CN106294794A - A kind of content recommendation method and device - Google Patents
A kind of content recommendation method and device Download PDFInfo
- Publication number
- CN106294794A CN106294794A CN201610670024.7A CN201610670024A CN106294794A CN 106294794 A CN106294794 A CN 106294794A CN 201610670024 A CN201610670024 A CN 201610670024A CN 106294794 A CN106294794 A CN 106294794A
- Authority
- CN
- China
- Prior art keywords
- data
- account
- historical behavior
- behavioural habits
- behavior data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
-
- 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
The present invention relates to Internet technical field, particularly relate to a kind of content recommendation method and device.The method includes: collect the same account historical behavior data at different terminals;Analyze described historical behavior data, and generate the behavioural habits that described account is corresponding;The terminal logged in the account that described behavioural habits are corresponding based on described behavioural habits carries out commending contents.Present invention achieves the same account the sharing of historical behavior data at different terminals, carry out the result of commending contents according to behavioural habits and more meet the demand of user, improve Consumer's Experience.
Description
Technical field
The present invention relates to Internet technical field, particularly relate to a kind of content recommendation method and device.
Background technology
Along with the development of communication technology and popularizing of terminal, obtain the user of content of multimedia increasingly in terminal
Many, and a lot of user has multiple terminal simultaneously, and such as one user has mobile phone, notebook computer and panel computer simultaneously
Deng.
At present, user's acquisition mode to content of multimedia, it is mostly directly to search in terminal in hope is watched perhaps
The page of recommending that person provides according to multimedia content provider selects the content oneself liked, and generally, user can be according to different fields
Scape selects suitable terminal to obtain content of multimedia, and such as, user is mobile phone viewing video accustomed to using on bus, and user
Video watched by notebook computer or computer that screen the most accustomed to using is bigger.
Inventor, during realizing the present invention, finds that correlation technique there is problems in that same user is in difference eventually
End uses historical behavior data produced by application program or website to be not carried out sharing, and especially these historical behavior data isolate
Be stored in each terminal, the user analyzed by these historical behavior data is for the hobby number of application content
Share according to can not realize.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of content recommendation method and device, solves same user's difference eventually
End uses the problem that historical behavior data produced by application program or website are not carried out sharing.
One aspect of the embodiment of the present invention, it is provided that a kind of content recommendation method, the method includes:
Collect the same account historical behavior data at different terminals;
Analyze described historical behavior data, and generate the behavioural habits that described account is corresponding;
The terminal logged in the account that described behavioural habits are corresponding based on described behavioural habits carries out commending contents.
Alternatively, the same account of described collection includes in the historical behavior data of different terminals:
The data space that the distribution of described same account is corresponding it is respectively in data base;
Collect the described same account historical behavior data at different terminals, described historical behavior data are added to described
The data space that same account is corresponding.
Alternatively, described analysis described historical behavior data, and the behavioural habits generating described account corresponding include:
Add up the frequency of every data in described historical behavior data respectively;
Choose described frequency and like data more than the data of the first predetermined threshold value as first, according to described first hobby number
The behavioural habits corresponding according to generating described account.
Alternatively, described analysis described historical behavior data, and the behavioural habits generating described account corresponding include:
According to preset rules, described historical behavior data are classified, generate at least one data according to described classification
Collection;
Add up the frequency of described data set respectively;
Choose described frequency and like data more than the data set of the second predetermined threshold value as second, according to described second hobby
The behavioural habits that account described in data genaration is corresponding.
Alternatively, described frequency includes accessing in remaining time, click volume, download, comment amount and the some amount of praising
Plant or multiple.
The another aspect of the embodiment of the present invention, it is provided that a kind of content recommendation device, this device includes:
Collection module, for collecting the same account historical behavior data at different terminals;
Analyze module, be used for analyzing described historical behavior data, and generate the behavioural habits that described account is corresponding;
Recommending module, is carried out for the terminal logged in the account that described behavioural habits are corresponding based on described behavioural habits
Commending contents.
Alternatively, described collection module includes:
Allocation unit, for being respectively the data space that the distribution of described same account is corresponding in data base;
Memory element, for collecting the described same account historical behavior data at different terminals, by described historical behavior
Data add the data space that extremely described same account is corresponding.
Alternatively, described analysis module includes:
First statistic unit, for adding up the frequency of every data in described historical behavior data respectively;
First selects unit, likes data more than the data of the first predetermined threshold value as first for choosing described frequency,
According to the behavioural habits that account described in described first hobby data genaration is corresponding.
Alternatively, described analysis module includes:
Taxon, for classifying described historical behavior data according to preset rules, generates according to described classification
At least one data set;
Second statistic unit, for adding up the frequency of described data set respectively;
Second chooses unit, likes several more than the data set of the second predetermined threshold value as second for choosing described frequency
According to, according to the behavioural habits that account described in described second hobby data genaration is corresponding.
Alternatively, described frequency includes accessing remaining time, visit capacity, click volume, download, comment amount and the some amount of praising
In one or more.
In embodiments of the present invention, by collecting same account in the historical behavior data of different terminals, and analyze this and go through
History behavioral data thus generate the behavioural habits that described account is corresponding, according to behavior custom to account corresponding to behavior custom
The terminal logged in carries out commending contents, on the one hand, achieve the historical behavior data that same account produces at different terminals
Share, on the other hand, carry out the result of commending contents according to behavioural habits and more meet the demand of user, improve Consumer's Experience.
Accompanying drawing explanation
One or more embodiments are illustrative by the picture in corresponding accompanying drawing, these exemplary theorys
Bright it is not intended that the restriction to embodiment, accompanying drawing has the element that the element of same reference numbers label is expressed as being similar to, removes
Non-have statement especially, and the not composition of the figure in accompanying drawing limits.
Fig. 1 is the structural representation of a kind of implementation environment involved by each embodiment of the present invention;
Fig. 2 is the schematic flow sheet of a kind of content recommendation method that the embodiment of the present invention one provides;
Fig. 3 is to collect same application account described in a kind of content recommendation method that the embodiment of the present invention two provides to exist
The schematic flow sheet of the method for the data that different terminals is browsed;
Fig. 4 is the schematic flow sheet of a kind of content recommendation method that the embodiment of the present invention three provides;
Fig. 5 is the schematic flow sheet of a kind of content recommendation method that the embodiment of the present invention four provides;
Fig. 6 is the structural representation of a kind of content recommendation device that the embodiment of the present invention five provides;
Fig. 7 is the structural representation of a kind of content recommendation device that the embodiment of the present invention six provides;
Fig. 8 is the structural representation of a kind of content recommendation device that the embodiment of the present invention seven provides;
Fig. 9 is the structural representation of a kind of electronic equipment that the embodiment of the present invention eight provides.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, right
The present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, not
For limiting the present invention.
Refer to Fig. 1, it illustrates the structural representation of a kind of implementation environment involved by each embodiment of the present invention, should
Implementation environment includes: terminal 100 and server 200.Wherein:
Terminal 100 can be mobile phone, panel computer, E-book reader, MP3 (Moving Picture Experts
Group Audio Layer III, dynamic image expert's compression standard audio frequency aspect 3) player, MP4 (Moving Picture
Experts Group Audio Layer IV, dynamic image expert's compression standard audio frequency aspect 4) player, on knee portable
Computer and desk computer etc..
Terminal 100 can be run browser, it is also possible to run and have other can load and show answering of Webpage
With program, such as video class application, payment class application, voice class application etc..
Terminal 100 is connected with server 200 by wireless network or cable network.
Server 200 can be a station server, or the server cluster being made up of some station servers, or one
Individual cloud computing service center.
Embodiment one
Refer to the schematic flow sheet that Fig. 2, Fig. 2 are a kind of content recommendation methods that the embodiment of the present invention one provides.Such as Fig. 2
Shown in, the method includes:
Step 11, collect the same account historical behavior data at different terminals.
In the present embodiment, described same account includes account or the account of same website of same application, described same
Account also includes, same account corresponding to multiple application and/or website, wherein, and same account corresponding to different application and/or website
Historical behavior data produced by number can be used for analyzing the behavioural habits of described account.
In the present embodiment, described historical behavior data are the exercisable data of user behavior, described historical behavior data
Including: video data, voice data, lteral data and image data etc..Corresponding user behavior includes: plays, browse, point
Praise, comment on, forwarding etc..
In the present embodiment, the same account of described collection is in the historical behavior data of different terminals, such as, uses A account
Have registered certain Video Applications, if A account has logged in, at notebook computer, the video website that this Video Applications is corresponding, and make at mobile phone
Having logged in this Video Applications by A account, then needed to collect respectively, this A account is produced after notebook computer logs in this video website
Raw historical behavior data, and the historical behavior data that this A account produces after mobile phone logs in this Video Applications, by the two
Historical behavior data as described A account in the historical behavior data of different terminals.
Step 12, analyze described historical behavior data, and generate the behavioural habits that described account is corresponding.
In the present embodiment, behavioural habits corresponding to described account are mainly determined by described historical behavior data, permissible
Content type according to described historical behavior data analyzes the behavioural habits that described account is corresponding, such as, described historical behavior number
According to for video data, then according to video content, described video can be divided into sport category, variety class, TV-like etc., classification
Result is as the behavioural habits of described account;The temperature of described historical behavior data can also be analyzed, it is judged that described historical behavior
Whether data are hot spot datas, using analysis result as behavioural habits corresponding to described account, such as, described historical behavior data
For TV play and the song of click volume first of playback volume first, then can show that the behavioural habits of this account are that custom obtains
The content that temperature is higher;Further, it is also possible to analyze described historical behavior data by other means, thus generate described account
Number corresponding behavioural habits.
Step 13, carry out content based on described behavioural habits to the terminal that the account that described behavioural habits are corresponding is logged in and push away
Recommend.
Such as, the A account obtaining a certain video website has been analyzed at the behavioural habits of this video website, then, Ke Yigen
The terminal logged in A account according to behavior custom carries out commending contents, it should be noted that this terminal can be multiple difference
Terminal, this video website can be identical or different video website, logs in as long as being ensured of this A account.Wherein, may be used
To carry out commending contents by the transmission mode such as note, PUSH message to terminal.
The embodiment of the present invention, by collecting the same account historical behavior data at different terminals, and analyzes this history row
For data thus generate the behavioural habits that described account is corresponding, stepped on to the account that behavior custom is corresponding according to behavior custom
The terminal of record carries out commending contents, on the one hand, achieve the shared of the historical behavior data that same account produces at different terminals,
On the other hand, carry out the result of commending contents according to behavioural habits and more meet the demand of user, improve Consumer's Experience.
Embodiment two
On the basis of embodiment one, the embodiment of the present invention two proposes another kind of content recommendation method, as in figure 2 it is shown, should
Method includes:
Step 11, collect the same account historical behavior data at different terminals.
As it is shown on figure 3, in the present embodiment, the same account of described collection includes in the historical behavior data of different terminals:
Step 111, the data space that respectively distribution of described same account is corresponding in data base.
Step 112, collect the described same account historical behavior data at different terminals, described historical behavior data are added
Add to the data space that described same account is corresponding.
It is understood that different application or website can corresponding different accounts, it is also possible to corresponding same account, with
One account can log in application corresponding to this account or website over multiple terminals.Described historical behavior data include: video counts
According to, voice data, lteral data and image data etc..In the present embodiment, the most same account distributes corresponding data
Memory space, such that it is able to collect the same account historical behavior data at different terminals respectively.
Such as, the account of certain Video Applications is A, and the account of certain music application is B, and account A is browsed at different terminals
Data are stored in the data space that this account A is corresponding, and account B is stored in this account B in the data that different terminals is browsed
Corresponding data space.
Step 12, analyze described historical behavior data, and generate the behavioural habits that described account is corresponding.
Step 13, carry out content based on described behavioural habits to the terminal that the account that described behavioural habits are corresponding is logged in and push away
Recommend.
It should be noted that the present embodiment step 12-13 refers to the narration of embodiment one, here is omitted.
The embodiment of the present invention, collects the different account historical behavior data at different terminals respectively, and is that different account is produced
Raw historical behavior data are respectively allocated different data spaces, generate each by analyzing described historical behavior data
The behavioural habits that account is corresponding, carry out content according to behavior custom to the terminal that the account that behavior custom is corresponding is logged in and push away
Recommend, on the one hand, achieve sharing, on the other hand, according to behavior of the historical behavior data that same account produces at different terminals
Custom carries out the result of commending contents and more meets the demand of user, improves Consumer's Experience.
Embodiment three
Refer to the schematic flow sheet that Fig. 4, Fig. 4 are a kind of content recommendation methods that the embodiment of the present invention three provides.Such as Fig. 4
Shown in, the method includes:
Step 21, collect the same account historical behavior data at different terminals.
Step 22, add up the frequency of every data in described historical behavior data respectively.
In the present embodiment, described frequency includes accessing remaining time, click volume, download, comment amount and the some amount of praising
In one or more, wherein this access remaining time is the duration that described historical behavior data are played or browsed, and needs
Illustrating, this access remaining time, click volume and download, comment amount and the some amount of praising are the historical behavior that this account is corresponding
The access remaining time of data, click volume, download, comment amount and the some amount of praising.
In the present embodiment, by specific algorithm add up the access remaining time of every data and/or click volume and/or
Download and/or comment amount and/or the summation of the some amount of praising, this summation is as the frequency of these data.
Further, it is to be appreciated that described access remaining time, click volume, download, comment amount and the some amount of praising etc. are equal
For the behavior of user, further, it is also possible to the behavior of described user is respectively provided with weight, by described weight and described weight
The summation of the statistical magnitude of corresponding user behavior is as described frequency, and wherein, described user behavior can give identical power
Weight or each behavior give different weights.
Step 23, choose the described frequency data more than the first predetermined threshold value as the first hobby data, according to described the
The behavioural habits that account described in one hobby data genaration is corresponding.
It is understood that i.e. choose the access remaining time of data and/or click volume and/or download and/or comment
The summation of amount and/or the some amount of praising is more than the data of the first predetermined threshold value, as the first hobby data, and this first hobby data reflection
The pouplarity of these historical behavior data.Further, analyze this first hobby data, and determine behavioural habits, such as,
Determine the classification etc. of the content that this account likes browsing.
Step 24, carry out content based on described behavioural habits to the terminal that the account that described behavioural habits are corresponding is logged in and push away
Recommend.
It should be noted that the present embodiment step 21, step 24 refer to the narration of embodiment one, here is omitted.
The embodiment of the present invention, by collecting the same account historical behavior data at different terminals, and statistics is described respectively
The frequency of every data in historical behavior data, is used for generating behavioural habits more than the data of the first predetermined threshold value by frequency.One
Aspect, it is achieved that sharing, on the other hand, according to described historical behavior of the historical behavior data produced at different terminals with account
The frequency of data determines behavioural habits and carries out commending contents, and the result of this recommendation is more accurate, improves Consumer's Experience.
Embodiment four
Refer to the schematic flow sheet that Fig. 5, Fig. 5 are a kind of content recommendation methods that the embodiment of the present invention four provides.Such as Fig. 5
Shown in, the method includes:
Step 31, collect the same account historical behavior data at different terminals.
Step 32, according to preset rules, described historical behavior data are classified, generate at least one according to described classification
Individual data set.
In the present embodiment, the class of described historical behavior data can be determined according to the content of described historical behavior data
Not, such as, video class, word class, audio class etc., further, described video class includes sport category, film class, amusement class etc.,
Described word class includes that short essay, novel, news release etc., described audio class include popular, classic, external, Chinese etc..No
The most corresponding data set of same classification results.
Step 33, add up the frequency of described data set respectively.
In the present embodiment, described frequency includes accessing remaining time, click volume, download, comment amount and the some amount of praising
In one or more, wherein this access remaining time is the duration that described historical behavior data are played or browsed, and needs
Illustrating, this access remaining time, click volume and download, comment amount and the some amount of praising are the historical behavior that this account is corresponding
The access remaining time of data, click volume, download, comment amount and the some amount of praising.
In the present embodiment, by specific algorithm add up the access remaining time of every data and/or click volume and/or
Download and/or comment amount and/or the summation of the some amount of praising, this summation is as the frequency of these data.
Further, it is to be appreciated that described access remaining time, click volume, download, comment amount and the some amount of praising etc. are equal
For the behavior of user, further, it is also possible to the behavior of described user is respectively provided with weight, by described weight and described weight
The summation of the statistical magnitude of corresponding user behavior is as described frequency, and wherein, described user behavior can give identical power
Weight or each behavior give different weights.
In another embodiment, described access remaining time, click volume, download, comment amount and the some amount of praising include net
Access remaining time, click volume, download, comment amount and the some amount of praising that the account of network user is corresponding.Can use based on network
The account at family, adds up the frequency of described data set, so that it is determined that the degree that this data set is welcome by masses.
Step 34, choose described frequency more than the second predetermined threshold value data set as second hobby data, according to described
The behavioural habits that account described in second hobby data genaration is corresponding.
It is understood that i.e. choose the access remaining time of data intensive data and/or click volume and/or download
And/or the summation of comment amount and/or the some amount of praising is more than the data set of the second predetermined threshold value, as the second hobby data, this is second years old
Hobby data reflect the pouplarity of this data set.Further, analyze this second hobby data, and determine described account
Corresponding behavioural habits, such as, determine that the behavioural habits of this account are audio class.
Step 35, carry out content based on described behavioural habits to the terminal that the account that described behavioural habits are corresponding is logged in and push away
Recommend.
It should be noted that the present embodiment step 31, step 35 refer to the narration of embodiment one, here is omitted.
The embodiment of the present invention, by collecting the same account historical behavior data at different terminals, and to described history row
Carry out classifying for data and obtain different classes of data set, determine behavioural habits according to the frequency of data set.On the one hand, it is achieved that
Same account different terminals historical behavior data share, on the other hand, the frequency of data set determine that behavioural habits are also
Carrying out commending contents, the result of this recommendation is more accurate, improves Consumer's Experience.
Embodiment five
Refer to the structural representation that Fig. 6, Fig. 6 are a kind of content recommendation devices that the embodiment of the present invention five provides.Such as Fig. 6
Shown in, this device 50 includes: collection module 501, analysis module 502 and recommending module 503.
In the present embodiment, described collection module 501, for collecting the same account historical behavior number at different terminals
According to;Described analysis module 502, is used for analyzing described historical behavior data, and generates the behavioural habits that described account is corresponding;Described
Recommending module 503, carries out content for the terminal logged in the account that described behavioural habits are corresponding based on described behavioural habits
Recommend.
In the present embodiment, the same account collected is sent to dividing by collection module in the historical behavior data of different terminals
Analysis module, is analyzed by described analysis module, thus generates the behavioural habits of described historical behavior data, described recommending module
Commending contents is carried out based on behavior custom.
What deserves to be explained is, the content such as the information between module in said apparatus is mutual, execution process, due to this
Bright embodiment of the method one is based on same design, and particular content can be found in the narration in the inventive method embodiment one, the most not
Repeat again.
The embodiment of the present invention, by collecting the same account historical behavior data at different terminals, and analyzes this collection
Historical behavior data thus generate behavioural habits, the terminal logged in the account that behavior custom is corresponding according to behavior custom
Carry out commending contents, on the one hand, achieve same account different terminals historical behavior data share, on the other hand, root
Carry out the result of commending contents according to behavioural habits and more meet the demand of user, improve Consumer's Experience.
Embodiment six
Refer to the structural representation that Fig. 7, Fig. 7 are a kind of content recommendation devices that the embodiment of the present invention six provides.Such as Fig. 7
Shown in, this device 60 includes: collection module 601, analysis module 602 and recommending module 603.
In the present embodiment, described collection module 601 is for collecting the same account historical behavior data at different terminals.
Further, described collection module 601 includes: allocation unit 6011, divides for being respectively described same account in data base
The data space that pairing is answered;Memory element 6012, for collecting the described same account historical behavior number at different terminals
According to, described historical behavior data are added the data space that extremely described same account is corresponding.
In the present embodiment, described analysis module 602 is used for analyzing described historical behavior data, and generates described account pair
The behavioural habits answered.Further, described analysis module 602 includes: the first statistic unit 6021, for going through described in statistics respectively
The frequency of every data in history behavioral data;First selects unit 6022, is used for choosing described frequency more than the first predetermined threshold value
Data as the first hobby data, according to behavioural habits corresponding to account described in described first hobby data genaration.
In the present embodiment, described recommending module 603 is for corresponding to described behavioural habits based on described behavioural habits
The terminal that account is logged in carries out commending contents.
What deserves to be explained is, the content such as the information between module in said apparatus, unit is mutual, execution process, due to
With embodiment of the method one, embodiment two and the embodiment three of the present invention based on same design, particular content can be found in side of the present invention
Narration in method embodiment one, embodiment two and embodiment three, here is omitted.
The embodiment of the present invention, by collecting the same account historical behavior data at different terminals, and statistics is described respectively
The frequency of every data in historical behavior data, is used for generating behavioural habits more than the data of the first predetermined threshold value by frequency.One
Aspect, it is achieved that same account different terminals historical behavior data share, on the other hand, the frequency of data determine row
For being accustomed to and carrying out commending contents, the result of this recommendation is more accurate, improves Consumer's Experience.
Embodiment seven
Refer to the structural representation that Fig. 8, Fig. 8 are a kind of content recommendation devices that the embodiment of the present invention seven provides.Such as Fig. 8
Shown in, this device 70 includes: collection module 701, analysis module 702 and recommending module 703.
In the present embodiment, described collection module 701 is for collecting the same account historical behavior data at different terminals.
Further, described collection module 701 includes: allocation unit 7011, divides for being respectively described same account in data base
The data space that pairing is answered;Memory element 7012, for collecting the described same account historical behavior number at different terminals
According to, described historical behavior data are added the data space that extremely described same account is corresponding.
In the present embodiment, described analysis module 702 is used for analyzing described historical behavior data, and generates described account pair
The behavioural habits answered.Further, described analysis module 702 includes: taxon 7021, is used for according to preset rules described
Historical behavior data are classified, and generate at least one data set according to classification;Second statistic unit 7022, for adding up respectively
The frequency of described data set;Second selects unit 7023, makees more than the data set of the second predetermined threshold value for choosing described frequency
It is the second hobby data, according to the behavioural habits that account described in described second hobby data genaration is corresponding.
In the present embodiment, described recommending module 703 is for corresponding to described behavioural habits based on described behavioural habits
The terminal that account is logged in carries out commending contents.
What deserves to be explained is, the content such as the information between module in said apparatus, unit is mutual, execution process, due to
With embodiment of the method one, embodiment two and the embodiment four of the present invention based on same design, particular content can be found in side of the present invention
Narration in method embodiment one, embodiment two and embodiment four, here is omitted.
The embodiment of the present invention, by collecting the same account historical behavior data at different terminals, and to described history row
Carry out classifying for data and obtain different classes of data set, determine behavioural habits according to the frequency of data set.On the one hand, it is achieved that
By the frequency of data set, sharing of the historical behavior data that same account produces at different terminals, on the other hand, determines that behavior is practised
Being used to and carry out commending contents, the result of this recommendation is more accurate, improves Consumer's Experience.
Embodiment eight
Refer to the structural representation that Fig. 9, Fig. 9 are a kind of electronic equipments that the embodiment of the present invention eight provides, such as Fig. 9 institute
Showing, this equipment 80 includes one or more processor 801 and memorizer 802.Wherein, Fig. 9 with a processor 801 is
Example.
The electronic equipment performing content recommendation method can also include input equipment 803 and output device 804.Processor
801, memorizer 802, input equipment 803 and output device 804 can be connected by bus or other modes, with logical in Fig. 9
As a example by crossing bus connection.
Memorizer 802, as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module, program as corresponding in the content recommendation method in the embodiment of the present invention
Instruction or module, such as, the collection module 501 shown in accompanying drawing 6, analysis module 502 and recommending module 503, or accompanying drawing 7 institute
The modules shown.Non-volatile software program, instruction and the mould that processor 801 is stored in memorizer 802 by operation
Block, thus perform the application of various functions and the data process of server, i.e. realize said method embodiment content recommendation method.
Memorizer 802 can include storing program area and storage data field, and wherein, storage program area can store operation system
Application program required for system, at least one function;Storage data field can store the number that the use according to searcher is created
According to etc..Additionally, memorizer 802 can include high-speed random access memory, it is also possible to include nonvolatile memory, the most extremely
A few disk memory, flush memory device or other non-volatile solid state memory parts.In certain embodiments, memorizer
802 optional include the memorizer remotely located relative to processor 801, and these remote memories can be connected to regard by network
Frequently pre-viewing device.The example of above-mentioned network include but not limited to the Internet, intranet, LAN, mobile radio communication and
Combination.
Input equipment 803 can receive numeral or the character information of input, and produce the user with content recommendation device and set
Put and function controls relevant key signals input.Output device 804 can include the display devices such as display screen.
One or more module stores is in described memorizer 802, when by one or more processor
During 801 execution, perform the content recommendation method in above-mentioned any means embodiment.
Through the above description of the embodiments, those skilled in the art it can be understood that to each embodiment can
The mode adding required general hardware platform by software realizes, naturally it is also possible to pass through hardware.Based on such understanding, on
State the part that prior art contributes by technical scheme the most in other words to embody with the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD etc., including some fingers
Make with so that a computer equipment (can be personal computer, server, or the network equipment etc.) performs each and implements
The method described in some part of example or embodiment.
In embodiments of the present invention, by collecting same account in the historical behavior data of different terminals, and analyze this and go through
History behavioral data thus generate behavioural habits, enter according to the terminal that behavior custom is logged in the account that behavior custom is corresponding
Row commending contents, on the one hand, achieve same account different terminals historical behavior data share, on the other hand, according to
Behavioural habits carry out the result of commending contents and more meet the demand of user, improve Consumer's Experience.Described electronic equipment can perform
The method that the embodiment of the present invention is provided, possesses the corresponding functional module of execution method and beneficial effect.The most in the present embodiment
The ins and outs of detailed description, can be found in the method that the embodiment of the present invention is provided.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all essences in the present invention
Any amendment, equivalent and the improvement etc. made within god and principle, should be included within the scope of the present invention.
Claims (10)
1. a content recommendation method, it is characterised in that described method includes:
Collect the same account historical behavior data at different terminals;
Analyze described historical behavior data, and generate the behavioural habits that described account is corresponding;
The terminal logged in the account that described behavioural habits are corresponding based on described behavioural habits carries out commending contents.
Method the most according to claim 1, it is characterised in that the same account of described collection is at the historical behavior of different terminals
Data include:
The data space that the distribution of described same account is corresponding it is respectively in data base;
Collect the described same account historical behavior data at different terminals, described historical behavior data are added to described same
The data space that account is corresponding.
Method the most according to claim 1, it is characterised in that described analysis described historical behavior data, and generate described
Behavioural habits corresponding to account include:
Add up the frequency of every data in described historical behavior data respectively;
Choose described frequency and like data more than the data of the first predetermined threshold value as first, raw according to described first hobby data
Become the behavioural habits that described account is corresponding.
Method the most according to claim 1, it is characterised in that described analysis described historical behavior data, and generate described
Behavioural habits corresponding to account include:
According to preset rules, described historical behavior data are classified, generate at least one data set according to described classification;
Add up the frequency of described data set respectively;
Choose described frequency and like data more than the data set of the second predetermined threshold value as second, according to described second hobby data
Generate the behavioural habits that described account is corresponding.
5. according to the method described in claim 3 or 4, it is characterised in that described frequency include access remaining time, click volume,
One or more in download, comment amount and the some amount of praising.
6. a content recommendation device, it is characterised in that described device includes:
Collection module, for collecting the same account historical behavior data at different terminals;
Analyze module, be used for analyzing described historical behavior data, and generate the behavioural habits that described account is corresponding;
Recommending module, carries out content for the terminal logged in the account that described behavioural habits are corresponding based on described behavioural habits
Recommend.
Device the most according to claim 6, it is characterised in that described collection module includes:
Allocation unit, for being respectively the data space that the distribution of described same account is corresponding in data base;
Memory element, for collecting the described same account historical behavior data at different terminals, by described historical behavior data
Add the data space that extremely described same account is corresponding.
Device the most according to claim 6, it is characterised in that described analysis module includes:
First statistic unit, for adding up the frequency of every data in described historical behavior data respectively;
First selects unit, likes data more than the data of the first predetermined threshold value as first for choosing described frequency, according to
The behavioural habits that account described in described first hobby data genaration is corresponding.
Device the most according to claim 6, it is characterised in that described analysis module includes:
Taxon, for classifying described historical behavior data according to preset rules, generates at least according to described classification
One data set;
Second statistic unit, for adding up the frequency of described data set respectively;
Second selects unit, for choosing the described frequency data set more than the second predetermined threshold value as the second hobby data, root
According to the behavioural habits that account described in described second hobby data genaration is corresponding.
Device the most according to claim 8 or claim 9, it is characterised in that described frequency include access remaining time, click volume,
One or more in download, comment amount and the some amount of praising.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610670024.7A CN106294794A (en) | 2016-08-15 | 2016-08-15 | A kind of content recommendation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610670024.7A CN106294794A (en) | 2016-08-15 | 2016-08-15 | A kind of content recommendation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106294794A true CN106294794A (en) | 2017-01-04 |
Family
ID=57670652
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610670024.7A Pending CN106294794A (en) | 2016-08-15 | 2016-08-15 | A kind of content recommendation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106294794A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766223A (en) * | 2017-11-06 | 2018-03-06 | 泰康保险集团股份有限公司 | The processing method and processing device of user's operation behavior trace information |
CN108182626A (en) * | 2017-12-28 | 2018-06-19 | 努比亚技术有限公司 | Service push method, information acquisition terminal and computer readable storage medium |
CN108924263A (en) * | 2018-08-21 | 2018-11-30 | 安徽讯飞智能科技有限公司 | A method of based on terminal space-time data to terminal pushed information |
CN110188280A (en) * | 2019-05-31 | 2019-08-30 | 三角兽(北京)科技有限公司 | A kind of content recommendation method, device, electronic equipment and computer-readable medium |
CN110276017A (en) * | 2019-06-28 | 2019-09-24 | 百度在线网络技术(北京)有限公司 | A kind of data analysing method and device |
CN110287339A (en) * | 2019-06-28 | 2019-09-27 | 百度在线网络技术(北京)有限公司 | A kind of broadcasting upgrade method and device |
CN110532472A (en) * | 2019-08-28 | 2019-12-03 | 百度在线网络技术(北京)有限公司 | Content synchronization recommended method, device, electronic equipment and storage medium |
CN111385658A (en) * | 2018-12-28 | 2020-07-07 | 深圳Tcl新技术有限公司 | Control method and control system for account information synchronization among multiple devices |
CN111538912A (en) * | 2020-07-07 | 2020-08-14 | 腾讯科技(深圳)有限公司 | Content recommendation method, device, equipment and readable storage medium |
CN111859136A (en) * | 2020-07-23 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Personalized recommendation method, device, equipment and readable storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103745384A (en) * | 2013-12-31 | 2014-04-23 | 北京百度网讯科技有限公司 | Method and device for providing information to user equipment |
CN103886090A (en) * | 2014-03-31 | 2014-06-25 | 北京搜狗科技发展有限公司 | Content recommendation method and device based on user favorites |
CN104735158A (en) * | 2015-03-31 | 2015-06-24 | 北京奇艺世纪科技有限公司 | Sorted storage method and device for user behavior data |
CN105095355A (en) * | 2015-06-19 | 2015-11-25 | 小米科技有限责任公司 | Website recommendation method and apparatus |
CN105205086A (en) * | 2014-06-30 | 2015-12-30 | 小米科技有限责任公司 | Sharing method and device for application program using information |
US20160066120A1 (en) * | 2014-08-29 | 2016-03-03 | Naver Corporation | System and method for collecting usage history of smartphone, recommending user fitting application, and providing research service based on reward using smartphone optimizing application |
CN105677715A (en) * | 2015-12-29 | 2016-06-15 | 海信集团有限公司 | Multiuser-based video recommendation method and apparatus |
-
2016
- 2016-08-15 CN CN201610670024.7A patent/CN106294794A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103745384A (en) * | 2013-12-31 | 2014-04-23 | 北京百度网讯科技有限公司 | Method and device for providing information to user equipment |
CN103886090A (en) * | 2014-03-31 | 2014-06-25 | 北京搜狗科技发展有限公司 | Content recommendation method and device based on user favorites |
CN105205086A (en) * | 2014-06-30 | 2015-12-30 | 小米科技有限责任公司 | Sharing method and device for application program using information |
US20160066120A1 (en) * | 2014-08-29 | 2016-03-03 | Naver Corporation | System and method for collecting usage history of smartphone, recommending user fitting application, and providing research service based on reward using smartphone optimizing application |
CN104735158A (en) * | 2015-03-31 | 2015-06-24 | 北京奇艺世纪科技有限公司 | Sorted storage method and device for user behavior data |
CN105095355A (en) * | 2015-06-19 | 2015-11-25 | 小米科技有限责任公司 | Website recommendation method and apparatus |
CN105677715A (en) * | 2015-12-29 | 2016-06-15 | 海信集团有限公司 | Multiuser-based video recommendation method and apparatus |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766223B (en) * | 2017-11-06 | 2021-06-01 | 泰康保险集团股份有限公司 | Processing method and device for user operation behavior track information |
CN107766223A (en) * | 2017-11-06 | 2018-03-06 | 泰康保险集团股份有限公司 | The processing method and processing device of user's operation behavior trace information |
CN108182626A (en) * | 2017-12-28 | 2018-06-19 | 努比亚技术有限公司 | Service push method, information acquisition terminal and computer readable storage medium |
CN108924263A (en) * | 2018-08-21 | 2018-11-30 | 安徽讯飞智能科技有限公司 | A method of based on terminal space-time data to terminal pushed information |
CN111385658B (en) * | 2018-12-28 | 2022-07-29 | 深圳Tcl新技术有限公司 | Control method and control system for account information synchronization among multiple devices |
CN111385658A (en) * | 2018-12-28 | 2020-07-07 | 深圳Tcl新技术有限公司 | Control method and control system for account information synchronization among multiple devices |
CN110188280A (en) * | 2019-05-31 | 2019-08-30 | 三角兽(北京)科技有限公司 | A kind of content recommendation method, device, electronic equipment and computer-readable medium |
CN110188280B (en) * | 2019-05-31 | 2022-03-01 | 腾讯科技(深圳)有限公司 | Content recommendation method and device, electronic equipment and computer readable medium |
US11138260B2 (en) | 2019-06-28 | 2021-10-05 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for determining output information |
CN110287339A (en) * | 2019-06-28 | 2019-09-27 | 百度在线网络技术(北京)有限公司 | A kind of broadcasting upgrade method and device |
CN110276017A (en) * | 2019-06-28 | 2019-09-24 | 百度在线网络技术(北京)有限公司 | A kind of data analysing method and device |
CN110532472A (en) * | 2019-08-28 | 2019-12-03 | 百度在线网络技术(北京)有限公司 | Content synchronization recommended method, device, electronic equipment and storage medium |
CN110532472B (en) * | 2019-08-28 | 2022-09-27 | 百度在线网络技术(北京)有限公司 | Content synchronous recommendation method and device, electronic equipment and storage medium |
CN111538912B (en) * | 2020-07-07 | 2020-12-25 | 腾讯科技(深圳)有限公司 | Content recommendation method, device, equipment and readable storage medium |
CN111538912A (en) * | 2020-07-07 | 2020-08-14 | 腾讯科技(深圳)有限公司 | Content recommendation method, device, equipment and readable storage medium |
CN111859136A (en) * | 2020-07-23 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Personalized recommendation method, device, equipment and readable storage medium |
CN111859136B (en) * | 2020-07-23 | 2024-03-15 | 深圳前海微众银行股份有限公司 | Personalized recommendation method, device, equipment and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106294794A (en) | A kind of content recommendation method and device | |
US11409792B2 (en) | System and method for streaming individualized media content | |
CN106326391B (en) | Multimedia resource recommendation method and device | |
KR102008000B1 (en) | Computing similarity between media programs | |
CN106503025B (en) | Application recommendation method and system | |
US20170169040A1 (en) | Method and electronic device for recommending video | |
CN108595492B (en) | Content pushing method and device, storage medium and electronic device | |
CN103886090A (en) | Content recommendation method and device based on user favorites | |
US11048771B1 (en) | Method and system for providing organized content | |
CN104079960A (en) | File recommending method and device | |
CN107592572B (en) | Video recommendation method, device and equipment | |
CN109511015A (en) | Multimedia resource recommended method, device, storage medium and equipment | |
CN103096139A (en) | Video relevant recommendation method and server | |
CN112100221A (en) | Information recommendation method and device, recommendation server and storage medium | |
CN109977313A (en) | The recommended method and system of learner model construction method, education resource | |
CN109446415A (en) | A kind of application recommendation, acquisition methods and equipment | |
JP6434954B2 (en) | Information processing apparatus, information processing method, and program | |
CN109819002A (en) | Data push method and device, storage medium and electronic device | |
CN107562847A (en) | Information processing method and related product | |
CN106294417A (en) | A kind of data reordering method, device and electronic equipment | |
US9330181B2 (en) | Methods and apparatuses for document processing at distributed processing nodes | |
KR101423690B1 (en) | Contents recommendation system and method based on social network | |
KR20200029822A (en) | Providing Method of parameter for advertisement and server device supporting the same | |
ur Rehman et al. | Frequency-based similarity measure for multimedia recommender systems | |
CN104991973B (en) | A kind of determination method and apparatus in user interest field |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170104 |
|
WD01 | Invention patent application deemed withdrawn after publication |