CN108090810A - A kind of Products Show system based on big data - Google Patents
A kind of Products Show system based on big data Download PDFInfo
- Publication number
- CN108090810A CN108090810A CN201711376018.1A CN201711376018A CN108090810A CN 108090810 A CN108090810 A CN 108090810A CN 201711376018 A CN201711376018 A CN 201711376018A CN 108090810 A CN108090810 A CN 108090810A
- Authority
- CN
- China
- Prior art keywords
- user
- recommendation information
- data
- unit
- information generation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Products Show systems based on big data, including server and client side, server includes Source Data Acquisition module, data processing module, recommendation information generation module and database, and Source Data Acquisition module, data processing module, recommendation information generation module are connected with database；The input terminal of Source Data Acquisition module and output terminal connection, output terminal and the data processing module of client connect, and the output terminal of data processing module is connected with the input terminal of recommendation information generation module, and the output terminal of recommendation information generation module is connected with client；The data that data processing module inputs Source Data Acquisition module using preference acquiring technology are handled, and obtain the searching preferences of user；User's searching preferences that recommendation information generation module is exported according to data processing module generate recommendation information, and recommendation information is back to client and is shown.The system is by realizing the recommendation of high quality information according to user preference data.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of Products Show system based on big data.
Background technology
In the epoch of this information explosion, when consumer faces numerous selections, unknown field, the information overloaded, often
It is at a loss as to what to do；However at the same time, the producer of content（Such as businessman）Also suitable user is earnestly being sought, it is most convenient to find
Channel, and the best tool for solving this two classes contradiction is exactly commending system.
Commending system genesis has the technology largely communicated both in first floor system, but is mutually applying in search system
In family demand and the scene of generation application, commending system is further from user：On the one hand, when the demand of user is specific and clear and definite
When, it scans for；When user demand is indefinite or beyond expression of words, demand recommendation is carried out.On the other hand, when user needs to look for certain
Under a field during generally acknowledged, popular content, scan for；When user needs to look for personalized content, recommended.Very much
Under scene, it is difficult to be converted into brief specific query word that the individual demand of user, which is, such as " this noon is wanted to look near a
, restaurant meeting my taste, consumption is inexpensive " as demand, it is very common but be difficult to be expressed clearly with query word.It pushes away
This blank can be filled up just by recommending system, clear personalized demand deeply to be excavated according to user's history behavior is excavated,
Realize ample scope for abilities.
At present, commending system generally comprises commending contents algorithm and collaborative filtering.Wherein commending contents algorithm is main
By analyzing content information caused by user, therefrom excavate user hobby and user between contact, finally
Complete the purpose to user's commercial product recommending.But either there are recommendation effects for commending contents algorithm or collaborative filtering
The problem of poor.
The content of the invention
It is an object of the invention to provide a kind of Products Show system based on big data, to improve the matter of recommendation information
Amount.
In order to achieve the above object, the technical solution adopted by the present invention is：Including server and client side, wherein, server
Including Source Data Acquisition module, data processing module, recommendation information generation module and database, Source Data Acquisition module, number
It is connected according to processing module, recommendation information generation module with database；
The input terminal of Source Data Acquisition module and output terminal connection, output terminal and the data processing module of client connect, data
The output terminal of processing module is connected with the input terminal of recommendation information generation module, the output terminal of recommendation information generation module and client
End connection；
Wherein, the data that data processing module inputs Source Data Acquisition module using preference acquiring technology are handled, and are obtained
The searching preferences of user；
User's searching preferences that recommendation information generation module is exported according to data processing module generate recommendation information, and will recommend
Information is back to client and is shown.
Wherein, client is pushed away including User Defined resource display unit, user interest list display unit, commodity of selling fast
Recommend information display unit and the automatic recommendation information display unit of commodity；
User Defined resource display unit is used to show the resource information that user independently adds；
User interest list display unit is used to show the interest list of user；
Commercial product recommending information of selling fast display unit is used to show commercial product recommending information of selling fast；
The automatic recommendation information display unit of commodity is used to show commercial product recommending information.
Wherein, the Source Data Acquisition module include user's score data collecting unit, user feedback data collecting unit,
User network data acquisition unit and user's Demographic's parameter acquisition unit；
User's score data collecting unit is used to gather score data of the user to commodity；
User feedback data collecting unit is used to gather the feedback data that user uses commodity；
User network data acquisition unit is used to gather the use data generated on user network；
User Demographic parameter acquisition unit uses user's statistical number of person of purchase commodity for gathering.
Wherein, the data processing module include user preference analytic unit, social network structural analysis unit and
Context user preference analysis unit；
User preference analytic unit is used for the data analysis user preference gathered according to Source Data Acquisition module, obtains user preference
Data；
Social network structural analysis unit is used for the data analysis social network structure gathered according to Source Data Acquisition module,
Obtain social network structured data；
Context user preference analysis unit is used for the data analysis context user preference gathered according to Source Data Acquisition module
Data.
Wherein, the recommendation information generation module includes the recommendation information generation unit based on matrix decomposition, based on implicit
Recommendation information generation unit, socialization recommendation information generation unit and the group recommendation information generation unit of feedback；
Recommendation information generation unit based on matrix decomposition is used for by the way of matrix decomposition to user preference data
Reason generates recommendation information；
Recommendation information generation unit based on implicit feedback is used for the feedback data according to user, generates recommendation information；
Socialization recommendation information generation unit is used to, according to social network structured data, generate recommendation information；
Group recommendation information generation unit is used for according to the recommendation information generation unit in matrix decomposition, the recommendation based on implicit feedback
Information generating unit, the recommendation information of socialization recommendation information generation unit generation, generate combined recommendation information.
Compared with prior art, there are following technique effects by the present invention：The present invention is mainly by analyzing caused by user
The hobby of user is therefrom excavated in contact between content information and user, can be by tracking, learning user's
The characteristic informations such as interest, preference and personality in real time, accurately find the demand of user.According to these information, system is judged
User most thinks the agricultural product of purchase, and recommends for it, is finally completed the purpose to user's commercial product recommending.The information that the present invention recommends
For the personalized access request of consumer, recommend the information of high quality.For data service, for consumer
Diversified access request, data service should be able to take flexible mode describe service and dynamic generate meet demand it is new
Data service.
Description of the drawings
Below in conjunction with the accompanying drawings, the specific embodiment of the present invention is described in detail：
Fig. 1 is a kind of structure diagram of the Products Show system based on big data in the present invention；
Fig. 2 is the structure diagram of server in the present invention；
Fig. 3 is the structure diagram of the proposed algorithm used in the present invention.
Specific embodiment
In order to illustrate further the feature of the present invention, please refer to the following detailed descriptions related to the present invention and attached drawing.Institute
Attached drawing is only for reference and purposes of discussion, is not used for being any limitation as protection scope of the present invention.
As shown in Figure 1, present embodiment discloses a kind of Products Show system based on big data, including server 10 and visitor
Family end 20, wherein, server 10 include Source Data Acquisition module 11, data processing module 12, recommendation information generation module 13 with
And database 14, Source Data Acquisition module 11, data processing module 12, recommendation information generation module 13 connect with database 14
It connects；
The input terminal of Source Data Acquisition module 11 is connected with the output terminal of client 20, output terminal and data processing module 12 connect
It connects, the output terminal of data processing module 12 is connected with the input terminal of recommendation information generation module 13, recommendation information generation module 13
Output terminal be connected with client 20；
Wherein, the data that data processing module 12 inputs Source Data Acquisition module 11 using preference acquiring technology are handled,
Obtain the searching preferences of user；
Recommendation information generation module 13 generates recommendation information according to user's searching preferences that data processing module 12 exports, and will
Recommendation information is back to client 20 and is shown.
Wherein, client 20 includes User Defined resource display unit, user interest list display unit, commodity of selling fast
Recommendation information display unit and the automatic recommendation information display unit of commodity；
User Defined resource display unit is used to show the resource information that user independently adds, such as some nets of user's collection
It stands, commodity etc.；
User interest list display unit is used to show the interest list of user, for example, have nothing to do, clothes, makeups etc.；
Commercial product recommending information of selling fast display unit mainly shows the business currently to sell fast for showing commercial product recommending information of selling fast
Product, such as commodity such as iPhone of new listing etc., commodity such as discount commodity etc. for selling at a special price recently；
The automatic recommendation information display unit of commodity is used to show commercial product recommending information.
In the present embodiment, client is scanned for by client 20, and the Source Data Acquisition module 11 in server 10 gathers
The input information of client in client 20, data processing module 12 handle the information using preference acquiring technology, obtain
The interest preference of user, and information recommendation is carried out for the interest preference of user, the quality of information recommendation is greatly improved, is carried
Rise CSAT.
Further, as shown in Fig. 2, Source Data Acquisition module 11 includes user's score data collecting unit, user feedback
Data acquisition unit, user network data acquisition unit and user's Demographic's parameter acquisition unit；
User's score data collecting unit is used to gather score data of the user to commodity, such as specific evaluation score or evaluation
Star etc.；
User feedback data collecting unit is used to gather the feedback data that user uses commodity, for example user uses the commodity
Afterwards, the data fed back from price, performance, appearance etc.；
User network data acquisition unit is used to gather the use data generated on user network, such as the webpage of user online browsing
Data, browsing or commodity data of collection etc.；
User Demographic parameter acquisition unit uses user's statistical number of person of purchase commodity for gathering.
Further, data processing module 12 include user preference analytic unit, social network structural analysis unit with
And context user preference analysis unit；
User preference analytic unit is used for the data analysis user preference gathered according to Source Data Acquisition module 11, and it is inclined to obtain user
Good data；
Social network structural analysis unit is used for the data analysis social network knot gathered according to Source Data Acquisition module 11
Structure obtains social network structured data；
It is inclined that context user preference analysis unit is used for the data analysis context user gathered according to Source Data Acquisition module 11
Good data, here context user preference data generally refer to the relevance between user, according to the association between user
The preference of property indirect gain user.
Further, recommendation information generation module 13 includes the recommendation information generation unit based on matrix decomposition, based on hidden
Recommendation information generation unit, socialization recommendation information generation unit and the group recommendation information generation unit of formula feedback；
Recommendation information generation unit based on matrix decomposition is used for by the way of matrix decomposition to user preference data
Reason generates recommendation information；
Recommendation information generation unit based on implicit feedback is used for the feedback data according to user, generates recommendation information；
Socialization recommendation information generation unit is used to, according to social network structured data, generate recommendation information；
Group recommendation information generation unit is used for according to the recommendation information generation unit in matrix decomposition, the recommendation based on implicit feedback
Information generating unit, the recommendation information of socialization recommendation information generation unit generation, generate combined recommendation information.
Further, server 10 further includes evaluation module 15, is mainly used for commenting the quality of current recommendation information
Valency, including real-time evaluation unit, evaluation of the accuracy unit, Diversity unit and novelty evaluation unit.
It should be noted that as shown in figure 3, the recommendation information generation module 13 in the present embodiment is different from the prior art
Use commending contents algorithm or Collaborative Recommendation algorithm, it is but comprehensive using commending contents algorithm and Collaborative Recommendation algorithm, together
When the defects of avoiding commending contents algorithm and Collaborative Recommendation algorithm, can by analyzing content information caused by user, from
In excavate user hobby and user between contact, be finally completed the purpose to user's commercial product recommending
A kind of Products Show system based on big data disclosed by the invention has the advantages that：
（1）The characteristic informations such as interest, preference and personality that can be by tracking, learning user in real time, accurately find user
Demand, and it is changed and is adjusted.According to these information, system judges that user most thinks the agricultural product of purchase, realizes high
The information recommendation of quality.
（2）For data service, for the diversified access request of consumer, the system can take flexible side
Formula generates the new data service of meet demand to describe service and dynamic.
（3）The system is served by combining the relevant application of data characteristics, realizes information inquiry, analysis and visual
Change.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modifications, equivalent replacements and improvements are made should all be included in the protection scope of the present invention.
Claims (5)
1. a kind of Products Show system based on big data, it is characterised in that：Including server（10）And client（20）,
In, server（10）Including Source Data Acquisition module（11）, data processing module（12）, recommendation information generation module（13）And
Database（14）, Source Data Acquisition module（11）, data processing module（12）, recommendation information generation module（13）And database
（14）Connection；
Source Data Acquisition module（11）Input terminal and client（20）Output terminal connection, output terminal and data processing module
（12）Connection, data processing module（12）Output terminal and recommendation information generation module（13）Input terminal connection, recommendation information
Generation module（13）Output terminal and client（20）Connection；
Wherein, data processing module（12）Using preference acquiring technology to Source Data Acquisition module（11）At the data of input
Reason, obtains the searching preferences of user；
Recommendation information generation module（13）According to data processing module（12）User's searching preferences of output generate recommendation information,
And recommendation information is back to client（20）It is shown.
2. the Products Show system based on big data as described in claim 1, it is characterised in that：The client（20）Bag
Include User Defined resource display unit, user interest list display unit, sell fast commercial product recommending information display unit and business
The automatic recommendation information display unit of product；
User Defined resource display unit is used to show the resource information that user independently adds；
User interest list display unit is used to show the interest list of user；
Commercial product recommending information of selling fast display unit is used to show commercial product recommending information of selling fast；
The automatic recommendation information display unit of commodity is used to show commercial product recommending information.
3. the Products Show system based on big data as described in claim 1, it is characterised in that：The Source Data Acquisition module
（11）Including user's score data collecting unit, user feedback data collecting unit, user network data acquisition unit and use
Family Demographic's parameter acquisition unit；
User's score data collecting unit is used to gather score data of the user to commodity；
User feedback data collecting unit is used to gather the feedback data that user uses commodity；
User network data acquisition unit is used to gather the use data generated on user network；
User Demographic parameter acquisition unit uses user's statistical number of person of purchase commodity for gathering.
4. the Products Show system based on big data as claimed in claim 3, it is characterised in that：The data processing module
（12）Including user preference analytic unit, social network structural analysis unit and context user preference analysis unit；
User preference analytic unit is used for according to Source Data Acquisition module（11）The data analysis user preference of acquisition, obtains user
Preference data；
Social network structural analysis unit is used for according to Source Data Acquisition module（11）The data analysis social network of acquisition
Structure obtains social network structured data；
Context user preference analysis unit is used for according to Source Data Acquisition module（11）The data analysis context user of acquisition
Preference data.
5. the Products Show system based on big data as described in claim 1, it is characterised in that：The recommendation information generates mould
Block（13）Including the recommendation information generation unit based on matrix decomposition, the recommendation information generation unit based on implicit feedback, society
Change recommendation information generation unit and group recommendation information generation unit；
Recommendation information generation unit based on matrix decomposition is used for by the way of matrix decomposition to user preference data
Reason generates recommendation information；
Recommendation information generation unit based on implicit feedback is used for the feedback data according to user, generates recommendation information；
Socialization recommendation information generation unit is used to, according to social network structured data, generate recommendation information；
Group recommendation information generation unit is used for according to the recommendation information generation unit in matrix decomposition, the recommendation based on implicit feedback
Information generating unit, the recommendation information of socialization recommendation information generation unit generation, generate combined recommendation information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711376018.1A CN108090810A (en) | 2017-12-19 | 2017-12-19 | A kind of Products Show system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711376018.1A CN108090810A (en) | 2017-12-19 | 2017-12-19 | A kind of Products Show system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108090810A true CN108090810A (en) | 2018-05-29 |
Family
ID=62176995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711376018.1A Pending CN108090810A (en) | 2017-12-19 | 2017-12-19 | A kind of Products Show system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108090810A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648188A (en) * | 2018-06-27 | 2020-01-03 | 江苏特易信息科技有限公司 | Cross-border trade BPO service recommendation system based on user preference |
| WO2020010570A1 (en) * | 2018-07-12 | 2020-01-16 | 深圳齐心集团股份有限公司 | Big data automatic analysis system based on consumer habits |
| CN112269934A (en) * | 2020-11-09 | 2021-01-26 | 武汉蝌蚪信息技术有限公司 | Reading correlation retrieval and recommendation system based on decentralized big data retrieval market |
| CN116975454A (en) * | 2023-09-22 | 2023-10-31 | 北京荆跃科技有限公司 | Large model generation method based on recommendation system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271558A (en) * | 2008-05-16 | 2008-09-24 | 华东师范大学 | Multi-policy commercial product recommending system based on context information |
| US20090248682A1 (en) * | 2008-04-01 | 2009-10-01 | Certona Corporation | System and method for personalized search |
| CN103593417A (en) * | 2013-10-25 | 2014-02-19 | 安徽教育网络出版有限公司 | Collaborative filtering recommendation method based on association rule prediction |
| CN105488216A (en) * | 2015-12-17 | 2016-04-13 | 上海中彦信息科技有限公司 | Recommendation system and method based on implicit feedback collaborative filtering algorithm |
-
2017
- 2017-12-19 CN CN201711376018.1A patent/CN108090810A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090248682A1 (en) * | 2008-04-01 | 2009-10-01 | Certona Corporation | System and method for personalized search |
| CN101271558A (en) * | 2008-05-16 | 2008-09-24 | 华东师范大学 | Multi-policy commercial product recommending system based on context information |
| CN103593417A (en) * | 2013-10-25 | 2014-02-19 | 安徽教育网络出版有限公司 | Collaborative filtering recommendation method based on association rule prediction |
| CN105488216A (en) * | 2015-12-17 | 2016-04-13 | 上海中彦信息科技有限公司 | Recommendation system and method based on implicit feedback collaborative filtering algorithm |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648188A (en) * | 2018-06-27 | 2020-01-03 | 江苏特易信息科技有限公司 | Cross-border trade BPO service recommendation system based on user preference |
| WO2020010570A1 (en) * | 2018-07-12 | 2020-01-16 | 深圳齐心集团股份有限公司 | Big data automatic analysis system based on consumer habits |
| CN112269934A (en) * | 2020-11-09 | 2021-01-26 | 武汉蝌蚪信息技术有限公司 | Reading correlation retrieval and recommendation system based on decentralized big data retrieval market |
| CN116975454A (en) * | 2023-09-22 | 2023-10-31 | 北京荆跃科技有限公司 | Large model generation method based on recommendation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108090810A (en) | A kind of Products Show system based on big data | |
| KR100961782B1 (en) | Apparatus and method for presenting personalized goods information based on artificial intelligence, and recording medium thereof | |
| CN108876526A (en) | Method of Commodity Recommendation, device and computer readable storage medium | |
| CN106326318B (en) | Searching method and device | |
| CN108537596B (en) | Method, device and system for recommending vehicle type in search box and memory | |
| CN103886487A (en) | Individualized recommendation method and system based on distributed B2B platform | |
| US11216852B2 (en) | Systems and methods for automatically generating remarketing lists | |
| US20090077081A1 (en) | Attribute-Based Item Similarity Using Collaborative Filtering Techniques | |
| KR102075038B1 (en) | Goods Recommendation Method Conisdering User's Chracter Using User's Big Data in Network, and Managing Server Used Therein | |
| JP2018156429A (en) | Information processing device, information processing method, and program | |
| CN110619559B (en) | Method for accurately recommending commodities in electronic commerce based on big data information | |
| CN111949887A (en) | Item recommendation method and device and computer-readable storage medium | |
| KR101740148B1 (en) | Method of recommending items at online shopping malls, based on clients' offline activity data | |
| EP3195559A1 (en) | A method and system for delivering context-relevant content to portable devices | |
| CN108182268B (en) | Collaborative filtering recommendation method and system based on social network | |
| Liu et al. | The Value of Multi-Dimensional Rating System: An Information Transfer View | |
| US20090077093A1 (en) | Feature Discretization and Cardinality Reduction Using Collaborative Filtering Techniques | |
| Hong et al. | A comparative study of video recommender systems in big data era | |
| CN105243557A (en) | Self-service type vegetable and fruit selection method and system | |
| KR102599842B1 (en) | Method and apparatus for analyzing advertising performance in a communication system | |
| Ringel et al. | Understanding competition using big consumer search data | |
| US20170017973A1 (en) | Method and survey server for generating predictive survey participation patterns using online profile data | |
| US20170017991A1 (en) | Method and system for advertising based on predictive survey participation patterns | |
| Wang et al. | Systematic approach for digital marketing strategy through data mining technology | |
| Ajaykrishna et al. | Online sales prediction in E-commerce market using machine learning |
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: 20180529 |
|
| RJ01 | Rejection of invention patent application after publication |