CN110110201A - A kind of content recommendation method and system - Google Patents
A kind of content recommendation method and system Download PDFInfo
- Publication number
- CN110110201A CN110110201A CN201810019351.5A CN201810019351A CN110110201A CN 110110201 A CN110110201 A CN 110110201A CN 201810019351 A CN201810019351 A CN 201810019351A CN 110110201 A CN110110201 A CN 110110201A
- Authority
- CN
- China
- Prior art keywords
- content
- attribute information
- characteristic values
- user
- interest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application provides a kind of content recommendation method and systems, comprising: obtains historical interest data from default platform;Content attribute information when the historical interest data include candidate user access content;Based on the historical interest data, at least one interest tags structure, the corresponding relationship between the interest tags structural characterization content attribute information and content characteristic values are constructed;The content characteristic values are to be determined based on content attribute information;According to the content attribute information of the browsing information representation of the user of acquisition and the interest tags structure, the determining and matched multiple content characteristic values of the user;Based on the mapping relations between the determining content characteristic values and preset content characteristic values and recommendation, the determining and matched recommendation of the user, and recommend.
Description
Technical field
This application involves information technology fields, in particular to a kind of content recommendation method and system.
Background technique
With the development of internet technology, each platform needs the demand based on user to push away the corresponding content of user's progress
It send, currently, when each platform is pushed, is analyzed by real time data to user and off-line data;
When being analyzed based on real time data, by obtaining user's such as clicking within the preceding paragraph time, watching operation,
Carry out the prediction of interest intention.Due to, the data of acquisition are not comprehensive enough, complete, and be easy to quote a remark out of its context the interest of user of guessing wrong, into
And user experience is influenced to make user dislike;Alternatively, similar hobby can only be predicted, and it can not accurately predict user
The intention of next step.
When being analyzed based on off-line data, by obtaining user in the data of longer period of time range, e.g., nearly three
Month, it is 1 year nearly in etc., using same Type of Collective, building portrait by the way of, user data is subjected to the filing under certain dimensions, can
The probability that prediction user is intended in next step is improved, being but unable to satisfy user really need to be with asking.
Apply for content
In view of this, the application's is designed to provide a kind of content recommendation method and system, for solving the prior art
In can not precisely understand user be intended to the problem of.
In a first aspect, the embodiment of the present application provides a kind of content recommendation method, this method comprises:
Historical interest data are obtained from default platform;It is interior when the historical interest data include candidate user access content
Hold attribute information;
Based on the historical interest data, at least one interest tags structure is constructed, in the interest tags structural characterization
Hold the corresponding relationship between attribute information and content characteristic values;The content characteristic values are to be determined based on content attribute information;
According to the content attribute information of the browsing information representation of the user of acquisition and the interest tags structure, determine
With the matched multiple content characteristic values of the user;
It is closed based on the mapping between the determining content characteristic values and preset content characteristic values and recommendation
System, the determining and matched recommendation of the user, and recommend.
Optionally, the interest tags structure includes user interest structure;It is described to be based on the historical interest data, building
At least one interest tags structure, comprising:
It determines user property, from the historical interest data, counts the corresponding content of candidate user with the attribute
Attribute information;
For each user property, the corresponding content attribute information of the attribute is screened according to the first preset condition,
Based on the content attribute information after screening, the corresponding relationship between content attribute information and content characteristic values is established, and then determine
User interest structure;
Wherein, the first preset condition includes: the content attribute information, be located at the content attribute information access time it
Preceding access time, corresponding content attribute information was identical.
Optionally, the interest tags structure includes content type interest structure;It is described to be based on the historical interest data,
Construct at least one interest tags structure, comprising:
Based on preset multiple content types, from the historical interest data, the time of the corresponding each content type of statistics
Select the content attribute information at family;
For each content type, the corresponding content attribute information of the content type is sieved according to the second preset condition
Choosing, based on the corresponding content attribute information of the content type after screening, is established between content attribute information and content characteristic values
Corresponding relationship, and then determine content type interest structure;
Wherein, the second preset condition includes: the content attribute information, be located at the content attribute information access time it
Preceding access time, corresponding content attribute information was identical.
Optionally, any content characteristic values W is determined according to the following formula:
W=(Num-m)x/(T-t+n)y
Wherein, W is content characteristic values;Num is access times when candidate user accesses content, and m is the first decaying base
Number;N is the second decaying radix;X is the decay factor of access times Num;Y is the decay factor of time;T is that user currently visits
Ask access time when content;T is access time when user accesses content for the first time.
Optionally, it is described based on the determining content characteristic values and preset content characteristic values and recommendation it
Between mapping relations, it is determining with the matched recommendation of the user, comprising:
The content characteristic values are ranked up, according to sequence from high to low, are selected from the content characteristic values after sequence
Select the content characteristic values of preset number;
Mapping between the content characteristic values and preset content characteristic values and recommendation based on selection is closed
System determines the recommendation of corresponding each content characteristic values;
Based on the corresponding interest tags structure of each content characteristic values, the sequence of recommendation is determined.
Second aspect, the embodiment of the present application provide a kind of content recommendation system, which includes:
Module is obtained, for obtaining historical interest data from default platform;The historical interest data include candidate user
Access content attribute information when content;
Module is constructed, for being based on the historical interest data, constructs at least one interest tags structure, the interest mark
Sign the corresponding relationship between structural characterization content attribute information and content characteristic values;The content characteristic values are based on contents attribute
What information determined;
First determining module, for according to the content attribute information of the browsing information representation of the user of acquisition and described
Interest tags structure, the determining and matched multiple content characteristic values of the user;
Second determining module, for based on the determining content characteristic values and preset content characteristic values and recommendation
Mapping relations between content, the determining and matched recommendation of the user, and recommend.
Optionally, the interest tags structure includes user interest structure;The building module is specifically used for:
It determines user property, from the historical interest data, counts the corresponding content of candidate user with the attribute
Attribute information;
For each user property, the corresponding content attribute information of the attribute is screened according to the first preset condition,
Based on the content attribute information after screening, the corresponding relationship between content attribute information and content characteristic values is established, and then determine
User interest structure;
Wherein, the first preset condition includes: the content attribute information, be located at the content attribute information access time it
Preceding access time, corresponding content attribute information was identical.
Optionally, the interest tags structure includes content type interest structure;The building module is specifically used for:
Based on preset multiple content types, from the historical interest data, the time of the corresponding each content type of statistics
Select the content attribute information at family;
For each content type, the corresponding content attribute information of the content type is sieved according to the second preset condition
Choosing, based on the corresponding content attribute information of the content type after screening, is established between content attribute information and content characteristic values
Corresponding relationship, and then determine content type interest structure;
Wherein, the second preset condition includes: the content attribute information, be located at the content attribute information access time it
Preceding access time, corresponding content attribute information was identical.
Optionally, the building module determines any content characteristic values W according to the following formula:
W=(Num-m)x/(T-t+n)y
Wherein, W is content characteristic values;Num is access times when candidate user accesses content, and m is the first decaying base
Number;N is the second decaying radix;X is the decay factor of access times Num;Y is the decay factor of time;T is that user currently visits
Ask access time when content;T is access time when user accesses content for the first time.
Optionally, second determining module is specifically used for:
The content characteristic values are ranked up, according to sequence from high to low, are selected from the content characteristic values after sequence
Select the content characteristic values of preset number;
Mapping between the content characteristic values and preset content characteristic values and recommendation based on selection is closed
System determines the recommendation of corresponding each content characteristic values;
Based on the corresponding interest tags structure of each content characteristic values, the sequence of recommendation is determined.
The content recommendation method and system of the embodiment of the present application, comprising: obtain historical interest data from default platform;It is described
Content attribute information when historical interest data include candidate user access content;Based on the historical interest data, building is extremely
A few interest tags structure, the corresponding pass between the interest tags structural characterization content attribute information and content characteristic values
System;The content characteristic values are to be determined based on content attribute information;According to the content of the browsing information representation of the user of acquisition
Attribute information and the interest tags structure, the determining and matched multiple content characteristic values of the user;Described in determining
Mapping relations between content characteristic values and preset content characteristic values and recommendation, determine and the user is matched pushes away
Content is recommended, and is recommended.Content recommendation method provided by the present application constructs interest tags structure based on historical interest data, increases
Data source, each operation of user can embody in interest tags structure, can react the real-time need of user
It asks, meanwhile, the more quasi- intention for understanding user, and then be the content of user's recommendation precision.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is a kind of flow diagram for content recommendation method that one embodiment of the application provides;
Fig. 2 is the schematic diagram of the direct coupled structure form for the interest tags structure that one embodiment of the application provides;
Fig. 3 is the schematic diagram of the topographical form for the interest tags structure that one embodiment of the application provides;
Fig. 4 is a kind of structural schematic diagram for content recommendation system that one embodiment of the application provides;
Fig. 5 provides a kind of structural schematic diagram of computer equipment by the embodiment of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application
Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall in the protection scope of this application.
The embodiment of the present application provides a kind of content recommendation method, as shown in Figure 1, method includes the following steps:
S101 obtains historical interest data from default platform;The historical interest data include candidate user access content
When content attribute information;
Specifically, default platform can be the available platform to candidate user related data in network, e.g., wechat,
The platforms such as today's tops, microblogging;Access time, access times, content category when historical interest data include user's access content
Property, content type etc., wherein content type characterizes the classification of content, such as entertainment news;Contents attribute characterizes the content in correspondence
The attribute of content type, e.g., when which is entertainment news, contents attribute can be model ice ice etc..
S102 is based on the historical interest data, constructs at least one interest tags structure, the interest tags structure table
Levy the corresponding relationship between content attribute information and content characteristic values;The content characteristic values are to be determined based on content attribute information
's;
Specifically, interest tags structure can be direct coupled structure (referring to Fig. 2) and topological structure (referring to Fig. 3).It is constructing
When interest tags structure, content attribute information is converted by all operation behaviors of candidate user in historical interest data, is belonged to
Property information can for candidate user browsing content label, according to operation behavior occur time, sequence so that each label
The node that upstream and downstream relies on is constituted, each interest tags structure can have multiple interest nodes, and interest node can be direct-connected
Structure is also possible to topological structure, each interest node corresponding content attribute information, content characteristic values, access times etc., visually
Depending on concrete condition.
Optionally, the interest tags structure includes user interest structure;It is described to be based on the historical interest data, building
At least one interest tags structure, comprising:
It determines user property, from the historical interest data, counts the corresponding content of candidate user with the attribute
Attribute information;
For each user property, the corresponding content attribute information of the attribute is screened according to the first preset condition,
Based on the content attribute information after screening, the corresponding relationship between content attribute information and content characteristic values is established, and then determine
User interest structure;
Wherein, the first preset condition includes: the content attribute information, be located at the content attribute information access time it
Preceding access time, corresponding content attribute information was identical.
Specifically, user interest structural characterization has the interest of the user of same user property;User property can be
Life, white collar, blue collar, old man etc., when determining user property, can by character image model to historical interest data at
Reason, to determine the candidate user with same user property, character image model has detailed introduction in the prior art, herein
No longer excessively illustrated;When constructing user interest structure, believed according to the contents attribute of the candidate user with same attribute
The access times of breath, determine the content attribute information of each interest node, e.g., in the access sequence of each candidate user, from
In the same content attribute information of access, the content attribute information that access times are more than setting number is determined as corresponding interest
The content attribute information of node.
For example, some candidate user has accessed a series of wechat contents, for candidate user when accessing wechat content, every micro-
Letter content all has label, and the label of first wechat content is NBA, and the label of Article 2 wechat content is basketball, Article 3
The label of wechat content is Lakers, and the label of Article 4 wechat content is Bryant, and the user interest structure that can be constructed can be M1
(NBA)-M2 (basketball)-M3 (Lakers)-M4 (Bryant), if the label of Article 5 wechat content is Lakers, by the M3 (Lakers)
Access times increase by 1 time.
Optionally, the interest tags structure includes content type interest structure;It is described to be based on the historical interest data,
Construct at least one interest tags structure, comprising:
Based on preset multiple content types, from the historical interest data, the time of the corresponding each content type of statistics
Select the content attribute information at family;
For each content type, the corresponding content attribute information of the content type is sieved according to the second preset condition
Choosing, based on the corresponding content attribute information of the content type after screening, is established between content attribute information and content characteristic values
Corresponding relationship, and then determine content type interest structure;
Wherein, the second preset condition includes: the content attribute information, be located at the content attribute information access time it
Preceding access time, corresponding content attribute information was identical.
Specifically, the classification of content type characterization candidate user access content, e.g., amusement, sport, science and technology, finance, consumption
Deng;In content construction classification interest structure, according to the access sequence for the content for belonging to same content type, each interest is determined
The content attribute information of node, e.g., in the access sequence of each content type, from the same content attribute information of access
In, the content attribute information that access times are more than setting number is determined as to the content attribute information of corresponding interest node.
For example, being the content of sport category for content type, the label of first content is NBA, the mark of Article 2 content
Label are basketball, and the label of Article 3 content is Lakers, and the label of Article 4 content is Bryant, and the user interest structure that can be constructed can
M1 (NBA)-M2 (basketball)-M3 (Lakers)-M4 (Bryant) is thought, if the label of Article 5 content is Lakers, by (the lake M3
People) access times increase by 1 time.
Optionally, any content characteristic values W is determined according to the following formula:
W=(Num-m)x/(T-t+n)y
Wherein, W is content characteristic values;Num is access times when candidate user accesses content, and m is the first decaying base
Number;N is the second decaying radix;X is the decay factor of access times Num;Y is the decay factor of time;T is that user currently visits
Ask access time when content;T is access time when user accesses content for the first time.
S103, according to the user of acquisition browsing information representation content attribute information and the interest tags structure,
The determining and matched multiple content characteristic values of the user;
In practical applications, each click behavior of user can correspond under some content attribute information, if in interest tags
Corresponding content attribute information is found in structure, then sets number of nodes, determination pair from the selection in the content attribute information downstream
Answer the content characteristic values of node;If not finding corresponding content attribute information in interest tags structure, by this contents attribute
Information increases in interest tags structure, and calculates corresponding content characteristic values.
For example, the content attribute information of user is basketball, then respectively from user interest structure and content type interest structure
Middle determination and the matched interest node of basketball select 3 from the downstream of the interest node of user interest structure current matching respectively
3 interest nodes are selected with the downstream of the matched interest node of current basketball in interest node and content type topological structure.
S104, based on reflecting between the determining content characteristic values and preset content characteristic values and recommendation
Relationship, the determining and matched recommendation of the user are penetrated, and is recommended.
Specifically, recommendation can be advertisement, content etc., wherein content can be news, wechat article etc..
In practical applications, the mapping relations of content characteristic range and recommendation are preset, e.g., content characteristic values exist
When between [0,20], only corresponding content;For content characteristic values at [21,80], possible corresponding content may correspond to advertisement;Content
When characteristic value is [81,100], advertisement is only corresponded to.
Optionally, it is described based on the determining content characteristic values and preset content characteristic values and recommendation it
Between mapping relations, it is determining with the matched recommendation of the user, comprising:
The content characteristic values are ranked up, according to sequence from high to low, are selected from the content characteristic values after sequence
Select the content characteristic values of preset number;
Mapping between the content characteristic values and preset content characteristic values and recommendation based on selection is closed
System determines the recommendation of corresponding each content characteristic values;
Based on the corresponding interest tags structure of each content characteristic values, the sequence of recommendation is determined.
In practical applications, if from 3 interest nodes have been determined in user interest structure, from content type interest structure
3 interest nodes have been determined, the content characteristic values of all interest nodes have been ranked up, according to sequential selection from high to low
3 content characteristic values determine the corresponding content characteristic range of each content characteristic values respectively, are based on this, determine corresponding recommendation
Content is ranked up recommendation, after sequence according to the corresponding interest tags structure priority of each content characteristic values
Recommendation is pushed.Wherein, the priority of interest tags structure is that the priority of user interest structure is higher than content type
The priority of interest structure.
Such as, the content characteristic values finally determined are respectively 90,75,75, and corresponding interest tags structure is user interest knot
Structure, content type interest structure, content type interest structure, then corresponding recommendation are as follows: advertisement A, advertisement B, content A etc..
In addition, increasing in interest tags structure emerging if not finding matched interest node in interest tags structure
Interesting node determines content attribute information and content characteristic values of the increased interest node etc., so that phase is accessed in user again
It can accurately be pushed when the content attribute information answered.
The content recommendation method provided according to embodiments of the present invention constructs interest tags structure based on historical interest data,
Data source is increased, each operation of user can embody in interest tags structure, can react the reality of user
When demand, meanwhile, the more quasi- intention for understanding user, so for user recommend precision content.
The embodiment of the invention provides a kind of content recommendation systems, as shown in figure 4, the system includes:
Module 41 is obtained, for obtaining historical interest data from default platform;The historical interest data include candidate use
Family accesses content attribute information when content;
Module 42 is constructed, for being based on the historical interest data, constructs at least one interest tags structure, the interest
Label construction characterizes the corresponding relationship between content attribute information and content characteristic values;The content characteristic values are based on content category
Property information determine;
First determining module 43, for the content attribute information according to the browsing information representation of the user of acquisition, Yi Jisuo
State interest tags structure, the determining and matched multiple content characteristic values of the user;
Second determining module 44, for based on the determining content characteristic values and preset content characteristic values with push away
The mapping relations between content, the determining and matched recommendation of the user are recommended, and is recommended.
Optionally, the interest tags structure includes user interest structure;The building module 42 is specifically used for:
It determines user property, from the historical interest data, counts the corresponding content of candidate user with the attribute
Attribute information;
For each user property, the corresponding content attribute information of the attribute is screened according to the first preset condition,
Based on the content attribute information after screening, the corresponding relationship between content attribute information and content characteristic values is established, and then determine
User interest structure;
Wherein, the first preset condition includes: the content attribute information, be located at the content attribute information access time it
Preceding access time, corresponding content attribute information was identical.
Optionally, the interest tags structure includes content type interest structure;The building module 43 is specifically used for:
Based on preset multiple content types, from the historical interest data, the time of the corresponding each content type of statistics
Select the content attribute information at family;
For each content type, the corresponding content attribute information of the content type is sieved according to the second preset condition
Choosing, based on the corresponding content attribute information of the content type after screening, is established between content attribute information and content characteristic values
Corresponding relationship, and then determine content type interest structure;
Wherein, the second preset condition includes: the content attribute information, be located at the content attribute information access time it
Preceding access time, corresponding content attribute information was identical.
Optionally, the building module 42 determines any content characteristic values W according to the following formula:
W=(Num-m)x/(T-t+n)y
Wherein, W is content characteristic values;Num is access times when candidate user accesses content, and m is the first decaying base
Number;N is the second decaying radix;X is the decay factor of access times Num;Y is the decay factor of time;T is that user currently visits
Ask access time when content;T is access time when user accesses content for the first time.
Optionally, second determining module 44 is specifically used for:
The content characteristic values are ranked up, according to sequence from high to low, are selected from the content characteristic values after sequence
Select the content characteristic values of preset number;
Mapping between the content characteristic values and preset content characteristic values and recommendation based on selection is closed
System determines the recommendation of corresponding each content characteristic values;
Based on the corresponding interest tags structure of each content characteristic values, the sequence of recommendation is determined.
Corresponding to the content recommendation method in Fig. 1, the embodiment of the present application also provides a kind of computer equipments, such as Fig. 5 institute
Show, which includes memory 1000, processor 2000 and be stored on the memory 1000 and can be on the processor 2000
The computer program of operation, wherein above-mentioned processor 2000 realizes above content recommended method when executing above-mentioned computer program
The step of.
Specifically, above-mentioned memory 1000 and processor 2000 can be general memory and processor, not do here
It is specific to limit, when the computer program of 2000 run memory 1000 of processor storage, it is able to carry out above-mentioned user recommendation side
Method to solve the problems, such as precisely understand that user is intended in the prior art, and then when carrying out commending contents, can react
The real-time requirement of user, meanwhile, the more quasi- intention for understanding user, and then be the content of user's recommendation precision.
Corresponding to the content recommendation method in Fig. 1, the embodiment of the present application also provides a kind of computer readable storage medium,
It is stored with computer program on the computer readable storage medium, which executes above content when being run by processor
The step of recommended method.
Specifically, which can be general storage medium, such as mobile disk, hard disk, on the storage medium
Computer program when being run, above content recommended method is able to carry out, to solve precisely understand in the prior art
The problem of user is intended to, and then when carrying out commending contents, the real-time requirement of user can be reacted, meanwhile, more quasi- understanding is used
The intention at family, and then be the content of user's recommendation precision.
In embodiment provided herein, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the present application can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application
Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen
It please be described in detail, those skilled in the art should understand that: anyone skilled in the art
Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution.The protection in the application should all be covered
Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (10)
1. a kind of content recommendation method, which is characterized in that this method comprises:
Historical interest data are obtained from default platform;Content category when the historical interest data include candidate user access content
Property information;
Based on the historical interest data, at least one interest tags structure, the interest tags structural characterization content category are constructed
Corresponding relationship between property information and content characteristic values;The content characteristic values are to be determined based on content attribute information;
According to the content attribute information of the browsing information representation of the user of acquisition and the interest tags structure, determines and be somebody's turn to do
The matched multiple content characteristic values of user;
Based on the mapping relations between the determining content characteristic values and preset content characteristic values and recommendation, really
The fixed and matched recommendation of the user, and recommend.
2. the method as described in claim 1, which is characterized in that the interest tags structure includes user interest structure;It is described
Based on the historical interest data, at least one interest tags structure is constructed, comprising:
It determines user property, from the historical interest data, counts the corresponding contents attribute of candidate user with the attribute
Information;
For each user property, the corresponding content attribute information of the attribute is screened according to the first preset condition, is based on
Content attribute information after screening establishes the corresponding relationship between content attribute information and content characteristic values, and then determines user
Interest structure;
Wherein, the first preset condition includes: the content attribute information, be located at the content attribute information access time before
Access time, corresponding content attribute information was identical.
3. the method as described in claim 1, which is characterized in that the interest tags structure includes content type interest structure;
It is described to be based on the historical interest data, construct at least one interest tags structure, comprising:
Based on preset multiple content types, from the historical interest data, candidate the using of the corresponding each content type of statistics
The content attribute information at family;
For each content type, the corresponding content attribute information of the content type is screened according to the second preset condition,
Based on the corresponding content attribute information of the content type after screening, pair between content attribute information and content characteristic values is established
It should be related to, and then determine content type interest structure;
Wherein, the second preset condition includes: the content attribute information, be located at the content attribute information access time before
Access time, corresponding content attribute information was identical.
4. the method as described in claim 1, which is characterized in that determine any content characteristic values W according to the following formula:
W=(Num-m)x/(T-t+n)y
Wherein, W is content characteristic values;Num is access times when candidate user accesses content, and m is the first decaying radix;N is
Second decaying radix;X is the decay factor of access times Num;Y is the decay factor of time;When T is user's current accessed content
Access time;T is access time when user accesses content for the first time.
5. the method as described in claim 1, which is characterized in that described based on the determining content characteristic values and default
Content characteristic values and recommendation between mapping relations, it is determining with the matched recommendation of the user, comprising:
The content characteristic values are ranked up, according to sequence from high to low, are selected from the content characteristic values after sequence pre-
If the content characteristic values of number;
Mapping relations between the content characteristic values and preset content characteristic values and recommendation based on selection, really
Surely the recommendation of each content characteristic values is corresponded to;
Based on the corresponding interest tags structure of each content characteristic values, the sequence of recommendation is determined.
6. a kind of content recommendation system, which is characterized in that the system includes:
Module is obtained, for obtaining historical interest data from default platform;The historical interest data include candidate user access
Content attribute information when content;
Module is constructed, for being based on the historical interest data, constructs at least one interest tags structure, the interest tags knot
Structure characterizes the corresponding relationship between content attribute information and content characteristic values;The content characteristic values are based on content attribute information
Determining;
First determining module, for according to the browsing information representation of the user of acquisition content attribute information and the interest
Label construction, the determining and matched multiple content characteristic values of the user;
Second determining module, for based on the determining content characteristic values and preset content characteristic values and recommendation
Between mapping relations, it is determining with the matched recommendation of the user, and recommend.
7. system as claimed in claim 6, which is characterized in that the interest tags structure includes user interest structure;It is described
Building module is specifically used for:
It determines user property, from the historical interest data, counts the corresponding contents attribute of candidate user with the attribute
Information;
For each user property, the corresponding content attribute information of the attribute is screened according to the first preset condition, is based on
Content attribute information after screening establishes the corresponding relationship between content attribute information and content characteristic values, and then determines user
Interest structure;
Wherein, the first preset condition includes: the content attribute information, be located at the content attribute information access time before
Access time, corresponding content attribute information was identical.
8. method as claimed in claim 6, which is characterized in that the interest tags structure includes content type interest structure;
The building module is specifically used for:
Based on preset multiple content types, from the historical interest data, candidate the using of the corresponding each content type of statistics
The content attribute information at family;
For each content type, the corresponding content attribute information of the content type is screened according to the second preset condition,
Based on the corresponding content attribute information of the content type after screening, pair between content attribute information and content characteristic values is established
It should be related to, and then determine content type interest structure;
Wherein, the second preset condition includes: the content attribute information, be located at the content attribute information access time before
Access time, corresponding content attribute information was identical.
9. system as claimed in claim 6, which is characterized in that the building module determines that any content is special according to the following formula
Value indicative W:
W=(Num-m)x/(T-t+n)y
Wherein, W is content characteristic values;Num is access times when candidate user accesses content, and m is the first decaying radix;N is
Second decaying radix;X is the decay factor of access times Num;Y is the decay factor of time;When T is user's current accessed content
Access time;T is access time when user accesses content for the first time.
10. system as claimed in claim 6, which is characterized in that second determining module is specifically used for:
The content characteristic values are ranked up, according to sequence from high to low, are selected from the content characteristic values after sequence pre-
If the content characteristic values of number;
Mapping relations between the content characteristic values and preset content characteristic values and recommendation based on selection, really
Surely the recommendation of each content characteristic values is corresponded to;
Based on the corresponding interest tags structure of each content characteristic values, the sequence of recommendation is determined.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810019351.5A CN110110201B (en) | 2018-01-09 | 2018-01-09 | Content recommendation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810019351.5A CN110110201B (en) | 2018-01-09 | 2018-01-09 | Content recommendation method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110110201A true CN110110201A (en) | 2019-08-09 |
CN110110201B CN110110201B (en) | 2021-10-08 |
Family
ID=67483098
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810019351.5A Active CN110110201B (en) | 2018-01-09 | 2018-01-09 | Content recommendation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110201B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110782290A (en) * | 2019-10-28 | 2020-02-11 | 苏州跃盟信息科技有限公司 | Media file processing method and device, storage medium and processor |
CN111180080A (en) * | 2019-12-30 | 2020-05-19 | 四川华迪信息技术有限公司 | Accurate pushing method for health knowledge base of old people |
CN111209474A (en) * | 2019-12-27 | 2020-05-29 | 广东德诚科教有限公司 | Online course recommendation method and device, computer equipment and storage medium |
CN112231563A (en) * | 2020-10-15 | 2021-01-15 | 腾讯科技(深圳)有限公司 | Content recommendation method and device and storage medium |
CN112818218A (en) * | 2021-01-21 | 2021-05-18 | 中国平安人寿保险股份有限公司 | Information recommendation method and device, terminal equipment and computer readable storage medium |
CN113407845A (en) * | 2021-07-14 | 2021-09-17 | 上海明略人工智能(集团)有限公司 | Method and device for information recommendation, electronic equipment and storage medium |
CN113420222A (en) * | 2021-07-08 | 2021-09-21 | 咪咕文化科技有限公司 | Content recommendation method and device |
CN113806605A (en) * | 2021-09-23 | 2021-12-17 | 深圳供电局有限公司 | Content recommendation method and system based on digital historical information |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103136275A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术(上海)有限公司 | System and method for recommending personalized video |
CN104090886A (en) * | 2013-12-09 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for constructing real-time portrayal of user |
US20150073931A1 (en) * | 2013-09-06 | 2015-03-12 | Microsoft Corporation | Feature selection for recommender systems |
CN104965889A (en) * | 2015-06-17 | 2015-10-07 | 腾讯科技(深圳)有限公司 | Content recommendation method and apparatus |
CN106919695A (en) * | 2017-03-07 | 2017-07-04 | 维沃移动通信有限公司 | A kind of information recommendation method and terminal |
CN107092629A (en) * | 2017-01-18 | 2017-08-25 | 北京小度信息科技有限公司 | Recommend method and device |
-
2018
- 2018-01-09 CN CN201810019351.5A patent/CN110110201B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103136275A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术(上海)有限公司 | System and method for recommending personalized video |
US20150073931A1 (en) * | 2013-09-06 | 2015-03-12 | Microsoft Corporation | Feature selection for recommender systems |
CN104090886A (en) * | 2013-12-09 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for constructing real-time portrayal of user |
CN104965889A (en) * | 2015-06-17 | 2015-10-07 | 腾讯科技(深圳)有限公司 | Content recommendation method and apparatus |
CN107092629A (en) * | 2017-01-18 | 2017-08-25 | 北京小度信息科技有限公司 | Recommend method and device |
CN106919695A (en) * | 2017-03-07 | 2017-07-04 | 维沃移动通信有限公司 | A kind of information recommendation method and terminal |
Non-Patent Citations (2)
Title |
---|
TOMAS DE LA ROSA等: ""Case-Based Recommendation for Node Ordering in Planning"", 《PROC. OF THE 20TH INTERNATIONAL FLAIRS CONFERENCE》 * |
缪平等: ""基于SVMs的微博信息推送同用户兴趣模型"", 《武汉理工大学学报(信息与管理工程版)》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110782290A (en) * | 2019-10-28 | 2020-02-11 | 苏州跃盟信息科技有限公司 | Media file processing method and device, storage medium and processor |
CN111209474A (en) * | 2019-12-27 | 2020-05-29 | 广东德诚科教有限公司 | Online course recommendation method and device, computer equipment and storage medium |
CN111180080A (en) * | 2019-12-30 | 2020-05-19 | 四川华迪信息技术有限公司 | Accurate pushing method for health knowledge base of old people |
CN112231563A (en) * | 2020-10-15 | 2021-01-15 | 腾讯科技(深圳)有限公司 | Content recommendation method and device and storage medium |
CN112231563B (en) * | 2020-10-15 | 2023-10-13 | 腾讯科技(深圳)有限公司 | Content recommendation method, device and storage medium |
CN112818218A (en) * | 2021-01-21 | 2021-05-18 | 中国平安人寿保险股份有限公司 | Information recommendation method and device, terminal equipment and computer readable storage medium |
CN113420222A (en) * | 2021-07-08 | 2021-09-21 | 咪咕文化科技有限公司 | Content recommendation method and device |
CN113407845A (en) * | 2021-07-14 | 2021-09-17 | 上海明略人工智能(集团)有限公司 | Method and device for information recommendation, electronic equipment and storage medium |
CN113806605A (en) * | 2021-09-23 | 2021-12-17 | 深圳供电局有限公司 | Content recommendation method and system based on digital historical information |
Also Published As
Publication number | Publication date |
---|---|
CN110110201B (en) | 2021-10-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110110201A (en) | A kind of content recommendation method and system | |
US20200242450A1 (en) | User behavior prediction method and apparatus, and behavior prediction model training method and apparatus | |
US10088974B2 (en) | Summarization and communication of large data sets | |
CN105023165A (en) | Method, device and system for controlling release tasks in social networking platform | |
CN106503269A (en) | Method, device and server that application is recommended | |
CN110413510B (en) | Data processing method, device and equipment | |
CN107888703A (en) | Information-pushing method, device, server and readable storage medium storing program for executing | |
CN108710711A (en) | Ranking results are shown on a mobile computing device | |
CN110503506A (en) | Item recommendation method, device and medium based on score data | |
CN109903076A (en) | A kind of ad data generation method, system, electronic equipment and storage medium | |
WO2008094786A2 (en) | Relevance slider in a site analysis report | |
CN105183295A (en) | Classification method for application icons and terminal | |
CN109117442A (en) | A kind of application recommended method and device | |
CN104809751A (en) | Method and device for generating event group evolution diagram | |
CN110020152B (en) | Application recommendation method and device | |
CN102315955A (en) | Control method for setting obstruction for junk information and corresponding control device | |
CN109446415A (en) | A kind of application recommendation, acquisition methods and equipment | |
CN110413926A (en) | A kind of questionnaire method and device | |
CN107944026A (en) | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation | |
CN110188276A (en) | Data sending device, method, electronic equipment and computer readable storage medium | |
CN109075987A (en) | Optimize digital assembly analysis system | |
CN112784159B (en) | Content recommendation method and device, terminal equipment and computer readable storage medium | |
CN103457944A (en) | Method and device for pushing information and server | |
CN106815285A (en) | The method of the video recommendations based on video website, device and electronic equipment | |
CN103179207A (en) | Data transmission method and system as well as device |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Li Dongjun Inventor after: Jiao Hongbo Inventor before: Jiao Hongbo |
|
GR01 | Patent grant | ||
GR01 | Patent grant |