CN110175892A - The two-way recommendation method and system of heating power ball based on consumer behaviour - Google Patents
The two-way recommendation method and system of heating power ball based on consumer behaviour Download PDFInfo
- Publication number
- CN110175892A CN110175892A CN201910447266.3A CN201910447266A CN110175892A CN 110175892 A CN110175892 A CN 110175892A CN 201910447266 A CN201910447266 A CN 201910447266A CN 110175892 A CN110175892 A CN 110175892A
- Authority
- CN
- China
- Prior art keywords
- product
- heating power
- consumer
- way
- power ball
- 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.)
- Granted
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Abstract
The present invention relates to the two-way recommendation method and system of heating power ball based on consumer behaviour, this method comprises: 1) assigning an initial heating power H to it to the new product that platform is added0；2) according to the two-way interactive behavior of product and user, active user interaction heating power H is generatedn；3) product heating power value is calculated, 4) recommended from high to low to consumer according to the sequence of various product heating power ball, this programme utilizes multidimensional information, the consumer behaviour of product, is the temperature that passage calculates product with the time, to carry out corresponding product pushed information.
Description
Technical field
The present invention relates to data analysis fields, and in particular to a kind of two-way recommended method of heating power ball based on consumer behaviour
And system.
Background technique
Currently, the Products Show system based on big data emerges one after another, most direct embody is that, according to the net of user
Page search history generates the consumption inventory of user, to carry out information push by way of playing wicket.The above push behavior
It is to be pushed according to the browsing of user record or consumer record, and have ignored product itself, belongs to a kind of unidirectional push, it can not
Know whether consumer is interested in the commodity, while being easy to be consumed using this kind of push mode of wicket bullet dialog box
The dislike of person, so that push is ineffective
For example, the Chinese patent of Publication No. publication number CN105450586A, discloses a kind of information-pushing method, packet
It includes: obtaining the browse request of user, wherein with the user identifier of user in browse request；It obtains corresponding to browse request
Data are browsed, and obtain the user information of user according to user identifier；The commodity letter in browsing data is extracted according to user information
Breath；Pushed information is generated according to merchandise news；And browsing data and pushed information are sent to client.
Hot benefit ball: being a kind of based on product multidimensional information, the data generated by algorithmic formula, there is presently no a kind of
The method for carrying out two-way recommendation according to user demand and product information.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of, and the heating power ball based on consumer behaviour is two-way
Recommended method and system are the temperature that passage calculates product with the time using the multidimensional information of product, consumer behaviour, thus
Carry out corresponding product pushed information.
The purpose of the present invention is achieved through the following technical solutions:
The two-way recommended method of heating power ball based on consumer behaviour, this method comprises:
1) to the new product that platform is added, an initial heating power H is assigned to it0；
2) according to the two-way interactive behavior of product and user, active user interaction heating power H is generatedn；
3) the then real-time heating power value calculation formula of the product are as follows:
Wherein TnFor current time, T0For issuing time, N is constant, indicates such product hot topic life cycle, n is nature
Number；
4) recommended from high to low to consumer according to the sequence of various product heating power ball.
It is entered in the present solution, initially setting up a platform for product, the product entered assigns at the beginning of one it
Beginning heating power, i.e., initial temperature show user couple based on the initial temperature, while using user's interaction temperature as calculating
The favorable rating of the product is changed over time finally by the issuing time of product, obtain the temperature variation an of product,
Whether there is advantage to calculate the product in similar product, to be pushed accordingly.
Further, the initial heating power H0By product type p, weight wn, hot word frequency of use si, hot word weight composition
ωi, then have:
Wherein A, B respectively indicate Product labelling and network hot word.
I.e. in a kind of product, similarity calculation is carried out according to the network hot word of the label of the product and such product, and
In conjunction with similarity and weight, the popularity (temperature) of the product is obtained, while obtaining product with product type and its weight again
Initial temperature, product type referred herein refer to that every profession and trade sales volume is determined in its weight, such as electronic product, mobile phone
Weight be higher than plate, the weight of plate is higher than sound equipment, i.e. initial weight wnIt is to be determined by the type of product, substantially etc.
In the market share of such product.
Further, the weight wnBy initial value w0Start to gradually change, variation tendency and upward price trend curve are kept
Unanimously, that is to say, that be in the present invention consistent the temperature of product with price curve, the fluctuation of price under normal circumstances is
The welcome degree of the product is shown, likewise, by taking mobile phone products as an example, its price highest when Mobile phone lists, temperature
Maximum, price is all to successively decrease at any time under normal circumstances, this reflection is product by containing to the variation to decline.
Further, user's interaction heating power HnIt is determined by the interbehavior between consumer and product, expression formula
Are as follows:
Wherein MiFor interbehavior number, wiFor the weight of the interbehavior, DnFor same day consumer
Participation amount.
Further, the interbehavior between the consumer and product includes number of clicks, concern quantity, comment number
Amount, beats reward number at analysis quantity, searching times.
It is directed to different products, the interbehavior between consumer and product is not identical, is produced according to specific here
The product characteristic of product, and its interbehavior that may occur carry out modeling analysis, belong to qualitative analysis.
Further, the time Tn-T0It is that unit is calculated with " day ", more than discontented 24 hours 0 hour in terms of 1 day
It calculates.
Further, the calculating timing node of the HS is between 23:00-24:00.
The two-way recommender system of heating power ball based on consumer behaviour, the system include:
Product resource pond enters product for businessman, and establishes Product labelling；
Input module, interbehavior type and weight for customized input consumer and product；
Crawler module, for crawling the friendship between network hot word relevant to the Product labelling and consumer and product
Mutual behavior；
Pushing module, for the product information orientation in resource pool to be pushed to target consumer.
Further, the system also includes an authentication modules, for identifying that merchant product is to enter production by having permission
Product resource pool.
Further, the push mode of the pushing module includes Web page push, SMS push, APP registration use
Family push.
The beneficial effects of the present invention are: in the present invention using the multidimensional information of product, in conjunction with hot word matching degree instantly and
The behavioral data of consumer, and the heating power value (temperature) for the product that timely updates daily, to obtain the product in its generic
Ranking realize the two-way identification of product information and user demand to preferentially be pushed so that message push it is more smart
It is quasi- effective.
Detailed description of the invention
Fig. 1 is whole composition schematic diagram of the invention.
Specific embodiment
Technical solution of the present invention is described in further detail combined with specific embodiments below, but protection scope of the present invention is not
It is confined to as described below.
As shown in Figure 1, the two-way recommended method of heating power ball based on consumer behaviour, this method comprises:
1) to the new product that platform is added, an initial heating power H is assigned to it0.The first step i.e. of the invention is taken for platform
It builds, which includes:
Product resource pond enters product for businessman, and establishes Product labelling；
Input module, interbehavior type and weight for customized input consumer and product；
Crawler module, for crawling the friendship between network hot word relevant to the Product labelling and consumer and product
Mutual behavior；
Pushing module, for the product information orientation in resource pool to be pushed to target consumer.
The system also includes an authentication modules, for identifying that merchant product is to enter product resource pond by having permission
(platform).
2) according to the two-way interactive behavior of product and user, active user interaction heating power H is generatedn；
3) the then real-time heating power value calculation formula of the product are as follows:
Wherein TnFor current time, T0For issuing time, N is constant, such product hot topic life cycle is indicated, with mobile phone
For N value be generally 180 days, for game class product, the value of N is usually no more than 90 days.N is naturally, indicating the
How many days, for example, at the tenth day product real-time heating power value
4) recommended from high to low to consumer according to the sequence of various product heating power ball.
That is, referred herein recommend to consumer from high to low according to sequence, it is according to this platform resource
Similar product in pond is ranked up, and does not enter the commodity of this platform not as sequence target.
The initial heating power H0By product type p, weight wn, hot word frequency of use si, hot word weight form ωi, then have.
Product type p value is constant 1, corresponding property right weight wnAccording to the market share of product class or market accounting
It determines, which obtains the market share of various product using web crawlers in real time, so that weight wnIt is one to become in real time
Change amount, so that calculated result is more accurate.Hot word frequency of use siRefer to the frequency that the hot word occurs in comment on commodity,
Such as the frequency that the cell phone standby time is long, the similar phrases such as goodlooking occur in comment, hot word weight form ωi, hot word
The value of weight is according to the accounting of hot word each in all comments, the above hot word frequency of use si, hot word weight form ωiIt is
Real-time update.
Wherein A, B respectively indicate Product labelling and network hot word,
WhereinWhat is indicated is the similarity between Product labelling and network hot word.
The weight wnBy initial value w0Starting to gradually change, variation tendency is consistent with upward price trend curve, wherein
w0Weight when platform is entered for product, the time variation amount that n here is indicated.
User's interaction heating power HnIt is determined by the interbehavior between consumer and product, expression formula are as follows:
Wherein MiFor interbehavior number, wiFor the weight of the interbehavior, DnFor same day consumer
Participation amount, the interbehavior between consumer and product include number of clicks, concern quantity, number of reviews, analysis quantity, search
Number beats reward number, in addition to this can also be like time, shares number, hop count, i.e., according to different product type,
Its interbehavior that may occur should all count.
The time Tn-T0It is that unit is calculated with " day ", was calculated more than discontented 24 hours 0 hour with 1 day.
The calculating timing node of the HS is between 23:00-24:00.
The push mode of the pushing module includes Web page push, SMS push, APP registration user's push.
The above is only a preferred embodiment of the present invention, it should be understood that the present invention is not limited to described herein
Form should not be regarded as an exclusion of other examples, and can be used for other combinations, modifications, and environments, and can be at this
In the text contemplated scope, modifications can be made through the above teachings or related fields of technology or knowledge.And those skilled in the art institute into
Capable modifications and changes do not depart from the spirit and scope of the present invention, then all should be in the protection scope of appended claims of the present invention
It is interior.
Claims (10)
1. the two-way recommended method of heating power ball based on consumer behaviour, which is characterized in that this method comprises:
1) to the new product that platform is added, an initial heating power H is assigned to it0；
2) according to the two-way interactive behavior of product and user, active user interaction heating power H is generatedn；
3) the then real-time heating power value calculation formula of the product are as follows:
Wherein TnFor current time, T0For issuing time, N is constant, indicates such product hot topic life cycle, n is natural number；
4) recommended from high to low to consumer according to the sequence of various product heating power ball.
2. the heating power ball two-way recommended method according to claim 1 based on consumer behaviour, which is characterized in that described first
Beginning heating power H0By product type p, weight wn, hot word frequency of use si, hot word weight form ωi, then have:
Wherein A, B respectively indicate Product labelling and network hot word.
3. the heating power ball two-way recommended method according to claim 2 based on consumer behaviour, which is characterized in that the power
Weight wnBy initial value w0Start to gradually change, variation tendency is consistent with upward price trend curve.
4. the heating power ball two-way recommended method according to claim 3 based on consumer behaviour, which is characterized in that the use
Family interacts heating power HnIt is determined by the interbehavior between consumer and product, expression formula are as follows:
Wherein MiFor interbehavior number, wiFor the weight of the interbehavior, DnFor same day consumer participation
Amount.
5. the heating power ball two-way recommended method according to claim 4 based on consumer behaviour, which is characterized in that described to disappear
Interbehavior between Fei Zheyu product includes number of clicks, concern quantity, number of reviews, analysis quantity, searching times, beats reward
Number.
6. the heating power ball two-way recommended method according to claim 1 based on consumer behaviour, which is characterized in that when described
Between Tn-T0It is that unit is calculated with " day ", was calculated more than discontented 24 hours 0 hour with 1 day.
7. the heating power ball two-way recommended method according to claim 6 based on consumer behaviour, which is characterized in that the HS
Calculating timing node between 23:00-24:00.
8. special for realizing the described in any item two-way recommender systems of heating power ball based on consumer behaviour of claim 1-7
Sign is that the system includes:
Product resource pond enters product for businessman, and establishes Product labelling；
Input module, interbehavior type and weight for customized input consumer and product；
Crawler module, for crawling the interaction row between network hot word relevant to the Product labelling and consumer and product
For；
Pushing module, for the product information orientation in resource pool to be pushed to target consumer.
9. the heating power ball two-way recommender system according to claim 8 based on consumer behaviour, which is characterized in that the system
System further includes an authentication module, for identifying that merchant product is to enter product resource pond by having permission.
10. the heating power ball two-way recommender system according to claim 1 based on consumer behaviour, which is characterized in that described
The push mode of pushing module includes Web page push, SMS push, APP registration user's push.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910447266.3A CN110175892B (en) | 2019-05-27 | 2019-05-27 | Bidirectional thermal ball recommendation method and system based on consumer behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910447266.3A CN110175892B (en) | 2019-05-27 | 2019-05-27 | Bidirectional thermal ball recommendation method and system based on consumer behaviors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110175892A true CN110175892A (en) | 2019-08-27 |
| CN110175892B CN110175892B (en) | 2021-06-29 |
Family
ID=67696310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910447266.3A Active CN110175892B (en) | 2019-05-27 | 2019-05-27 | Bidirectional thermal ball recommendation method and system based on consumer behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110175892B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052651A (en) * | 2021-03-17 | 2021-06-29 | 广东便捷神科技股份有限公司 | Intelligent retail management method and system based on big data |
| 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 |
| CN116562960A (en) * | 2023-04-19 | 2023-08-08 | 上海聚灵兽科技有限公司 | Commodity recommendation method, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096152A (en) * | 2014-05-20 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Commodity popularity-based operation execution method and device |
| CN107657506A (en) * | 2017-09-06 | 2018-02-02 | 北京五八到家信息技术有限公司 | The intelligent recommendation method and commending system of a kind of service commodity |
| CN108632311A (en) * | 2017-03-20 | 2018-10-09 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN109376305A (en) * | 2018-12-04 | 2019-02-22 | 山东浪潮通软信息科技有限公司 | A kind of news temperature sort method and system based on user behavior analysis |
| CN109636497A (en) * | 2018-10-26 | 2019-04-16 | 平安科技（深圳）有限公司 | A kind of Products Show method and apparatus |
| WO2019085372A1 (en) * | 2017-10-31 | 2019-05-09 | 深圳春沐源控股有限公司 | Commodity recommendation method and commodity recommendation system for online shopping mall |
-
2019
- 2019-05-27 CN CN201910447266.3A patent/CN110175892B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096152A (en) * | 2014-05-20 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Commodity popularity-based operation execution method and device |
| CN108632311A (en) * | 2017-03-20 | 2018-10-09 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN107657506A (en) * | 2017-09-06 | 2018-02-02 | 北京五八到家信息技术有限公司 | The intelligent recommendation method and commending system of a kind of service commodity |
| WO2019085372A1 (en) * | 2017-10-31 | 2019-05-09 | 深圳春沐源控股有限公司 | Commodity recommendation method and commodity recommendation system for online shopping mall |
| CN109636497A (en) * | 2018-10-26 | 2019-04-16 | 平安科技（深圳）有限公司 | A kind of Products Show method and apparatus |
| CN109376305A (en) * | 2018-12-04 | 2019-02-22 | 山东浪潮通软信息科技有限公司 | A kind of news temperature sort method and system based on user behavior analysis |
Non-Patent Citations (3)
| Title |
|---|
| 何林海: "基于群体动态兴趣度的个性化推荐方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 成军: "面向电子商务的协同过滤推荐算法与推荐系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 金石: "基于运营商管道大数据的智能电商推荐系统", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (5)
| 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 |
| CN113052651A (en) * | 2021-03-17 | 2021-06-29 | 广东便捷神科技股份有限公司 | Intelligent retail management method and system based on big data |
| CN113052651B (en) * | 2021-03-17 | 2024-04-23 | 广东便捷神科技股份有限公司 | Intelligent retail management method and system based on big data |
| CN116562960A (en) * | 2023-04-19 | 2023-08-08 | 上海聚灵兽科技有限公司 | Commodity recommendation method, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110175892B (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8533043B2 (en) | Clickable terms for contextual advertising | |
| CN104281961B (en) | For the advertisement in on-line system and the quality score system of content | |
| Zhou et al. | Preference-based mining of top-K influential nodes in social networks | |
| JP6067713B2 (en) | Understand the effectiveness of communications propagated through social networking systems | |
| US20120066073A1 (en) | User interest analysis systems and methods | |
| TWI603273B (en) | Method and device for placing information search | |
| CN103473354A (en) | Insurance recommendation system framework and insurance recommendation method based on e-commerce platform | |
| CN105956146A (en) | Article information recommending method and device | |
| CN105718184A (en) | Data processing method and apparatus | |
| CN106355442A (en) | Online precise advertising method and system based on big data driving | |
| CN110175892A (en) | The two-way recommendation method and system of heating power ball based on consumer behaviour | |
| CN103971265A (en) | User Terminal And Method And System For Providing Advertisement | |
| CN105225129A (en) | Mobile O2O recommend method and system thereof | |
| US20120054042A1 (en) | Id-value assessment device, id-value assessment system, and id-value assessment method | |
| CN102479366A (en) | Commodity recommending method and system | |
| CN102509233A (en) | User online action information-based recommendation method | |
| CN106062743A (en) | Systems and methods for keyword suggestion | |
| CN106447463A (en) | Commodity recommendation method based on Markov decision-making process model | |
| US20090018932A1 (en) | System and method for idea sharing | |
| Aharon et al. | Off-set: one-pass factorization of feature sets for online recommendation in persistent cold start settings | |
| CN109615432A (en) | Consumer behaviour portrait tool based on big data | |
| CN109325179A (en) | A kind of method and device that content is promoted | |
| US20130035996A1 (en) | Social advertising technology (so-ad-tec) system and method for advertising for and in documents, and other systems and methods for accessing, structuring, and evaluating documents | |
| CN110020200A (en) | A kind of personalized recommendation method and system based on history material | |
| Sun et al. | Leveraging friend and group information to improve social recommender system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |