CN107766584A - A kind of product in knowledge based storehouse subscribes to recommendation method - Google Patents
A kind of product in knowledge based storehouse subscribes to recommendation method Download PDFInfo
- Publication number
- CN107766584A CN107766584A CN201711223004.6A CN201711223004A CN107766584A CN 107766584 A CN107766584 A CN 107766584A CN 201711223004 A CN201711223004 A CN 201711223004A CN 107766584 A CN107766584 A CN 107766584A
- Authority
- CN
- China
- Prior art keywords
- product
- user
- information
- knowledge base
- knowledge
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of product in knowledge based storehouse to subscribe to recommendation method, comprises the following steps:S10:Structure includes some knowledge bases of product;S20:Obtain user and habits information is browsed to product, habits information is browsed according to described, from the knowledge base of S10 structures, search corresponding knowledge base;S30:Knowledge base list to knowledge base information of user's push comprising the knowledge base found out;S40:Receive feedback information of the user to the knowledge base list;S50:Recommend the product list that knowledge place corresponding to the feedback information includes to user, user is received in the product list, if the subscription of dryed product;S60:Receive user and request is unsubscribed to subscription product, no longer push the product unsubscribed.By this recommendation method, realize and browse historical data according to user, selectively recommend the effect of Related product to it based on user, avoid the problem of user voluntarily investigates content product one by one, practical, user's summary is good.
Description
Technical field
The present invention relates to data analysis field, the product in especially a kind of knowledge based storehouse subscribes to recommendation method.
Background technology
With the development that the development of internet, especially big data calculate, the various applications based on internet and big data
Also correspondingly it is born successively.Wherein, greatly it is related to the application of content, for example includes news or technical data product.
The product to be become increasingly abundant for content and species, even the product under belonging to same subject, its content issued
Also it is far from each other, and for a user, it is impossible to browse one by one, therefore, how to ensure that user can be browsed under particular topic,
Correlation is high, abundant in content product, is one and meets information development demand, and urgent problem to be solved.
The content of the invention
The goal of the invention of the present invention is:For above-mentioned problem, there is provided one kind is based on user to its historical viewings
Content product data, automatic push correlation is high, meets it browse custom other content products scheme, for user
Selected, so as to solve the covering problem that user obtains to content product, and ensure the content of its product browsed for symbol
Close the problem of it browses demand.
The technical solution adopted by the present invention is as follows:
The product in knowledge based storehouse subscribes to recommendation method, comprises the following steps:
S10:Structure includes some knowledge bases of product;
S20:Obtain user and habits information is browsed to product, habits information is browsed according to described, from the knowledge base of S10 structures
In, search corresponding knowledge base;
S30:Knowledge base list to knowledge base information of user's push comprising the knowledge base found out;
S40:Receive feedback information of the user to the knowledge base list;
S50:The product list included to knowledge place corresponding to user's recommendation feedback information, receives user to the product
In list, if the subscription of dryed product.
Habits information is browsed by obtain user, is filtered out in the knowledge base of structure and meets that user browses knowing for custom
Know storehouse, and then chosen for user;Further, after user chooses knowledge base, the content product in it is recommended into user, for it
Product is selected, after the selection of user is received, the product of selection is pushed to user, to reach the knot of product subscription
Fruit.
Such scheme browses custom by user and pushes knowledge base/product to it, and product need to be investigated one by one by avoiding user
The problem of, on the one hand, the time that user selects product is saved, on the other hand, also ensure that the knowledge coverage rate of recommended products,
It ensure that good product subscribes to effect.
Preferably, the identification information pair product that above-mentioned S10 carries according to product is classified, built with this comprising product
Some knowledge bases.
Further, above-mentioned S20 is specially:
S201:Historical viewings data of the user to product are obtained, model is browsed according to historical viewings data structure;
S202:Model is browsed according to described, analyzes and browses habits information, the habits information that browses includes:To knowledge base category
The preference information of property;Habits information is browsed according to described, from the knowledge base of S10 structures, finds out corresponding knowledge base.
The above-mentioned model that browses is the model that is browsed to being matched with user to each product of virtual user, with this from objective
In data, thus it is speculated that go out the user browses habits information.
Preferably, above-mentioned historical viewings data are:User is to all historical viewings data of product, or user is to product
Scheduled time slot historical viewings data.
The program ensure that according to user it is long-term/short term need recommends the effect of corresponding product.
Preferably, historical viewings data include:User browses duration, used to the click volume of product, user to product
Family browses one or more in the markup information of the attribute information or user of product to browsing product.
Preferably, above-mentioned knowledge base information is the brief introduction to knowledge base or the attribute information of knowledge base, the attribute letter
Breath includes:The structure historical information of the classification information of knowledge base, the author information of knowledge base or knowledge base.
Further, user is to the flag information for browsing product:User is to browsing the Information on Collection of product.
Preferably, above-mentioned S201 browses model by regression analysis structure.
Preferably, after S50, in addition to:
S60:Receive user and request is unsubscribed to subscription product, no longer push the product unsubscribed.
Further, unsubscribing request is:The request that unsubscribes of knowledge base is corresponded to the feedback information of the S40, or
Request is unsubscribed to product ordered in the S50.Realized with this to all over products in whole knowledge base or indivedual
Product directly takes pass.
In summary, by adopting the above-described technical solution, the beneficial effects of the invention are as follows:
With the method for the invention it is achieved that browsing historical data according to user, recommend the effect of Related product to it, to avoid
User voluntarily investigates the problem of content product one by one, saves that product searches the time and experience, Consumer's Experience are good.Further
, in recommendation process, also realize autonomous selection of the user to product and cancel at any time, so as to reach the Products Show of hommization
Effect.
Brief description of the drawings
Examples of the present invention will be described by way of reference to the accompanying drawings, wherein:
Fig. 1 is that the product in knowledge based storehouse subscribes to recommendation method.
Embodiment
All features disclosed in this specification, or disclosed all methods or during the step of, except mutually exclusive
Feature and/or step beyond, can combine in any way.
This specification(Including any accessory claim, summary)Disclosed in any feature, unless specifically stated otherwise,
Replaced by other equivalent or with similar purpose alternative features.I.e., unless specifically stated otherwise, each feature is a series of
An example in equivalent or similar characteristics.
As shown in figure 1, present embodiment discloses a kind of product in knowledge based storehouse to subscribe to recommendation method, including following step
Suddenly:
S10:Structure includes some knowledge bases of product;
S20:Obtain user and habits information is browsed to product, habits information is browsed according to described, from the knowledge base of S10 structures
In, search corresponding knowledge base;
S30:Knowledge base list to knowledge base information of user's push comprising the knowledge base found out;
S40:Receive feedback information of the user to the knowledge base list;
S50:The product list included to knowledge place corresponding to user's recommendation feedback information, receives user to the product
In list, if the subscription of dryed product.
S60:Receive user and request is unsubscribed to subscription product, no longer push the product unsubscribed.
Further, the present embodiment is specifically disclosed in above-described embodiment, the specific implementation step of each step:
The identification information pair product that S10 carries according to product is classified, and some knowledge bases comprising product are built with this.Such as name
For " sports news ", the product of " NBA is live ", its product identification is " physical culture ", then two products are built such as " physical culture " class
Knowledge base, such as " finance and economics ", " science and technology ", " design " some knowledge bases are constructed by that analogy.
S20 is specially:
S201:Historical viewings data of the user to product are obtained, model is browsed according to historical viewings data structure;
S202:Model is browsed according to described, analyzes and browses habits information, the habits information that browses includes:To knowledge base category
The preference information of property;Habits information is browsed according to described, from the knowledge base of S10 structures, finds out corresponding knowledge base.
Above-mentioned historical viewings data are:User is to all historical viewings data of product, or pre- timing of the user to product
The historical viewings data of section.Such as the data on flows that self installation product has used first, or data were browsed to product in nearly one week.
Above-mentioned historical viewings data include:User to the click volume of product, user to product browse duration, user browses
It is one or more in the markup information of the attribute information of product or user to browsing product.
Above-mentioned knowledge base information includes for the brief introduction to knowledge base or the attribute information of knowledge base, the attribute information:Know
Know classification information, the author information of knowledge base or the structure historical information of knowledge base in storehouse.
Wherein, user is to the flag information for browsing product:User is to browsing the Information on Collection of product.Such as whether by product
Put into collection folder.
Preferably, S201 browses model by regression analysis structure.Also model can be built by other prior arts.
In S60, unsubscribing request is:The request that unsubscribes of knowledge base is corresponded to the feedback information of the S40, or
Request is unsubscribed to product ordered in the S50.
The invention is not limited in foregoing embodiment.The present invention, which expands to, any in this manual to be disclosed
New feature or any new combination, and disclose any new method or process the step of or any new combination.
Claims (10)
1. the product in knowledge based storehouse subscribes to recommendation method, it is characterized in that, comprise the following steps:
S10:Structure includes some knowledge bases of product;
S20:Obtain user and habits information is browsed to product, habits information is browsed according to described, from the knowledge base of S10 structures
In, search corresponding knowledge base;
S30:Knowledge base list to knowledge base information of user's push comprising the knowledge base found out;
S40:Receive feedback information of the user to the knowledge base list;
S50:The product list included to knowledge place corresponding to user's recommendation feedback information, receives user to the product
In list, if the subscription of dryed product.
2. the method as described in claim 1, it is characterized in that, the identification information pair product that the S10 carries according to product is carried out
Classification, some knowledge bases comprising product are built with this.
3. method as claimed in claim 2, it is characterized in that, the S20 is specially:
S201:Historical viewings data of the user to product are obtained, model is browsed according to historical viewings data structure;
S202:Model is browsed according to described, analyzes and browses habits information, the habits information that browses includes:To knowledge base category
The preference information of property;Habits information is browsed according to described, from the knowledge base of S10 structures, finds out corresponding knowledge base.
4. method as claimed in claim 3, it is characterized in that, the historical viewings data are:All history of the user to product
Data, or user are browsed to the historical viewings data of the scheduled time slot of product.
5. method as claimed in claim 3, it is characterized in that, the historical viewings data include:User to the click volume of product,
User to product browse duration, user browses one in the markup information of the attribute information or user of product to browsing product
It is or multinomial.
6. the method as described in claim 4 or 5, it is characterized in that, the knowledge base information is the brief introduction to knowledge base or knowledge
The attribute information in storehouse, the attribute information include:The structure of the classification information of knowledge base, the author information of knowledge base or knowledge base
Historical information.
7. method as claimed in claim 6, it is characterized in that, the user is to the flag information for browsing product:User is to clear
Look at the Information on Collection of product.
8. claim 3-5,7 it is any as described in method, it is characterized in that, the S201 is built described clear by regression analysis
Look at model.
9. method as claimed in claim 8, it is characterized in that, after the S50, in addition to:
S60:Receive user and request is unsubscribed to subscription product, no longer push the product unsubscribed.
10. method as claimed in claim 9, it is characterized in that, in the S60, unsubscribing request is:To the anti-of the S40
Feedforward information corresponds to the request that unsubscribes of knowledge base, or unsubscribes request to product ordered in the S50.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711223004.6A CN107766584A (en) | 2017-11-29 | 2017-11-29 | A kind of product in knowledge based storehouse subscribes to recommendation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711223004.6A CN107766584A (en) | 2017-11-29 | 2017-11-29 | A kind of product in knowledge based storehouse subscribes to recommendation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107766584A true CN107766584A (en) | 2018-03-06 |
Family
ID=61275682
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711223004.6A Withdrawn CN107766584A (en) | 2017-11-29 | 2017-11-29 | A kind of product in knowledge based storehouse subscribes to recommendation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107766584A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107533747A (en) * | 2012-12-14 | 2018-01-02 | 脸谱公司 | For notice to be sent to the technology of subscriber |
-
2017
- 2017-11-29 CN CN201711223004.6A patent/CN107766584A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107533747A (en) * | 2012-12-14 | 2018-01-02 | 脸谱公司 | For notice to be sent to the technology of subscriber |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104053032B (en) | Virtual channel management method and network multimedia reproduction system | |
EP1374573B1 (en) | Tv program profiling technique and interface | |
CN103491441B (en) | Recommendation method and system of live television programs | |
CN104462292B (en) | Socially collaborative filtering | |
JP5285196B1 (en) | Recommended content providing apparatus, recommended content providing program, and recommended content providing method | |
CN102843586B (en) | Video recommendation method and terminal | |
US7996399B2 (en) | Presenting media guidance search results based on relevancy | |
CN103200279B (en) | Recommendation method and cloud server | |
CN110430471A (en) | It is a kind of based on the television recommendations method and system instantaneously calculated | |
US20080104058A1 (en) | Presenting media guidance search results based on relevancy | |
CN101840410A (en) | Learning device and method, signal conditioning package and method and program | |
JP2004513572A (en) | Method and apparatus for automatically generating query search terms for program recommendations | |
WO2011112982A2 (en) | Systems and methods for organizing and displaying electronic media content | |
CN102917269A (en) | Television program recommendation system and method | |
CN102724570B (en) | IPTV program display method and system | |
WO2017067525A1 (en) | Product package recommendation method, device and system | |
CN103327049A (en) | Rich content pushing method and system based on browser address bar | |
CN103927673A (en) | Method and device for recommending service information | |
CN104469429A (en) | Method and device for pushing program | |
EP2870578A1 (en) | Device and method for automatic filter adjustment | |
CN102186115B (en) | Set top box based program display system and method | |
CN107766584A (en) | A kind of product in knowledge based storehouse subscribes to recommendation method | |
JP6103813B2 (en) | Information processing apparatus, information processing method, and program | |
JP2015022551A (en) | Terminal device and program | |
US20160086220A1 (en) | Terminal device and device program |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180306 |