CN110348964A - It is a kind of based on the wisdom electronic commerce recommending method more perceived - Google Patents
It is a kind of based on the wisdom electronic commerce recommending method more perceived Download PDFInfo
- Publication number
- CN110348964A CN110348964A CN201910612530.4A CN201910612530A CN110348964A CN 110348964 A CN110348964 A CN 110348964A CN 201910612530 A CN201910612530 A CN 201910612530A CN 110348964 A CN110348964 A CN 110348964A
- Authority
- CN
- China
- Prior art keywords
- commodity
- data
- perceived
- user
- electronic commerce
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012937 correction Methods 0.000 claims abstract description 13
- 239000000047 product Substances 0.000 claims abstract description 9
- 239000013065 commercial product Substances 0.000 claims abstract description 8
- 210000003746 feather Anatomy 0.000 claims abstract description 5
- 244000144992 flock Species 0.000 claims abstract description 5
- 238000005457 optimization Methods 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000013278 delphi method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000000052 comparative effect Effects 0.000 claims description 2
- 230000008439 repair process Effects 0.000 claims description 2
- 230000005611 electricity Effects 0.000 claims 1
- 238000012360 testing method Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 7
- 230000008901 benefit Effects 0.000 abstract description 2
- 230000008447 perception Effects 0.000 abstract description 2
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to Technologies of Recommendation System in E-Commerce technical fields, more particularly to a kind of based on the wisdom electronic commerce recommending method more perceived, after active user's selection target commodity, end article and the corresponding Raw performance of similar commodity and the distribution of additional index are entered into rule base, according to algorithm of birdsing of the same feather flock together, the weight distribution system of user's commercial product recommending is formed by computer;Selected correction value assigns power result to the corresponding commodity of the weight distribution system formed for the first time using reversed prospecting tools and carries out positive amendment and adjusting.The present invention has the advantage that the present invention carries out intelligent amendment according to system situation in time compared with prior art, it is different from the narrow-mindedness of traditional electronic commerce Recommendations, recommend meet user demand to agree with commodity, realize preferable user's perception, in combination with sales promotion information, institute's recommended products is made to be more in line with the consumption feature and consumption choice of consumer.
Description
Technical field
The invention belongs to Technologies of Recommendation System in E-Commerce technical fields, and in particular to a kind of based on the wisdom electronics more perceived
Commercial recommended method.
Background technique
Artificial intelligence refers to the ability that computer system executes complex task.There are three Main Branches altogether for this technology.
First is that rule-based artificial intelligence;Second is that irregular artificial intelligence, computer reads mass data, then according to data
Statistics, the methods of probability analysis carry out Intelligent treatment;Third is that a kind of deep learning neural network based.
It has been trend of the times that conglomerate, which introduces artificial intelligence technology and carries out Industry Reform, at present.And how to utilize existing
Technological frame, develop that more efficient, ease for use is higher, the wider array of AI of applicability, then become the most important thing.From business application
From the perspective of, AI platform has consequence in AI technical field, its emergence and development, it will largely
The upper speed for promoting industrial upgrading, helps e-commerce venture to carry out technological improvement, allows consumption while completing improved efficiency
Person most preferably realizes shopping need, declines e-commerce merchants O&M cost.
In this context, the recommendation of intelligent electronic business users is designed and Implemented herein, passes through computer deep learning, machine
Device study and computer related algorithm, realize effective recommendation function of system.
As an advanced subject, artificial intelligence has been a great concern in the entire field of computer science.Manually
Intelligence has become the important driving force promoted economic development, as the mark post of contemporary industry transformation, artificial intelligence technology, it will
The fields such as e-commerce have an important influence on, and form new standard, new thinking, new model.
In E-business applications field, user selection, identification and for user Products Show, be e-commerce very
An important link largely uses at present in this link and is accustomed to and consumes spy according to the search of previous user
Levy the intelligent recommendation carried out.Although this recommend have certain specific aim, after the selection diversification of user, for
This recommendation, effect also can be unsatisfactory.
Traditional e-commerce recommends difficulty to be mainly reflected in:
More recommendation is to use user's currently selectivity, recommends similar product, but user's selection has jumping characteristic, different
It is fixed that interest is generated again to such product;
For the recommendation of user, it may be possible to which the commodity of the businessman's routine commodity with promotion higher for discounting dynamics, system is not
There is a preferable recommendation, such as top set;
For the preference of user, E-commerce platform system does not provide the product to match partially with user, it is likely that causes to use
The loss at family.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of based on the wisdom e-commerce more perceived recommendation
Method.
The present invention is achieved by the following technical solutions: a kind of based on the wisdom e-commerce recommendation side more perceived
Method, including rule base, the rule base are based on primary data and weigh equipped with original tax, i.e., primary data is first with original weight
Beginning index, the primary data include consumption foundation data and item property data, will be based on e-commerce user basic data
Index with weight in addition to primary data and commodity basic attribute data is removed based on e-commerce platform commodity data
The outer index with weight is as additional index;
Specifically includes the following steps:
(1) after active user's selection target commodity, system is in e-commerce user basic data and e-commerce platform commodity
Raw performance and the corresponding data of additional index are chosen in data respectively, by end article and the corresponding Raw performance of similar commodity
Enter rule base with the distribution of additional index, additional index is assigned in conjunction with the commodity consumption weight of existing e-commerce platform
Power, according to algorithm of birdsing of the same feather flock together, is formed the weight distribution system of user's commercial product recommending by computer, weight distribution system is carried at this time
Commodity be for active user initial recommendation scheme;
(2) in order to preferably estimate current commercial product recommending state, correction value is selected, using reversed prospecting tools to being formed for the first time
The corresponding commodity of weight distribution system assign power result and carry out positive amendment and adjusting, real on the basis of having consumption satisfaction
Existing weight soft readjustment, the weight distribution system after being optimized, the commodity that the weight distribution system after the optimization is carried
For the optimization suggested design for active user, the Recommendations optimized in suggested design respectively correspond different appraisal rights
Weight coefficient, the Recommendations are presented according to its corresponding assessment weight coefficient descending arrangement.
Further, the e-commerce user basic data includes customer consumption habit data, consuming capacity data, choosing
Select preference data;
The e-commerce platform commodity data includes commodity basic attribute data, merchandise promotion information data, commodity evaluation letter
Cease data, the affiliated merchant information data of commodity.
Further, the consumption habit data include the comparative quantity of user's closing time, similar commodity;The consumption energy
Force data includes commodity concluded price, commodity conclusion of the business quantity;Selection preference data include user voluntarily select characteristic information, at
Hand over the characteristic information of commodity.
Further, the characteristic information of the bargain include feature attribute of commodity (such as red, bowknot element),
Whether the difference (classifying to positive value and negative value) of commodity concluded price and the commodity corresponding goods average price is commodity sales promotion.
Further, the consumption habit data, consuming capacity data, selection preference data are with customer transaction data
Update is updated.
Further, the merchandise promotion information data are real time information when active user uses;The commodity evaluation
Information data is obtained by commodity integrated evaluating information system, is updated with the update of commodity integrated evaluating information system.
Further, the correction value is needed using Expert opinion synthesis evaluation Delphi method screening, screening gained correction value
The cooperation index for meeting expert is higher than 0.65, can guarantee the validity of correction value.
Further, the commodity assign power result after amendment and adjusting, after being optimized after being confirmed by assessment panel
Weight distribution system;The assessment panel is made of the professional person for representing trade company's interests, and number is no less than 5 people, wherein at least 3
The artificial personnel that there is abundant practical experience, be responsible for end article correlation category.
Further, the rule base that computer is entered using the process that correction value amendment commodity assign power result, establishes rule
Data base, the adaptive ability of training weight distribution system are conducive to improve amendment, adjust efficiency.
The present invention has the advantage that the present invention in e-commerce user basic data and e-commerce compared with prior art
On the basis of platform commodity data, end article and the corresponding Raw performance of similar commodity and the distribution of additional index are entered into rule
Library carries out tax power to additional index in conjunction with the commodity consumption weight of existing e-commerce platform, according to algorithm of birdsing of the same feather flock together, by computer
The weight distribution system for forming user's commercial product recommending carries out forward direction to result using reversed prospecting tools then in conjunction with correction value and repairs
It just and adjusts, obtains the optimization suggested design for active user, carry out intelligent amendment in time according to system situation, be different from
The narrow-mindedness of traditional electronic commerce Recommendations recommends a variety of commodity for meeting user demand, realizes preferable user's perception, together
When combine sales promotion information, so that institute's recommended products is more in line with the consumption feature and consumption choice of consumer.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention.
Specific embodiment
The following further describes the present invention with reference to the drawings.
As shown in fig. 1, a kind of based on the wisdom electronic commerce recommending method more perceived, on e-commerce user basis
On the basis of data and e-commerce platform commodity data, i.e. the comprehensive history fetched data of user, according to existing rule base
Original tax power, in conjunction with the commodity consumption weight in existing e-commerce platform, according to customer consumption habit data, consuming capacity number
According to, selection preference data, commodity basic attribute data, merchandise promotion information data (including quick-fried money commodity, bargain goods), commodity
Whether evaluation information data (such as the evaluation systems such as public comment statistical data), the affiliated merchant information data of commodity (are high-quality
Trade company) in additional index in addition to Raw performance recommend as extraordinary, the power of tax gives active user to select similar commodity, according to birdsing of the same feather flock together
Algorithm, is formed the weight distribution system of user's commercial product recommending by computer, and the commodity that weight distribution system is carried at this time are needle
To the initial recommendation scheme of active user;In order to preferably estimate current commercial product recommending state, correction value is selected, is visited using reversed
Survey tool assigns power result to the corresponding commodity of the weight distribution system formed for the first time and carries out positive amendment and adjusting, is having consumption
On the basis of satisfaction, weight soft readjustment, the weight distribution system after being optimized, the weight distribution after the optimization are realized
The commodity that system is carried are the optimization suggested design for active user, the Recommendations difference in the optimization suggested design
Corresponding different assessment weight coefficient, the Recommendations are presented according to its corresponding assessment weight coefficient descending arrangement, and will
The rule base of this adjustment input computer, establishes regular data base, and the adaptive ability of training system is gradually established intelligent
Processing module carries out efficient, accurate commercial product recommending processing.
Embodiment 1
The specific implementation of the technology of the present invention the following steps are included:
(1) the original tax power of e-commerce commodity is established;
(2) it sampled, analyzed according to user's history conclusion of the business track, according to customer consumption habit data, consuming capacity data, quotient
Product basic attribute data establishes rule base using computer, and the Raw performance distribution with weight is entered rule base;
(3) end article according to selected by active user and the corresponding commodity data of similar commodity, including real-time merchandise promotion information
Data (including quick-fried money commodity, bargain goods), information on commodity comment data (such as the evaluation systems such as public comment), affiliated trade company
Information data (whether being high-quality trade company) enters rule base as additional index distribution, wants to the weight proposition processing of additional index
It asks, the collaboration processing of computer is carried out, for example, the weight of " real-time merchandise promotion information ", is adjusted to 2 by original weight 1;
(4) estimate intelligentized consumption assessment weight coefficient out as the selection of system user by computer to refer to, for example, mentioning
After rising " affiliated merchant information " weight, 2 are adjusted to by original weight 1,1 weight having more can be by computer according to rule base
It to be formed with estimating, it is understood that there may be following embodiments:
;
(5) correction value is selected using Expert opinion synthesis evaluation Delphi method, in this process, by statistician according to expert
Opinion, in e-commerce user basic data (including consumption habit data, consuming capacity data, selection preference data), in real time
It is merchandise promotion information (including quick-fried money commodity, bargain goods), information on commodity comment (such as the evaluation systems such as public comment), affiliated
Under the treatment conditions of the lot of essential factors such as merchant information (whether being high-quality trade company) constraint, to the generation processing side of computer rule base
Case is selected, can also be by computer according to intelligent program (selection, user preference, the randomness etc. handled according to previous weight
Screening conditions) recommended, obtain correction value;
(6) selection result and scheme obtained by step (5), using reversed prospecting tools to be related in weight distribution system need
Weight in the additional index to be adjusted carries out positive amendment, on the basis of user has satisfaction, realizes that weight is adjusted, obtains
Weight distribution system after to optimization;
The user has satisfaction and refers to that fellow users are satisfied with journey to Recommendations corresponding to weight distribution system at that time
The feedback of degree;
(7) the weight distribution system after optimization that step (6) obtains is applied in existing recommender system, and covered existing
Weight distribution system forms current implementable solution, and by the weight rule library of this process record to computer, is formed primary
Operation note is integrated into operation log, realizes recalling for weight;
(8) according to existing weight distribution system, sampled data is estimated, using detection pond, the weight operation of detection system
Effect, and the satisfaction for recommending the lot of essential factors constraint conditions such as effect, consumption satisfaction is analyzed, if system processing knot
Fruit falls flat, then return step (4), again operation serial word, until reaching promising result, obtains.
Embodiment 2
On the basis of embodiment 1, assessment panel is set up, during step (6) carry out, is obtained after being confirmed by assessment panel excellent
Weight distribution system after change;The assessment panel is made of the professional person for representing trade company's interests, and number is no less than 5 people,
In at least 3 people be with abundant practical experience, be responsible for end article correlation category personnel.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of based on the wisdom electronic commerce recommending method more perceived, including rule base, the rule base is based on initial number
It is weighed according to original tax is equipped with, i.e., primary data is the Raw performance with original weight, and the primary data includes consumption foundation number
According to item property data, which is characterized in that will there is power in addition to primary data based on e-commerce user basic data
Heavy index and the index conduct with weight in addition to commodity basic attribute data based on e-commerce platform commodity data
Additional index;
Specifically includes the following steps:
(1) after active user's selection target commodity, system is in e-commerce user basic data and e-commerce platform commodity
Raw performance and the corresponding data of additional index are chosen in data respectively, by end article and the corresponding Raw performance of similar commodity
Enter rule base with the distribution of additional index, additional index is assigned in conjunction with the commodity consumption weight of existing e-commerce platform
Power, according to algorithm of birdsing of the same feather flock together, is formed the weight distribution system of user's commercial product recommending by computer, weight distribution system is carried at this time
Commodity be for active user initial recommendation scheme;
(2) correction value is selected, power result is assigned to the corresponding commodity of the weight distribution system formed for the first time using reversed prospecting tools
Positive amendment and adjusting are carried out, on the basis of having consumption satisfaction, realizes weight soft readjustment, the weight after being optimized
Distribution system, the commodity that the weight distribution system after the optimization is carried are the optimization suggested design for active user, institute
The Recommendations stated in optimization suggested design respectively correspond different assessment weight coefficients, and the Recommendations are corresponding according to its
The arrangement of assessment weight coefficient descending is presented.
2. a kind of based on the wisdom electronic commerce recommending method more perceived as described in claim 1, which is characterized in that the electricity
Sub- business users basic data includes customer consumption habit data, consuming capacity data, selection preference data;
The e-commerce platform commodity data includes commodity basic attribute data, merchandise promotion information data, commodity evaluation letter
Cease data, the affiliated merchant information data of commodity.
3. a kind of based on the wisdom electronic commerce recommending method more perceived as claimed in claim 2, which is characterized in that described to disappear
Expense habit data include the comparative quantity of user's closing time, similar commodity;The consuming capacity data include commodity concluded price,
Commodity conclusion of the business quantity;Selection preference data include user voluntarily select characteristic information, bargain characteristic information.
4. as claimed in claim 3 it is a kind of based on the wisdom electronic commerce recommending method more perceived, which is characterized in that it is described at
Hand over commodity characteristic information include feature attribute of commodity, commodity concluded price and the commodity corresponding goods average price difference,
It whether is commodity sales promotion.
5. a kind of based on the wisdom electronic commerce recommending method more perceived as claimed in claim 2, which is characterized in that described to disappear
Expense habit data, select preference data as the update of customer transaction data is updated at consuming capacity data.
6. a kind of based on the wisdom electronic commerce recommending method more perceived as claimed in claim 2, which is characterized in that the quotient
Product sales promotion information data are real time information when active user uses;The information on commodity comment data are believed by commodity overall merit
Breath system obtains, and is updated with the update of commodity integrated evaluating information system.
7. a kind of based on the wisdom electronic commerce recommending method more perceived as described in claim 1, which is characterized in that described to repair
Positive value is screened using Delphi method, and the cooperation index that screening gained correction value needs to meet expert is higher than 0.65.
8. a kind of based on the wisdom electronic commerce recommending method more perceived as described in claim 1, which is characterized in that the quotient
Product assign weight distribution system of the power result after amendment and adjusting, after being optimized after being confirmed by assessment panel.
9. a kind of based on the wisdom electronic commerce recommending method more perceived as claimed in claim 8, which is characterized in that institute's commentary
Estimate group to be made of the professional person for representing businessman's interests, number is no less than 5 people, and wherein at least 3 people are to pass through with abundant practice
Test, be responsible for the personnel of end article correlation category.
10. a kind of based on the wisdom electronic commerce recommending method more perceived as described in claim 1, which is characterized in that utilize
The process that correction value amendment commodity assign power result enters the rule base of computer, establishes regular data base, training weight distribution body
The adaptive ability of system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910612530.4A CN110348964A (en) | 2019-07-09 | 2019-07-09 | It is a kind of based on the wisdom electronic commerce recommending method more perceived |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910612530.4A CN110348964A (en) | 2019-07-09 | 2019-07-09 | It is a kind of based on the wisdom electronic commerce recommending method more perceived |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110348964A true CN110348964A (en) | 2019-10-18 |
Family
ID=68178491
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910612530.4A Pending CN110348964A (en) | 2019-07-09 | 2019-07-09 | It is a kind of based on the wisdom electronic commerce recommending method more perceived |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110348964A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111339432A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Recommendation method and device of electronic object and electronic equipment |
CN113157708A (en) * | 2020-01-07 | 2021-07-23 | 青岛九石智能科技股份有限公司 | Method and device for updating wine information and intelligent wine cabinet |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663627A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Personalized recommendation method |
CN103325052A (en) * | 2013-07-03 | 2013-09-25 | 姚明东 | Commodity recommendation method based on multidimensional user consumption propensity modeling |
CN103886486A (en) * | 2014-03-21 | 2014-06-25 | 吉首大学 | Electronic commerce recommending method based on support vector machine (SVM) |
CN104462827A (en) * | 2014-12-12 | 2015-03-25 | 湖北工业大学 | Method for computing flexible coupling of index weights during comprehensive assessment |
CN104700216A (en) * | 2015-03-12 | 2015-06-10 | 葛晓滨 | Flexible treatment process for weight retroegulation of survey systems |
CN106708821A (en) * | 2015-07-21 | 2017-05-24 | 广州市本真网络科技有限公司 | User personalized shopping behavior-based commodity recommendation method |
CN107133836A (en) * | 2017-03-22 | 2017-09-05 | 无锡中科富农物联科技有限公司 | A kind of adaptive weighting combined recommendation algorithm |
CN108009897A (en) * | 2017-12-25 | 2018-05-08 | 北京中关村科金技术有限公司 | A kind of real-time recommendation method of commodity, system and readable storage medium storing program for executing |
CN109785064A (en) * | 2019-01-14 | 2019-05-21 | 南京信息工程大学 | A kind of mobile e-business recommended method and system based on Multi-source Information Fusion |
CN109816413A (en) * | 2017-11-22 | 2019-05-28 | 苏州云之道网络科技有限公司 | A kind of electric business recommender system and recommended method based on social networks |
-
2019
- 2019-07-09 CN CN201910612530.4A patent/CN110348964A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663627A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Personalized recommendation method |
CN103325052A (en) * | 2013-07-03 | 2013-09-25 | 姚明东 | Commodity recommendation method based on multidimensional user consumption propensity modeling |
CN103886486A (en) * | 2014-03-21 | 2014-06-25 | 吉首大学 | Electronic commerce recommending method based on support vector machine (SVM) |
CN104462827A (en) * | 2014-12-12 | 2015-03-25 | 湖北工业大学 | Method for computing flexible coupling of index weights during comprehensive assessment |
CN104700216A (en) * | 2015-03-12 | 2015-06-10 | 葛晓滨 | Flexible treatment process for weight retroegulation of survey systems |
CN106708821A (en) * | 2015-07-21 | 2017-05-24 | 广州市本真网络科技有限公司 | User personalized shopping behavior-based commodity recommendation method |
CN107133836A (en) * | 2017-03-22 | 2017-09-05 | 无锡中科富农物联科技有限公司 | A kind of adaptive weighting combined recommendation algorithm |
CN109816413A (en) * | 2017-11-22 | 2019-05-28 | 苏州云之道网络科技有限公司 | A kind of electric business recommender system and recommended method based on social networks |
CN108009897A (en) * | 2017-12-25 | 2018-05-08 | 北京中关村科金技术有限公司 | A kind of real-time recommendation method of commodity, system and readable storage medium storing program for executing |
CN109785064A (en) * | 2019-01-14 | 2019-05-21 | 南京信息工程大学 | A kind of mobile e-business recommended method and system based on Multi-source Information Fusion |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113157708A (en) * | 2020-01-07 | 2021-07-23 | 青岛九石智能科技股份有限公司 | Method and device for updating wine information and intelligent wine cabinet |
CN113157708B (en) * | 2020-01-07 | 2022-09-20 | 青岛博芬智能科技股份有限公司 | Method and device for updating wine information and intelligent wine cabinet |
CN111339432A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Recommendation method and device of electronic object and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Plakandaras et al. | Forecasting daily and monthly exchange rates with machine learning techniques | |
Gan et al. | Consumer choice prediction: Artificial neural networks versus logistic models | |
CN102902691B (en) | Recommend method and system | |
Bandyopadhyay et al. | Product recommendation for e-commerce business by applying principal component analysis (PCA) and K-means clustering: benefit for the society | |
US20160350834A1 (en) | Systems and methods for constructing and applying synaptic networks | |
Bauer et al. | Recommender systems based on quantitative implicit customer feedback | |
Yadav et al. | Intelligent evaluation of suppliers using extent fuzzy TOPSIS method: A case study of an Indian manufacturing SME | |
CN109377260A (en) | User behavior analysis system towards apparel industry | |
CN102067105A (en) | Personalizing sponsored search advertising layout using user behavior history | |
CN114219169A (en) | Script banner supply chain sales and inventory prediction algorithm model and application system | |
CN109767032A (en) | A kind of business finance operation digital management optimization system based on data analysis | |
Wang et al. | M-GAN-XGBOOST model for sales prediction and precision marketing strategy making of each product in online stores | |
CN110348964A (en) | It is a kind of based on the wisdom electronic commerce recommending method more perceived | |
Liu et al. | A big data-Kano and SNA-CRP based QFD model: Application to product design under Chinese new E-commerce model | |
Agarwal et al. | Machine Learning and Natural Language Processing in Supply Chain Management: A Comprehensive Review and Future Research Directions. | |
Xuefeng et al. | Predicting the final prices of online auction items | |
CN111861679A (en) | Commodity recommendation method based on artificial intelligence | |
Ayoubi | Customer segmentation based on CLV model and neural network | |
Chaurasiya et al. | Improving performance of product recommendations using user reviews | |
Dixit et al. | A propound hybrid approach for personalized online product recommendations | |
US10013699B1 (en) | Reverse associate website discovery | |
Kuo et al. | Integration of particle swarm optimization and immune genetic algorithm-based dynamic clustering for customer clustering | |
Sobhanallahi et al. | An aggregated supplier selection method based on QFD and TOPSIS (case study: A financial institution) | |
Osman et al. | Application of fuzzy logic for adaptive food recommendation | |
Kulkarni et al. | Fusion of selection parameters for customer behavior prediction based on web usage mining |
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: 20191018 |
|
RJ01 | Rejection of invention patent application after publication |