CN107273131A - A kind of machine learning method applied to Configurable BOM - Google Patents
A kind of machine learning method applied to Configurable BOM Download PDFInfo
- Publication number
- CN107273131A CN107273131A CN201710480009.0A CN201710480009A CN107273131A CN 107273131 A CN107273131 A CN 107273131A CN 201710480009 A CN201710480009 A CN 201710480009A CN 107273131 A CN107273131 A CN 107273131A
- Authority
- CN
- China
- Prior art keywords
- configurable
- bom
- configurable bom
- apolegamy
- item
- 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
- G06F8/70—Software maintenance or management
- G06F8/71—Version control; Configuration management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The present invention is a kind of machine learning method applied to Configurable BOM, is comprised the steps of:A, the config option for obtaining Configurable BOM;B, the configurable option and value for obtaining current design;C, the state for obtaining all apolegamy items in Configurable BOM;D, the sample data got is trained;E, the fitting function for updating apolegamy item;F, it is designed using the fitting function after renewal, utilize method proposed by the present invention, only need to carry out product design based on Configurable BOM, the configuration rule for meeting current Configurable BOM can be continuously updated, after design reaches certain number of times, or even the optimal design rule of the Configurable BOM can be found.
Description
Technical field
The present invention relates to a kind of machine learning method, particularly a kind of machine learning method applied to Configurable BOM.
Background technology
Currently, user's request often has height unpredictability, in this case(Large-scale customization), how quickly
Customer in response demand, as enterprise's focus of interest.
In order to improve the design efficiency under large-scale customization, enterprise is configurable often by building by the way of
BOM structures, and to Configurable BOM addition apolegamy rule, so as to reach reduction data redudancy, improve design efficiency, even
It is the purpose of the Automation Design.But, often occurred using this kind of method, the regular imperfect, Policy Updates of apolegamy are delayed, very
To the situation for being rule errors.
The content of the invention
It is an object of the invention to provide a kind of machine learning method applied to Configurable BOM, to solve above-mentioned background
The problem of being proposed in technology.
To achieve the above object, the present invention provides following technical scheme:
A kind of machine learning method applied to Configurable BOM, is comprised the steps of:
A, the config option for obtaining Configurable BOM;
B, the configurable option and value for obtaining current design;
C, the state for obtaining all apolegamy items in Configurable BOM;
D, the sample data got is trained;
E, the fitting function for updating apolegamy item;
F, it is designed using the fitting function after renewal.
It is used as the further technical scheme of the present invention:The step C is specifically:Because the demand of client has height can not
Predictability, can make it that already present apolegamy item is from meeting all customer demands in current Configurable BOM, it is thus possible to occur
Situation about being extended to existing Configurable BOM, therefore get all apolegamy item states herein and also include newly adding
Match the state of item;According to the state of each apolegamy item, the output vector in machine learning is obtained.
It is used as the further technical scheme of the present invention:The step D is specifically:Utilize the characteristic vector, sample got
Data and output vector utilize suitable network structure, choose suitable activation primitive, and corresponding weights are obtained by calculating
Matrix, finally gives and meets expected network structure, i.e. fitting function.
It is used as the further technical scheme of the present invention:The step E is specifically:For each choosing in Configurable BOM
Its fitting function is all updated with item, in the method, be not for whole Configurable BOM digital simulation function, but for
Each apolegamy item digital simulation function, the purpose so done in Configurable BOM so that Configurable BOM is ensureing expansible
Property in the case of, more neatly obtain and meet the fitting function of input quantity
Compared with prior art, the beneficial effects of the invention are as follows:Utilize method proposed by the present invention, it is only necessary to based on configurable
BOM carries out product design, so that it may the configuration rule for meeting current Configurable BOM is continuously updated, when design reaches certain number of times
Afterwards, in addition can find the Configurable BOM optimal design rule.
Brief description of the drawings
Fig. 1 is the machine learning schematic diagram applied to Configurable BOM of the invention.
Embodiment
The technical scheme in the embodiment of the present invention will be clearly and completely described below, it is clear that described implementation
Example only a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, this area is common
The every other embodiment that technical staff is obtained under the premise of creative work is not made, belongs to the model that the present invention is protected
Enclose.
Refering to Fig. 1;In the embodiment of the present invention, a kind of machine learning method applied to Configurable BOM, specifically comprising following
Step:
A, the config option for obtaining Configurable BOM.The maximum feature of Configurable BOM, is exactly with config option(Parameter);Without
Same Configurable BOM, its config option is different, using the config option in Configurable BOM, to determine the feature in machine learning
Vector.
B, the configurable option and value for obtaining current design.After the completion of the design based on Configurable BOM, obtaining this can match somebody with somebody
BOM config option and its corresponding numerical value is put, for the sample input in machine learning;
C, the state for obtaining apolegamy items all in current Configurable BOM.Because the demand of client has height unpredictability,
It can make it that already present apolegamy item is from meeting all customer demands in current Configurable BOM, it is thus possible to occur to existing
Configurable BOM situation about being extended, therefore get the apolegamy that all apolegamy item states also include newly adding herein
State;According to the state of each apolegamy item, the output vector in machine learning is obtained
D, the sample data got is trained.Utilize characteristic vector, sample data and the output vector profit got
Use suitable network structure(Perceptron, multilayer neural network etc.), choose suitable activation primitive(Such as Linear, Tanh,
Sigmoid, ReLu etc.), by calculating(BP neural network etc.)Corresponding weight matrix is obtained, finally gives and meets expected net
Network structure, i.e. fitting function(Equation).
E, the fitting function for updating apolegamy item(Equation).Its plan is updated for each apolegamy item in Configurable BOM
Function is closed, is not for whole Configurable BOM digital simulation function, but for every in Configurable BOM in the method
One apolegamy item digital simulation function, the purpose so done so that Configurable BOM is in the case where ensureing scalability, more
Neatly obtain the fitting function for meeting input quantity.
F, newly designed using the fitting function after renewal., can be with Configurable BOM for the new demand of user
Directly calculated using obtained fitting function, so that each apolegamy item is obtained, the state under current demand, from
And complete the apolegamy design of Configurable BOM.
The better embodiment to the present invention is illustrated above, but the invention is not limited to the implementation
Example, those skilled in the art can also make a variety of equivalent modifications or replace on the premise of without prejudice to spirit of the invention
Change, these equivalent modifications or replacement are all contained in the application claim limited range.
Claims (4)
1. a kind of machine learning method applied to Configurable BOM, it is characterised in that comprise the steps of:
Obtain the config option of Configurable BOM;
Obtain the configurable option and value of current design;
Obtain the state of all apolegamy items in Configurable BOM;
The sample data got is trained;
Update the fitting function of apolegamy item;
It is designed using the fitting function after renewal.
2. a kind of machine learning method applied to Configurable BOM according to claim 1, it is characterised in that the step
Suddenly C is specifically:Because the demand of client has height unpredictability, already present apolegamy in current Configurable BOM can be caused
Item can not meet all customer demands, it is thus possible to situation about being extended to existing Configurable BOM occurs, therefore herein
Get the state for matching item that all apolegamy item states also include newly adding;According to the state of each apolegamy item, machine is obtained
Output vector in device study.
3. a kind of machine learning method applied to Configurable BOM according to claim 1, it is characterised in that the step
Suddenly D is specifically:Suitable network structure is utilized using the characteristic vector, sample data and output vector got, chooses and closes
Suitable activation primitive, obtains corresponding weight matrix by calculating, finally gives and meet expected network structure, that is, be fitted letter
Number.
4. a kind of machine learning method applied to Configurable BOM according to claim 1, it is characterised in that the step
Suddenly E is specifically:For in Configurable BOM each apolegamy item update its fitting function, in the method, be not for
Whole Configurable BOM digital simulation function, but item digital simulation function is matched for each in Configurable BOM, so
The purpose done so that Configurable BOM more neatly obtains the fitting letter for meeting input quantity in the case where ensureing scalability
Number.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710480009.0A CN107273131A (en) | 2017-06-22 | 2017-06-22 | A kind of machine learning method applied to Configurable BOM |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710480009.0A CN107273131A (en) | 2017-06-22 | 2017-06-22 | A kind of machine learning method applied to Configurable BOM |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107273131A true CN107273131A (en) | 2017-10-20 |
Family
ID=60068743
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710480009.0A Pending CN107273131A (en) | 2017-06-22 | 2017-06-22 | A kind of machine learning method applied to Configurable BOM |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107273131A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108121887A (en) * | 2018-02-05 | 2018-06-05 | 艾凯克斯(嘉兴)信息科技有限公司 | A kind of method that enterprise standardization is handled by machine learning |
CN111625912A (en) * | 2020-06-04 | 2020-09-04 | 深制科技(苏州)有限公司 | Deep learning oriented Bom structure and creation method thereof |
CN111857793A (en) * | 2019-04-30 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Network model training method, device, equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105512258A (en) * | 2015-12-02 | 2016-04-20 | 上海大学 | Intelligent configuration method for automobile generalized products |
CN105677353A (en) * | 2016-01-08 | 2016-06-15 | 北京物思创想科技有限公司 | Feature extraction method and machine learning method and device thereof |
CN106294456A (en) * | 2015-05-29 | 2017-01-04 | 华为技术有限公司 | The method and apparatus of machine learning |
-
2017
- 2017-06-22 CN CN201710480009.0A patent/CN107273131A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106294456A (en) * | 2015-05-29 | 2017-01-04 | 华为技术有限公司 | The method and apparatus of machine learning |
CN105512258A (en) * | 2015-12-02 | 2016-04-20 | 上海大学 | Intelligent configuration method for automobile generalized products |
CN105677353A (en) * | 2016-01-08 | 2016-06-15 | 北京物思创想科技有限公司 | Feature extraction method and machine learning method and device thereof |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108121887A (en) * | 2018-02-05 | 2018-06-05 | 艾凯克斯(嘉兴)信息科技有限公司 | A kind of method that enterprise standardization is handled by machine learning |
CN111857793A (en) * | 2019-04-30 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Network model training method, device, equipment and storage medium |
CN111625912A (en) * | 2020-06-04 | 2020-09-04 | 深制科技(苏州)有限公司 | Deep learning oriented Bom structure and creation method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Alyasseri et al. | Variants of the flower pollination algorithm: a review | |
Huang et al. | A chaos control optimal algorithm for QoS-based service composition selection in cloud manufacturing system | |
Zhou et al. | Multi-objective artificial bee colony algorithm for short-term scheduling of hydrothermal system | |
Zandieh et al. | Dynamic job shop scheduling using variable neighbourhood search | |
CN108694673A (en) | A kind of processing method, device and the processing equipment of insurance business risk profile | |
CN109360097A (en) | Prediction of Stock Index method, apparatus, equipment and storage medium based on deep learning | |
Sivanagaraju et al. | Discrete particle swarm optimization to network reconfiguration for loss reduction and load balancing | |
CN102769635A (en) | Internet of things system and implementation method of internet of things system | |
CN107273131A (en) | A kind of machine learning method applied to Configurable BOM | |
AU2015203754B2 (en) | System and method for prescriptive analytics | |
Ma et al. | A novel dynamic integration approach for multiple load forecasts based on Q‐learning algorithm | |
Ziari et al. | Optimal allocation and sizing of active power line conditioners using a new particle swarm optimization-based approach | |
Sang et al. | Ensembles of gradient boosting recurrent neural network for time series data prediction | |
CN107743071A (en) | The enhancing method for expressing and device of a kind of network node | |
Motlagh et al. | A new architecture for modeling and prediction of dynamic systems using neural networks: Application in Tehran stock exchange | |
CN108230121A (en) | A kind of product design method based on Recognition with Recurrent Neural Network | |
CN106127420A (en) | A kind of finishing based on distributed deployment system management cloud system | |
Tomlinson et al. | Toward alternative decentralized infrastructures | |
Mou et al. | Optimisation of the reverse scheduling problem by a modified genetic algorithm | |
CN109710653A (en) | A kind of test data source configuration method and device | |
US20110137622A1 (en) | Assessing the maturity of an industry architecture model | |
Amali et al. | Fuzzy logic-based diversity-controlled self-adaptive differential evolution | |
Fujita | Deep Reinforcement Learning Approach for Maintenance Planning in a Flow-Shop Scheduling Problem | |
Sørensen et al. | An extensible component-based multi-objective evolutionary algorithm framework | |
CN113610474A (en) | Inventory management method and management system based on event network |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171020 |