CN105975535A - Recommendation method and device for multimedia resource - Google Patents

Recommendation method and device for multimedia resource Download PDF

Info

Publication number
CN105975535A
CN105975535A CN201610282384.XA CN201610282384A CN105975535A CN 105975535 A CN105975535 A CN 105975535A CN 201610282384 A CN201610282384 A CN 201610282384A CN 105975535 A CN105975535 A CN 105975535A
Authority
CN
China
Prior art keywords
user
resource
recommended
multimedia resource
multimedia
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
Application number
CN201610282384.XA
Other languages
Chinese (zh)
Inventor
胡壁
吕红亮
单明辉
尹玉宗
林岳
姚键
顾思斌
潘柏宇
王冀
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba China Co Ltd
Original Assignee
1Verge Internet Technology Beijing Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 1Verge Internet Technology Beijing Co Ltd filed Critical 1Verge Internet Technology Beijing Co Ltd
Priority to CN201610282384.XA priority Critical patent/CN105975535A/en
Publication of CN105975535A publication Critical patent/CN105975535A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43Querying
    • G06F16/435Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search 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)
  • Multimedia (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The invention discloses a recommendation method and device for a multimedia resource. The recommendation method comprises the following steps of determining a target user visiting a first multimedia resource according to the first multimedia resource visited by a reference user, wherein the number of visits of the first multimedia resource in a predetermined time period is smaller than a predetermined threshold; determining a recommendation weight value of a to-be-recommended resource according to feature information of the first multimedia resource, wherein the to-be-recommended resource is a multimedia resource except for the first multimedia resource in the multimedia resources visited by the reference user; and recommending the to-be-recommended resource to a target user according to the recommendation weight value of the to-be-recommended resource. According to the method and the device, the multimedia resource which is visited by the reference user and is not visited by the target user can be recommended to the target user having the same preference as the reference user, so that the accuracy for recommendation to the target user can be improved, the recommendation can be carried out on the target user quickly and effectively, and the user experience is good.

Description

The recommendation method and apparatus of multimedia resource
Technical field
The present invention relates to Internet technical field, particularly relate to the recommendation method and apparatus of a kind of multimedia resource.
Background technology
It is currently, there are and first calculates user's similar matrix in viewing behavior between any two, carry out according still further to similar matrix The recommendation method recommended.But, this recommendation method is computationally intensive and recommendation effect is the most bad.
Summary of the invention
Technical problem
In view of this, the technical problem to be solved in the present invention is, how to improve the accuracy recommending multimedia resource.
Solution
In order to solve above-mentioned technical problem, in first aspect, the invention provides a kind of recommendation method of multimedia resource, Including:
According to the first multimedia resource accessed with reference to user, determine the target accessing described first multimedia resource User, wherein, described first multimedia resource is the multimedia being accessed for number of times within a predetermined period of time less than predetermined threshold Resource;
According to the characteristic information of described first multimedia resource, determine the advowson weight values of resource to be recommended, wherein, described Resource to be recommended is the many matchmakers in addition to described first multimedia resource in the multimedia resource that described reference user is accessed Body resource;And
According to the advowson weight values of described resource to be recommended, recommend described resource to be recommended to described targeted customer.
In conjunction with first aspect, in the implementation that the first is possible, described characteristic information be finish playing than feelings Under condition, the described characteristic information according to described first multimedia resource, determine the advowson weight values of resource to be recommended, including:
According to described with reference to user for described first multimedia resource finish playing than with described targeted customer for The ratio that finishes playing of described first multimedia resource, determines the advowson weight values of described resource to be recommended.
In conjunction with the first possible implementation of first aspect, in the implementation that the second is possible, determining One with reference in the case of user, described according to described with reference to user for described first multimedia resource finish playing than with Described targeted customer, for the ratio that finishes playing of described first multimedia resource, determines the recommendation weight of described resource to be recommended Value, including:
By described with reference to user for each first multimedia resource finish playing than respectively with described targeted customer for Corresponding first multimedia resource finish playing than and this three of time decay factor of presetting be multiplied, and after being multiplied Value is added, as the advowson weight values of described resource to be recommended.
In conjunction with the first possible implementation of first aspect, in the implementation that the third is possible, determining The situation comprising identical resource to be recommended in the multimedia resource that multiple reference users and the plurality of reference user are accessed Under, described according to described with reference to user for described first multimedia resource finish playing than with described targeted customer for institute State the ratio that finishes playing of the first multimedia resource, determine the advowson weight values of described resource to be recommended, including:
For each with reference to user, by this reference user for the ratio that finishes playing of each first multimedia resource respectively with described Targeted customer for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied;
Will for each be multiplied with reference to user after value be added, and the value after will add up is defined as described identical money to be recommended The advowson weight values in source.
In conjunction with the first possible implementation of first aspect, in the 4th kind of possible embodiment, determining The situation comprising different resources to be recommended in the multimedia resource that multiple reference users and the plurality of reference user are accessed Under, described according to described with reference to user for described first multimedia resource finish playing than with described targeted customer for institute State the ratio that finishes playing of the first multimedia resource, determine the advowson weight values of described resource to be recommended, including:
For each with reference to user, by this reference user for the ratio that finishes playing of each first multimedia resource respectively with described Targeted customer for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, And the value after being multiplied is added, as the recommendation weight of the to be recommended resource different from other reference user of this reference user Value,
The described advowson weight values according to described resource to be recommended, recommends described resource to be recommended to described targeted customer, Including:
According to the advowson weight values of the described different resource to be recommended determined, described different resource to be recommended is entered Row sequence, to generate the recommendation list of described targeted customer.
In conjunction with the third possible implementation of first aspect, in the 5th kind of possible embodiment, described many In the case of the multimedia resource that individual reference user is accessed also comprises different resources to be recommended, described according to described reference User for described first multimedia resource finish playing than with described targeted customer for described first multimedia resource Finish playing ratio, determines the advowson weight values of described resource to be recommended, including:
For each with reference to user, by this reference user for the ratio that finishes playing of each first multimedia resource respectively with described Targeted customer for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, And the value after being multiplied is added, as the recommendation weight of the to be recommended resource different from other reference user of this reference user Value,
The described advowson weight values according to described resource to be recommended, recommends described resource to be recommended to described targeted customer, Including:
Advowson weight values according to the described identical resource to be recommended determined and described different resource to be recommended Advowson weight values, the resource to be recommended included in multimedia resource accessed the plurality of reference user is ranked up, To generate the recommendation list of described targeted customer.
The third possible implementation of the implementation possible in conjunction with the second of first aspect or first aspect or 4th kind of possible implementation of first aspect or the 5th kind of possible implementation of first aspect are possible at the 6th kind In embodiment, following formula 1 is used to represent described time decay factor,
Wherein, k represents described time decay factor, and t represents described and accesses described first multimedia resource with reference to user Time and described targeted customer access the absolute value of the difference of the time of described first multimedia resource.
In second aspect, the invention provides the recommendation apparatus of a kind of multimedia resource, including:
First determines unit, for according to the first multimedia resource accessed with reference to user, determines and accessed described the The targeted customer of one multimedia resource, wherein, described first multimedia resource is that to be accessed for number of times within a predetermined period of time little Multimedia resource in predetermined threshold;
Second determines unit, determines that unit is connected with described first, for the feature according to described first multimedia resource Information, determines the advowson weight values of resource to be recommended, and wherein, described resource to be recommended is the described many matchmakers accessed with reference to user The multimedia resource in addition to described first multimedia resource in body resource;And
With described second, recommendation unit, determines that unit is connected, be used for the advowson weight values according to described resource to be recommended, to Described targeted customer recommends described resource to be recommended.
In conjunction with second aspect, in the implementation that the first is possible, described characteristic information be finish playing than feelings Under condition, described second determine unit for:
According to described with reference to user for described first multimedia resource finish playing than with described targeted customer for The ratio that finishes playing of described first multimedia resource, determines the advowson weight values of described resource to be recommended.
In conjunction with the first possible implementation of second aspect, in the implementation that the second is possible, described One determine unit determine one with reference in the case of user, described second determine unit for:
By described with reference to user for each first multimedia resource finish playing than respectively with described targeted customer for Corresponding first multimedia resource finish playing than and this three of time decay factor of presetting be multiplied, and after being multiplied Value is added, as the advowson weight values of described resource to be recommended.
In conjunction with the first possible implementation of second aspect, in the implementation that the third is possible, described One to determine that unit is determined multiple with reference to user and comprise identical in the plurality of multimedia resource accessed with reference to user In the case of resource to be recommended, described second determine unit for:
For each with reference to user, by this reference user for the ratio that finishes playing of each first multimedia resource respectively with described Targeted customer for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied;
Will for each be multiplied with reference to user after value be added, and the value after will add up is defined as described identical money to be recommended The advowson weight values in source.
In conjunction with the first possible implementation of second aspect, in the 4th kind of possible embodiment, described One to determine that unit is determined multiple with reference to user and comprise different in the plurality of multimedia resource accessed with reference to user In the case of resource to be recommended, described second determine unit for:
For each with reference to user, by this reference user for the ratio that finishes playing of each first multimedia resource respectively with described Targeted customer for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, And the value after being multiplied is added, as the recommendation weight of the to be recommended resource different from other reference user of this reference user Value,
Described recommendation unit is used for:
According to the advowson weight values of the described different resource to be recommended determined, described different resource to be recommended is entered Row sequence, to generate the recommendation list of described targeted customer.
In conjunction with the third possible implementation of second aspect, in the 5th kind of possible embodiment, described many In the case of also comprising different resources to be recommended in the multimedia resource that individual reference user is accessed, described second determines unit For:
For each with reference to user, by this reference user for the ratio that finishes playing of each first multimedia resource respectively with described Targeted customer for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, And the value after being multiplied is added, as the recommendation weight of the to be recommended resource different from other reference user of this reference user Value,
Described recommendation unit is used for:
Advowson weight values according to the described identical resource to be recommended determined and described different resource to be recommended Advowson weight values, the resource to be recommended included in multimedia resource accessed the plurality of reference user is ranked up, To generate the recommendation list of described targeted customer.
The third possible implementation of the implementation possible in conjunction with the second of second aspect or second aspect or 4th kind of possible implementation of second aspect or the 5th kind of possible implementation of second aspect are possible at the 6th kind In embodiment, following formula 1 is used to represent described time decay factor,
Wherein, k represents described time decay factor, and t represents described and accesses described first multimedia resource with reference to user Time and described targeted customer access the absolute value of the difference of the time of described first multimedia resource.
Beneficial effect
The recommendation method and apparatus of the multimedia resource of the embodiment of the present invention, according to the characteristic information of the first multimedia resource Determine the advowson weight values of resource to be recommended, and recommend resource to be recommended with the advowson weight values determined to targeted customer.By This, can recommend be referenced that user accessed and do not accessed by targeted customer to the targeted customer that preference is identical with reference to user The multimedia resource crossed, can improve the accuracy recommended to targeted customer, recommend targeted customer fast and effectively, uses Family is experienced good.
According to below with reference to the accompanying drawings detailed description of illustrative embodiments, the further feature of the present invention and aspect being become Clear.
Accompanying drawing explanation
The accompanying drawing of the part comprising in the description and constituting description together illustrates the present invention's with description Exemplary embodiment, feature and aspect, and for explaining the principle of the present invention.
Fig. 1 illustrates the flow chart of the recommendation method of the multimedia resource of according to embodiments of the present invention;
Fig. 2 a illustrates the flow chart of the recommendation method of the multimedia resource of according to embodiments of the present invention two;
Fig. 2 b illustrates the flow example figure of the recommendation method of the multimedia resource of according to embodiments of the present invention two;
Fig. 3 illustrates the structured flowchart of the recommendation apparatus of the multimedia resource of according to embodiments of the present invention three;And
Fig. 4 illustrates the structured flowchart of the recommendation apparatus of the multimedia resource of according to embodiments of the present invention four.
Detailed description of the invention
Various exemplary embodiments, feature and the aspect of the present invention is described in detail below with reference to accompanying drawing.In accompanying drawing identical Reference represent the same or analogous element of function.Although the various aspects of embodiment shown in the drawings, but remove Non-specifically is pointed out, it is not necessary to accompanying drawing drawn to scale.
The most special word " exemplary " means " as example, embodiment or illustrative ".Here as " exemplary " Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.
It addition, in order to better illustrate the present invention, detailed description of the invention below gives numerous details. It will be appreciated by those skilled in the art that do not have some detail, the present invention equally implements.In some instances, for Method well known to those skilled in the art, means, element and circuit are not described in detail, in order to highlight the purport of the present invention.
Embodiment 1
Fig. 1 illustrates the flow chart of the recommendation method of the multimedia resource of according to embodiments of the present invention.As it is shown in figure 1, should Recommendation method mainly may include that
Step S100, the first multimedia resource accessed according to reference user, determine and accessed the first multimedia resource Targeted customer.Wherein, the first multimedia resource is the many matchmakers being accessed for number of times within a predetermined period of time less than predetermined threshold Body resource.
User can use subscriber equipment to communicate with the network equipment.Wherein, subscriber equipment includes but not limited to use Family can carry out the electronic product of man-machine interaction by modes such as keyboard, mouse, remote controller, touch pad, handwriting equipments, such as, Computer, mobile phone, personal digital assistant (English: Personal Digital Assistant, PDA), notebook, platform be called for short: Formula computer, intelligent television etc..The network equipment includes but not limited to network host, single network server, multiple webserver The cloud that collection or multiple server are constituted.Multimedia resource includes but not limited to video, audio frequency, picture.
It should be noted that above-mentioned subscriber equipment, the network equipment and multimedia resource are not limited only to above-mentioned example, this area Technical staff should be able to understand, other existing or be likely to occur from now on the subscriber equipment of other form, the network equipment and many Media resource all goes for the present invention, say, that the present invention is not intended to subscriber equipment, the network equipment and multimedia resource Concrete form.
Specifically, can be stored according to the network equipment or the third party device being connected with the network equipment via network Multimedia resource accesses record, extracts all multimedia resources accessed with reference to user, then, it is judged that the multimedia extracted Resource is accessed for whether number of times is less than predetermined threshold within a predetermined period of time, finally, will determine that out within a predetermined period of time It is accessed for number of times and is defined as the first multimedia resource less than the multimedia resource of predetermined threshold, such as, will tire out within 10 days The meter viewing number of times multimedia resource less than 260 is defined as the first multimedia resource, and especially, the first multimedia resource also can claim For " side door multimedia resource ".
After determining the first multimedia resource, the multimedia that can be stored according to the network equipment or third party device Resource accesses record, determines the targeted customer accessing the first multimedia resource.For example, it is possible to the first multimedia resource for closing Keyword, multimedia resource access record in inquire about, determine targeted customer.Wherein, the many matchmakers accessed with reference to user Body resource includes that the first multimedia resource that targeted customer accessed and the multimedia resource that targeted customer did not access (are waited to push away Recommend resource).
Step S120, characteristic information according to the first multimedia resource, determine the advowson weight values of resource to be recommended.Its In, resource to be recommended is the money of the multimedia in addition to the first multimedia resource in the multimedia resource that reference user is accessed Source.
In order to do not accessed by targeted customer in the multimedia resource that targeted customer recommends reference user to access Multimedia resource (that is, to be recommended resource), it is thus necessary to determine that the advowson weight values of resource to be recommended.Specifically, can be according to reference The ratio that such as finishes playing of the first multimedia resource that user accessed, reproduction time length, viewing (broadcasting) time are with current The characteristic information of the time interval of time, the popular degree of multimedia resource, user's liveness etc., determines resource to be recommended Advowson weight values.Wherein, the ratio that finishes playing is that user plays the time span of multimedia resource in this played multimedia money The total time in source the percentage ratio in length.Reproduction time length is the time span that user plays multimedia resource.Can use Multimedia resource is accessed within a period of time whether number of times is more than predetermined threshold to measure the popular degree of multimedia resource. Number or the reproduction time length sum that can use the multimedia resource that user plays within a period of time carry out measure user and live Jerk.
Step S140, advowson weight values according to resource to be recommended, recommend resource to be recommended to targeted customer.
After the advowson weight values determining resource to be recommended, can the advowson of resource to be recommended to be determined Weight values recommends resource to be recommended to targeted customer.For example, it is assumed that determine that the advowson weight values of resource 1 to be recommended is 5, waits to push away The advowson weight values recommending resource 2 is 7, then can to recommend to user with the resource 2 to be recommended order before resource 1 to be recommended Resource 1 to be recommended and resource to be recommended 2.
The recommendation method of the multimedia resource of the embodiment of the present invention, determines according to the characteristic information of the first multimedia resource and treats Recommend the advowson weight values of resource, and recommend resource to be recommended with the advowson weight values determined to targeted customer.Thus, it is possible to Recommend be referenced that user accessed and do not accessed by targeted customer many to the targeted customer that preference is identical with reference to user Media resource, can improve the accuracy recommended to targeted customer, recommend targeted customer fast and effectively, Consumer's Experience Well.
Embodiment 2
Fig. 2 a illustrates the flow chart of the recommendation method of the multimedia resource of according to embodiments of the present invention two, and Fig. 2 b illustrates basis The flow example figure of the recommendation method of the multimedia resource of the embodiment of the present invention two.The present embodiment is with the spy of the first multimedia resource Reference breath than as a example by illustrates for finishing playing.Wherein, finish playing than being user's time span of accessing multimedia resource It is accessed for the total time of multimedia resource percentage ratio in length at this.As shown in Figure 2 a, this recommendation method mainly can be wrapped Include:
Step S200, the first multimedia resource accessed according to reference user, determine and accessed the first multimedia resource Targeted customer.Illustrating of this step may refer to the description of step S100 in above-described embodiment 1.
Step S220, according to reference to user for the first multimedia resource finish playing than with targeted customer for first The ratio that finishes playing of multimedia resource, determines the advowson weight values of resource to be recommended.
In a kind of possible implementation, determine one with reference in the case of user, according to reference to user for First multimedia resource finish playing than with targeted customer for the ratio that finishes playing of the first multimedia resource, determine to be recommended The advowson weight values of resource, may include that
By with reference to user for each first multimedia resource finish playing than respectively with targeted customer for corresponding the One multimedia resource finish playing than and this three of time decay factor of presetting be multiplied, and the value after being multiplied is added, Advowson weight values as resource to be recommended.
Wherein it is possible to use following formula 1 to represent above-mentioned time decay factor,
Wherein, k express time decay factor, t represents time and the target use accessing the first multimedia resource with reference to user Family accesses the absolute value of the difference of the time of the first multimedia resource.
For example, as shown in Figure 2 b, user 1 have viewed member film A, film B and film C, and user 2 have viewed film B and film C, film B and film C are the first multimedia resource, and member film A is resource to be recommended, then user 1 is with reference to user And user 2 is targeted customer, owing to user 1 and user 2 all have viewed film B and film C, therefore user 1 and user 2 phase Seemingly.Can be according to user 1 finishing playing than (being referred to as " degree of finishing playing ") perc for film B1, user 1 for Perc is compared in finishing playing of film C2, user 2 compare perc for finishing playing of film B3, user 2 plays for film C's Become to compare perc4, calculating user 1 and user 2 for the similar value of film B is perc1*perc3* k and user 1 and user 2 pin Similar value to film C is perc2*perc4*k;Again the two similar value is sued for peace, it becomes possible to obtain the recommendation of member film A Weighted value wAFor wA=perc1*perc3*k+perc2*perc4* k, i.e. user 1 is with advowson weight values wAMember is recommended to user 2 Film A.
In a kind of possible implementation, determining multiple reference user and multiple many matchmakers accessed with reference to user In the case of body resource comprises identical resource to be recommended, according to reference to user's finishing playing for the first multimedia resource Ratio and targeted customer, for the ratio that finishes playing of the first multimedia resource, determine the advowson weight values of resource to be recommended, can wrap Include:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied;
Will for each be multiplied with reference to user after value be added, and the value after will add up is defined as identical resource to be recommended Advowson weight values.
For example, as shown in Figure 2 b, user 1 have viewed member film A, film B and film C, and user 2 have viewed film B, film C and film D, user 3 have viewed film D and member film A, and film B, film C and film D are the first multimedia money Source, member film A is resource to be recommended, then user 1 and user 3 are to be targeted customer with reference to user and user 2.Due to user 1 and user 2 all have viewed film B and film C, therefore user 1 is similar with user 2, and user 3 and user 2 all have viewed electricity Shadow D, therefore user 3 is similar with user 2.Perc can be compared for finishing playing of film B according to user 11, user 1 is for electricity Perc is compared in finishing playing of shadow C2, user 2 compare perc for finishing playing of film B3, user 2 finishes playing for film C's Compare perc4, user 2 compare perc for finishing playing of film D5, user 3 compare perc for finishing playing of film D6, calculate User 1 and user 2 are perc for the similar value of film B1*perc3* k, user 1 and user 2 for the similar value of film C are perc2*perc4* k and user 3 and user 2 are perc for the similar value of film D5*perc6*k;Again by user 1 and user 2 Sue for peace for the similar value of film C for the similar value of film B and user 1 and user 2, it becomes possible to obtain user 1 and push away to user 2 Recommend advowson weight values w of member film AA1For wA1=perc1*perc3*k+perc2*perc4* k, user 3 is to user 2 promotion expo Advowson weight values w of member film AA3For wA3=perc5*perc6*k;Finally by advowson weight values wA1With advowson weight values wA3Ask With, it becomes possible to obtain recommending advowson weight values w of member film A to user 2AFor wA=wA1+wA3=perc1*perc3*k+ perc2*perc4*k+perc5*perc6* k, i.e. with advowson weight values wAMember film A is recommended to user 2.
Step S240, advowson weight values according to resource to be recommended, recommend resource to be recommended to targeted customer.This step Illustrate and may refer to the description of step S140 in above-described embodiment 1.
In a kind of possible implementation, determining multiple reference user and multiple many matchmakers accessed with reference to user In the case of body resource comprises different resources to be recommended, according to reference to user's finishing playing for the first multimedia resource Ratio and targeted customer, for the ratio that finishes playing of the first multimedia resource, determine the advowson weight values of resource to be recommended, can wrap Include:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, and will Value after being multiplied is added, as the advowson weight values of the to be recommended resource different from other reference user of this reference user,
Advowson weight values according to resource to be recommended, recommends resource to be recommended to targeted customer, including:
According to the advowson weight values of the different resource to be recommended determined, different resources to be recommended is ranked up, To generate the recommendation list of targeted customer.
For example, it is assumed that user 1 have viewed member film A, film B and film C, user 2 have viewed film B, film C With film D, user 3 have viewed film D and member film E, and film B, film C and film D are the first multimedia resource, Hui Yuan electricity Shadow A and member film E is resource to be recommended, then user 1 and user 3 are to be targeted customer with reference to user and user 2.Due to Family 1 and user 2 all have viewed film B and film C, and therefore user 1 is similar with user 2, and owing to user 3 and user 2 all see Having seen film D, therefore user 3 is similar with user 2.Perc can be compared for finishing playing of film B according to user 11, user 1 Perc is compared for finishing playing of film C2, user 2 compare perc for finishing playing of film B3, user 2 broadcasts for film C's Discharge into and compare perc4, user 2 compare perc for finishing playing of film D5, user 3 compare perc for finishing playing of film D6, Calculating user 1 and user 2 for the similar value of film B is perc1*perc3* similar for film C of k, user 1 and user 2 Value is perc2*perc4* k and user 3 and user 2 are perc for the similar value of film D5*perc6*k;Again by user 1 He User 2 sues for peace for the similar value of film C for the similar value of film B and user 1 and user 2, it becomes possible to obtain user 1 to Advowson weight values w of member film A is recommended at family 2AFor wA=perc1*perc3*k+perc2*perc4* k, user 3 pushes away to user 2 Recommend advowson weight values w of member film EEFor wE=perc5*perc6*k;Finally by member film A and member film E according to respectively From advowson weight values wAAnd wESequence, it becomes possible to obtain comprising member film A and the recommendation of member film E to what user 2 recommended List, i.e. recommends multimedia resource according to the sequencing of this recommendation list to user 2.
It is apparent that the amount of calculation of the recommendation method of the present invention be significantly less than of the prior art first calculate user two-by-two it Between similar matrix in viewing behavior, carry out the amount of calculation of the recommendation method recommended, and the present invention according still further to similar matrix The recommendation effect of recommendation method be also significantly better than the recommendation effect of aforementioned recommendation method of the prior art.
In a kind of possible implementation, both comprised identical in multiple multimedia resources accessed with reference to user In the case of resource to be recommended comprises again different resources to be recommended, can determine according to said method that identical waiting pushes away respectively Recommend advowson weight values and the advowson weight values of different resources to be recommended of resource, further according to the identical money to be recommended determined The advowson weight values in source and the advowson weight values of different resources to be recommended are to multiple multimedia resources accessed with reference to user Included in resource to be recommended be ranked up, to generate the recommendation list of targeted customer.
The recommendation method of the multimedia resource of the embodiment of the present invention, the ratio that finishes playing according to the first multimedia resource is (special Reference ceases) determine the advowson weight values of resource to be recommended, and recommend to be recommended to targeted customer with the advowson weight values determined Resource.It addition, for the resource multiple to be recommended of targeted customer, can generate according to the advowson weight values of each resource to be recommended The recommendation list of targeted customer.Access thus, it is possible to recommend to be referenced user to the targeted customer that preference is identical with reference to user Multimedia resource that is that cross and that do not accessed by targeted customer, can improve the accuracy recommended to targeted customer, uses target Family is recommended fast and effectively, and Consumer's Experience is good.
Embodiment 3
Fig. 3 illustrates the structured flowchart of the recommendation apparatus of the multimedia resource of according to embodiments of the present invention three.As it is shown on figure 3, This recommendation apparatus mainly may include that
First determines unit 310, for according to the first multimedia resource accessed with reference to user, determining and accessed first The targeted customer of multimedia resource.Wherein, the first multimedia resource is to be accessed for number of times within a predetermined period of time less than predetermined The multimedia resource of threshold value.
User can use subscriber equipment to communicate with the network equipment.Wherein, subscriber equipment includes but not limited to use Family can carry out the electronic product of man-machine interaction by modes such as keyboard, mouse, remote controller, touch pad, handwriting equipments, such as, Computer, mobile phone, personal digital assistant (English: Personal Digital Assistant, PDA), notebook, platform be called for short: Formula computer, intelligent television etc..The network equipment includes but not limited to network host, single network server, multiple webserver The cloud that collection or multiple server are constituted.Multimedia resource includes but not limited to video, audio frequency, picture.
It should be noted that above-mentioned subscriber equipment, the network equipment and multimedia resource are not limited only to above-mentioned example, this area Technical staff should be able to understand, other existing or be likely to occur from now on the subscriber equipment of other form, the network equipment and many Media resource all goes for the present invention, say, that the present invention is not intended to subscriber equipment, the network equipment and multimedia resource Concrete form.
Specifically, can be stored according to the network equipment or the third party device being connected with the network equipment via network Multimedia resource accesses record, extracts all multimedia resources accessed with reference to user, then, it is judged that the multimedia extracted Resource is accessed for whether number of times is less than predetermined threshold within a predetermined period of time, finally, will determine that out within a predetermined period of time It is accessed for number of times and is defined as the first multimedia resource less than the multimedia resource of predetermined threshold, such as, will tire out within 10 days The meter viewing number of times multimedia resource less than 260 is defined as the first multimedia resource, and especially, the first multimedia resource also can claim For " side door multimedia resource ".
After determining the first multimedia resource, first determines that unit 310 can set according to the network equipment or third party The standby multimedia resource stored accesses record, determines the targeted customer accessing the first multimedia resource.Such as, first determines Unit 310 can with the first multimedia resource as key word, multimedia resource access record in inquire about, determine target User.Wherein, the multimedia resource accessed with reference to user includes the first multimedia resource and the target that targeted customer accessed The multimedia resource (resource to be recommended) that user did not access.
Second determines unit 330, determines that unit 310 is connected with first, believes for the feature according to the first multimedia resource Breath, determines the advowson weight values of resource to be recommended.Wherein, during resource to be recommended is the multimedia resource that reference user is accessed Multimedia resource in addition to the first multimedia resource.
In order to do not accessed by targeted customer in the multimedia resource that targeted customer recommends reference user to access Multimedia resource (that is, to be recommended resource), second determines unit 330 it needs to be determined that the advowson weight values of resource to be recommended.Specifically Ground, second determines that unit 330 can be according to such as finish playing ratio, the broadcasting of the first multimedia resource accessed with reference to user Time span, viewing (broadcasting) time and the time interval of current time, the popular degree of multimedia resource, user's liveness etc. Characteristic information, determine the advowson weight values of resource to be recommended.Wherein, the ratio that finishes playing is that user plays multimedia resource Time span is the percentage ratio in length in total time of this played multimedia resource.It is many that reproduction time length is that user plays The time span of media resource.Multimedia resource can be used whether to be accessed for number of times within a period of time more than predetermined threshold Measure the popular degree of multimedia resource.The number of the multimedia resource that user plays within a period of time can be used or broadcast Put time span sum and carry out measure user liveness.
With second, recommendation unit 350, determines that unit 330 is connected, for the advowson weight values according to resource to be recommended, to mesh Mark user recommends resource to be recommended.
After second determines the advowson weight values that unit 330 determines resource to be recommended, it is recommended that unit 350 can be with Two determine that the advowson weight values of the resource to be recommended that unit 330 determined recommends resource to be recommended to targeted customer.Such as, Assume second determine unit 330 determine the advowson weight values of resource 1 to be recommended be 5, the advowson weight values of resource to be recommended 2 be 7, then recommendation unit 350 can recommend resource to be recommended with the resource 2 to be recommended order before resource 1 to be recommended to user 1 and resource to be recommended 2.
The recommendation apparatus of the multimedia resource of the embodiment of the present invention, determines according to the characteristic information of the first multimedia resource and treats Recommend the advowson weight values of resource, and recommend resource to be recommended with the advowson weight values determined to targeted customer.Thus, it is possible to Recommend be referenced that user accessed and do not accessed by targeted customer many to the targeted customer that preference is identical with reference to user Media resource, can improve the accuracy recommended to targeted customer, recommend targeted customer fast and effectively, Consumer's Experience Well.
Embodiment 4
Fig. 4 illustrates the structured flowchart of the recommendation apparatus of the multimedia resource of according to embodiments of the present invention four.The present embodiment with The characteristic information of the first multimedia resource than as a example by illustrates for finishing playing.Wherein, finish playing more than being that user accesses The time span of media resource is accessed for the total time of multimedia resource percentage ratio in length at this.As shown in Figure 4, this pushes away Recommend device mainly to may include that
First determines unit 410, for according to the first multimedia resource accessed with reference to user, determining and accessed first The targeted customer of multimedia resource.Illustrate and may refer to the description of step S100 in above-described embodiment 1.
Second determines unit 430, determines that unit 410 is connected with first, is used for according to reference user for the first multimedia Resource finish playing than with targeted customer for the ratio that finishes playing of the first multimedia resource, determine the recommendation of resource to be recommended Weighted value.
In a kind of possible implementation, in the case of determining that unit 410 determines a reference user first, the Two determine unit 430 for:
By with reference to user for each first multimedia resource finish playing than respectively with targeted customer for corresponding the One multimedia resource finish playing than and this three of time decay factor of presetting be multiplied, and the value after being multiplied is added, Advowson weight values as resource to be recommended.
Wherein it is possible to use following formula 1 to represent above-mentioned time decay factor,
Wherein, k express time decay factor, t represents time and the target use accessing the first multimedia resource with reference to user Family accesses the absolute value of the difference of the time of the first multimedia resource.
For example, as shown in Figure 2 b, user 1 have viewed member film A, film B and film C, and user 2 have viewed film B and film C, film B and film C are the first multimedia resource, and member film A is resource to be recommended, then user 1 is with reference to user And user 2 is targeted customer, owing to user 1 and user 2 all have viewed film B and film C, therefore user 1 and user 2 phase Seemingly.Second determines that unit 430 can be according to user 1 finishing playing than (being referred to as " degree of finishing playing ") for film B perc1, user 1 compare perc for finishing playing of film C2, user 2 compare perc for finishing playing of film B3, user 2 pin Film C is finished playing and compares perc4, calculating user 1 and user 2 for the similar value of film B is perc1*perc3* k with And user 1 and user 2 are perc for the similar value of film C2*perc4*k;Again the two similar value is sued for peace, it becomes possible to obtain Advowson weight values w of member film AAFor wA=perc1*perc3*k+perc2*perc4* k, i.e. user 1 is with advowson weight values wA Member film A is recommended to user 2.
In a kind of possible implementation, determine that unit 410 determines multiple reference users and multiple reference first In the case of the multimedia resource that user is accessed comprises identical resource to be recommended, second determine unit 430 for:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied;
Will for each be multiplied with reference to user after value be added, and the value after will add up is defined as identical resource to be recommended Advowson weight values.
For example, as shown in Figure 2 b, user 1 have viewed member film A, film B and film C, and user 2 have viewed film B, film C and film D, user 3 have viewed film D and member film A, and film B, film C and film D are the first multimedia money Source, member film A is resource to be recommended, then user 1 and user 3 are to be targeted customer with reference to user and user 2.Due to user 1 and user 2 all have viewed film B and film C, therefore user 1 is similar with user 2, and user 3 and user 2 all have viewed electricity Shadow D, therefore user 3 is similar with user 2.Second determines that unit 430 can be according to user 1 for the ratio that finishes playing of film B perc1, user 1 compare perc for finishing playing of film C2, user 2 compare perc for finishing playing of film B3, user 2 pin Film C is finished playing and compares perc4, user 2 compare perc for finishing playing of film D5, user 3 is for the broadcasting of film D Complete to compare perc6, calculating user 1 and user 2 for the similar value of film B is perc1*perc3* k, user 1 and user 2 pin Similar value to film C is perc2*perc4* k and user 3 and user 2 are perc for the similar value of film D5*perc6* k;Again user 1 and user 2 are sued for peace for the similar value of film C for the similar value of film B and user 1 and user 2, it becomes possible to Obtain user 1 and recommend advowson weight values w of member film A to user 2A1For wA1=perc1*perc3*k+perc2*perc4* k, User 3 recommends advowson weight values w of member film A to user 2A3For wA3=perc5*perc6*k;Finally by advowson weight values wA1 With advowson weight values wA3Summation, it becomes possible to obtain recommending advowson weight values w of member film A to user 2AFor wA=wA1+wA3= perc1*perc3*k+perc2*perc4*k+perc5*perc6* k, i.e. with advowson weight values wAMember's film is recommended to user 2 A。
With second, recommendation unit 450, determines that unit 430 is connected, for the advowson weight values according to resource to be recommended, to mesh Mark user recommends resource to be recommended.Illustrate and may refer to the description of step S140 in above-described embodiment 1.
In a kind of possible implementation, determine that unit 410 determines multiple reference users and multiple reference first In the case of the multimedia resource that user is accessed comprises different resources to be recommended, second determine unit 430 for:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, and will Value after being multiplied is added, as the advowson weight values of the to be recommended resource different from other reference user of this reference user,
Recommendation unit 450 is used for:
According to the advowson weight values of the different resource to be recommended determined, different resources to be recommended is ranked up, To generate the recommendation list of targeted customer.
For example, it is assumed that user 1 have viewed member film A, film B and film C, user 2 have viewed film B, film C With film D, user 3 have viewed film D and member film E, and film B, film C and film D are the first multimedia resource, Hui Yuan electricity Shadow A and member film E is resource to be recommended, then user 1 and user 3 are to be targeted customer with reference to user and user 2.Due to Family 1 and user 2 all have viewed film B and film C, and therefore user 1 is similar with user 2, and owing to user 3 and user 2 all see Having seen film D, therefore user 3 is similar with user 2.Second determines that unit 430 can be according to user 1 playing for film B Become to compare perc1, user 1 compare perc for finishing playing of film C2, user 2 compare perc for finishing playing of film B3, user 2 compare perc for finishing playing of film C4, user 2 compare perc for finishing playing of film D5, user 3 broadcasts for film D's Discharge into and compare perc6, calculating user 1 and user 2 for the similar value of film B is perc1*perc3* k, user 1 and user 2 Similar value for film C is perc2*perc4* k and user 3 and user 2 are perc for the similar value of film D5* perc6*k;Again user 1 and user 2 are sued for peace for the similar value of film C for the similar value of film B and user 1 and user 2, Just can obtain user 1 and recommend advowson weight values w of member film A to user 2AFor wA=perc1*perc3*k+perc2* perc4* k, user 3 recommends advowson weight values w of member film E to user 2EFor wE=perc5*perc6*k;Finally by member's electricity Shadow A and member film E is according to respective advowson weight values wAAnd wESequence, it becomes possible to obtain comprising member's electricity to what user 2 recommended Shadow A and the recommendation list of member film E, i.e. recommendation unit 450 are recommended many according to the sequencing of this recommendation list to user 2 Media resource.
It is apparent that the amount of calculation of the recommendation apparatus of the present invention be significantly less than of the prior art first calculate user two-by-two it Between similar matrix in viewing behavior, carry out the amount of calculation of the recommendation method recommended, and the present invention according still further to similar matrix The recommendation effect of recommendation apparatus be also significantly better than the recommendation effect of aforementioned recommendation method of the prior art.
In a kind of possible implementation, both comprised identical in multiple multimedia resources accessed with reference to user In the case of resource to be recommended comprises again different resources to be recommended, second determines that unit 430 can according to said method respectively Determine advowson weight values and the advowson weight values of different resources to be recommended of identical resource to be recommended, further according to determining The advowson weight values of identical resource to be recommended and the advowson weight values of different resources to be recommended to multiple with reference to user institutes The resource to be recommended included in multimedia resource accessed is ranked up, to generate the recommendation list of targeted customer.
The recommendation apparatus of the multimedia resource of the embodiment of the present invention, the ratio that finishes playing according to the first multimedia resource is (special Reference ceases) determine the advowson weight values of resource to be recommended, and recommend to be recommended to targeted customer with the advowson weight values determined Resource.It addition, for the resource multiple to be recommended of targeted customer, can generate according to the advowson weight values of each resource to be recommended The recommendation list of targeted customer.Access thus, it is possible to recommend to be referenced user to the targeted customer that preference is identical with reference to user Multimedia resource that is that cross and that do not accessed by targeted customer, can improve the accuracy recommended to targeted customer, uses target Family is recommended fast and effectively, and Consumer's Experience is good.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited thereto, and any Those familiar with the art, in the technical scope that the invention discloses, can readily occur in change or replace, should contain Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with described scope of the claims.

Claims (14)

1. the recommendation method of a multimedia resource, it is characterised in that including:
According to the first multimedia resource accessed with reference to user, determine that the target accessing described first multimedia resource is used Family, wherein, described first multimedia resource is the multimedia money being accessed for number of times within a predetermined period of time less than predetermined threshold Source;
According to the characteristic information of described first multimedia resource, determine the advowson weight values of resource to be recommended, wherein, described in wait to push away Recommending resource is the money of the multimedia in addition to described first multimedia resource in the described multimedia resource accessed with reference to user Source;And
According to the advowson weight values of described resource to be recommended, recommend described resource to be recommended to described targeted customer.
Recommendation method the most according to claim 1, it is characterised in that described characteristic information be finish playing than situation Under, the described characteristic information according to described first multimedia resource, determine the advowson weight values of resource to be recommended, including:
According to described with reference to user for described first multimedia resource finish playing than with described targeted customer for described The ratio that finishes playing of the first multimedia resource, determines the advowson weight values of described resource to be recommended.
Recommendation method the most according to claim 2, it is characterised in that in the case of determining a reference user, institute State according to described with reference to user for described first multimedia resource finish playing than with described targeted customer for described the The ratio that finishes playing of one multimedia resource, determines the advowson weight values of described resource to be recommended, including:
By described with reference to user for each first multimedia resource finish playing than respectively to described targeted customer for corresponding The first multimedia resource finish playing than and this three of time decay factor of presetting be multiplied, and the value phase after being multiplied Add, as the advowson weight values of described resource to be recommended.
Recommendation method the most according to claim 2, it is characterised in that determining multiple reference users and the plurality of ginseng Examine in the case of the multimedia resource that user is accessed comprises identical resource to be recommended, described according to described reference user's pin Described first multimedia resource is finished playing than with described targeted customer playing for described first multimedia resource Become ratio, determine the advowson weight values of described resource to be recommended, including:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with described target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied;
Will for each be multiplied with reference to user after value be added, and the value after will add up is defined as described identical resource to be recommended Advowson weight values.
Recommendation method the most according to claim 2, it is characterised in that determining multiple reference users and the plurality of ginseng Examine in the case of the multimedia resource that user is accessed comprises different resources to be recommended, described according to described reference user's pin Described first multimedia resource is finished playing than with described targeted customer playing for described first multimedia resource Become ratio, determine the advowson weight values of described resource to be recommended, including:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with described target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, and will Value after being multiplied is added, as the advowson weight values of the to be recommended resource different from other reference user of this reference user,
The described advowson weight values according to described resource to be recommended, recommends described resource to be recommended to described targeted customer, including:
According to the advowson weight values of the described different resource to be recommended determined, described different resource to be recommended is arranged Sequence, to generate the recommendation list of described targeted customer.
Recommendation method the most according to claim 4, it is characterised in that in the plurality of multimedia accessed with reference to user In the case of resource also comprises different resources to be recommended, described according to described with reference to user for described first multimedia money Source finish playing than with described targeted customer for the ratio that finishes playing of described first multimedia resource, determine described to be recommended The advowson weight values of resource, including:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with described target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, and will Value after being multiplied is added, as the advowson weight values of the to be recommended resource different from other reference user of this reference user,
The described advowson weight values according to described resource to be recommended, recommends described resource to be recommended to described targeted customer, including:
Advowson weight values according to the described identical resource to be recommended determined and the recommendation of described different resource to be recommended Weighted value, the resource to be recommended included in multimedia resource accessed the plurality of reference user is ranked up, with life Become the recommendation list of described targeted customer.
7. according to the recommendation method according to any one of claim 3 to 6, it is characterised in that use following formula 1 to represent the described time Decay factor,
Wherein, k represents described time decay factor, and t represents the described time accessing described first multimedia resource with reference to user The absolute value of the difference of the time of described first multimedia resource is accessed with described targeted customer.
8. the recommendation apparatus of a multimedia resource, it is characterised in that including:
First determines unit, for according to the first multimedia resource accessed with reference to user, determining and accessed described more than first The targeted customer of media resource, wherein, described first multimedia resource is to be accessed for number of times within a predetermined period of time less than pre- Determine the multimedia resource of threshold value;
Second determines unit, determines that unit is connected with described first, for the characteristic information according to described first multimedia resource, Determining the advowson weight values of resource to be recommended, wherein, described resource to be recommended is the described multimedia money accessed with reference to user The multimedia resource in addition to described first multimedia resource in source;And
With described second, recommendation unit, determines that unit is connected, for the advowson weight values according to described resource to be recommended, to described Targeted customer recommends described resource to be recommended.
Recommendation apparatus the most according to claim 8, it is characterised in that described characteristic information be finish playing than situation Under, described second determine unit for:
According to described with reference to user for described first multimedia resource finish playing than with described targeted customer for described The ratio that finishes playing of the first multimedia resource, determines the advowson weight values of described resource to be recommended.
Recommendation apparatus the most according to claim 9, it is characterised in that determine that unit determines a ginseng described first In the case of examining user, described second determine unit for:
By described with reference to user for each first multimedia resource finish playing than respectively to described targeted customer for corresponding The first multimedia resource finish playing than and this three of time decay factor of presetting be multiplied, and the value phase after being multiplied Add, as the advowson weight values of described resource to be recommended.
11. recommendation apparatus according to claim 9, it is characterised in that determine that unit determines multiple ginseng described first Examine in the case of user and the plurality of multimedia resource accessed with reference to user comprise identical resource to be recommended, described Second determine unit for:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with described target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied;
Will for each be multiplied with reference to user after value be added, and the value after will add up is defined as described identical resource to be recommended Advowson weight values.
12. recommendation apparatus according to claim 9, it is characterised in that determine that unit determines multiple ginseng described first Examine in the case of user and the plurality of multimedia resource accessed with reference to user comprise different resources to be recommended, described Second determine unit for:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with described target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, and will Value after being multiplied is added, as the advowson weight values of the to be recommended resource different from other reference user of this reference user,
Described recommendation unit is used for:
According to the advowson weight values of the described different resource to be recommended determined, described different resource to be recommended is arranged Sequence, to generate the recommendation list of described targeted customer.
13. recommendation apparatus according to claim 11, it is characterised in that the plurality of many matchmakers accessed with reference to user In the case of body resource also comprises different resources to be recommended, described second determine unit for:
For each with reference to user, by this reference user for each first multimedia resource finish playing than respectively with described target User for corresponding first multimedia resource finish playing than and preset this three of time decay factor be multiplied, and will Value after being multiplied is added, as the advowson weight values of the to be recommended resource different from other reference user of this reference user,
Described recommendation unit is used for:
Advowson weight values according to the described identical resource to be recommended determined and the recommendation of described different resource to be recommended Weighted value, the resource to be recommended included in multimedia resource accessed the plurality of reference user is ranked up, with life Become the recommendation list of described targeted customer.
14. according to the recommendation apparatus according to any one of claim 10 to 13, it is characterised in that use following formula 1 to represent described Time decay factor,
Wherein, k represents described time decay factor, and t represents the described time accessing described first multimedia resource with reference to user The absolute value of the difference of the time of described first multimedia resource is accessed with described targeted customer.
CN201610282384.XA 2016-04-29 2016-04-29 Recommendation method and device for multimedia resource Pending CN105975535A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610282384.XA CN105975535A (en) 2016-04-29 2016-04-29 Recommendation method and device for multimedia resource

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610282384.XA CN105975535A (en) 2016-04-29 2016-04-29 Recommendation method and device for multimedia resource

Publications (1)

Publication Number Publication Date
CN105975535A true CN105975535A (en) 2016-09-28

Family

ID=56994914

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610282384.XA Pending CN105975535A (en) 2016-04-29 2016-04-29 Recommendation method and device for multimedia resource

Country Status (1)

Country Link
CN (1) CN105975535A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106790369A (en) * 2016-11-09 2017-05-31 腾讯科技(深圳)有限公司 A kind of multimedia application interface is dressed up method and device
CN107341245A (en) * 2017-07-06 2017-11-10 广州优视网络科技有限公司 Data processing method, device and server
CN113468373A (en) * 2021-05-31 2021-10-01 北京达佳互联信息技术有限公司 Information acquisition method and device, electronic equipment and storage medium
CN113742600A (en) * 2021-11-05 2021-12-03 北京达佳互联信息技术有限公司 Resource recommendation method and device, computer equipment and medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103198418A (en) * 2013-03-15 2013-07-10 北京亿赞普网络技术有限公司 Application recommendation method and application recommendation system
CN103353868A (en) * 2013-05-30 2013-10-16 百度在线网络技术(北京)有限公司 Method and equipment for determining resource evaluation information on multimedia resource
CN103648031A (en) * 2013-11-15 2014-03-19 乐视致新电子科技(天津)有限公司 Program recommending method and apparatus for smart television
CN104035982A (en) * 2014-05-28 2014-09-10 小米科技有限责任公司 Multimedia resource recommendation method and device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103198418A (en) * 2013-03-15 2013-07-10 北京亿赞普网络技术有限公司 Application recommendation method and application recommendation system
CN103353868A (en) * 2013-05-30 2013-10-16 百度在线网络技术(北京)有限公司 Method and equipment for determining resource evaluation information on multimedia resource
CN103648031A (en) * 2013-11-15 2014-03-19 乐视致新电子科技(天津)有限公司 Program recommending method and apparatus for smart television
CN104035982A (en) * 2014-05-28 2014-09-10 小米科技有限责任公司 Multimedia resource recommendation method and device

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106790369A (en) * 2016-11-09 2017-05-31 腾讯科技(深圳)有限公司 A kind of multimedia application interface is dressed up method and device
CN106790369B (en) * 2016-11-09 2021-12-14 腾讯科技(深圳)有限公司 Multimedia application interface decorating method and device
CN107341245A (en) * 2017-07-06 2017-11-10 广州优视网络科技有限公司 Data processing method, device and server
CN107341245B (en) * 2017-07-06 2020-08-21 阿里巴巴(中国)有限公司 Data processing method and device and server
CN113468373A (en) * 2021-05-31 2021-10-01 北京达佳互联信息技术有限公司 Information acquisition method and device, electronic equipment and storage medium
CN113468373B (en) * 2021-05-31 2022-09-02 北京达佳互联信息技术有限公司 Information acquisition method and device, electronic equipment and storage medium
CN113742600A (en) * 2021-11-05 2021-12-03 北京达佳互联信息技术有限公司 Resource recommendation method and device, computer equipment and medium
CN113742600B (en) * 2021-11-05 2022-03-25 北京达佳互联信息技术有限公司 Resource recommendation method and device, computer equipment and medium

Similar Documents

Publication Publication Date Title
CN105975535A (en) Recommendation method and device for multimedia resource
CN108307207A (en) A kind of video pushing method and device
CN109348237A (en) A kind of direct broadcasting room management method, device, server and storage medium
CN109348302A (en) Connect wheat user recommended method, device, server and storage medium in live streaming
Grad-Gyenge et al. Graph embedding based recommendation techniques on the knowledge graph
CN106649482A (en) Information push method and device
CN106687923A (en) Presentation of computing environment on multiple devices
CN105100164B (en) Network service recommends method and apparatus
CN107566862B (en) Method and system for sharing music among multimedia communication terminals
EP3346396A1 (en) Multimedia resource quality assessment method and apparatus
CN106155789A (en) A kind of application freezing method and mobile terminal
CN109379608A (en) A kind of recommended method and relevant device of direct broadcasting room
CN106156351B (en) Multimedia resource recommendation information generation method and device
CN106372101A (en) Video recommendation method and apparatus
CN103731737B (en) A kind of video information update method and electronic equipment
CN109246483A (en) A kind of direct broadcasting room recommended method, device, equipment and storage medium
CN105956061B (en) Method and device for determining similarity between users
CN114040216B (en) Live broadcast room recommendation method, medium, device and computing equipment
CN110855487A (en) Network user similarity management method, device and storage medium
CN112843723B (en) Interaction method, interaction device, electronic equipment and storage medium
CN110324713A (en) The management method and device of virtual resource, live broadcast system
Chen et al. Adversarial Collaborative Filtering for Free
CN109857907A (en) Video locating method and device
CN103631872B (en) A kind of method for broadcasting multimedia file and electric terminal
CN115858182B (en) Intelligent adaptation method and system applied to edge computing nodes of meta universe

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C

Applicant after: Youku network technology (Beijing) Co.,Ltd.

Address before: 100080 area a and C, 5 / F, block a, Sinosteel International Plaza, No. 8, Haidian Street, Haidian District, Beijing

Applicant before: 1VERGE INTERNET TECHNOLOGY (BEIJING) Co.,Ltd.

CB02 Change of applicant information
TA01 Transfer of patent application right

Effective date of registration: 20200617

Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province

Applicant after: Alibaba (China) Co.,Ltd.

Address before: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C

Applicant before: Youku network technology (Beijing) Co.,Ltd.

TA01 Transfer of patent application right
RJ01 Rejection of invention patent application after publication

Application publication date: 20160928

RJ01 Rejection of invention patent application after publication