatically generate composition based on template |
| CN108710625A (en) * | 2018-03-16 | 2018-10-26 | 电子科技大学成都研究院 | A kind of special topic knowledge automatic mining system and method |
| CN108563620A (en) * | 2018-04-13 | 2018-09-21 | 上海财梵泰传媒科技有限公司 | The automatic writing method of text and system |
| CN108447534A (en) * | 2018-05-18 | 2018-08-24 | 灵玖中科软件（北京）有限公司 | A kind of electronic health record data quality management method based on NLP |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109992662A (en) * | 2019-04-12 | 2019-07-09 | 上海晏鼠计算机技术股份有限公司 | A kind of Innovation Process method that intelligent text automation generates |
| CN112446526A (en) * | 2019-09-05 | 2021-03-05 | 美商讯能集思智能科技股份有限公司台湾分公司 | Production scheduling system and method |
| CN112446526B (en) * | 2019-09-05 | 2024-03-12 | 美商讯能集思智能科技股份有限公司台湾分公司 | Production scheduling system and method |
| CN111177238A (en) * | 2019-12-13 | 2020-05-19 | 北京航天云路有限公司 | Data set generation method based on user definition |
| CN111177238B (en) * | 2019-12-13 | 2023-12-08 | 北京航天云路有限公司 | User-defined data set generation method |
| CN111309378A (en) * | 2020-02-25 | 2020-06-19 | 电子科技大学 | Machine learning model life cycle management system and method |
| CN111339375A (en) * | 2020-03-19 | 2020-06-26 | 中国海洋石油集团有限公司 | Universal big data model configuration and analysis method |
| CN111695734A (en) * | 2020-06-12 | 2020-09-22 | 中国科学院重庆绿色智能技术研究院 | Multi-process planning comprehensive evaluation system and method based on digital twin and deep learning |
| CN113177040A (en) * | 2021-04-29 | 2021-07-27 | 东北大学 | Full-process big data cleaning and analyzing method for aluminum/copper plate strip production |
| CN113485694A (en) * | 2021-07-06 | 2021-10-08 | 算话信息科技(上海)有限公司 | Variable data intelligent middle station system of algorithm |
| CN115577646A (en) * | 2022-12-08 | 2023-01-06 | 北京领雁科技股份有限公司 | Data modeling method, device, equipment and medium based on multi-source heterogeneous data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284298A (en) | A kind of contents production system handled based on machine learning and big data | |
| Zhou et al. | Hyper-heuristic coevolution of machine assignment and job sequencing rules for multi-objective dynamic flexible job shop scheduling | |
| CN110378528A (en) | Workshop scheduled production method and system based on genetic algorithm | |
| CN104798043B (en) | A kind of data processing method and computer system | |
| CN111080408B (en) | Order information processing method based on deep reinforcement learning | |
| CN109919489B (en) | Enterprise asset management system and GA-BP-based enterprise equipment life prediction method | |
| CN111178680B (en) | Wind power plant engineering quality overall process management system, method and equipment | |
| CN109255440A (en) | The method that predictive maintenance is carried out to Electric Power Generating Equipment based on recurrent neural network (RNN) | |
| Demircan Keskin | A two‐stage fuzzy approach for Industry 4.0 project portfolio selection within criteria and project interdependencies context | |
| CN115081913A (en) | Supply chain risk assessment and prevention and control system | |
| Yang et al. | Optimization of aircraft maintenance plan based on genetic algorithm | |
| CN103761618A (en) | Control method and system of science and technology item | |
| CN114387121A (en) | Collaborative optimization scheduling method and system for power storage material supply | |
| CN115965154A (en) | Knowledge graph-based digital twin machining process scheduling method | |
| CN113127537B (en) | Spare part demand prediction method integrating time sequence prediction model and machine learning model | |
| CN116308482A (en) | Order sales prediction method and device based on neural network model and Xgboost | |
| Farooq et al. | Evolving the quality of a model based test suite | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN111401651A (en) | Method for predicting material purchasing demand based on L STM network | |
| CN109816228A (en) | A kind of enterprise B IM technical application ability quantitative evaluation system and method | |
| Krishnamoorthy et al. | Optimizing stochastic temporal manufacturing processes with inventories: An efficient heuristic algorithm based on deterministic approximations | |
| Xiwang et al. | An improved multi-objective scatter search approach for solving selective disassembly optimization problem | |
| CN112381396B (en) | Integrated management method and system for serving enterprise development planning | |
| Chen et al. | Construction of a Blockchain Cross-Border e-Commerce Traceability Security System Based on Genetic Algorithm | |
| CN104123585A (en) | Service organization optimization analysis method based on service simulation |
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: 20190129 |
|
| RJ01 | Rejection of invention patent application after publication |