CN109241425A - A kind of resource recommendation method, device, equipment and storage medium - Google Patents
A kind of resource recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN109241425A CN109241425A CN201811013083.2A CN201811013083A CN109241425A CN 109241425 A CN109241425 A CN 109241425A CN 201811013083 A CN201811013083 A CN 201811013083A CN 109241425 A CN109241425 A CN 109241425A
- Authority
- CN
- China
- Prior art keywords
- resource
- parameter
- candidate
- weight
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of resource recommendation method, device, equipment and storage mediums, which comprises receives resource recommendation request；According to the resource content in the geographical location and preset range for issuing recommendation request, candidate resource set is obtained；Obtain itself relevant parameter and intercorrelation parameter of all candidate resources in the candidate resource set；By itself relevant parameter and intercorrelation parameter, the table of quality scores of the candidate resource set is obtained；It determines to recommend resource from the candidate resource set according to the table of quality scores, and sends the recommendation resource.The present invention can be target customer's end subscriber automatic screening and recommend good resource content near out, improve the experience sense of user by user's viscosity of the corresponding client of promotion.
Description
Technical field
The present invention relates to network communication technology fields more particularly to a kind of resource recommendation method, device, equipment and storage to be situated between
Matter.
Background technique
With the continuous development of network technology, the type and quantity for the resource that network platform can be provided gradually increase；With
Family can use the terminal devices such as mobile phone, computer, MAC access network platform, and browsing checks interested resource content.
Wherein, the resource content that can be touched by user is more and more and more and more abundant, so now in resource
The requirement of appearance also becomes higher and higher；Also, user increasingly focuses on service quality and life comfort level, so experiencing to resource
The requirement of impression is also more stringent.Although resource content can be completed with the application program of many recommendation service functions now
Recommendation；But the resource of Many times recommendation is simultaneously not belonging to good content；If user wants to obtain from application software high-quality
Resource, it is desired nonetheless to making a large amount of search can just obtain.This not only influences the experience sense of user by having an effect on resource content
The user of quality evaluation and corresponding client retains.
Accordingly, it is desirable to provide a kind of technical solution that can recommend automatically high-quality resource content for user.
Summary of the invention
The present invention provides a kind of resource recommendation method, device, equipment and storage mediums, specifically:
On the one hand a kind of resource recommendation method is provided, which comprises
Receive resource recommendation request；
According to the resource content in the geographical location and preset range for issuing recommendation request, candidate resource set is obtained；
Obtain itself relevant parameter and intercorrelation parameter of all candidate resources in the candidate resource set；
By itself relevant parameter and intercorrelation parameter, the table of quality scores of the candidate resource set is obtained；
It determines to recommend resource from the candidate resource set according to the table of quality scores, and sends the recommendation money
Source.
On the other hand a kind of resource recommendation device is provided, described device includes:
Recommendation request receiving module, for receiving resource recommendation request；
Candidate resource obtains module, for according in the resource in the geographical location and preset range for issuing recommendation request
Hold, obtains candidate resource set；
Relevant parameter obtains module, for obtaining itself relevant parameter of all candidate resources in the candidate resource set
With intercorrelation parameter；
Table of quality scores obtains module, for obtaining the candidate by itself relevant parameter and intercorrelation parameter
The table of quality scores of resource collection；
Recommend resource determination module, for determining to recommend from the candidate resource set according to the table of quality scores
Resource, and send the recommendation resource.
On the other hand a kind of equipment is provided, the equipment includes processor and memory, is stored in the memory
At least one instruction, at least one section of program, code set or instruction set, at least one instruction, at least one section of program, institute
Code set or instruction set is stated to be loaded as the processor and executed to realize resource recommendation method described in one side as above.
On the other hand a kind of computer readable storage medium is provided, at least one finger is stored in the storage medium
Enable, at least one section of program, code set or instruction set, at least one instruction, at least one section of program, the code set or
Instruction set is loaded as processor and is executed to realize resource recommendation method described in one side as above.
A kind of resource allocation method, device, equipment and storage medium provided by the invention, have the following technical effect that
The present invention obtains target visitor according to the geographical location information of client and the resource content in preset range
All candidate resources at family end；Further, itself relevant parameter and intercorrelation parameter of all candidate resources are obtained；By institute
Itself relevant parameter and intercorrelation parameter are stated, obtains the table of quality scores of the candidate resource set；According to the quality point
It is worth table, the recommendation resource to be recommended to the destination client is determined from the candidate resource set.The present invention can be
Target customer's end subscriber automatic screening simultaneously recommends good resource content near out, and premium content is allowed to have more presentation chances；
To improve the experience sense of user by promotion corresponds to user's viscosity of client, and then plays the effect of drainage.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology and advantage, below will be to implementation
Example or attached drawing needed to be used in the description of the prior art are briefly described, it should be apparent that, the accompanying drawings in the following description is only
It is only some embodiments of the present invention, for those of ordinary skill in the art, without creative efforts,
It can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is the schematic diagram for the implementation environment that this specification embodiment provides；
Fig. 2 is a kind of resource recommendation method flow chart that this specification embodiment provides；
Fig. 3 is the offer of this specification embodiment by itself relevant parameter and intercorrelation parameter, obtains the time
Select the step flow chart of the table of quality scores of resource collection；
Fig. 4 be this specification embodiment provide the first weight parameter and the second weight parameter acquisition methods the step of stream
Cheng Tu；
Fig. 5 is determining from the candidate resource set according to the table of quality scores for this specification embodiment offer
Recommend the step flow chart of resource；
Fig. 6 is the schematic diagram of a scenario with the application program for recommending interface that this specification embodiment provides；
Fig. 7 is a kind of structural schematic diagram for resource recommendation device that this specification embodiment provides；
Fig. 8 is that the table of quality scores that this specification embodiment provides obtains the composition schematic diagram of module；
Fig. 9 is the composition schematic diagram for the weight parameter acquiring unit that this specification embodiment provides；
Figure 10 is the composition schematic diagram for the recommendation resource determination module that this specification embodiment provides；
Figure 11 is the composition schematic diagram for the negative resource removing module that this specification embodiment provides；
Figure 12 is a kind of structural schematic diagram for resource recommendation equipment that this specification embodiment provides.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art without making creative work it is obtained it is all its
His embodiment, shall fall within the protection scope of the present invention.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
In the suggested design of existing resource, exist in such a way that geographical location information carries out resource content recommendation,
Exactly resource content is successively recommended on the interface of the client according to the sequencing of distance；But the way of recommendation
There is no the browse operation behaviors before consideration user, and also there is no the relevant informations of the Comprehensive resource content to carry out resource
Effective judgement of quality so recommended resource content is for target customer's end subscriber, and is not belonging to high-quality resource.
Therefore, the invention proposes a kind of suggested design of resource, can based on the geographical location information of destination client,
The browsing behavior parameter of combining target client user and by the relevant parameter of browsing resource, is ranked up resource content and pushes away
It recommends, good resource content nearby is presented for the client, allows more good resource contents to be presented, improves user's body
It tests.
As shown in Figure 1, it illustrates the schematic diagrames of the implementation environment under the technical program；The implementation environment includes: service
Device 02, the multiple terminals communicated with the server 02 (than terminal 01 and terminal 03 as shown in figure 1).Wherein, eventually
It end all can be mobile phone, tablet computer, portable acquisition machine on knee, PAD or desk-top acquisition machine etc..Operation is answered in terminal
With program, application program can be any application program with virtual resource transmission-receiving function.
The client has Application Program Interface, may include one or more kinds of composition interfaces in Application Program Interface
Interface element, specific interface element include but is not limited to one of window, dialog box, message box, status bar etc. or
Person is a variety of.Also, Application Program Interface may include the interface being shown in terminal screen and be stored in user terminal but not have
There is the interface for being shown in terminal screen.The interface of display on a terminal screen is referred to as display interface.Various interfaces in interface
Element may be collectively referred to as the content information in interface.
Server 02 can be a server, be also possible to the server cluster consisted of several servers, or
It is that a cloud obtains service centre；Server 02 is established and is communicated to connect by network and one or more terminals.
Specifically, the application program in this specification can be used for recommending multimedia resource content, such as " NOW live streaming --
Near -- dynamic " commending contents, or the commending contents of " near microblogging -- hot topic -- " etc..Application journey in this specification
Sequence can also be recommendation service class resource content, for example, shopping retail shop recommendation, take out shop or neighbouring cuisines recommendation interface,
Parking lot recommendation etc..
This specification embodiment provides a kind of resource recommendation method, as shown in Fig. 2, the method may include:
S202. resource recommendation request is received；
S204. according to the resource content in the geographical location and preset range for issuing recommendation request, candidate resource is obtained
Set；
When destination client issues the recommendation request of resource in the present embodiment, server receives the recommendation request；Into
One step, server obtains the position that destination client issues recommendation request.Similarly, the server can get client
The geographical location of end publication resource.
Specifically, the server, using pre-determined distance as radius, is obtained centered on the geographical location information of destination client
To corresponding preset range, there can be the second client of a large amount of publication resources in the preset range；Wherein, all to be located at institute
The resource for stating the client publication in preset range is candidate resource, and all candidate resources constitute the destination client
Candidate resource set.The resource content for being intended to oneself publication based on each destination client can also be shown in commending contents circle
It clicks and browses for other users on face, so the resource content of destination client publication also belongs to candidate resource.
For example, by taking the NOW live streaming with a large number of users as an example；If will browse " NOW live streaming -- near -- dynamic "
Small red client is as destination client (small red for target user), using 70KM as pre-determined distance；The then preset range
It is exactly centered on small red client, using 70KM as the regional scope of radius；" NOW is straight for use in this regional scope
Broadcast -- near -- dynamic " all multimedia resources of publication just belong to the candidate resource set of the destination client.
It should be noted that the destination client and the second client in the present embodiment correspond to identical application program,
In resource content can carry out publication displaying in the same application domain, propagate and reprint or comment such as thumbs up at the operations
Resource content may include multimedia resource or service class resource.Specifically, the multimedia resource may include recommending interface
On audio content, video content, text or image content etc.；The service class resource may include shopping retail shop, take out
Shop or neighbouring cuisines, parking lot etc..Some of them application program not only only has a kind of resource content, as long as answering
Recommend the resource content that can be recommended on interface to belong to the resource in the present embodiment with program, does not do unique restriction.
S206. itself relevant parameter and intercorrelation parameter of all candidate resources in the candidate resource set are obtained；
Itself relevant parameter in the present embodiment may include: the time-parameters timeScore of the candidate resource, with
And the association parameter corrScore of the candidate resource.It is given and is illustrated with multimedia resource below:
Explanation is given for the time-parameters timeScore of candidate resource:
When multimedia resource is issued from client, the multimedia resource currently can be automatically record as at the time of publication
Content production time；Server is obtained according to current time (recommending at the time of resource) and the generation time of multimedia resource
intertime；Wherein intertime is the interval between content production time and the current time for carrying out multimedia resource recommendation
Duration.
Wherein, the time-parameters of the candidate resource in the present embodiment can pass through formula timeScore=100-5*
Intertime is obtained.It needs to give explanation, it, will be in resource in order to give the more chances for exposure of resource content newly uploaded
The time-parameters of appearance are as one of Consideration；TimeScore is given in the present embodiment is up to 100 score values；This implementation
The resource content newly uploaded in example is preferably away from the resource content in current time 20 hours, that is to say, that and intertime≤
20 hours.Wherein, over time, resource content generated time and current time closer to 20 hours, then the time joins
The score value of amount is just close to zero；If the resource content is not outstanding enough within this 20 hours, its whole mass parameter can drop
Low, recommended sequence automatically can be rearward.
Specifically, explanation is given to the association parameter corrScore of the candidate resource:
In detail, the association parameter corrScore of the candidate resource may include the size, described of the candidate resource
The grade of candidate resource publisher, the user feedback of the candidate resource etc..
For the candidate resource after being uploaded to corresponding client, corresponding client can calculate candidate money automatically
The size in source, at the same can by the grade of the user of the candidate resource, and later the candidate resource user feedback letter
Breath together get up by associated storage, forms the relevant parameter of the candidate resource.
The upper limit value of the size of the candidate resource generally according to using application program require limit value be bound；
Wherein when content format is video or audio format, considers the size of resource content while can consider audio or view together
The time span of frequency.The grade of the candidate resource publisher, specifically ranking of the publisher in used application program
Or intelligent's rank etc..The user feedback of the candidate resource, for example, user to the viewing number of the candidate resource, thumb up number, comment
By number, sharing number etc..The higher grade of the candidate resource publisher, user feedback is better, the entirety of the candidate resource
It is bigger that quality score allows for the higher probability of final score value by way of superposition.
If then the association parameter of the candidate resource can be when user feedback than only considering the candidate resource
CorrScore=(viewing number/impression) * 10+ (thumbing up number/viewing number) * 20+ (sharing number/impression) * 30+ (comment number/
Thumb up number) * 40；The ratio (viewing number/impression) for wherein watching number and impression can embody the candidate resource content
To the Attraction Degree of user, the ratio (thumbing up number/viewing number) for thumbing up number and viewing number can embody user in candidate resource
The degree of recognition of appearance is shared number and (is commented on the ratio (sharing number/impression) of impression and comment number with several ratio is thumbed up
Count/thumb up number) can to embody candidate resource content be the probability that user strikes a chord；The present embodiment is examined by many factors
Consider, to investigate the total quality score value of multimedia resource content indirectly.
Wherein, the multimedia resource in certain application programs with identifiable face information is compared relatively without face information
Multimedia resource, for users have higher attraction, can be preferentially by more matchmakers with identifiable face information
Body resource is considered as alternative recommendation resource；So accordingly: if detecting in candidate resource has identifiable face letter
Breath then carries out the increase of score value on the basis of parameter value before, such as: corrScore '=(viewing number/impression) * 10+
(thumbing up number/viewing number) * 20+ (sharing number/impression) * 30+ (comment number/thumb up number) * 40+50.
Wherein, general each client user is the resource content for being highly desirable to oneself upload, can be shown in recommendation
It is browsed before the Resources list by other users；So this psychology based on user considers: if detecting, candidate resource is
The resource content of user's publication of destination client, then carry out the increase of score value on the basis of parameter value before, such as: association
Parameter is corrScore=(viewing number/impression) * 20+ (thumbing up number/viewing number) * 30+ (comment on number/thumb up number) * 50+
100。
It needs to give explanation, for the Multiple factors considered, if obtaining being able to ascend candidate money by analysis
The quality score (being positively correlated with quality score) in source can then be superimposed consideration in corresponding parameter, to promote total quality
Score value.
So after the delimitation Jing Guo preset range, determining the multimedia resource in the present embodiment as candidate money
In the case where source, further server obtains itself relevant parameter of these candidate resources from client.
Wherein, the intercorrelation parameter in the present embodiment may include: between the candidate resource and destination client
Social parameter socScore apart from the publisher of parameter disScore and the candidate resource and target customer's end subscriber.
In detail, the social networks of the publisher of the candidate resource and target customer's end subscriber may include: the candidate resource
The intimate pass of publisher and the gender relation of target customer's end subscriber, the publisher of the candidate resource and target customer's end subscriber
System.
Specifically, for the publisher of the candidate resource, parameter disScore is given at a distance from target customer's end subscriber
With explanation:
When the multimedia resource being located in preset range is judged as the candidate resource of the destination client, server
It is calculated according to the geographical location in the geographical location of the destination client and candidate resource issue client terminal between the two
Distance interdis.It wherein, is about the candidate resource and target if 70km is accounted for the radius in a city
The distance between client parameter disScore=700-(interdis) * 10；Digit therein apart from parameter is thousand
Meter Dan Wei.
Also, the server can get the publisher of the candidate resource and the social of target customer's end subscriber is joined
It measures in socScore；The publisher of candidate resource and the gender relation of target customer's end subscriber, may include: candidate money in detail
Account gender of the source publisher in application program, the similarities and differences relationship with the account gender of target customer's end subscriber.Wherein
Candidate resource when belonging to special-shaped relationship, the candidate resource to compare when belonging to homosexuality have higher attraction；Institute
SocScore=100 can be set when belonging to heterosexual relations.
Further, the server can get the publisher of the candidate resource and the society of target customer's end subscriber
It hands in parameter socScore；The publisher of the candidate resource and the close relationship of target customer's end subscriber give explanation:
The close relationship can be according to the parent of the second client and destination client in the same application domain used
Close relationship (for example whether mutually being paid close attention on microblogging) or other applications associated with the application program used
The close relationship of (such as with the associated wechat of microblogging) or be that close relationship on terminal contact (is stored in the logical of other side
In news record)；For example, can be set when the publisher of the candidate resource and target customer's end subscriber mutually pay close attention to
SocScore=200 when meeting other conditions again on this basis, then can carry out the superposition of score value；That is: in candidate
The publisher of resource and target customer's end subscriber are mutually paid close attention to, belong to friend relation, associated application journey in current application program
Belong to friend relation in sequence, be stored on the address list of other side, wherein can be by setting when meeting above-mentioned a variety of situations
Being overlapped mutually for corresponding score value, improves the total quality score value of the candidate resource.
So after the delimitation Jing Guo above-mentioned preset range, determining the multimedia resource in the present embodiment as institute
In the case where stating destination client candidate resource, further server obtains the intercorrelation of these candidate resources from client
Parameter.
S208. by itself relevant parameter and intercorrelation parameter, the quality score of the candidate resource set is obtained
Table；
Wherein, each candidate resource all has itself corresponding relevant parameter and intercorrelation parameter, using it is corresponding from
The quality score of the candidate resource is calculated in body relevant parameter and intercorrelation parameter；Obtained all quality scores are with regard to group
At the table of quality scores；The pass of the corresponding quality score composition of candidate resource is specifically included in the table of quality scores
It is the table of comparisons.So further:
As a kind of feasible embodiment, step S208 is obtained by itself relevant parameter and intercorrelation parameter
The table of quality scores of the candidate resource set, as shown in figure 3, may include:
S402. obtain each candidate resource itself relevant parameter the first weight parameter and intercorrelation parameter
Two weight parameters；
Specifically, the present embodiment when judging the quality score of the candidate resource, join by itself correlation being directed to
Several and intercorrelation parameter all has corresponding weight parameter: first weight parameter is the weight of itself relevant parameter
Parameter, second weight parameter are the weight parameter of the intercorrelation parameter.
It needs to give explanation, it is accordingly described if itself relevant parameter includes the first parameter and the second parameter
Weight parameter includes the first weighted value and the second weighted value；Wherein first weighted value is the weight that first parameter occupies
Value, second weighted value are the weighted value that second parameter occupies.
So itself relevant parameter includes the time-parameters timeScore of the candidate resource in the present embodiment,
And the candidate resource association parameter corrScore when；First weight parameter includes: the weighted value of timeScore
The weighted value wc of wt and corrScore.The intercorrelation parameter includes: between the candidate resource and the client
The social parameter socScore apart from the publisher of parameter disScore and the candidate resource and the client user
When；Second weight parameter includes: the weighted value ws of the weighted value wd and socScore of disScore.
Wherein, the acquisition methods of the first weight parameter and the second weight parameter described in step S402, as shown in Fig. 4, packet
It includes:
S602. the first initial weight parameter, the second initial weight parameter and interval weight are set；
S604. it is obtained using the first initial weight parameter as initial parameters using the interval weight as moving parameter
To the first candidate weight；
S606. the described first candidate weight is updated to the first initial weight parameter, according to obtaining the first candidate weight
Mode obtains the second candidate weight；Multiple candidate weights of first weight parameter are obtained with this；
S608. in the way of the multiple candidate weights for obtaining first weight parameter, with second initial weight
Parameter is initial parameters, obtains multiple candidate weights of second weight parameter；
S610. it by the candidate weight of first weight parameter, is arranged with the candidate weight of second weight parameter
Column combination obtains multiple candidate weights pair；
S612. according to the candidate weight parameter, the output data of candidate resource set in preset duration is statisticallyd analyze；
S614. according to the statistic analysis result of output data, the first weight parameter is determined from the candidate weight pair
With the second weight parameter.
Specifically, the present embodiment can rule of thumb be arranged one and write from memory before carrying out resource recommendation to destination client
The initial weight value proportion combination recognized, by each weighted value input weight value management system in initial weight value proportion combination
It unites in (weighted value analysis program), observes the output data in weighted value management system (weighted value analysis program) later；Then
By continuously adjusting each weighted value, and the data variation of the output result of adjustment front and back is compared, obtaining can make to export result
Optimal weight proportion.
Wherein, the output data being statistically analyzed may include PV (Page View) amount of access, UV of the candidate resource
(Unique Visitor) independent user sessions averagely watches resource duration, averagely watches the data such as resource number.PV amount of access is
(preferably 1min in practice) the every opening of client user or one page of refreshing are just recorded as 1 PV in certain measurement period
Amount of access, repeatedly open or refresh the same page then belong to it is accumulative.UV independence user sessions is the (practice in certain measurement period
In preferably 1min) the access candidate resource number of users；One client account belongs to 1 independent user sessions.
Need to give explanation, the determination of first weight parameter and the second weight parameter is to carry out resource recommendation
Step analyzes obtained data before；In detail, multiple weighted values are all had in the first weight parameter and the second weight parameter
In the case of:
The certain weighted value combination (combination of initial weight value) of weighted value management system (weighted value analysis program) is given, is
System can respond output data result (data values such as PV, UV)；Usually data value is shown in graph form；
(such as one week) adjusts each weighted value in successively weighted value combination at regular intervals, before Record Comparison adjustment
The variation of output result afterwards, in all adjustment traversal post analysis tracing pattern tendencies, obtaining can make output result optimal
The weight of (maximization of the data such as PV, UV) matches, and obtains target weight combination and (has also just obtained the first weight parameter and the second power
Weight parameter).
For example, wc (weighted value of association parameter) is adjusted to 1 by 0.3, and when other weighted values remain unchanged, continuous observation
The variation tendency of weight output result adjusted (PV, UV, averagely watch resource duration, averagely watch resource number)；Other
Weighted value adjustment can constantly repeat above step, observe corresponding output result；It is optimal to obtain one
Weight configuration.
Further explanation is given, each weighted value adjustment is adjusted generally according to 0.05 interval, is weighed
Weight values will meet wd+wt+wc+ws=1；Weighted value generally has specific value in the combination of initial weight value in practice, each
The adjusting range of weighted value is positive and negative the 50% of corresponding initial weight value；For example, if when the initial weight value of wt is 0.2, it can be with
The adjusting range of wt is set as 0.1-0.3.In the present embodiment weighted value combination quantity be each weighted value parameter (such as
Wd, wt, wc, ws) all weighted values combinations of permutation and combination method composition；It automatically analyzes to obtain most by weighted value management system
Excellent weight configuration.
S404. according to itself relevant parameter of each candidate resource, the first weight parameter, intercorrelation parameter and
The quality score of the candidate resource is calculated in two weight parameters；
S406. the table of quality scores is formed by all quality score sequences.
Further, itself relevant parameter of the step S404 according to each candidate resource, the first weight parameter, interaction
Relevant parameter and the second weight parameter, are calculated the quality score of the candidate resource, may include:
The quality score of the candidate resource is calculated using the first formula；
First formula is totalScore=disScore*wd+timeScore*wt+ corrScore*wc+
socScore*ws。
Wherein, according to the time-parameters of the corresponding candidate resource of each candidate resource obtained above
TimeScore, the candidate resource association parameter corrScore, timeScore weighted value wt and corrScore
Weighted value wc；The publisher of the distance between the candidate resource and the client parameter disScore, the candidate resource
With the weighted value of the weighted value wd and socScore of social parameter socScore, disScore of the client user
ws；It is input in the first formula, and then the corresponding quality score of the candidate resource is calculated.
Need to give explanation, wd, wt, wc, ws can analyze the mode screening mode of program according to above-mentioned weighted value
It obtains；Application scenarios in view of the technical program are that the recommendation of neighbouring resource content is based on so accounting for for distance weighting is relatively high
Its content quality is considered the case where browsing more consideration is given to the candidate resource, so being followed by associated with parameter；Therefore, excellent
Selection of land initial weight group is combined into wd=0.4, wc=0.25, wt=0.2, ws=0.15.
Further, all candidate resources are calculated in the manner described above, and the server obtains the quality
Score table.
S210. it determines to recommend resource from the candidate resource set according to the table of quality scores, and described in transmission
Recommend resource；
In a kind of specific embodiment, step S210 according to the table of quality scores from the candidate resource set really
Recommendation resource is made, as shown in figure 5, may include:
S802. all quality scores in the table of quality scores are compared with default score value；
S804. when the quality score is greater than the default score value, then the corresponding candidate resource of the quality score is
The recommendation resource of the client.
The condition set in the present embodiment is quality score is more than that the candidate resource of default score value is the excellent of destination client
Matter resource；So pushing away for destination client is filtered out from the candidate resource compared with default score value by quality score
Recommend resource.Further, the recommendation resource is sent to destination client by server, and the recommendation resource is presented on target visitor
On the end of family, checked for target customer's end subscriber.Specifically, server will be greater than the quality score of the default score value from high to low
It successively sorts, so that the corresponding candidate resource of these quality scores successively be sorted, and ranking results is shown in target customer
On end.
As a preferred embodiment, before sending the recommendation resource further include:
Judge the candidate resource whether with the target user there are interactive information；Specifically from the candidate resource
In user feedback, judge to issue whether the user of feedback information is target user, if it is, illustrating that the candidate resource is target
The resource content that user browsed before；The candidate resource is then deleted to filtering from candidate resource set；
The sequence that remaining candidate resource is carried out to quality score, recommends destination client.
Specifically, it is deleted by the way that user to be watched to the resource content of (commented on, thumbed up or the behaviors such as forwarded over), from
And reduce the quantity and efficiency of candidate resource processing, the quality score of the resource content provided for target user is provided.
Wherein, the method can also include:
Obtain the unfavorable ratings data and front evaluation data of resource content；
Corresponding negative index is obtained according to the unfavorable ratings data and front evaluation data；
When the negative index is greater than default index, the resource content is deleted out of described preset range.
Wherein, the unfavorable ratings data may include reported, the data informations such as difference is commented, is not liked.Such as in user
When feeling the situations such as some content is illegal or encroaches right, it can be reported by the report entrance on interface；Such as user
Poor quality was not liked or thought after browsing some content, is given and is not liked or the evaluation commented of difference.
It may include counting reported, do not liked and number that difference is commented etc. that unfavorable ratings data are obtained in the present embodiment；
Accordingly, it may include counting the number liked with favorable comment etc. that front evaluation data are obtained in the present embodiment.Further, lead to
It crosses accounting of the calculating unfavorable ratings data in all evaluation data and obtains corresponding negative index；It is greater than in the negative index
When default index, which is deleted out of corresponding preset range.Wherein, unfavorable ratings data in the present embodiment and just
Face evaluation data are not limited to above- mentioned information, are specifically applicable in and all have similar front evaluation information and negatively in scene
Evaluation information.
Explanation is given for the resource content reported:
Based on by report operation critical nature, can when the number of resource content reported reaches preset times,
The resource content is deleted out of preset range directly, the resource content is made to lose the user client as operation report movement
Candidate resource qualification (be added operation report movement user client blacklist ranks), do not showing client.
Wherein, in order to guarantee the reasonability and correctness of being reported that resource is deleted, usually need to make user's selection of report movement
It reports reason or fills in report reason and be submitted to backstage, backstage personnel audit report content later.
Wherein, the adjustment of adaptability can be made in the present embodiment to content, time limit shown in resource and form.This reality
The recommendation process for applying the resource content in example is as report and delete operation are constantly adjusting；If it is in this time
The operation reported and deleted is performed before recommendation process, then the recommendation results at the moment be after delete operation is made more
It is obtained on the basis of the candidate resource newly obtained；The behaviour for being reported and being deleted is performed if it is after the secondary recommendation process
Make, then the recommendation results of subsequent time are obtained on the basis of the candidate resource updated after delete operation is made.
The resource recommendation method that this specification provides constantly can comprehensively collect all clients user and browse resource
Browsing behavior record when content；Information is recorded according to itself relevant information of resource and the browsing behavior of user, is obtained pair
Answer itself relevant parameter and intercorrelation parameter of resource；By itself relevant parameter and intercorrelation parameter, obtain described
The table of quality scores of candidate resource set；According to the ranking results of quality score in table of quality scores, by determining recommendation resource
It is shown on destination client with different displaying sequences.The scene with the application program for recommending interface is illustrated in figure 6 to show
It is intended to.The present invention can comprehensively consider information relevant to candidate resource by comprehensive, the quality score essence being calculated
True property is high, and the resource content that Automatic sieve is selected more is bonded the demand of destination client, belongs to good resource content nearby, improves
The experience sense of user is by user's viscosity of the corresponding client of promotion；And the premium content is allowed there are more presentation chances, in turn
Play the effect of drainage；Further, on the basis of the recommendation of neighbouring premium content, be able to ascend target customer's end subscriber with it is high-quality
Interaction probability and friend-making enthusiasm between content user.
Client user can be reported or be drawn to low quality resource content at black equal operations in this specification embodiment
Reason, server can carry out the management service of respective resources content (such as by low-quality content based on this generic operation of user
Carry out undercarriage or deletion), the total quality of resource content is improved, it is final to be provided for user in neighbouring more good resource
Hold, makes user that there is better Product Experience.
This specification embodiment provides a kind of resource recommendation device, as shown in fig. 7, described device includes:
Recommendation request receiving module 202, for receiving resource recommendation request；
Candidate resource obtains module 204, for according to the money in the geographical location and preset range for issuing recommendation request
Source contents obtain candidate resource set；
Relevant parameter obtains module 206, for obtaining itself correlation of all candidate resources in the candidate resource set
Parameter and intercorrelation parameter；
Table of quality scores obtains module 208, for obtaining the time by itself relevant parameter and intercorrelation parameter
Select the table of quality scores of resource collection；
Recommend resource determination module 210, for determining from the candidate resource set according to the table of quality scores
Recommend resource, and sends the recommendation resource.
One kind is specifically in embodiment, and the table of quality scores obtains module 208, as shown in figure 8, may include:
Weight parameter acquiring unit 402, for obtaining the first weight parameter of itself relevant parameter of each candidate resource, with
And the second weight parameter of intercorrelation parameter；
Quality score obtains unit 404, for being joined according to itself relevant parameter of each candidate resource, the first weight
Number, intercorrelation parameter and the second weight parameter, are calculated the quality score of the candidate resource；
Table of quality scores obtains unit 406, for forming the table of quality scores by all quality score sequences.
In a kind of specifically embodiment, the weight parameter acquiring unit 402, as shown in figure 9, may include:
Parameter setting subelement 602, for setting the first initial weight parameter, the second initial weight parameter and interval power
Weight；
First candidate weight obtains subelement 604, is used for using the first initial weight parameter as initial parameters, with institute
Interval weight is stated as moving parameter, obtains the first candidate weight；
First weight set obtains subelement 606, for the described first candidate weight to be updated to the first initial weight ginseng
Number obtains the second candidate weight according to the mode of the first candidate weight is obtained；The multiple of first weight parameter are obtained with this
Candidate weight；
Second weight set obtains subelement 608, for according to obtaining multiple candidate weights of first weight parameter
Mode obtain multiple candidate weights of second weight parameter using the second initial weight parameter as initial parameters；
Weight is to subelement 610 is obtained, for joining with second weight by the candidate weight of first weight parameter
Several candidate weights carries out permutation and combination, obtains multiple candidate weights pair；
Output data obtains subelement 612, for statisticalling analyze candidate in preset duration according to the candidate weight parameter
The output data of resource collection；
Weight parameter obtains subelement 614, for the statistic analysis result according to output data, from the candidate weight pair
In determine the first weight parameter and the second weight parameter.
In detail, itself relevant parameter includes: the time-parameters timeScore of the candidate resource and described
The association parameter corrScore of candidate resource；
First weight parameter includes: the weighted value wc of the weighted value wt and corrScore of timeScore；
The intercorrelation parameter includes: the distance between the candidate resource and the client parameter disScore,
And the social parameter socScore of the publisher of the candidate resource and the client user；
Second weight parameter includes: the weighted value ws of the weighted value wd and socScore of disScore.
In a kind of feasible embodiment, the quality score obtains unit 404, comprising:
Quality score obtains subelement, for the quality score of the candidate resource to be calculated using the first formula；Institute
Stating the first formula is totalScore=disScore*wd+timeScore*wt+corrScore*wc+socScore*ws.
Specifically in embodiment, the recommendation resource determination module 210 as shown in Figure 10, may include: one kind
Quality score comparing unit 802, for by the table of quality scores all quality scores and default score value into
Row compares；
Recommend resource determination unit 804, for when the quality score is greater than the default score value, then the quality to be divided
It is worth the recommendation resource that corresponding candidate resource is the client.
For one kind specifically in embodiment, described device further includes negative resource removing module 212, as shown in Figure 11, institute
Stating negative resource removing module includes:
Data capture unit 1002 is evaluated, for obtaining the unfavorable ratings data and front evaluation data of resource content；
Negative index obtains unit 1004, corresponding for being obtained according to the unfavorable ratings data and front evaluation data
Negative index；
Resource content deletes unit 1006, is used for when the negative index is greater than default index, by the resource content
It is deleted out of described preset range.
Need to give explanation, Installation practice provided in this embodiment is identical with having with above method embodiment
Inventive concept.
This specification embodiment provides a kind of equipment, and the equipment includes processor and memory, in the memory
It is stored at least one instruction, at least one section of program, code set or instruction set, described at least one instructs, is at least one section described
Program, the code set or instruction set are loaded as the processor and are executed to realize the resource as described in above method embodiment
Recommended method.
Specifically, this specification embodiment additionally provides a kind of schematic diagram of resource recommendation equipment, please refers to Figure 12.This sets
It is ready for use on the resource recommendation method for implementing to provide in above-described embodiment.Specifically:
The server 2000 includes central processing unit (CPU) 2001 including random access memory (RAM) 2002
With the system storage 2004 of read-only memory (ROM) 2003, and connection system storage 2004 and central processing unit
2001 system bus 2005.The server 2000 further includes the base that information is transmitted between each device helped in computer
This input/output (I/O system) 2006, and it is used for storage program area 2013, application program 2014 and other program moulds
The mass-memory unit 2007 of block 2015.
The basic input/output 2006 includes display 2008 for showing information and inputs for user
The input equipment 2009 of such as mouse, keyboard etc of information.Wherein the display 2008 and input equipment 2009 all pass through
The input and output controller 2010 for being connected to system bus 2005 is connected to central processing unit 2001.The basic input/defeated
System 2006 can also include input and output controller 2010 to touch for receiving and handling from keyboard, mouse or electronics out
Control the input of multiple other equipment such as pen.Similarly, input and output controller 2010 also provide output to display screen, printer or
Other kinds of output equipment.
The mass-memory unit 2007 (is not shown by being connected to the bulk memory controller of system bus 2005
It is connected to central processing unit 2001 out).The mass-memory unit 2007 and its associated computer-readable medium are
Server 2000 provides non-volatile memories.That is, the mass-memory unit 2007 may include such as hard disk or
The computer-readable medium (not shown) of person's CD-ROM drive etc.
Without loss of generality, the computer-readable medium may include computer storage media and communication media.Computer
Storage medium includes information such as computer readable instructions, data structure, program module or other data for storage
The volatile and non-volatile of any method or technique realization, removable and irremovable medium.Computer storage medium includes
RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storages its technologies, CD-ROM, DVD or other optical storages, tape
Box, tape, disk storage or other magnetic storage devices.Certainly, skilled person will appreciate that the computer storage medium
It is not limited to above-mentioned several.Above-mentioned system storage 2004 and mass-memory unit 2007 may be collectively referred to as memory.
According to various embodiments of the present invention, the server 2000 can also be arrived by network connections such as internets
Remote computer operation on network.Namely server 2000 can be connect by the network being connected on the system bus 2005
Mouth unit 2011 is connected to network 2012, in other words, it is other kinds of to be connected to that Network Interface Unit 2011 also can be used
Network or remote computer system (not shown).
The memory further includes that one or more than one program, the one or more programs are stored in
In memory, and it is configured to be executed by one or more than one processor；Said one or more than one program include
For executing the instruction of the method for above-mentioned background server side, described instruction is for executing resource recommendation described in above-described embodiment
Method.
This specification embodiment provides a kind of computer readable storage medium, and at least one is stored in the storage medium
Item instruction, at least one section of program, code set or instruction set, at least one instruction, at least one section of program, the code
Collection or instruction set are loaded as processor and are executed to realize the resource recommendation method as described in above-described embodiment.
Optionally, in the present embodiment, above-mentioned storage medium can be located in multiple network equipments of computer network
At least one network equipment.Optionally, in the present embodiment, above-mentioned storage medium can include but is not limited to: USB flash disk read-only is deposited
Reservoir (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), movement are hard
The various media that can store program code such as disk, magnetic or disk.
It should be understood that above-mentioned this specification embodiment sequencing is for illustration only, the excellent of embodiment is not represented
It is bad.And above-mentioned this specification specific embodiment is described.Other embodiments are within the scope of the appended claims.?
The movement recorded in detail in the claims under some cases or step can execute simultaneously according to the sequence being different from embodiment
And desired result still may be implemented.In addition, process depicted in the drawing not necessarily require the particular order shown or
Consecutive order is just able to achieve desired result.In some embodiments, multitasking and parallel processing it is also possible or
Person may be advantageous.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device and
For server example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to side
The part of method embodiment illustrates.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (15)
1. a kind of resource recommendation method, which is characterized in that the described method includes:
Receive resource recommendation request；
According to the resource content in the geographical location and preset range for issuing recommendation request, candidate resource set is obtained；
Obtain itself relevant parameter and intercorrelation parameter of all candidate resources in the candidate resource set；
By itself relevant parameter and intercorrelation parameter, the table of quality scores of the candidate resource set is obtained；
It determines to recommend resource from the candidate resource set according to the table of quality scores, and sends the recommendation resource.
2. resource recommendation method according to claim 1, which is characterized in that described by itself relevant parameter and interaction
Relevant parameter obtains the table of quality scores of the candidate resource set, comprising:
Obtain each first weight parameter of itself relevant parameter and the second weight parameter of intercorrelation parameter；
Joined according to itself relevant parameter of each candidate resource, the first weight parameter, intercorrelation parameter and the second weight
Number, is calculated the quality score of the candidate resource；
The table of quality scores is formed by all quality score sequences.
3. resource recommendation method according to claim 2, which is characterized in that first weight parameter and the second weight ginseng
Several acquisition methods, comprising:
Set the first initial weight parameter, the second initial weight parameter and interval weight；
The first time is obtained using the interval weight as moving parameter using the first initial weight parameter as initial parameters
Select weight；
Described first candidate weight is updated to the first initial weight parameter, according to the mode of the first candidate weight is obtained, is obtained
Second candidate weight；Multiple candidate weights of first weight parameter are obtained with this；
It is starting with the second initial weight parameter in the way of the multiple candidate weights for obtaining first weight parameter
Parameter obtains multiple candidate weights of second weight parameter；
By the candidate weight of first weight parameter, permutation and combination is carried out with the candidate weight of second weight parameter, is obtained
To multiple candidate weights pair；
According to the candidate weight parameter, the output data of candidate resource set in preset duration is statisticallyd analyze；
According to the statistic analysis result of output data, the first weight parameter and the second weight are determined from the candidate weight pair
Parameter.
4. resource recommendation method according to claim 2, which is characterized in that
Itself relevant parameter includes: the time-parameters timeScore and the candidate resource of the candidate resource
It is associated with parameter corrScore；
First weight parameter includes: the first weighted value wt of time-parameters timeScore, and association parameter
The second weighted value wc of corrScore；
The intercorrelation parameter includes: the distance between the candidate resource and destination client parameter disScore, and
The social parameter socScore of the publisher of the candidate resource and target customer's end subscriber；
Second weight parameter includes: the third weighted value wd apart from parameter disScore, and social parameter socScore
The 4th weighted value ws.
5. resource recommendation method according to claim 4, which is characterized in that it is described according to each candidate resource from
Body relevant parameter, the first weight parameter, intercorrelation parameter and the second weight parameter, are calculated the quality of the candidate resource
Score value, comprising:
The quality score totalScore of the candidate resource is calculated using the first formula；
First formula is totalScore=disScore*wd+timeScore*wt+corrScore*wc+socScor e*
ws。
6. resource recommendation method according to claim 1, which is characterized in that it is described according to the table of quality scores from described
It determines to recommend resource in candidate resource set, and sends the recommendation resource, comprising:
All quality scores in the table of quality scores are compared with default score value；
When quality score is greater than the default score value, then the corresponding candidate resource of the quality score is the recommendation resource.
7. resource recommendation method according to claim 1, which is characterized in that the method also includes:
Obtain the unfavorable ratings data and front evaluation data of resource content；
Corresponding negative index is obtained according to the unfavorable ratings data and front evaluation data；
When the negative index is greater than default index, the resource content is deleted out of described preset range.
8. a kind of resource recommendation device, which is characterized in that described device includes:
Recommendation request receiving module, for receiving resource recommendation request；
Candidate resource obtain module, for according to issue recommendation request geographical location and preset range in resource content,
Obtain candidate resource set；
Relevant parameter obtains module, for obtaining itself relevant parameter of all candidate resources and friendship in the candidate resource set
Cross-correlation parameter；
Table of quality scores obtains module, for obtaining the candidate resource by itself relevant parameter and intercorrelation parameter
The table of quality scores of set；
Recommend resource determination module, recommends money for determining from the candidate resource set according to the table of quality scores
Source, and send the recommendation resource.
9. resource recommendation device according to claim 8, which is characterized in that the table of quality scores obtains module, comprising:
Weight parameter acquiring unit, for obtaining the first weight parameter of itself relevant parameter of each candidate resource, and interaction
Second weight parameter of relevant parameter；
Quality score obtains unit, for itself relevant parameter according to each candidate resource, the first weight parameter, interaction
Relevant parameter and the second weight parameter, are calculated the quality score of the candidate resource；
Table of quality scores obtains unit, for forming the table of quality scores by all quality score sequences.
10. resource recommendation device according to claim 9, which is characterized in that the weight parameter acquiring unit, comprising:
Parameter setting subelement, for setting the first initial weight parameter, the second initial weight parameter and interval weight；
First candidate weight obtains subelement, is used for using the first initial weight parameter as initial parameters, with the interval
Weight obtains the first candidate weight as moving parameter；
First weight set obtains subelement, for the described first candidate weight to be updated to the first initial weight parameter, according to
The mode of the first candidate weight is obtained, the second candidate weight is obtained；Multiple candidate power of first weight parameter are obtained with this
Weight；
Second weight set obtains subelement, in the way of the multiple candidate weights for obtaining first weight parameter,
Using the second initial weight parameter as initial parameters, multiple candidate weights of second weight parameter are obtained；
Weight is to subelement is obtained, for the time by the candidate weight of first weight parameter, with second weight parameter
It selects weight to carry out permutation and combination, obtains multiple candidate weights pair；
Output data obtains subelement, for statisticalling analyze candidate resource collection in preset duration according to the candidate weight parameter
The output data of conjunction；
Weight parameter obtains subelement, for the statistic analysis result according to output data, determines from the candidate weight centering
First weight parameter and the second weight parameter out.
11. resource recommendation device according to claim 9, which is characterized in that
Itself relevant parameter includes: the time-parameters timeScore of the candidate resource and the pass of the candidate resource
Join parameter corrScore；
First weight parameter includes: the weighted value wc of the weighted value wt and corrScore of timeScore；
The intercorrelation parameter includes: the distance between the candidate resource and destination client parameter disScore, and
The social parameter socScore of the publisher of the candidate resource and target customer's end subscriber；
Second weight parameter includes: the weighted value ws of the weighted value wd and socScore of disScore.
12. resource recommendation device according to claim 8, which is characterized in that the recommendation resource determination module, comprising:
Quality score comparing unit, for being compared all quality scores in the table of quality scores with default score value；
Recommend resource determination unit, is used for when quality score is greater than the default score value, then the corresponding time of the quality score
Selecting resource is the recommendation resource.
13. resource recommendation device according to claim 8, which is characterized in that described device further includes that negative resource is deleted
Module, the negative resource removing module include:
Data capture unit is evaluated, for obtaining the unfavorable ratings data and front evaluation data of resource content；
Negative index obtains unit, for obtaining corresponding negative finger according to the unfavorable ratings data and front evaluation data
Number；
Resource content deletes unit, for when the negative index is greater than default index, by the resource content from described pre-
If being deleted in range.
14. a kind of equipment, which is characterized in that the equipment includes processor and memory, is stored at least in the memory
One instruction, at least one section of program, code set or instruction set, at least one instruction, at least one section of program, the generation
Code collection or instruction set are loaded by the processor and are executed to realize the resource recommendation method as described in claim 1 to 7 is any.
15. a kind of computer readable storage medium, which is characterized in that be stored at least one instruction, extremely in the storage medium
Few one section of program, code set or instruction set, at least one instruction, at least one section of program, the code set or the instruction
Collection is loaded by processor and is executed to realize the resource recommendation method as described in claim 1 to 7 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811013083.2A CN109241425B (en) | 2018-08-31 | 2018-08-31 | Resource recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811013083.2A CN109241425B (en) | 2018-08-31 | 2018-08-31 | Resource recommendation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109241425A true CN109241425A (en) | 2019-01-18 |
| CN109241425B CN109241425B (en) | 2022-02-18 |
Family
ID=65059868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811013083.2A Active CN109241425B (en) | 2018-08-31 | 2018-08-31 | Resource recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109241425B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110266745A (en) * | 2019-03-08 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Information flow recommended method, device, equipment and storage medium based on depth network |
| CN110489655A (en) * | 2019-09-16 | 2019-11-22 | 浙江同花顺智能科技有限公司 | Hot content determination, recommended method, device, equipment and readable storage medium storing program for executing |
| CN110727858A (en) * | 2019-09-09 | 2020-01-24 | 上海凯京信达科技集团有限公司 | Recommendation method, computer storage medium and electronic device |
| CN110784508A (en) * | 2019-09-12 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Information processing method, device and equipment |
| CN110909184A (en) * | 2019-11-19 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Multimedia resource display method, device, equipment and medium |
| CN111008331A (en) * | 2019-11-29 | 2020-04-14 | 拉扎斯网络科技（上海）有限公司 | Shop-side display method and device, electronic equipment and storage medium |
| CN111427660A (en) * | 2020-03-19 | 2020-07-17 | 北京奇艺世纪科技有限公司 | Scheduling method and device for uploading machine |
| CN111461833A (en) * | 2020-03-31 | 2020-07-28 | 拉扎斯网络科技（上海）有限公司 | Information loading method, system, server, terminal and storage medium |
| CN111737566A (en) * | 2020-05-15 | 2020-10-02 | 深圳市战音科技有限公司 | Work sorting method, device and storage medium |
| CN111861605A (en) * | 2019-04-28 | 2020-10-30 | 阿里巴巴集团控股有限公司 | Business object recommendation method |
| CN112199187A (en) * | 2019-07-08 | 2021-01-08 | 北京字节跳动网络技术有限公司 | Content display method and device, electronic equipment and computer readable storage medium |
| CN112328865A (en) * | 2019-07-31 | 2021-02-05 | 北京达佳互联信息技术有限公司 | Information processing and recommending method, device, equipment and storage medium |
| CN112749333A (en) * | 2020-07-24 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Resource searching method and device, computer equipment and storage medium |
| CN113032686A (en) * | 2019-12-25 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Content recommendation method, device, storage medium and server |
| CN113362109A (en) * | 2021-05-31 | 2021-09-07 | 北京达佳互联信息技术有限公司 | Recommendation method and device for media resources, electronic equipment and storage medium |
| CN113365090A (en) * | 2021-05-31 | 2021-09-07 | 北京百度网讯科技有限公司 | Object recommendation method, object recommendation device, electronic equipment and readable storage medium |
| CN114139049A (en) * | 2021-11-19 | 2022-03-04 | 北京三快在线科技有限公司 | Resource recommendation method and device |
| CN114186050A (en) * | 2021-12-06 | 2022-03-15 | 北京达佳互联信息技术有限公司 | Resource recommendation method and device, electronic equipment and storage medium |
| CN114296598A (en) * | 2021-12-01 | 2022-04-08 | 北京达佳互联信息技术有限公司 | Information display method, device, equipment, system and computer product |
| CN114691970A (en) * | 2020-12-30 | 2022-07-01 | 北京达佳互联信息技术有限公司 | Data processing method, device, server and storage medium |
| CN113032686B (en) * | 2019-12-25 | 2024-05-28 | 北京达佳互联信息技术有限公司 | Content recommendation method, device, storage medium and server |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103581270A (en) * | 2012-08-08 | 2014-02-12 | 腾讯科技（深圳）有限公司 | User recommendation method and system |
| US20160085816A1 (en) * | 2014-09-19 | 2016-03-24 | Kabushiki Kaisha Toshiba | Information processing apparatus, information processing system, information processing method, and recording medium |
| CN105589852A (en) * | 2014-10-20 | 2016-05-18 | 阿里巴巴集团控股有限公司 | Information recommendation method and device |
| US20170004557A1 (en) * | 2015-07-02 | 2017-01-05 | Ebay Inc. | Data recommendation and prioritization |
| CN106326391A (en) * | 2016-08-17 | 2017-01-11 | 合智能科技（深圳）有限公司 | Method and device for recommending multimedia resources |
| CN106385634A (en) * | 2016-09-07 | 2017-02-08 | 合智能科技（深圳）有限公司 | Video recommendation method and device |
| CN107944026A (en) * | 2017-12-12 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation |
| CN108446410A (en) * | 2018-05-29 | 2018-08-24 | 科大讯飞股份有限公司 | Information recommendation method, device, system, equipment and readable storage medium storing program for executing |
-
2018
- 2018-08-31 CN CN201811013083.2A patent/CN109241425B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103581270A (en) * | 2012-08-08 | 2014-02-12 | 腾讯科技（深圳）有限公司 | User recommendation method and system |
| US20160085816A1 (en) * | 2014-09-19 | 2016-03-24 | Kabushiki Kaisha Toshiba | Information processing apparatus, information processing system, information processing method, and recording medium |
| CN105589852A (en) * | 2014-10-20 | 2016-05-18 | 阿里巴巴集团控股有限公司 | Information recommendation method and device |
| US20170004557A1 (en) * | 2015-07-02 | 2017-01-05 | Ebay Inc. | Data recommendation and prioritization |
| CN106326391A (en) * | 2016-08-17 | 2017-01-11 | 合智能科技（深圳）有限公司 | Method and device for recommending multimedia resources |
| CN106385634A (en) * | 2016-09-07 | 2017-02-08 | 合智能科技（深圳）有限公司 | Video recommendation method and device |
| CN107944026A (en) * | 2017-12-12 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation |
| CN108446410A (en) * | 2018-05-29 | 2018-08-24 | 科大讯飞股份有限公司 | Information recommendation method, device, system, equipment and readable storage medium storing program for executing |
Non-Patent Citations (1)
| Title |
|---|
| 高秋云: "基于用户兴趣度和地理位置的活动推荐", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110266745A (en) * | 2019-03-08 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Information flow recommended method, device, equipment and storage medium based on depth network |
| CN110266745B (en) * | 2019-03-08 | 2022-02-25 | 腾讯科技（深圳）有限公司 | Information flow recommendation method, device, equipment and storage medium based on deep network |
| CN111861605A (en) * | 2019-04-28 | 2020-10-30 | 阿里巴巴集团控股有限公司 | Business object recommendation method |
| CN112199187A (en) * | 2019-07-08 | 2021-01-08 | 北京字节跳动网络技术有限公司 | Content display method and device, electronic equipment and computer readable storage medium |
| CN112328865B (en) * | 2019-07-31 | 2024-01-05 | 北京达佳互联信息技术有限公司 | Information processing and recommending method, device, equipment and storage medium |
| CN112328865A (en) * | 2019-07-31 | 2021-02-05 | 北京达佳互联信息技术有限公司 | Information processing and recommending method, device, equipment and storage medium |
| CN110727858A (en) * | 2019-09-09 | 2020-01-24 | 上海凯京信达科技集团有限公司 | Recommendation method, computer storage medium and electronic device |
| CN110784508A (en) * | 2019-09-12 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Information processing method, device and equipment |
| CN110489655A (en) * | 2019-09-16 | 2019-11-22 | 浙江同花顺智能科技有限公司 | Hot content determination, recommended method, device, equipment and readable storage medium storing program for executing |
| CN110909184A (en) * | 2019-11-19 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Multimedia resource display method, device, equipment and medium |
| CN111008331A (en) * | 2019-11-29 | 2020-04-14 | 拉扎斯网络科技（上海）有限公司 | Shop-side display method and device, electronic equipment and storage medium |
| CN111008331B (en) * | 2019-11-29 | 2023-09-15 | 拉扎斯网络科技（上海）有限公司 | Store-side display method and device, electronic equipment and storage medium |
| CN113032686B (en) * | 2019-12-25 | 2024-05-28 | 北京达佳互联信息技术有限公司 | Content recommendation method, device, storage medium and server |
| CN113032686A (en) * | 2019-12-25 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Content recommendation method, device, storage medium and server |
| CN111427660A (en) * | 2020-03-19 | 2020-07-17 | 北京奇艺世纪科技有限公司 | Scheduling method and device for uploading machine |
| CN111461833B (en) * | 2020-03-31 | 2021-07-23 | 拉扎斯网络科技（上海）有限公司 | Information loading method, system, server, terminal and storage medium |
| CN111461833A (en) * | 2020-03-31 | 2020-07-28 | 拉扎斯网络科技（上海）有限公司 | Information loading method, system, server, terminal and storage medium |
| CN111737566A (en) * | 2020-05-15 | 2020-10-02 | 深圳市战音科技有限公司 | Work sorting method, device and storage medium |
| CN112749333B (en) * | 2020-07-24 | 2024-01-16 | 腾讯科技（深圳）有限公司 | Resource searching method, device, computer equipment and storage medium |
| CN112749333A (en) * | 2020-07-24 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Resource searching method and device, computer equipment and storage medium |
| CN114691970A (en) * | 2020-12-30 | 2022-07-01 | 北京达佳互联信息技术有限公司 | Data processing method, device, server and storage medium |
| CN113365090B (en) * | 2021-05-31 | 2022-11-18 | 北京百度网讯科技有限公司 | Object recommendation method, object recommendation device, electronic equipment and readable storage medium |
| CN113365090A (en) * | 2021-05-31 | 2021-09-07 | 北京百度网讯科技有限公司 | Object recommendation method, object recommendation device, electronic equipment and readable storage medium |
| CN113362109B (en) * | 2021-05-31 | 2023-09-26 | 北京达佳互联信息技术有限公司 | Recommendation method and device for media resources, electronic equipment and storage medium |
| CN113362109A (en) * | 2021-05-31 | 2021-09-07 | 北京达佳互联信息技术有限公司 | Recommendation method and device for media resources, electronic equipment and storage medium |
| CN114139049A (en) * | 2021-11-19 | 2022-03-04 | 北京三快在线科技有限公司 | Resource recommendation method and device |
| CN114296598A (en) * | 2021-12-01 | 2022-04-08 | 北京达佳互联信息技术有限公司 | Information display method, device, equipment, system and computer product |
| CN114296598B (en) * | 2021-12-01 | 2024-03-15 | 北京达佳互联信息技术有限公司 | Information display method, device, equipment, system and computer product |
| CN114186050A (en) * | 2021-12-06 | 2022-03-15 | 北京达佳互联信息技术有限公司 | Resource recommendation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109241425B (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241425A (en) | A kind of resource recommendation method, device, equipment and storage medium | |
| Baum | Red state, blue state, flu state: Media self-selection and partisan gaps in swine flu vaccinations | |
| Chung et al. | Triggering participation: Exploring the effects of third-person and hostile media perceptions on online participation | |
| US9467408B1 (en) | Interactive commentary based on video-content characteristics | |
| US20130317808A1 (en) | System for and method of analyzing and responding to user generated content | |
| US20140047049A1 (en) | Methods and systems for linking and prioritizing chat messages | |
| Hu et al. | Predicting user engagement on twitter with real-world events | |
| US20200097462A1 (en) | Experience analytic objects, systems and methods | |
| CN106445929A (en) | Activeness based user ranking method and system | |
| Hosseinmardi et al. | Evaluating the scale, growth, and origins of right-wing echo chambers on YouTube | |
| US20150142486A1 (en) | Systems and methods for cloud-based digital asset management | |
| US11030656B2 (en) | Media information presentation method, server, and storage medium | |
| CN107896153B (en) | Traffic package recommendation method and device based on mobile user internet surfing behavior | |
| Griessner | News agencies and Social Media | |
| CN105279587A (en) | Mobile internet based intelligent answer and questionnaire investigation evaluation analysis and transformation system | |
| CN103440237A (en) | Microblog data processing visualization system based on 3D (3-dimensional) model | |
| CN106779608B (en) | Information processing method and information processing system based on WeChat platform | |
| CN106231436A (en) | Message treatment method and processing means | |
| CN113535991A (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| Jan et al. | Pay-per-question: towards targeted Q&A with payments | |
| CN105635210A (en) | Network information recommending method and device, and reading system | |
| US9223887B2 (en) | Self-organizing community system | |
| WO2017062907A1 (en) | Online entertainment and brand matching | |
| CN109062945B (en) | Information recommendation method, device and system for social network | |
| Zhao et al. | Association rules analysis between brand post characteristics and consumer engagement on social media |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |