CN111859131B

CN111859131B - Personalized information recommendation method and information recommendation system under multiple constraint conditions

Info

Publication number: CN111859131B
Application number: CN202010703187.7A
Authority: CN
Inventors: 张伟; 徐志峰
Original assignee: Shandong Academy Of Sciences Yida Technology Consulting Co ltd
Current assignee: Shandong Academy Of Sciences Yida Information Technology Co ltd
Priority date: 2020-07-21
Filing date: 2020-07-21
Publication date: 2021-06-15
Anticipated expiration: 2040-07-21
Also published as: CN111859131A

Abstract

The invention discloses a personalized information recommendation method under multiple constraint conditions, which comprises the steps of recording an attention tag list and a corresponding content list of a user, and displaying recommended content when a user terminal is connected with an information platform; obtaining at least one attention tag from a first user, and recording the at least one attention tag as an attention tag list; matching identification information of the same concerned label in the concerned label list of the first user and the concerned label list of the second user to obtain a concerned list; receiving content from the user terminal and setting a content tag; matching the tag information of the tag of interest paired in the tag of interest list of the first user with the content; recording the content and the mark information of the attention label matched with the content on a content list; the recommendation method and the recommendation system perform recommendation based on the association between the attention label of the user and the user, the association degree of the recommended content is high, and the recommended content is free from the problems of sparseness and deficiency.

Description

Personalized information recommendation method and information recommendation system under multiple constraint conditions

Technical Field

The invention relates to a recommendation method, in particular to a personalized information recommendation method under multiple constraint conditions.

Background

The Content-Based recommendation algorithm (Content-Based Recommendations) is to construct a recommendation algorithm model Based on object-related information, user-related information and user operation behaviors on an object, and provide a recommendation service for a user. The object-related information may be metadata information, a tag, a user comment, manually-labeled information, or the like, which is described in the text of the object. User-related information refers to demographic information (e.g., age, gender, preferences, location, income, etc.). The operation behavior of the user on the object can be comment, collection, praise, watching, browsing, clicking, shopping cart adding, purchasing and the like. Content-based recommendation algorithms generally rely only on the user's own behavior to provide recommendations to the user, and do not involve the behavior of other users.

The content-based recommendation algorithm predicts inaccuracy and sparseness or lack of recommendation information only according to scores caused by interest content recommendation.

Disclosure of Invention

The invention provides a personalized information recommendation method under multiple constraint conditions for recommendation based on the association between a user attention tag and a user, which solves the technical problems of inaccurate score prediction and sparse or missing recommendation information caused by recommendation only according to interest content in the related technology.

According to one aspect of the invention, the personalized information recommendation method under the multi-constraint condition is provided, and comprises the steps of recording an attention tag list and a corresponding content list of a user, and displaying recommended content when a user terminal is connected with an information platform;

the recording of the attention tag list and the corresponding content list of the user comprises:

obtaining at least one attention tag from a first user, and recording the at least one attention tag as an attention tag list;

matching identification information of the same concerned label in the concerned label list of the first user and the concerned label list of the second user to obtain a concerned list;

receiving content from the user terminal and setting a content tag;

matching the tag information of the tag of interest paired in the tag of interest list of the first user with the content;

recording the content and the tag information of the tag of interest matching the content on a content list.

Further, the displaying the recommended content when the user terminal is connected to the information platform includes:

receiving user information of a user terminal logging in an information platform;

identifying a user logging in an information platform according to user information, and extracting label information of a paired attention label from an attention list of the user;

and extracting content from the content list according to the marking information of the extracted paired attention labels and providing the content to the user.

Further, the obtaining of the attention list by pairing the identification information of the same attention tag in the attention tag list of the first user and the attention tag list of the second user includes:

recording other users with connection relation on a connection relation table of the first user by taking the first user as a standard;

searching a second user on the connection relation table of the first user, searching the concerned labels in the concerned label list of the second user, which are the same as the concerned label list of the first user, and pairing the identification information of the same concerned labels;

and recording mark information of the paired attention labels to obtain an attention list of the first user.

Further, the receiving the content from the user terminal and setting the content tag includes:

detecting at least the content received from one user terminal among the plurality of user terminals, and if the content received from only one user terminal is received or not received, re-detecting;

and if the contents received by at least two user terminals are received, setting a content label for the received contents.

According to one aspect of the invention, the personalized information recommendation system under the multi-constraint condition comprises a recommendation server and a user terminal connected with the recommendation server through a network, wherein the recommendation server can provide recommendation service through the user terminal.

Further, the recommendation server includes an attention tag management section, a connection management section, an attention management section, an association section, a content management section, and a content providing section,

the tag-of-interest management unit stores at least one tag of interest indicating a content of interest to the user, and generates a tag-of-interest list corresponding to the user.

The connection management part manages a connection relation table corresponding to each user;

the attention management part manages an attention tag list of a user;

the association part is used for establishing an attention list based on the attention label list of the attention label management part and the connection relation list of the connection management part;

the content management part records the mark information of the concerned label in the concerned list of the association part and the corresponding content together to form a content list;

the content providing part extracts content from the content list according to the attention list of the user logging in the recommendation service and recommends the content to the user.

Further, the attention label management unit classifies and stores the attention labels according to the categories to which the attention labels belong, and sets a hierarchical relationship according to the upper and lower concepts of the attention labels of the same category.

Further, the associating unit is configured to establish the interest list based on the interest tag list of the interest tag management unit and the connection relation table of the connection management unit, and includes: the association unit takes a certain user as a reference user, extracts the same attention tag pair as the attention tag list of the reference user from the attention tag lists of other users in the connection relation table of the reference user, and records the identification information of the same attention tag in the attention list of the reference user in a matching manner.

The invention has the beneficial effects that: according to the recommendation method and the recommendation system, recommendation is performed based on the association between the attention tag of the user and the user, the association degree of the recommended content is high, the problems of sparseness and missing of the recommended content are avoided, and compared with the recommendation which depends on the interest content and is purely obtained through a multi-constraint condition, recommendation with higher matching degree is obtained;

the invention provides the operation space for changing the attention label and the related list for the user, and is convenient for the user to customize and recommend.

Drawings

Fig. 1 is a schematic view of the overall structure of a cleaning apparatus for a depressed floor according to an embodiment of the present invention;

FIG. 2 is a chart of a list of focus labels for a first user in accordance with an embodiment of the present invention;

FIG. 3 is a table of connections for a first user in accordance with an embodiment of the present invention;

FIG. 4 is a chart of a list of focus labels for a second user in accordance with an embodiment of the present invention;

FIG. 5 is a chart of a first user's attention list of an embodiment of the present invention;

FIG. 6 is a table of contents diagram of an embodiment of the present invention;

FIG. 7 is a schematic diagram of a personalized information recommendation system under multiple constraints, according to an embodiment of the invention;

FIG. 8 is a schematic diagram of a recommendation server of an embodiment of the present invention.

In the figure: a

first user terminal

10, 11; a recommendation server 20; a focused label management unit 210; a connection management unit 220; a focus management unit 230; a correlation section 240; a content management unit 250; the content providing unit 260.

Detailed Description

The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and thereby implement the subject matter described herein, and are not intended to limit the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components as needed. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with respect to some examples may also be combined in other examples.

In this embodiment, a method for recommending personalized information under multiple constraints is provided, as shown in fig. 1, which is a flowchart of a method for recommending personalized information under multiple constraints according to the present invention, as shown in the drawing, the flowchart includes that a recommendation server 20 records a list of tags of interest of a user and a corresponding content list, and the recommendation server 20 displays recommended content when

user terminals

10 and 11 are connected to an information platform;

the recommendation server 20 records the attention tag list and the corresponding content list of the user;

step 100, firstly, the recommendation server 20 obtains at least one concerned label from a first user, and records the concerned label as a concerned label list;

the recommendation server 20 may provide at least one or more tag of interest obtained from the first user to the

first user terminal

10, 11;

the recommendation server 20 may receive a new tag of interest from the

first user terminal

10, 11, or may save the modified tag of interest;

the hierarchy can be set according to the upper and lower concepts between the modified attention tag and the saved attention tag;

if the first user sets the attention tag, the recommendation server 20 may assign different identification information to at least one attention tag, and may perform matching on at least the first attention tag, and record the matching on the attention tag table of the first user;

that is, in step 100, the recommendation server 20 records at least one attention tag set by the first user on the attention tag table of the first user;

the recommendation server 20 may provide different label information for each attention tag in order to identify the attention tag on the first user's attention tag table;

as shown in FIG. 2, an example of the recommendation server 20 recording the tag of interest of the first user and providing the tagging information

The recommendation server 20 obtains the "football", "baseball" and "volleyball" attention tags of the first user, and records according to each attention tag;

for the convenience of identification, the label of interest of "soccer" is given with marking information of Z1540, the label of interest of "baseball" is given with marking information of B1540, and the label of interest of "volleyball" is given with marking information of P1540;

200, the recommendation server 20 matches the identification information of the same concerned label in the concerned label list of the first user and the concerned label list of the second user to obtain an concerned list;

firstly, the recommendation server 20 takes the first user as a standard, and records other users with connection relations on a connection relation table of the first user;

as shown in fig. 3, the recommendation server 20 generates a connection relation table of the first user according to the connection relation of the first user, where the connection relation table includes user information of the second user (ERD) and the third user (SRD);

the user information may be selected from, but is not limited to: personalized information recommendation method under multiple constraint conditions or character strings which can be used as indexes.

In the second step, the recommendation server 20 searches the connection relationship table of the first user for the second user, searches the focused tags in the focused tag list of the second user, which are the same as the focused tag list of the first user, and matches the identification information of the focused tags.

As shown in fig. 4, an example of a tag list of interest and tag information of the second user;

the attention tag list of the second user records the attention tags of football and baseball, wherein the mark information corresponding to the attention tag of football is Z1550, and the mark information corresponding to the attention tag of baseball is B1550;

the tag information Z1540 of the "soccer" care tag registered in the care tag list of the first user is paired with the tag information Z1550 of the "soccer" care tag registered in the care tag list of the second user;

the tag information B1540 of the "baseball" care tab registered in the care tab list of the first user is paired with the tag information B1550 of the "baseball" care tab registered in the care tab list of the second user;

third, the recommendation server 20 records label information of the paired attention tags on the attention list of the first user;

as shown in fig. 5, the marking information of the paired "soccer" focus tags (Z1540, Z1550) is recorded on the first user's focus list, and the marking information of the paired "baseball" focus tags (B1540, B1550) is recorded on the first user's focus list;

step 300, the recommendation server 20 can detect at least the content received from one

user terminal

10, 11 among the plurality of

user terminals

10, 11, and detect again if only the content received by one

user terminal

10, 11 is received or not received;

step 400, if receiving the content received by at least two

user terminals

10, 11, setting a content tag for the received content;

the recommendation server 20 may provide a user interface that may input content according to a specific situation, and the

user terminals

10 and 11 may receive the content and may set a focus label to the received content;

content including at least one of an author of the content, data of the content, and a review of the content;

the content "the soccer tournament" and the content author "a" are received from the terminal of the first user, and the content tag is set to "soccer".

Step 500, matching the label information of the attention label paired in the attention label list of the first user with the content by the recommendation server 20;

specifically, as shown in fig. 6, the content "soccer tournament" related to the "soccer" content tag and the author "a" of the content are received from the terminal of the first user; the content is matched with the marking information Z1540 corresponding to the 'football' attention label of the first user;

receiving a content "Mangan" related to the "football" content tag and an author "B" of the content from a terminal of a second user; the content is matched with the label information Z1550 corresponding to the "football" focus label of the second user;

receiving, from the terminal of the second user, a content "Major League Baseball (MLB)" regarding a "Baseball" content tag, which matches the tag information B1550 corresponding to the "Baseball" attention tag of the second user, and an author "c" of the content;

the recommendation server 20 records the content and the tag information of the tag of interest matched thereto on the content list, step 600.

Step 700, the method for displaying the recommended content by the recommendation server 20 when the

user terminals

10 and 11 are connected to the information platform:

the recommendation server 20 receives the user information of the

user terminals

10 and 11 logging in the information platform;

the recommendation server 20 identifies the user logging in the information platform according to the user information, and extracts the label information of the paired attention label from the attention list of the user;

If the attention tags of the upper and lower concepts set by the user, the label information of the attention tags of the lower level to which the paired attention tags belong is extracted together.

In this embodiment, a personalized information recommendation system under multiple constraints is provided, as shown in fig. 7, which is a block diagram of a personalized information recommendation system under multiple constraints according to the present invention, as shown in fig. 7, a personalized information recommendation system under multiple constraints includes a recommendation server 20 and

user terminals

10 and 11 connected thereto via a network, the recommendation server 20 may be formed by a general-purpose computer, and is connected to the network to communicate with the

user terminals

10 and 11, and information received from the

user terminals

10 and 11 may be received via the network.

In addition, the recommendation server 20 may provide a recommendation service through the

user terminals

10, 11;

as shown in fig. 8, the recommendation server 20 includes an attention tag management part 210, a connection management part 220, an attention management part 230, an association part 240, a content management part 250, and a content providing part 260,

the focused label management unit 210 stores at least one focused label indicating the focused content of the user, and generates a focused label list corresponding to the user.

For example, the attention label management unit 210 may classify and store the attention labels according to the categories to which the attention labels belong, and set the hierarchical relationship according to the top and bottom concepts of the attention labels of the same category.

The focused tag management unit 210 may receive and store a new focused tag from the

user terminals

10 and 11, or may receive a modification request for storing the focused tag and modify the stored focused tag.

For example, the attention label management unit 210 may receive a new attention label from the

user terminals

10 and 11, and may classify the attention label received from the

user terminals

10 and 11.

Alternatively, for example, the focused tag management unit 210 may determine the similarity between the received focused tag and the stored focused tag, and determine the type of the modified focused tag;

the focused tag management unit 210 may obtain the stored focused tags or the relationship between the upper and lower levels of the focused tags received by the

user terminals

10 and 11 from the user.

For example, the focused tag management unit 210 may receive a modification request for storing the hierarchical relationship of the focused tag from one or

more user terminals

10 and 11, and modify the hierarchy of the focused tag according to the modification request that has been requested recently.

Alternatively, for example, when the attention tag management unit 210 requests modification of the hierarchical relationship of the attention tag, votes may be cast from a plurality of users on the hierarchical relationship before and after the modification, or may be updated to the hierarchical relationship supported by a majority of votes;

the connection management section 220 manages a connection relationship table corresponding to each user;

for example, when the first user and the second user are registered in a friend relationship, the connection manager 220 may record the user information of the second user in the connection relationship table of the first user. The user information of a third user with a friend relationship of the second user may also be recorded on the connection relationship table of the first user.

The attention managing section 230 manages an attention tag list of the user;

for example, when the first user pays attention to "soccer", the attention management unit 230 records the "soccer" attention tag in the attention tag list of the first user and sets corresponding flag information Z1540;

if the first user cancels the attention to "soccer", the attention managing section 230 deletes the "soccer" attention tag from the attention tag list of the first user.

The association unit 240 is configured to create a focus list based on the focus label list of the focus label management unit 210 and the connection relationship table of the connection management unit 220, extract a focus label pair identical to the focus label list of the reference user from the focus label lists of other users in the connection relationship table of the user with reference to a certain user, and pair and record identification information of the same focus label in the focus list of the reference user.

When the user cancels the focused attention tag, the corresponding focus list is updated as the focus tag list is changed.

The content management unit 250 records the tag information of the tag of interest in the interest list of the association unit 240 together with the corresponding content to form a content list;

the content providing part 260 extracts content recommendation from the content list to the user according to the focus list of the user who logs in the recommendation service.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims

1. A personalized information recommendation method under multiple constraint conditions is characterized by comprising the steps of recording an attention tag list and a corresponding content list of a user, and displaying recommended content when a user terminal is connected with an information platform;

receiving content from the user terminal and setting a content tag;

2. The method for recommending personalized information under multiple constraints according to claim 1, wherein the displaying the recommended content when the user terminal is connected to the information platform comprises:

3. The method of claim 1, wherein the obtaining of the focus list by pairing the identification information of the same focus label in the focus label list of the first user and the focus label list of the second user comprises:

4. The method of claim 1, wherein the receiving content from a user terminal and setting a content tag comprises:

5. A personalized information recommendation system under multiple constraint conditions is characterized by comprising a recommendation server and a user terminal connected with the recommendation server through a network, wherein the recommendation server provides recommendation service through the user terminal;

the recommendation server includes an attention tag management section, a connection management section, an attention management section, an association section, a content management section, and a content providing section,

the attention tag management part at least stores one attention tag representing the attention content of the user and generates an attention tag list corresponding to the user;

the attention management part manages an attention tag list of a user;

the association unit creates an attention list based on the attention label list of the attention label management unit and the connection relationship list of the connection management unit, and includes: the association part takes a certain user as a reference user, extracts the attention label pair which is the same as the attention label list of the reference user from the attention label lists of other users in the connection relation table of the reference user, and matches and records the identification information of the same attention label in the attention list of the reference user;

6. The system according to claim 5, wherein the attention tag management unit classifies and stores the attention tags according to the categories to which the attention tags belong, and sets a hierarchical relationship according to the upper and lower concepts of the attention tags of the same category.