CN108960986A - A kind of supplier's recommended method based on web crawlers - Google Patents
A kind of supplier's recommended method based on web crawlers Download PDFInfo
- Publication number
- CN108960986A CN108960986A CN201810670387.XA CN201810670387A CN108960986A CN 108960986 A CN108960986 A CN 108960986A CN 201810670387 A CN201810670387 A CN 201810670387A CN 108960986 A CN108960986 A CN 108960986A
- Authority
- CN
- China
- Prior art keywords
- supplier
- enterprise
- information
- user
- feature
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Supplier's recommended method based on web crawlers that the invention discloses a kind of obtains the company information that a large amount of supplier provides with it by using crawler technology, and by data cleansing, feature database is established in feature extraction.Letter related to the enterprise for needing to carry out supplier's recommendation and enterprise have the calculating that supplier information feature carries out similarity later, so as to provide corresponding recommendation sequence, the supplier for being suitble to oneself can be quickly selected for enterprise, supplier is investigated so as to avoid artificial, carry out the complex process of a large amount of supplier information screenings, reduce manpower, the unnecessary consumption of material resources, and with the increase of number, recommender system can pass through study, so that recommendation is more accurate, this is also a trend of future development, the direction of enterprise's production development can preferably be adapted to.
Description
Technical field
Supplier's recommended method based on web crawlers that the present invention relates to a kind of.
Background technique
Under the background of supply chain management, enterprise to obtain efficient sustainable development, it is necessary that its
The quality problems of product, raw material, while should also ensure that the services such as the delivery of the product in the prescribed time-limit and Resolving probiems, therefore want
Ask that its supplier provides raw material and when product must satisfy the conditions such as quality, punctual, defined number.Therefore, for enterprise and
Speech, the selection and evaluation of supplier is often an important task, how to select and meets among numerous suppliers
The supplier that enterprise oneself generates characteristic is very valuable must to study.
In view of the above problems, often there is the supplier's Strategic Platform of oneself in the enterprise large-scale for one, it is special to collect
The whole nation and the supplier information for being likely to become this enterprise all over the world, then go to scene to be investigated, for qualification
Supplier is included in the Strategic Platform of oneself, and the supplier of selection oneself is waited for this, it is being allowed to provide product for oneself
When, it needs to examine again, however for its subordinate enterprise, it tends not to oneself look for supplier, is directly under normal conditions
Supplier information is obtained from supplier's Strategic Platform of Shang Shu enterprise, carries out certain screening, then carries out the signing supply of material again
Agreement etc., and for newly established enterprise, it generally requires to devote a tremendous amount of time the supplier for looking for meeting enterprise.
In addition to this, when in face of supplier's selection, required index, weight be not often identical for different enterprises, and one
As be all according to the indexs such as Professional performance, professional ability, quality system ability, risk assessment, the potential for cooperation different weights into
Row marking, so that it is determined that the supplier met, however it is often also different for weighted value determined by different enterprises.Generally adopt
Different indexs when being selected with analytic hierarchy process (AHP) supplier carry out weight distribution.This is also to be selected at present using more supplier
One of selection method.
It is studied by supplier's selection to existing enterprise, discovery enterprise generally requires in terms of the selection of supplier
It expends considerable time and effort, while there is also inevitable human factors, and often all for most of small business
It is directly to be screened from supplier of Shang Shu enterprise.Therefore there are certain inadaptabilities, and for new firms with greater need for
Time and efforts looks for the supplier for meeting itself.However big data is faced, and the epoch of artificial intelligence, based on data,
It is analyzed by data, the epoch of definitive result, we more neededly simplify the complexity of operation, more allow computer generation
It goes to select for people, in today of data-driven social development, the appearance of the following various recommender systems is tended to
The demand and hobby of meet demand person, therefore giving that computer goes to select the artificial selection of supplier can be to avoid complicated
Screening, while the supplier for completing different enterprises can be recommended to recommend by two kinds based on enterprise and based on supplier.For
The supplier information of magnanimity takes the mode of web crawlers to be crawled from relevant supplier web site, crawls letter by obtaining
Breath, cleans relevant information, screens, and according to the generation product of enterprise, the features such as processing characteristics carry out the recommendation of supplier,
With the increase of data volume, the number of study increases, final recommendation also can it is more intelligent, rationalize, meeting, to keep away
The defect of manpower-free's screening.
Summary of the invention
It is an object of the invention to overcome the above-mentioned prior art, a kind of supplier based on web crawlers is provided and is pushed away
Recommend method, this method can obtain supplier information from relevant supplier website by web crawlers, by the processing to information,
The enterprise of offer supplier produces product characteristic as needed, supplier required for recommending, so as to avoid selection confession is thought
Answer complex process when quotient.
In order to achieve the above objectives, the present invention is achieved by the following scheme:
Frame scrapy-redis is crawled by the distribution of python first and crawls related letter from relevant supplier website
Breath mainly includes the company information of the provided product of supplier information and supplier, and needs to carry out by crawler technology acquisition
The company information that supplier recommends obtains the existing supplier's letter of enterprise if there has been the supplier of oneself in enterprise simultaneously
Breath.
Secondly, carrying out data cleansing, the information that crawler climbs to is cleaned, chooses relevant feature, such as enterprise
Product characteristic is produced, supplier provides product characteristic, ability, quality etc..
Relevant recommended method is selected, the present invention uses based on article (Item-Based CF) and is based on user (User-
Based CF) the collaborative filtering that combines of recommendation, for after the information cleaning climbed to, if enterprise is newly established
Enterprise, there is no one's own supplier information, using the proposed algorithm for being based on user (User-Based CF), to enterprise
The similar enterprise of industry is ranked up, and by recommending the supplier of existing enterprise to the new firms for needing to recommend supplier.It is right
In the enterprise for having possessed one's own supplier, when needing to recommend supplier, using based on user (User-Based CF)
With based on article (Item-Based CF) collaborative filtering combine method, to the enterprise for needing to recommend supplier and its
The supplier information feature that existing supplier information feature possesses with the enterprise and enterprise crawled carries out similarity calculation, point
Two kinds are not provided according to the collaborative filtering method based on user (User-Based CF) and based on article (Item-Based CF)
Different sequences mentions for business choice.
Compared with prior art, the invention has the following advantages:
The present invention obtains the company information that a large amount of supplier provides with it by using crawler technology, and clear by data
It washes, feature database is established in feature extraction.Letter related to the enterprise for needing to carry out supplier's recommendation and enterprise have supplier's letter later
The calculating of feature progress similarity is ceased, so as to provide corresponding recommendation sequence, can quickly select to be suitble to certainly for enterprise
Oneself supplier investigates supplier so as to avoid artificial, carries out the complex process of a large amount of supplier information screenings, reduce people
The unnecessary consumption of power, material resources, and with the increase of number, recommender system can be by study, so that recommending more
Accurately, this is also a trend of future development, can preferably adapt to the direction of enterprise's production development.
Detailed description of the invention
Fig. 1 supplier recommender system structural schematic diagram.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
The invention will be described in further detail with reference to the accompanying drawing:
Referring to Fig. 1, Fig. 1 is the overall structure diagram of specific embodiments of the present invention, in enterprise demand supplier, is needed
The side's of asking login system, inputs enterprise's URL information, and system crawls the phase of enterprise using focused crawler by the address URL of input
Close information, such as the converted products of enterprise, process equipment, main supplier provide product, supplier's qualification, address, legal person,
Working ability mainly provides the features such as product information, registered capital.Simultaneity factor crawls phase using general crawler from internet
The supplier information of pass, essential information, qualification, business license, corporate message, working ability comprising supplier, mainly for answering
Product, process equipment and the existing company information by this supplier offer product, property, life comprising enterprise
Produce product, other supplier information etc..And establish relevant supplier of enterprise character pair library.
Recommend whether supplier contains one's own supplier information to carry out different recommendation moulds as needed
Formula, for a new firms, there is no one's own suppliers, it is therefore desirable to and it uses for reference and oneself produces like product, with
Similar enterprise of oneself enterprise selected supplier selects, therefore for new firms, and the present invention is using being based on
User (User-Based CF) collaborative filtering method is recommended, according to the letter of swash from the network supplier and enterprise that get
The feature database established is ceased, by selecting suitable similar algorithm, such as cosine similarity algorithm to carry out recommending supply to needs
Enterprise similar with its is found by the enterprise of quotient, and similar enterprise is carried out a sequence, and believe its selected supplier
Breath carries out a sequence, recently and supplier information similarity is close to the supplier more than frequency of occurrence preferential according to similarity
Principle carries out the sequence of supplier, so that demand enterprise carries out the selection of supplier.
It, can be using based on article containing one's own supplier for having run the enterprise of a period of time
(Item-Based CF) and the recommended method of collaborative filtering based on user (User-Based CF) combine, for from
The enterprise and its supplier information that network is got above, establish characteristic information library for its correlated characteristic, and select from feature database
Relevant feature is selected, using the collaborative filtering recommending for being based on user (User-Based CF), by enterprise's phase with demand supplier
As enterprise be ranked up, then it is high or the similar supplier of property is ranked up from the frequency of occurrences among sequence enterprise, give
Recommend sequence selective out.In addition to this it is possible to be carried out using the collaborative filtering method based on article (Item-Based CF)
Recommend, the existing supplier information of the enterprise of demand supplier is lifted, similar supplier is selected to press from feature database
It is ranked up according to similarity, and ranking results is shown, selected for demand enterprise.
The above content is merely illustrative of the invention's technical idea, and this does not limit the scope of protection of the present invention, all to press
According to technical idea proposed by the present invention, any changes made on the basis of the technical scheme each falls within claims of the present invention
Protection scope within.
Claims (4)
1. a kind of supplier's recommended method based on web crawlers, which comprises the following steps:
Step 1: frame scrapy-redis being crawled by the distribution of python and crawls information, the information from supplier web site
Company information comprising the provided product of supplier information and supplier, and need to carry out supplier by crawler technology acquisition
The company information of recommendation obtains the existing supplier information of enterprise if there has been the supplier of oneself in enterprise simultaneously;
Step 2: carrying out data cleansing, the information that crawler climbs to is cleaned, relevant feature is chosen;
Step 3: the collaborative filtering that selection is combined using the recommendation based on article and based on user;
For after the information cleaning climbed to, if enterprise is newly established enterprise, there is no one's own supplier information,
Using the proposed algorithm based on user, enterprise similar with enterprise is ranked up, and the supplier by recommending existing enterprise
To the new firms for needing to recommend supplier;For having possessed the enterprise of one's own supplier, need to recommend supplier
When, using based on user and based on article collaborative filtering combine method, to the enterprise for needing to recommend supplier and its
The supplier information feature that existing supplier information feature possesses with the enterprise and enterprise crawled carries out similarity calculation, point
Two different sequences are not provided according to the collaborative filtering method based on user and based on article, are mentioned for business choice.
2. supplier's recommended method according to claim 1 based on web crawlers, which is characterized in that step 1 it is specific
Method is as follows:
In enterprise demand supplier, party in request's login system inputs enterprise's URL information, and system passes through the address URL of input,
Using focused crawler, the relevant information of enterprise is crawled;Simultaneity factor crawls relevant supply using general crawler from internet
Quotient's information, essential information, qualification, business license, corporate message, working ability comprising supplier, mainly for answer product, processing
Equipment and the existing company information by this supplier offer product, company information include the property of enterprise, production
Product and other supplier information;And establish relevant supplier of enterprise character pair library.
3. supplier's recommended method according to claim 1 based on web crawlers, which is characterized in that step 3 it is specific
Method is as follows:
For new spectra, recommended using based on user collaborative filter method, according to swash from network the supplier that gets with
The feature database that the information of enterprise is established, by select cosine similarity algorithm carry out to need to recommend the enterprise of supplier find with
Its similar enterprise, and similar enterprise is subjected to a sequence, and a sequence is carried out to its selected supplier information,
Recently and supplier information similarity close to supplier's preferential principle more than frequency of occurrence carries out supplier according to similarity
Sequence, for demand enterprise carry out supplier selection;
For there is the enterprise of one's own supplier, using the recommended method phase of the collaborative filtering based on article and based on user
In conjunction with, for the enterprise got above network and its supplier information, its correlated characteristic is established into characteristic information library,
And relevant feature is selected from feature database, using the collaborative filtering recommending based on user, by enterprise's phase with demand supplier
As enterprise be ranked up, then it is high or the similar supplier of property is ranked up from the frequency of occurrences among sequence enterprise, give
Recommend sequence selective out.
4. supplier's recommended method according to claim 3 based on web crawlers, which is characterized in that base can also be used
Recommended in the collaborative filtering method of article, the existing supplier information of the enterprise of demand supplier is lifted, from spy
Sign selects similar supplier to be ranked up according to similarity in library, and ranking results are shown, selects for demand enterprise.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810670387.XA CN108960986A (en) | 2018-06-26 | 2018-06-26 | A kind of supplier's recommended method based on web crawlers |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810670387.XA CN108960986A (en) | 2018-06-26 | 2018-06-26 | A kind of supplier's recommended method based on web crawlers |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108960986A true CN108960986A (en) | 2018-12-07 |
Family
ID=64486749
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810670387.XA Pending CN108960986A (en) | 2018-06-26 | 2018-06-26 | A kind of supplier's recommended method based on web crawlers |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108960986A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112380457A (en) * | 2020-12-07 | 2021-02-19 | 长沙军民先进技术研究有限公司 | Accurate personalized recommendation method based on purchase information |
CN112465389A (en) * | 2020-12-12 | 2021-03-09 | 广东电力信息科技有限公司 | Word frequency-based similar provider recommendation method and device |
CN112861004A (en) * | 2021-02-20 | 2021-05-28 | 中国联合网络通信集团有限公司 | Rich media determination method and device |
CN113837793A (en) * | 2021-08-25 | 2021-12-24 | 杭州杰牌传动科技有限公司 | Supplier recommendation method and device, storage medium and terminal |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103578007A (en) * | 2012-07-20 | 2014-02-12 | 三星电子(中国)研发中心 | Mixed recommendation system and method for intelligent device |
CN104156450A (en) * | 2014-08-15 | 2014-11-19 | 同济大学 | Item information recommending method based on user network data |
CN105183767A (en) * | 2015-07-31 | 2015-12-23 | 山东大学 | Enterprise network-based enterprise business similarity calculation method and system |
CN106971053A (en) * | 2016-01-08 | 2017-07-21 | 车海莺 | A kind of recommendation method based on mixing collaborative filtering |
CN107194754A (en) * | 2017-04-11 | 2017-09-22 | 美林数据技术股份有限公司 | Stock trader's Products Show method based on mixing collaborative filtering |
-
2018
- 2018-06-26 CN CN201810670387.XA patent/CN108960986A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103578007A (en) * | 2012-07-20 | 2014-02-12 | 三星电子(中国)研发中心 | Mixed recommendation system and method for intelligent device |
CN104156450A (en) * | 2014-08-15 | 2014-11-19 | 同济大学 | Item information recommending method based on user network data |
CN105183767A (en) * | 2015-07-31 | 2015-12-23 | 山东大学 | Enterprise network-based enterprise business similarity calculation method and system |
CN106971053A (en) * | 2016-01-08 | 2017-07-21 | 车海莺 | A kind of recommendation method based on mixing collaborative filtering |
CN107194754A (en) * | 2017-04-11 | 2017-09-22 | 美林数据技术股份有限公司 | Stock trader's Products Show method based on mixing collaborative filtering |
Non-Patent Citations (2)
Title |
---|
吴海峰: "基于多agent的物流服务提供商推荐系统设计", 《中国优秀硕士学位论文全文数据库 信息安全辑》 * |
黄鹏: "基于互联网用户特征的商品推荐系统研究", 《中国优秀硕士学位论文全文数据库 信息安全辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112380457A (en) * | 2020-12-07 | 2021-02-19 | 长沙军民先进技术研究有限公司 | Accurate personalized recommendation method based on purchase information |
CN112465389A (en) * | 2020-12-12 | 2021-03-09 | 广东电力信息科技有限公司 | Word frequency-based similar provider recommendation method and device |
CN112861004A (en) * | 2021-02-20 | 2021-05-28 | 中国联合网络通信集团有限公司 | Rich media determination method and device |
CN112861004B (en) * | 2021-02-20 | 2024-02-06 | 中国联合网络通信集团有限公司 | Method and device for determining rich media |
CN113837793A (en) * | 2021-08-25 | 2021-12-24 | 杭州杰牌传动科技有限公司 | Supplier recommendation method and device, storage medium and terminal |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108960986A (en) | A kind of supplier's recommended method based on web crawlers | |
Bai et al. | Multicriteria green supplier segmentation | |
US11676087B2 (en) | Systems and methods for vulnerability assessment and remedy identification | |
CN101334787B (en) | Objects evaluation information enquiry system and method | |
CN109697657A (en) | A kind of dining recommending method, server and storage medium | |
Miroslav et al. | Semantic technologies on the mission: Preventing corruption in public procurement | |
CN103646092A (en) | SE (search engine) ordering method based on user participation | |
CN108109066A (en) | A kind of credit scoring model update method and system | |
CN110659937A (en) | Gradient-lifting-tree-based improved supplier quantitative scoring prediction algorithm | |
CN110399559A (en) | Intelligence insurance recommender system and computer storage medium | |
CN108256970A (en) | A kind of method that Products Show is carried out based on shopping need | |
Lim et al. | Hybrid genetic algorithm and association rules for mining workflow best practices | |
Jokonya et al. | Factors influencing retail SMEs adoption of social media for digital marketing | |
Abbasimehr et al. | A novel interval type-2 fuzzy AHP-TOPSIS approach for ranking reviewers in online communities | |
CN113641904A (en) | Method and device for recommending target customers for stores under Internet marriage line | |
Al-Taie et al. | Applying social network analysis to analyze a web-based community | |
CN111125561A (en) | Network heat display method and device | |
CN110287402A (en) | A kind of personalized reviews recommended method based on user preference | |
CN116128589A (en) | Transaction recommendation method and system based on DSSM | |
Jung | Visualizing Recommendation Flow on Social Network. | |
CN108629649A (en) | Engineering mechanical device user information intelligent Matching management method | |
Tyasari et al. | The adoption of information technology as decision support system in SMEs | |
Ramlan et al. | The impact of ICT in Malaysia: A simultaneous equations approach | |
Ke et al. | A Selection Approach for Optimized Problem‐Solving Process by Grey Relational Utility Model and Multicriteria Decision Analysis | |
Gobin-Rahimbux et al. | Investigating technology awareness and usage in Mauritian SMEs in the handicraft sector |
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 |