CN106874352A - A kind of method of search factor adjustment - Google Patents
A kind of method of search factor adjustment Download PDFInfo
- Publication number
- CN106874352A CN106874352A CN201611235174.1A CN201611235174A CN106874352A CN 106874352 A CN106874352 A CN 106874352A CN 201611235174 A CN201611235174 A CN 201611235174A CN 106874352 A CN106874352 A CN 106874352A
- Authority
- CN
- China
- Prior art keywords
- factor
- search
- product
- deduction
- city
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of method of search factor adjustment, the method includes several flows:A, search factor parameter setting, and be that the product factor, seller's factor, correlation factors, the service score deduction factor, the deduction of points of multi-brand word are the non-factors by search parameter Factorization;B, preservation rule;C, issue rules;D, product data update.Wherein described search factor parameter setting principle is:From bottom to top, the adjustment of category → classification is sequentially;Emphasis is grabbed, core category is preferentially adjusted, non-core category inherits higher level's rule.Using the method, the correlation of Search Results when scanning for, can be preferably improved, improve searching order result according to embodiments of the present invention so that Search Results are more accurate, can more meet the individual demand of user.
Description
Technical field
The present invention relates to Computer Applied Technology field, more particularly to a kind of method that search factor is adjusted.
Background technology
At present, with the surge of networking products information content, the concern of people's product information closely bound up to self-demand
More and more higher, the sequence of search engine is a process for complexity, and the selection of feature, the change of algorithm, the renewal of model all can
Cause the change of ranking results.
Search Results are the most important parts of search engine, for electric business website comes both parties, product search row
Sequence rule is all most important, most in the information of itself correlation.In a platform for online transaction, the rule of sequence just seems especially
It is important.Counted according to platform, in equivalents level, sequence can just lift the pageview of 6-8% per lifting one forward,
Often the lifting corresponding pageview of one page will increase by more than 300% for sequence.
There are more chances for exposure to allow seller, obtain more conclusion of the business chances, topmost is exactly the model sequencing factor.
The present invention proposes a kind of method of search factor adjustment, enables to searching order result more relevant, can more meet
The demand of user.
The content of the invention
In view of this, the method it is a primary object of the present invention to provide a kind of adjustment of search factor, by search parameter because
Son is decomposed into the product factor (Commodity), seller's factor (Seller), correlation factors (Relative), service score and subtracts
Molecular group (Services), the deduction of points of multi-brand word are the non-factor (Brands), and weight is set by scoring model, are being searched
When rope, ranking results are improved so that Search Results are more accurate, can more meet the personalized search demand of user.
To reach above-mentioned purpose, the technical proposal of the invention is realized in this way:
A kind of method of search factor adjustment, the method includes:
A, search factor parameter setting, and be the product factor, seller's factor, correlation factors, clothes by search parameter Factorization
The business score deduction factor, the deduction of points of multi-brand word are the non-factors;
B, preservation rule;
C, issue rules;
D, product data update.
Wherein described step A search factors parameter setting is main to be illustrated from following process:A1, ordering principle, A2,
Computing formula, A3, scoring model, A4, adjustment thinking, A5, parameter setting;And search parameter setting principle:From bottom to top, product
The adjustment of class → classification is sequentially;Emphasis is grabbed, core category is preferentially adjusted, non-core category inherits higher level's rule.
A1, ordering principle
Product score span:[-10000~10000]
Front end ordering rule:
Default sort:Fraction " high → low " according to product is ranked up;
Newly push away information:First by addition time-sequencing (M_gqinfo.addtime), then by moral treasured index sequence (czizhi_
rz.qyrz);
Moral treasured certification:First by moral treasured index (czizhi_rz.qyrz), then sorted by the time of renewal (M_gqinfo.fbdate),
Then by authority sequence (sys_user.rankid).
A2, computing formula
Search factor parameter decomposition is:The product factor (Commodity), seller's factor (Seller), correlation factors
(Relative), the service score deduction factor (Services), the deduction of points of multi-brand word are the non-factor (Brands), wherein each product
The score computing formula of product is as follows:
Score =(Commodity)* w1%+(Seller)* w2% +(Relative)* w3%
-(Services)-(Brands)
Wherein described w1, w2, w3 is weight, w1+w2+w3=100;
10000 points of product score full marks.
A3, scoring model
Scoring model mainly includes:
1)Trapezoidal factor model:As shown in Figure 2.
2)Yes-no type factor model:It is the non-not score with regard to score;If that is this factor is certain kind specified
Property, then the corresponding whole fractions of the factor are obtained, otherwise obtain 0 point.
3)Deduction factor model:
Given a mark by interval:If the value of a certain factor falls specified in interval, the corresponding whole fractions of this factor are obtained, it is no
Then obtain 0 point.
4)Growth form factor model:As shown in Figure 3
Calibration slope:(1/ maximum);
In [turning point, maximum] segment:Increase slope=(1/3) × calibration slope;
In [0, turning point] segment:By G-bar polishing remaining space.
5)Negative growth type deduction factor model:As shown in Figure 4
Calibration slope:(1/ maximum);
In [turning point, maximum] segment:Increase slope=(1/3) × calibration slope;
In [0, turning point] segment:By G-bar polishing remaining space.
A4, adjustment thinking
Before the purpose of adjustment arranges core classes purpose quality product.
Thinking:
Core category is found, to core category bonus point;Such as waste plastics>Pp waste materials;
Quality product is found, to quality product bonus point;
Classification standard is such as set up, certified products, conversion ratio, wherein described conversion ratio embodies the most crucial factor of value of the product
Point, the people for buying is more, illustrates that product gets over situation of selling well.It should be noted that conversion ratio here refers to searching for conversion ratio, with shop
Conversion ratio is unrelated.Non-search conversion is that conversion ratio can typically be accomplished 2 times by the present invention not for search rank increases any weight
More than;
Variable is reduced, control is expected;Quality product parameterized template is such as set, different categories only change price range.
A5, parameter setting
Parameter adjustment mainly includes the product factor, seller's factor, correlation factors, the service score deduction factor, multi-brand word button
It is the non-factor to divide.
A51, the product factor
The weight of the product factor this factor, as long as referring to that product information can accomplish that the Keywords matching searched with user is all right.
Reuse keyword simple in product information is invalid to product ranking.Error understanding product correlation, causes keyword heap
Build, product information quality reduction influence searching order can be caused on the contrary, serious meeting causes product to drop power.Product information description will
Information requirement and buying habit according to user.Too many duplicate message or unnecessary Custom Attributes is filled in, not only not
Integrity degree can be lifted, the professional degree of product can be influenceed on the contrary.During release product, the feature that user most pays close attention to is described clear.
The scoring model of the product factor mainly includes trapezoidal factor model, yes-no type factor model, the growth form bonus point factor
Model, negative growth type deduction factor model, deduction factor model.
1)Trapezoidal factor model leading indicator includes:Product sum, surplus products sum, product price.Such as table 1 below institute
Show, table 1 schematically illustrates weight shared by trapezoidal factor model items factor of influence;
Table 1
The bonus point upper limit, lower limit, product price sequence, look for critical point such as:PP films floor price 400, the upper limit 3000.
The full marks upper limit, lower limit, with reference to waste or used plastics category data, quality product is interval, and as shown in table 2 below, table 2 is schematic
Illustrate statistical items each item data after treatment;
Table 2
2)Yes-no type factor model leading indicator includes:Whether manage mainly category, whether newest release product, whether false one pay for three
Product, whether recommended products, whether support to cash on delivery.As shown in table 3 below, table 3 schematically illustrates yes-no type factor modulus
Every factor of influence and shared weight of type.
Table 3
Following parameter is adjusted according to each classification situation:Main management category, recommended products, new release product, false one pay for three, can take the circumstances into consideration
Improve false one weight for paying for three.Corresponding weight is adjusted according to the product factor, in incorporating searching order result, so that user examines
Rope improves Consumer's Experience to the product for best suiting its demand.
3)Growth form bonus point factor model leading indicator includes:By collection number of times, exchange hand, current favorable comment number, current good
Comment rate, number of visits, detail information.As shown in table 4 below, table 4 schematically illustrates growth form bonus point factor model items shadow
Ring weight shared by the factor.
Table 4
4)Negative growth type deduction factor model leading indicator includes:Difference comments number in current product.As shown in table 5 below, table 5 is illustrated
Property illustrate negative growth type deduction factor model items factor of influence shared by weight.
Table 5
5)Deduction factor model leading indicator includes:Product length for heading minimum value.As shown in table 6 below, table 6 is schematically opened up
Weight shared by deduction factor model items factor of influence is shown.
Table 6
A52, seller's factor
The weight of seller's factor this factor, is in order to be able to more represent chance to honest operation, the seller for carrying out service, it is desirable to
More energy are placed on seller aspect of improving service quality, and from Buyers's Experience, lift information quality, honest operation,
For buyer creates good purchase experiences, the doulbe-sides' victory of both parties is reached.
The scoring model of seller's factor mainly includes trapezoidal factor model, yes-no type bonus point factor model, the growth form factor
Model, yes-no type deduction factor model.
1)Trapezoidal factor model leading indicator includes:Seller shop quality product sum.The information displaying matter of seller's issue
Amount product high is more, can more embody the professional ability of seller, can also allow buyer to more clearly understand product information, trust purchase
Buy.Quality product number is more, and sequence also can be more preferential.As shown in table 7 below, table 7 schematically illustrates the trapezoidal of seller's factor
Weight shared by the every influence data of factor model.
Table 7
The total bonus point upper limit of shop product, lower limit, are sorted by product sum, find the critical value i.e. full marks upper limit, lower limit, than
Such as, product number in waste plastics shop covers 80% trade company.As shown in table 8 below, table 8 schematically illustrates the critical value number of statistical items
According to.
Table 8
2)Yes-no type bonus point factor model leading indicator includes:Whether moral treasured certification, whether outstanding retail shop, whether industry leader,
Whether industry recommend, whether gold medal member, whether silver medal member, whether VIP member, whether in give up it is logical, whether excellent distinguished gathering person, be
No magnificent paper life, whether hundred million gold medal members, whether mould again it is precious, whether advertisement member, whether 29 degree of members, whether medium-sized and small enterprises, whether
Enterprise group, whether regular member.
Wherein described moral treasured certification is directed to the prestige authentication service that all members release, and either businessman of enterprise is still
As long as it is personal provide it is corresponding prove to can be carried out authentication, by after certification, can in the detailed page of supply and demand, retail shop, search
The rope page, your enterprise of preferential recommendation page presentation and certification mark, promotion effect are greatly promoted, and facilitate business order volume, are helped
You is helped preferably to obtain the trust of waste and old businessman, 80% businessman prioritizing selection certification member is traded!It is as shown in table 9 below, table
9 show schematically weight shared by yes-no type bonus point factor model items factor of influence.
Table 9
3)Growth form factor model leading indicator includes:Seller's rank, seller's favorable comment degree, the certification of moral treasured, empirical value, business opportunity letter
Breath, certificate and honor, cooperation case, member evaluate.In addition, increasing relative weight to moral treasured certification.It is as shown in table 10 below, table
10 schematically illustrate weight shared by growth form factor model items factor of influence.
Table 10
4)Yes-no type deduction factor model leading indicator includes:Whether seller is reported.As shown in table 11 below, table 11 is schematic
Illustrate yes-no type deduction factor model items factor of influence shared by weight.
Table 11
A53, correlation factors
The weight of correlation factors this factors, refers to the match relations of product and user's search keyword(Matching degree).It is as follows
Shown in table 12, table 12 schematically illustrates weight shared by correlation factors items bonus point keyword.
Table 12
A54, service to obtain molecular group
Service molecular group this factor weight, be for embodying seller's service quality, attitude, service response speed, middle difference
Comment number.As shown in table 13 below, table 13 schematically illustrates the data after the every treatment of the service score deduction factor.
Table 13
A55, the deduction of points of multi-brand word are the non-factors
The deduction of points of multi-brand word is the weight of non-this factor of the factor, refers to error understanding product correlation, causes brand word to be piled up.
As shown in table 14 below, it is data of the non-factor after collecting that table 14 schematically illustrates the deduction of points of multi-brand word.
Table 14
Comprising multiple brands in brand storehouse in same product name, such as:Reclaim scrap iron and steel, high price and reclaim scrap iron and steel, steel scrap
Iron high price is reclaimed;
Further, by it is above-mentioned to the product factor, seller's factor, correlation factors, service to obtain molecular group, multi-brand word deduct points
That the weight of the non-factor this five factors of influence is illustrated, then with computing formula Score=(Commodity)* w1% +
(Seller)* w2% +(Relative)* w3% -(Services)-(Brands), wherein described w1, w2, w3 are weight,
w1+w2+w3=100;Draw the score of each product.
The step B preserves rule, and the score of each product is preserved by redis, and wherein key is product IDs, and value is
The corresponding score of the product.
The step C issue rules, the weight point of each data model is adjusted according to different sequencing models.
The step D product data update and mainly pass through two ways:1)Automatically come into force, commodity " undercarriage → restocking again " behaviour
Make, generally 2-14 days;2)Update manually, universal class mesh number submits category name and product IDs, classification refresh data to according to renewal
(At most refresh once within one week, general 2-4 hours comes into force).
The method of search factor adjustment provided by the present invention, with advantages below:
1)Search Results are more related, help user more efficiently to find the product for meeting its demand;
2)Improve Search Results accuracy;
3)Searching order result is preferable.
Brief description of the drawings
Fig. 1 is the method flow schematic diagram of search factor adjustment of the present invention;
Fig. 2 is the trapezoidal factor model schematic diagram of method of search factor adjustment of the present invention;
Fig. 3 is the method growth form factor model schematic diagram of search factor adjustment of the present invention;
Fig. 4 is the method negative growth type deduction factor model schematic diagram of search factor adjustment of the present invention;
Fig. 5 is the method application scenarios schematic diagram of search factor adjustment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawings and the method that is adjusted to search factor of the invention of embodiments of the invention is made further in detail
Explanation.
The method, mainly comprising following flow:
Step A:Search factor parameter setting, and by search parameter Factorization be the product factor, seller's factor, correlation because
Son, the service score deduction factor, the deduction of points of multi-brand word are the non-factors;
Step B:Preserve rule;
Step C:Issue rules;
Step D:Product data update.
The present invention is adjusted to solve the problems, such as search factor, mainly employs following technology, and these technologies are carried out below
It is simple to introduce.
1)Sort result technology.It is the product factor (Commodity), seller's factor by search factor parameter decomposition
(Seller), correlation factors (Relative), the service score deduction factor (Services), the deduction of points of multi-brand word are the non-factors
(Brands), by scoring model calculating these factor proportions improves ranking results so that Search Results more meet
The demand of user, and then lift Consumer's Experience.
2)Data-modeling technique.It is of the invention main used in scoring model module, mainly including following model:It is trapezoidal
Factor model, yes-no type factor model, deduction factor model, growth form factor model, negative growth type deduction factor model.
3)Data statistic analysis technology.Main two modules of the present invention have used data statistic analysis technology.The product factor
Module, when the trapezoidal full marks upper limit, lower limit is counted, with reference to waste or used plastics category data, in quality product is interval, to product valency
Lattice carry out statistical analysis to look for critical point, and then count product price to weight shared by the product factor;Seller's factor module, system
Meter analysis product sum sequence, finds critical value, and then find the full marks upper limit, the lower limit of trapezoidal factor model, such as, waste plastics
Shop product number covers 80% trade company.
The several typical application scenarios of the method are described below:
Application scenarios one:
The method of search factor adjustment of the invention is applied in certain waste and old industry search system.
Fig. 5 is the method application scenario diagram of search factor adjustment of the invention, and the search system mainly includes:Index database mould
Block, reading word-dividing mode, syntax Analysis Module, indexed search module, scoring modules, Query Result module.
Wherein described scoring modules are mainly calculated by five scoring models, mainly including trapezoidal factor marking mould
Type, yes-no type factor scoring model, deduction factor scoring model, growth form factor scoring model, negative growth type deduction factor modulus
Type.
The list page of wherein described Query Result is, in the waste and old site search frame input keyword, to click on search, is entered
The product information list page of waste and old website.
Input:The ID of user is M161109100002, is input into keyword:Scrap iron and steel
Output Search Results:
{"resultCode":1,"resultMessage":"","params":{"province":"","city":"","
prostatus":0,"keyWord":"","minPrice":0,"maxPrice":0,"category":""},"product":
[{"isLoolApply":"","applyStatus":1,"lookApply":1,"auctionStatus":"","code":"
5d9e1fee363f40ae9a3f5e3c049fd2e2","pmCode":null,"name":It is " steel scrap, scrap iron, waste plastics, useless
Aluminium, network auction meeting ", " imgUrl ":null,"price":null,"valuation":" nothing ", " status ":null,"
time":"2016-12-28","releaseTime":"2016-12-24","num":83,"address":" Henan Province-Luoyang
City ", " endTime ":"2016-12-27 00:00:00","bidCompany":""},{"isLoolApply":"","
applyStatus":1,"lookApply":1,"auctionStatus":"","code":"
26a0d390a52d461a80c0c3f7261bb652","pmCode":null,"name":It is " steel scrap, scrap iron, waste plastics, useless
Aluminium, network auction meeting ", " imgUrl ":null,"price":null,"valuation":" nothing ", " status ":null,"
time":"2016-12-28","releaseTime":"2016-12-24","num":7,"address":" Henan Province-Luoyang
City ", " endTime ":"2016-12-27 00:00:00","bidCompany":""},{"isLoolApply":"","
applyStatus":1,"lookApply":1,"auctionStatus":"","code":"
9cdddb1a9a3146a5984510e7057613e6","pmCode":null,"name":" the steel-making steel scrap bucket call for tender ", "
imgUrl":null,"price":null,"valuation":" nothing ", " status ":null,"time":"2016-11-
11","releaseTime":"2016-11-08","num":0,"address":" Hebei province-Xingtai City ", " endTime ":"
2016-11-11 00:00:00","bidCompany":""},{"isLoolApply":"","applyStatus":1,"
lookApply":1,"auctionStatus":"","code":"d9e18ea7fbb94a19adf5d8b470cc0d43","
pmCode":null,"name":" scrap house trailer steel scrap vie for selling bulletin ", " imgUrl ":null,"price":null,"
valuation":" nothing ", " status ":null,"time":"2016-11-16","releaseTime":"2016-11-
08","num":0,"address":" Beijing-districts under city administration ", " endTime ":"2016-11-16 00:00:00","
bidCompany":""},{"isLoolApply":"","applyStatus":1,"lookApply":1,"
auctionStatus":"","code":"c74d9959c6f64b71af8e532107ed0714","pmCode":null,"
name":" scrap lorry steel scrap vie for selling bulletin ", " imgUrl ":null,"price":null,"valuation":" without ", "
status":null,"time":"2016-11-15","releaseTime":"2016-11-08","num":0,"
address":" Beijing-districts under city administration ", " endTime ":"2016-11-15 00:00:00","bidCompany":""},{"
isLoolApply":"","applyStatus":1,"lookApply":1,"auctionStatus":"","code":"
303c762d475d4bb28053ccb270ab00e6","pmCode":null,"name":" 320 tons of steel scrap cords of coal industry company
Core conveyer belt transfer is announced ", " imgUrl ":null,"price":null,"valuation":" nothing ", " status ":null,"
time":"2016-11-21","releaseTime":"2016-11-08","num":0,"address":" Hui Nationality in Ningxia Hui Nationality Autonomy is autonomous
Area-Yinchuan City ", " endTime ":"2016-11-21 00:00:00","bidCompany":""},{"
isLoolApply":"","applyStatus":1,"lookApply":1,"auctionStatus":"","code":"
5721a3dad2bb4fac94e6c5359bf5cd44","pmCode":null,"name":" 300 tons of steel scrap cords transfer the possession of public
Accuse ", " imgUrl ":null,"price":null,"valuation":" nothing ", " status ":null,"time":"2016-
11-21","releaseTime":"2016-11-08","num":0,"address":" Ningxia Hui Autonomous Region-Yinchuan City ", "
endTime":"2016-11-21 00:00:00","bidCompany":""},{"isLoolApply":"","
applyStatus":1,"lookApply":1,"auctionStatus":"","code":"
a3dad8ab200c42ff8d734a2f7ed61b10","pmCode":null,"name":" 2000 tons of steel scraps(It is medium-sized)Transfer the possession of
Bulletin ", " imgUrl ":null,"price":null,"valuation":" 50-100 ten thousand ", " status ":null,"
time":"2016-11-21","releaseTime":"2016-11-08","num":0,"address":" Hui Nationality in Ningxia Hui Nationality Autonomy is autonomous
Area-Yinchuan City ", " endTime ":"2016-11-21 00:00:00","bidCompany":""},{"
isLoolApply":"","applyStatus":1,"lookApply":1,"auctionStatus":"","code":"
31e00b9286454f35b70b2f4bce1adbd8","pmCode":null,"name":" 630 tons of reports of the miscellaneous steel scrap of logistics company
The useless a collection of disposal of equipment goods and materials is announced ", " imgUrl ":null,"price":null,"valuation":" nothing ", " status ":
null,"time":"2016-11-16","releaseTime":"2016-11-08","num":0,"address":" Hubei
Province-Wuhan City ", " endTime ":"2016-11-15 00:00:00","bidCompany":""},{"
isLoolApply":"","applyStatus":1,"lookApply":1,"auctionStatus":"","code":"
9d5be35e5bc44f16a8cd31fb68f39494","pmCode":null,"name":" useless modeling copper cash waste steel plate punching press
The waste disposal call for tender ", " imgUrl ":null,"price":null,"valuation":" nothing ", " status ":null,"
time":"2016-11-08","releaseTime":"2016-11-08","num":0,"address":" Shandong Province-Tai'an
City ", " endTime ":"2016-11-08 00:00:00","bidCompany":""}],"page":{"pageSize":10,"
recordNum":208,"pageNum":21,"pageNo":1},"address":[{"areaName":" Guangdong Province ", "
children":[" Guangzhou ", " Huizhou City ", " Meizhou City ", " Zhaoqing "] }, { " areaName ":" Shaanxi Province ", "
children":[" Yulin City ", " Hanzhong City "] }, { " areaName ":" Henan Province ", " children ":[" Sanmenxia City ", "
Zhengzhou City ", " Luoyang City ", " Jiaozuo City ", " Xuchang City ", " Xinxiang City "] }, { " areaName ":" Jiangxi Province ", "
children":[" Nanchang City "] }, { " areaName ":" Shanghai City ", " children ":[" districts under city administration "] }, { "
areaName":" Anhui Province ", " children ":[" Bengbu ", " Lu'an City ", " Maanshan City ", " Bozhou City ", " Hefei
City "] }, { " areaName ":" Tianjin ", " children ":[" districts under city administration "] }, { " areaName ":" Hebei province ", "
children":[" Zhangjiakou City ", " Baoding ", " Tangshan City ", " Handan City ", " Hengshui City ", " Xingtai City ", " Chengde ", "
Shijiazhuang City "] }, { " areaName ":" Chongqing City ", " children ":[" districts under city administration "] }, { " areaName ":" Gansu
Save ", " children ":[" Lanzhou "] }, { " areaName ":" Ningxia Hui Autonomous Region ", " children ":[" Yinchuan
City "] }, { " areaName ":" Shanxi Province ", " children ":[" Yuncheng ", " Changzhi City ", " Taiyuan City "] }, { "
areaName":" Jiangsu Province ", " children ":[" Xuzhou City ", " Taizhou City ", " Nanjing ", " Changzhou ", " Yangzhou ", "
Suzhou City ", " Huai'an ", " Lianyungang ", " Wuxi City ", " Nantong City "] }, { " areaName ":"null","
children":["null"]},{"areaName":" Sichuan Province ", " children ":[" Chengdu ", " Meishan City ", " inland river
City ", " Panzhihua City ", " Guangan City ", " Leshan "] }, { " areaName ":" Hunan Province ", " children ":[" Changsha
City ", " Chenzhou City ", " Zhuzhou "] }, { " areaName ":" Zhejiang Province ", " children ":[" Hangzhou ", " Ningbo City "] },
{"areaName":" Liaoning Province ", " children ":[" Anshan ", " Shenyang City ", " Jinzhou City ", " Daliang City ", " Dandong
City "] }, { " areaName ":" Shandong Province ", " children ":[" Laiwu City ", " Zibo City ", " Jinan City ", " Tai'an ", "
Yantai City ", " Liaocheng City ", " Weifang City ", " Qingdao City "] }, { " areaName ":" Beijing ", " children ":[" city has jurisdiction over
Area "] }, { " areaName ":" Xinjiang Uygur Autonomous Regions ", " children ":[" Urumqi City "] }, { " areaName ":"
Inner Mongolia Autonomous Region ", " children ":[" Baotou ", " Ordos City ", " Huhehaote City "] }, { " areaName ":"
Guangxi Zhuang Autonomous Region ", " children ":[" Nanning City "] }, { " areaName ":" Hubei Province ", " children ":[" Wuhan
City ", " Shiyan City "] }, { " areaName ":" Heilongjiang Province ", " children ":[" Harbin City "] }, { " areaName ":"
Yunnan Province ", " children ":[" Bai Autonomous Prefecture of Dali ", " Kunming "] }, { " areaName ":" Qinghai Province ", "
children":[" Xining "] }], " category ":{"listOneCode":[],"listOneName":[{"name":"
Other are auctioned ", " sum ":207},{"name":" material equipment auction ", " sum ":1}]},"valuation":{"
valuation":[{"name":" nothing ", " sum ":449700160001},{"name":" within 500,000 ", " sum ":
449700160002},{"name":" 50-100 ten thousand ", " sum ":449700160003},{"name":" 100-200 ten thousand ", "
sum":449700160004},{"name":" 200-500 ten thousand ", " sum ":449700160005},{"name":" 50,000,000 with
It is upper ", " sum ":449700160008}]}}
Application scenarios two:
Input product ID=e4e63f29fdf44f819f726947d6ec209e, is calculated the score of each factor of product, such as
Shown in table 15 below, table 15 schematically illustrates the correlation factor of influence product score.
Table 15
The above, only presently preferred embodiments of the present invention is not intended to limit the scope of the present invention.
The technical staff in the field can be understood that, for convenience of description and succinctly, foregoing description is
The specific work process of system, device and unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In several embodiments provided by the present invention, it should be understood that disclosed system, apparatus and method, can be with
Realize by another way.For example, it is described above to device embodiment be only schematical, for example, the unit
Division, only a kind of division of logic function can have other dividing mode when actually realizing, such as multiple units or group
Part can be combined or be desirably integrated into another system, or some features can be ignored, or not performed.It is another, it is shown or
The coupling each other for discussing or direct-coupling or communication connection can be the indirect couplings of device or unit by some interfaces
Close or communicate to connect, can be electrical, mechanical or other forms.
The unit as separating component explanation can be or can also be physically separate, be shown as unit
Part can be or may not be physical location, you can with positioned at a place, or multiple nets can also be distributed to
On network unit.Some or all of unit therein can be according to the actual needs selected to realize the mesh of this embodiment scheme
's.
In addition, during each functional unit in each embodiment of the invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.Above-mentioned integrated list
Unit can both be realized in the form of hardware, can be realized in the form of SFU software functional unit.
It should be noted that one of ordinary skill in the art will appreciate that whole or portion in realizing above-described embodiment method
Split flow, can be by computer program to instruct the hardware of correlation to complete, and described program can be stored in a computer
In read/write memory medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, it is described
Storage medium can be magnetic disc, CD, read-only memory(Read-Only Memory, ROM)Or random access memory
(Random Access Memory, RAM)Deng.
The method to search factor provided by the present invention adjustment is described in detail above, used herein specifically
Embodiment is set forth to principle of the invention and implementation method, and the explanation of above example is only intended to help and understands this hair
Bright method and its core concept;Simultaneously for those of ordinary skill in the art, according to thought of the invention, specific real
Apply and be will change in mode and range of application, in sum, this specification content should not be construed as to limit of the invention
System.
Claims (8)
1. a kind of method that search factor is adjusted, it is characterised in that the method includes:
A, search factor parameter setting, and be the product factor, seller's factor, correlation factors, clothes by search parameter Factorization
The business score deduction factor, the deduction of points of multi-brand word are the non-factors;
B, preservation rule;
C, issue rules;
D, product data update.
2. the method that search factor is adjusted according to claim 1, it is characterised in that the step A search factor parameters set
Determining principle is:
From bottom to top, the adjustment of category → classification is sequentially;Emphasis is grabbed, core category is preferentially adjusted, non-core category inherits higher level
Rule.
3. the method that search factor is adjusted according to claim 1, it is characterised in that the step A search parameter factors
Computing formula is specially:By the search factor parameter decomposition product factor (Commodity), seller's factor (Seller), correlation
The factor (Relative), the service score deduction factor (Services), the deduction of points of multi-brand word are the non-factor (Brands), each product
The score computing formula of product is as follows:
Score =(Commodity)* w1% +(Seller)* w2% +(Relative)* w3% -(Services)-
(Brands), wherein described w1, w2, w3 are weight, w1+w2+w3=100;10000 points of product score full marks.
4. the method that search factor is adjusted according to claim 1, it is characterised in that the step A search parameter factors
Scoring model is specifically included:Trapezoidal factor model, yes-no type factor model, deduction factor model, growth form factor model, negative increasing
Elongated deduction factor model.
5. the method that search factor is adjusted according to claim 1, it is characterised in that the step A search parameter factors
Adjustment thinking is specifically included:
A1, core category is found, to core category bonus point;
A2, quality product is found, to quality product bonus point, set up classification standard, certified products, conversion ratio, wherein described turns
Rate embodies the most crucial factor point of value of the product, and the people for buying is more, illustrates that product gets over situation of selling well;It should be noted that here
Conversion ratio refers to searching for conversion ratio, unrelated with shop conversion ratio;Non-search conversion is not for search rank increases any weight
, conversion ratio can typically be accomplished more than 2 times by the present invention;
A3, reduction variable, control is expected, and sets quality product parameterized template, and different categories only change price range.
6. the method that search factor is adjusted according to claim 1, it is characterised in that the step B preserves rule and is specially:
The score of each product is preserved by redis, wherein key is product IDs, and value is the corresponding score of the product.
7. the method that search factor is adjusted according to claim 1, it is characterised in that the step C issue rules are specially:
The weight point of each data model is adjusted according to different sequencing models.
8. the method that search factor is adjusted according to claim 1, it is characterised in that the step D product data renewal side
Formula includes:
D1, come into force automatically:Commodity " undercarriage → restocking again " are operated, generally 2-14 days;
D2, manually renewal:Universal class mesh number submits category name and product IDs, classification refresh data to according to renewal(At most refresh within one week
Once, general 2-4 hours comes into force).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611235174.1A CN106874352A (en) | 2016-12-28 | 2016-12-28 | A kind of method of search factor adjustment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611235174.1A CN106874352A (en) | 2016-12-28 | 2016-12-28 | A kind of method of search factor adjustment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106874352A true CN106874352A (en) | 2017-06-20 |
Family
ID=59164378
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611235174.1A Pending CN106874352A (en) | 2016-12-28 | 2016-12-28 | A kind of method of search factor adjustment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106874352A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109242604A (en) * | 2018-08-15 | 2019-01-18 | 深圳壹账通智能科技有限公司 | Service recommendation method, electronic equipment and computer readable storage medium |
CN110827106A (en) * | 2018-08-08 | 2020-02-21 | 北京京东尚科信息技术有限公司 | Method and device for constructing search model and method and device for searching commodities |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104063523A (en) * | 2014-07-21 | 2014-09-24 | 焦点科技股份有限公司 | E-commerce search scoring and ranking method and system |
CN104077306A (en) * | 2013-03-28 | 2014-10-01 | 阿里巴巴集团控股有限公司 | Search engine result sequencing method and search engine result sequencing system |
CN104281585A (en) * | 2013-07-02 | 2015-01-14 | 阿里巴巴集团控股有限公司 | Object ordering method and device |
US20160055253A1 (en) * | 2014-08-20 | 2016-02-25 | International Business Machines Corporation | Identifying Influencers in Computer Networks |
CN105760446A (en) * | 2016-02-03 | 2016-07-13 | 杭州驭猫科技有限公司 | Big data analysis method for shopping website |
CN105809458A (en) * | 2014-12-29 | 2016-07-27 | 苏宁云商集团股份有限公司 | Advertisement accurate delivery method and system in e-commerce site |
-
2016
- 2016-12-28 CN CN201611235174.1A patent/CN106874352A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104077306A (en) * | 2013-03-28 | 2014-10-01 | 阿里巴巴集团控股有限公司 | Search engine result sequencing method and search engine result sequencing system |
CN104281585A (en) * | 2013-07-02 | 2015-01-14 | 阿里巴巴集团控股有限公司 | Object ordering method and device |
CN104063523A (en) * | 2014-07-21 | 2014-09-24 | 焦点科技股份有限公司 | E-commerce search scoring and ranking method and system |
US20160055253A1 (en) * | 2014-08-20 | 2016-02-25 | International Business Machines Corporation | Identifying Influencers in Computer Networks |
CN105809458A (en) * | 2014-12-29 | 2016-07-27 | 苏宁云商集团股份有限公司 | Advertisement accurate delivery method and system in e-commerce site |
CN105760446A (en) * | 2016-02-03 | 2016-07-13 | 杭州驭猫科技有限公司 | Big data analysis method for shopping website |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110827106A (en) * | 2018-08-08 | 2020-02-21 | 北京京东尚科信息技术有限公司 | Method and device for constructing search model and method and device for searching commodities |
CN109242604A (en) * | 2018-08-15 | 2019-01-18 | 深圳壹账通智能科技有限公司 | Service recommendation method, electronic equipment and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Higashida et al. | Determinants of trade in recyclable wastes: evidence from commodity-based trade of waste and scrap | |
CN111159533B (en) | Intelligent charging service recommendation method and system based on user image | |
CN105931068A (en) | Cardholder consumption figure generation method and device | |
CN108491388A (en) | Data set acquisition methods, sorting technique, device, equipment and storage medium | |
CN104715409A (en) | Method and system for electronic commerce user purchasing power classification | |
CN107958043A (en) | A kind of electricity power engineering budget inventory automatic generation method | |
CN107545038A (en) | A kind of file classification method and equipment | |
CN109389321A (en) | A kind of price evaluation method and device | |
CN108389069A (en) | Top-tier customer recognition methods based on random forest and logistic regression and device | |
CN110472053A (en) | A kind of automatic classification method and its system towards public resource bidding advertisement data | |
CN109978061A (en) | A kind of recovery method as resource based on resource reclaim O2O platform | |
Zhang et al. | Second use value of China’s new energy vehicle battery: A view based on multi-scenario simulation | |
CN109062881A (en) | Purchase bidding documenting method and system | |
CN109740036A (en) | OTA platform hotel's sort method and device | |
CN106874352A (en) | A kind of method of search factor adjustment | |
Guo et al. | Quality control in production process of product-service system: A method based on turtle diagram and evaluation model | |
CN106294410A (en) | A kind of determination method of personalized information push time and determine system | |
Fukao et al. | Estimates of Total Factor Productivity, the Contribution of ICT, and Resource Reallocation Effects in Japan and Korea | |
CN110750572A (en) | Adaptive method and device for heuristic evaluation of scientific and technological achievements | |
CN112508375A (en) | Intelligent production scheduling and feeding system for hot continuous rolling process of high-speed tool steel | |
CN117391478A (en) | Product supply chain management system for cargo transportation | |
CN110490461A (en) | Door and window enterprise resource planning | |
CN107633429A (en) | Shared box for material circulation pricing method, apparatus and system | |
Hon et al. | Regional distribution of foreign direct investment in China: A multivariate data analysis of major socioeconomic variables | |
Liubarskaia et al. | The role of secondary resource market in the development of the extended producer responsibility mechanism in Russia |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170620 |
|
WD01 | Invention patent application deemed withdrawn after publication |