CN111859157A - Recommendation method for expressing relation between information - Google Patents
Recommendation method for expressing relation between information Download PDFInfo
- Publication number
- CN111859157A CN111859157A CN202010775598.7A CN202010775598A CN111859157A CN 111859157 A CN111859157 A CN 111859157A CN 202010775598 A CN202010775598 A CN 202010775598A CN 111859157 A CN111859157 A CN 111859157A
- Authority
- CN
- China
- Prior art keywords
- information
- recommendation
- piece
- mobile terminal
- module
- 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 30
- 238000002372 labelling Methods 0.000 claims 1
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
Images
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
- 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
- G06F16/906—Clustering; Classification
-
- 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
- G06F16/9538—Presentation of query results
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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a recommendation method for expressing the relation between information, which relates to the technical field of internet information recommendation, and specifically comprises a display system positioned on a mobile terminal and an information recommendation system positioned on a server, wherein the information recommendation system positioned on the server runs two or more algorithms to establish the relation between information, and the display system positioned on the mobile terminal calls two recommendation lists from the server through the mobile internet and displays the two recommendation lists on the longitudinal and transverse dimensions of a screen of the mobile terminal. The invention realizes the two-dimensional relation of expressing information in one page at the same time, so that the user can selectively browse information from different dimensions, and the problem that the user falls into an algorithm cocoon house is solved.
Description
Technical Field
The invention discloses a recommendation method for expressing the relation between information, relates to the technical field of mobile internet information recommendation, and particularly relates to a method for sorting the same group of information, establishing the multi-dimensional relation between the information, and expressing the information relation by displaying in the longitudinal direction and the transverse direction on a screen of a mobile terminal.
Background
At present, personalized recommendation is the mainstream mobile internet information recommendation technology, a user portrait is constructed by acquiring user data, information matched with the user portrait in an information database is sorted into a recommendation list, and then the recommendation list is displayed to a user in a waterfall flow mode in the longitudinal direction of a mobile terminal screen. The personalized recommendation technology cannot express the relation between information, so that the fragmentation of the information is caused, and a user is trapped in an algorithm cocoon room.
Disclosure of Invention
The present invention is directed to a recommendation method for expressing a relationship between information, so as to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a recommendation method for expressing the relation between information comprises an information recommendation system on a server and a display system on a mobile terminal, wherein the display system of the mobile terminal calls two recommendation lists establishing the relation between information from the server through a mobile internet network, and displays the two recommendation lists on the vertical and horizontal dimensions of a screen of the mobile terminal.
As a further scheme of the invention: the information recommendation system comprises an algorithm module, a feature marking module and a clustering module.
As a further scheme of the invention: the display system comprises a longitudinal display module and a transverse display module.
As a further scheme of the invention: the algorithm module runs an algorithm 1 on the information of the known information database to obtain an information recommendation list.
As a further scheme of the invention: the characteristic marking module is used for marking the characteristics of each piece of information, and each piece of information can have a plurality of characteristic marks to obtain an information characteristic mark set.
As a further scheme of the invention: the clustering module is used for clustering the information of the known information database according to the feature label set of each piece of information to obtain a clustering information set corresponding to each piece of information.
As a further scheme of the invention: and the algorithm module respectively operates an algorithm 2 on each clustering information set to obtain a clustering information recommendation list of each piece of information and establish multi-dimensional relation of the information.
As a further scheme of the invention: and the longitudinal display module of the display system is used for calling the information recommendation list from the server through the mobile internet and displaying the information recommendation list in the longitudinal direction of the screen of the mobile terminal.
As a further scheme of the invention: and the transverse display module of the display system is used for calling the clustering information recommendation list of each piece of information from the server through the mobile internet and displaying the transverse information of the piece of information on the screen of the mobile terminal.
A recommendation method for expressing the relation between information specifically comprises the following steps:
the information recommendation system is located on a server, an algorithm module runs an algorithm 1 on a known information database to obtain a 'longitudinal recommendation list', a characteristic marking module carries out characteristic marking on information of the known information database, then clustering is carried out on the information of the known information database through a clustering module according to a characteristic mark set of each piece of information in sequence to obtain a clustering information set of each piece of information, and an algorithm module runs an algorithm 2 on the clustering information set of each piece of information to obtain a 'transverse recommendation list'; the display system is located at the mobile terminal, the longitudinal display module calls a longitudinal recommendation list from the server through the mobile internet and displays the longitudinal recommendation list on the screen of the mobile terminal in a waterfall flow mode, and the transverse display module calls a transverse recommendation list of each piece of information from the server through the mobile internet and displays the transverse recommendation list of the piece of information on the screen of the mobile terminal.
Compared with the prior art, the invention has the beneficial effects that:
1. the multi-dimensional relation among the information is established, the information recommendation method is favorably promoted from the conventional single information recommendation to the information recommendation according to the form of clustering, and the recommendation efficiency of massive information is improved.
2. The two-dimensional relationship of the information is displayed in the longitudinal direction and the transverse direction of the plane at the same time, so that the amplitude and the depth of the information acquired by a user can be expanded, and the algorithm cocoon room recommended individually can be avoided.
Drawings
Fig. 1 is a block diagram of a recommendation method for expressing a relationship between information.
Fig. 2 is a flowchart of an embodiment 2 of a recommendation method for expressing a relationship between information.
Fig. 3 is a news view of embodiment 3 in a recommendation method for expressing a connection between information.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "longitudinal", "lateral", and the like indicate orientations or positional relationships based on those shown in the drawings, which are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "Algorithm 1" and "Algorithm 2" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance, nor should they be construed as corresponding to an algorithm or designated algorithm. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1, in an embodiment of the present invention, a recommendation method for expressing an inter-information connection includes a display system located in a mobile terminal and an information recommendation system located in a server, where the display system calls two recommendation lists of the inter-information connection established by the information recommendation system on the server through a mobile internet, and the display system respectively displays the two recommendation lists in two dimensions, namely, vertical and horizontal dimensions, on a screen of the mobile terminal.
The information recommendation system comprises an algorithm module, a feature marking module and a clustering module;
wherein the display system comprises a longitudinal display module and a transverse display module;
it should be noted that, the algorithm module runs algorithm 1, and processes the information in the known information database according to preset rules, respectively, to obtain an information recommendation list (longitudinal recommendation list);
it should be noted that, the feature marking module is configured to mark features of the information, where each piece of information may have a plurality of feature marks, to obtain an information feature mark set;
it should be noted that, the clustering module is configured to cluster the information in the known information database according to the feature label set of each piece of information, and obtain a clustering information set corresponding to each piece of information;
it should be noted that, the algorithm module runs the algorithm 2, and respectively processes the cluster information set corresponding to each piece of information according to preset rules to obtain a cluster information recommendation list (transverse recommendation list) corresponding to each piece of information;
it should be noted that, the vertical display module of the display system is used for calling an information recommendation list (vertical recommendation list) from the server through the mobile internet, and displaying the information recommendation list in the vertical direction of the mobile terminal screen in the form of waterfall flow;
it should be noted that, the horizontal presentation module of the presentation system is configured to retrieve, from the server through the mobile internet, a cluster information recommendation list (horizontal recommendation list) corresponding to each piece of information, and present the horizontal direction of each piece of information corresponding to the mobile screen.
A recommendation method for expressing the relation between information specifically comprises the following steps:
the information recommendation system is located on a server, an algorithm module runs an algorithm 1 on a known information database to obtain a 'longitudinal recommendation list', a characteristic marking module carries out characteristic marking on information of the known information database, then clustering is carried out on the information of the known information database through a clustering module according to a characteristic mark set of each piece of information in sequence to obtain a clustering information set of each piece of information, and an algorithm module runs an algorithm 2 on the clustering information set of each piece of information to obtain a 'transverse recommendation list'; the display system is located at the mobile terminal, the longitudinal display module calls a longitudinal recommendation list from the server through the mobile internet and displays the longitudinal recommendation list on the screen of the mobile terminal in a waterfall flow mode, and the transverse display module calls a transverse recommendation list of each piece of information from the server through the mobile internet and displays the transverse recommendation list of the piece of information on the screen of the mobile terminal.
Example 2
Please refer to fig. 2, which is a method for recommending a relationship between information, comprising:
database of information known to be located on a server
The method comprises the following steps: running an algorithm 1, processing the information of the known information database according to a preset rule, and obtaining a longitudinal information recommendation list;
step two: making feature marks on information of a known information database, wherein each piece of information can have a plurality of feature marks to obtain a feature mark set of each piece of information;
step three: clustering all information of a known information database according to a feature label set of a certain piece of information to obtain a clustering information set of the information;
step four: running an algorithm 2, processing the clustering information set of each piece of information according to a preset rule, and obtaining a transverse information recommendation list of each piece of information;
step five: repeating the second step to the fourth step to obtain a transverse information recommendation list of each piece of information;
step six: the mobile terminal calls a longitudinal information recommendation list from the server and displays the longitudinal information recommendation list on a screen of the mobile terminal;
step seven: the mobile terminal calls a transverse information recommendation list of each piece of information from the server and displays the transverse information of the information on a screen of the mobile terminal.
Example 3
Please refer to fig. 3, which is an embodiment applied to a news application;
known news information database
The method comprises the following steps: and the hot list algorithm calculates and obtains the hot list weight value of each news according to a preset rule, and obtains a news information hot list (used for longitudinal display) by descending the order from the hottest news.
Step two: marking the characteristics of each piece of news, wherein each piece of news obtains a characteristic mark set consisting of a plurality of characteristic marks;
step three: clustering news in a news database according to the feature mark set of each news, and acquiring a corresponding clustered news set for each news;
step four: and according to the user portrait, operating a user personalized recommendation algorithm to process a cluster news set corresponding to each piece of news, calculating a user preference weight value of each piece of news in the cluster set according to a preset rule, and arranging the news in a descending order according to the user preference degree to obtain a user personalized recommendation list (used for transverse display) of the cluster set.
Step five: repeating the second step to the fourth step to obtain a user personalized recommendation list (for horizontal display) corresponding to each news item
Step six: the display system of the mobile terminal calls the 'hot list' from the server through the mobile internet and displays the hot list in the longitudinal direction of the screen of the mobile terminal, and the display system calls the 'user personalized recommendation list' corresponding to each piece of news from the server and displays the user personalized recommendation list in the transverse direction of corresponding information on the screen of the mobile terminal.
Step seven: when a user transversely strokes a certain piece of information on the screen of the mobile terminal, the display system calls a user personalized recommendation list corresponding to the news from the server, and the user personalized recommendation list is loaded at the end of a transverse line of the news on the screen of the mobile terminal.
It should be noted that the original media involved in the present invention may be video, audio, text, etc.; the information related to the invention can be commodity information, video information, audio information, application program information, service information and the like; the application fields related to the invention can be news, information, video, e-commerce, local services, application program market, system desktop and the like.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes in the embodiments and/or modifications of the invention can be made, and equivalents and modifications of some features of the invention without departing from the spirit and scope of the invention.
Claims (10)
1. A recommendation method for expressing the relation between information comprises a display system located on a mobile terminal and an information recommendation system located on a server, and is characterized in that the display system of the mobile terminal calls two recommendation lists which are established by the information recommendation system through a mobile internet from the server and are displayed on the longitudinal dimension and the transverse dimension of a screen of the mobile terminal.
2. The information recommendation system for expressing a recommendation method of an inter-information linkage as claimed in claim 1, wherein said information recommendation system comprises an algorithm module, a feature labeling module and a clustering module.
3. The presentation system of a recommendation method for expressing association between information as claimed in claim 1, wherein said presentation system located at said mobile terminal comprises a vertical presentation module and a horizontal presentation module.
4. The information recommendation system for expressing a recommendation method of an inter-information linkage as claimed in claim 2, wherein said algorithm module runs algorithm 1 on information in a known information database to obtain an information recommendation list.
5. The information recommendation system for expressing a recommendation method for an inter-information linkage as claimed in claim 2, wherein said feature tag module is configured to tag information in the information database with features, and each piece of information may have a plurality of feature tags, so as to obtain an information feature tag set.
6. The information recommendation system for expressing a recommendation method of an inter-information linkage as claimed in claim 2, wherein said clustering module is configured to cluster the information in the information database according to the feature tag set of each piece of information, to obtain the clustered information set of each piece of information.
7. The information recommendation system for expressing a recommendation method of an inter-information linkage as claimed in claim 2, wherein said algorithm module runs algorithm 2 on the cluster information set of each piece of information to obtain the cluster information recommendation list of each piece of information.
8. The presentation system of a recommendation method for expressing association between information as claimed in claim 3, wherein the vertical presentation module of the presentation system located at the mobile terminal retrieves the information recommendation list from the server through the mobile internet, and presents the information recommendation list in a waterfall flow manner in a vertical direction of the screen of the mobile terminal.
9. The presentation system of a recommendation method for expressing association between information as claimed in claim 3, wherein said horizontal presentation module of the presentation system located at the mobile terminal retrieves the cluster information recommendation list of each piece of information from the server through the mobile internet, and presents the information displayed on the screen of the mobile terminal horizontally.
10. A recommendation method for expressing the relation between information is characterized by comprising the following steps:
the information recommendation system is located on a server, an algorithm module runs an algorithm 1 on a known information database to obtain a 'longitudinal recommendation list', a characteristic marking module carries out characteristic marking on information of the known information database, then clustering is carried out on the information of the known information database through a clustering module according to a characteristic mark set of each piece of information in sequence to obtain a clustering information set of each piece of information, and an algorithm module runs an algorithm 2 on the clustering information set of each piece of information to obtain a 'transverse recommendation list'; the display system is located at the mobile terminal, the longitudinal display module calls a longitudinal recommendation list from the server through the mobile internet and displays the longitudinal recommendation list in the longitudinal direction of the screen of the mobile terminal in a waterfall flow mode, and the transverse display module calls a transverse recommendation list of each piece of information from the server through the mobile internet and displays the transverse recommendation list of the piece of information displayed on the screen of the mobile terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010775598.7A CN111859157A (en) | 2020-08-05 | 2020-08-05 | Recommendation method for expressing relation between information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010775598.7A CN111859157A (en) | 2020-08-05 | 2020-08-05 | Recommendation method for expressing relation between information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111859157A true CN111859157A (en) | 2020-10-30 |
Family
ID=72971013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010775598.7A Pending CN111859157A (en) | 2020-08-05 | 2020-08-05 | Recommendation method for expressing relation between information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111859157A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130332523A1 (en) * | 2012-06-12 | 2013-12-12 | Francis Luu | Providing a multi-column newsfeed of content on a social networking system |
| CN108198045A (en) * | 2018-01-30 | 2018-06-22 | 东华大学 | The design method of mixing commending system based on e-commerce website data mining |
| KR101984937B1 (en) * | 2018-11-28 | 2019-09-03 | 주식회사 피씨엔 | 3 dimensions digital timeline output system of traditional culture |
| CN111209386A (en) * | 2020-01-07 | 2020-05-29 | 重庆邮电大学 | Personalized text recommendation method based on deep learning |
-
2020
- 2020-08-05 CN CN202010775598.7A patent/CN111859157A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130332523A1 (en) * | 2012-06-12 | 2013-12-12 | Francis Luu | Providing a multi-column newsfeed of content on a social networking system |
| CN108198045A (en) * | 2018-01-30 | 2018-06-22 | 东华大学 | The design method of mixing commending system based on e-commerce website data mining |
| KR101984937B1 (en) * | 2018-11-28 | 2019-09-03 | 주식회사 피씨엔 | 3 dimensions digital timeline output system of traditional culture |
| CN111209386A (en) * | 2020-01-07 | 2020-05-29 | 重庆邮电大学 | Personalized text recommendation method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107665225B (en) | Information pushing method and device | |
| US20130238393A1 (en) | System and method for brand monitoring and trend analysis based on deep-content-classification | |
| CN110020162B (en) | User identification method and device | |
| WO2020078050A1 (en) | Comment information processing method and apparatus, and server, terminal and readable medium | |
| CN108595448A (en) | Information-pushing method and device | |
| CN111105297A (en) | Information pushing method and related device | |
| CN112015986A (en) | Data pushing method and device, electronic equipment and computer readable storage medium | |
| CN110910178A (en) | Method and device for generating advertisement | |
| CN113298568B (en) | Method and device for advertising | |
| US11599590B2 (en) | Poll-based networking system | |
| CN111144964A (en) | Commodity information sending and displaying method, device, medium and equipment | |
| WO2019076294A1 (en) | Promotion information delivery method and apparatus, and medium and device | |
| CN109087139A (en) | Advertisement placement method and device for feed stream | |
| CN113469786A (en) | Method and device for recommending articles, computer equipment and storage medium | |
| CN113111198A (en) | Demonstration manuscript recommendation method based on collaborative filtering algorithm and related equipment | |
| CN111859157A (en) | Recommendation method for expressing relation between information | |
| CN106709742B (en) | Native advertisement data processing method and device | |
| CN111833085A (en) | Method and device for calculating price of article | |
| CN113313542B (en) | Method and device for pushing channel pages | |
| CN115103015A (en) | Data pushing method and device, electronic equipment and computer readable medium | |
| CN109885710B (en) | User image depicting method based on differential evolution algorithm and server | |
| CN113191840A (en) | Article information display method and device, electronic equipment and computer readable medium | |
| CN110851568A (en) | Commodity information processing method, terminal device and computer-readable storage medium | |
| CN110858363A (en) | Method and device for identifying seasonal commodities | |
| CN113763091B (en) | Article display method and device based on express cabinet |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201030 |