CN107992548A

CN107992548A - Information processing method, system, medium and computing device

Info

Publication number: CN107992548A
Application number: CN201711211142.2A
Authority: CN
Inventors: 王啸飞; 陈保需
Original assignee: Netease Media Technology Beijing Co Ltd
Current assignee: Netease Media Technology Beijing Co Ltd
Priority date: 2017-11-27
Filing date: 2017-11-27
Publication date: 2018-05-04
Anticipated expiration: 2037-11-27
Also published as: CN107992548B

Abstract

Embodiments of the present invention provide a kind of information processing method.The information processing method includes：The first feedback information for the media content pushed is obtained, wherein, the first feedback information is used to reflect tolerance of the user to media content quality；According to the first feedback information, tolerance of the user to media content quality is determined；Obtain at least one media content；And the media content to match with user to the tolerance of media content quality is selected from least one media content.Pass through the first feedback information, determine tolerance of the user to media content quality, the method of the present invention causes during personalized recommendation, take into account difference of the different user to media content quality tolerance, the media content for recommending to match with tolerance to user, more preferable reading experience is brought for user, and reduces the complaint related with media quality.In addition, embodiments of the present invention provide a kind of information processing system, a kind of medium and a kind of computing device.

Description

Information processing method, system, medium and computing device

Technical field

Embodiments of the present invention are related to field of information processing, more specifically, embodiments of the present invention are related to a kind of letter Cease processing method, system, medium and computing device.

Background technology

Background that this section is intended to provide an explanation of the embodiments of the present invention set forth in the claims or context.Herein Description recognizes it is the prior art not because not being included in this part.

In whole field of information processing, user can be interacted and be produced by the various clients on smart machine Raw substantial amounts of information.For Branding image, enhancing user's viscosity, is the personalized content of its recommendation according to the hobby of user Already as one of necessary functions of news category client, but the media content quality recommended may be uneven, causes " interior Hold of poor quality " become and be often mentioned in field feedback and a kind of problem that accounting amount is larger, such as title party, old heavy Multiple, wrong word, poor, the picture improper fit of content typesetting etc..For there is the user of feedback behavior, it is most of be the active of product and Core customer, for these feedbacks, main processing mode is without any processing or skimble-skamble reply, and such as feedback has been received Arrive, can solve as early as possible etc., while customer loss is caused, it is also possible to cause certain customers to select other channels, to product Produce further negative effect.Therefore, recommend the media content of high quality to user when personalized recommendation, can subtract The feedback of few user " content quality is poor ", can also to brand image establish and positive work is played in the retention of core customer With.

At present, there is the side of some media contents for recommending high quality to user when personalized recommendation Method, such as simple quality standard improved into recommendation pond, however, during disclosure design is realized, invention human hair At least there are the following problems in existing correlation technique：

Different users is different to the tolerance of same media content quality, and in the process of personalized recommendation In, the difference not in view of user to the tolerance of media content quality.

For the above problem in correlation technique, effective solution is not proposed also at present.

The content of the invention

As noted previously, as different users is different to the tolerance of same media content quality, that is to say, that For same media content, the higher user A of tolerance angle value may can tolerate the poor media content of content quality, and right Tolerate for the relatively low user B of angle value, may just can not put up with the poor media content of the content quality, may provide The feedback information of " content quality is poor ", is even complained.

Therefore in the prior art, during personalized recommendation is done, not in view of user to media content matter The difference of the tolerance of amount, this is very bothersome process.

For this, it is also very desirable to which a kind of improved information processing method, so that during personalized recommendation is done, considers to use Difference of the family to the tolerance of media content quality so that recommendation results accuracy and it is rich on meet the personalization of user Demand.

In the present context, embodiments of the present invention are intended to provide a kind of information processing method and its system.

In the first aspect of embodiment of the present invention, there is provided a kind of information processing method, including：Obtain to be directed to and pushed away First feedback information of the media content sent, wherein, above-mentioned first feedback information is used to reflect user to media content quality Tolerance；According to above-mentioned first feedback information, tolerance of the above-mentioned user to media content quality is determined；Obtain at least one matchmaker Hold in vivo；And select from above-mentioned at least one media content and match with above-mentioned user to the tolerance of media content quality Media content.

In the second aspect of embodiment of the present invention, there is provided a kind of information processing system, including：First obtains mould Block, for obtaining the first feedback information for the media content pushed, wherein, above-mentioned first feedback information, which is used to reflect, to be used Tolerance of the family to media content quality；Determining module, for according to above-mentioned first feedback information, determining above-mentioned user to media The tolerance of content quality；Second acquisition module, for obtaining at least one media content；And selecting module, for from State the media content selected at least one media content and matched with above-mentioned user to the tolerance of media content quality.

In the third aspect of embodiment of the present invention, there is provided a kind of computer-readable recording medium, is stored thereon with Executable instruction, above-metioned instruction, which is processed when unit performs, makes above-mentioned processing unit perform any one of above-described embodiment Information processing method.

In the fourth aspect of embodiment of the present invention, there is provided a kind of computing device, including：Processing unit；And deposit Storage unit, is stored thereon with computer executable instructions, and above-metioned instruction holds above-mentioned processing unit when processed unit performs Information processing method any one of row above-described embodiment.

The information processing method and its system of embodiment according to the present invention, by the first feedback information, determines user couple The tolerance of media content quality, method of the invention cause during personalized recommendation, take into account different user to matchmaker The difference of body content quality tolerance, while the media content to match with tolerance is recommended to user, it can also be ensured that The accuracy of personalized recommendation result and rich, more preferable reading experience is brought for user, and is reduced and media matter Measure related complaint.

Brief description of the drawings

Detailed description below, above-mentioned and other mesh of exemplary embodiment of the invention are read by reference to attached drawing , feature and advantage will become prone to understand.In the accompanying drawings, if showing the present invention's by way of example, and not by way of limitation Dry embodiment, wherein：

Fig. 1 schematically shows the environment that can be implemented within according to embodiments of the present invention；

Fig. 2 schematically shows the flow chart of information processing method according to an embodiment of the invention；

Fig. 3 A schematically show according to an embodiment of the invention according to the first feedback information, determine user to media The flow chart of the tolerance of content quality；

Fig. 3 B schematically show according to an embodiment of the invention selected from least one media content and user The flow chart of the media content to match to the tolerance of media content quality；

Fig. 3 C schematically show point of the performance figure according to an embodiment of the invention based on each bar media content Cloth situation, selects the media content that matches with user to the tolerance of media content quality from least one media content Flow chart；

Fig. 3 D schematically show the distribution map of the performance figure of media content according to an embodiment of the invention；

Fig. 3 E are schematically shown according to an embodiment of the invention to be selected based on accounting from least one media content Go out flow chart of the corresponding media content as the media content to match with user to the tolerance of media content quality；

Fig. 3 F schematically show the flow chart of information processing method according to another embodiment of the present invention；

Fig. 3 G schematically show the media content according to another embodiment of the present invention for obtaining and being directed to predetermined quantity The flow chart of second feedback information；

Fig. 3 H schematically show it is according to another embodiment of the present invention be based on the second feedback information, repair user to matchmaker The flow chart of the tolerance of body content quality；

Fig. 3 I schematically show it is according to another embodiment of the present invention be based on the second feedback information, determine to user couple What the tolerance of media content quality was repaired drafts the flow chart of reparation value；

Fig. 3 J schematically show it is according to another embodiment of the present invention based on repair weighted value, determine to user to matchmaker What the tolerance of body content quality was repaired drafts the flow chart of reparation value；

Fig. 4 schematically shows the block diagram of information processing system according to an embodiment of the invention；

Fig. 5 A schematically show the block diagram of determining module according to an embodiment of the invention；

Fig. 5 B schematically show the block diagram of selecting module according to an embodiment of the invention；

Fig. 5 C schematically show the block diagram of selecting unit according to an embodiment of the invention；

Fig. 5 D schematically show the block diagram of information processing system according to another embodiment of the present invention；

Fig. 5 E schematically show the block diagram of the 3rd acquisition module according to another embodiment of the present invention；

Fig. 5 F schematically show the block diagram of repair module according to another embodiment of the present invention；

Fig. 5 G schematically show the block diagram of the 6th determination unit according to another embodiment of the present invention；

Fig. 6 schematically shows the schematic diagram of computer-readable recording medium product according to embodiments of the present invention；With And

Fig. 7 schematically shows the block diagram of computing device according to embodiments of the present invention.

In the accompanying drawings, identical or corresponding label represents identical or corresponding part.

Embodiment

The principle of the present invention and spirit are described below with reference to some illustrative embodiments.It should be appreciated that provide this A little embodiments are not with any just for the sake of better understood when those skilled in the art and then realize the present invention Mode limits the scope of the invention.On the contrary, these embodiments are provided so that the disclosure is more thorough and complete, and energy It is enough that the scope of the present disclosure is intactly communicated to those skilled in the art.

One skilled in the art will appreciate that embodiments of the present invention can be implemented as a kind of system, device, equipment, method Or computer program product.Therefore, the disclosure can be implemented as following form, i.e.,：Complete hardware, complete software (including firmware, resident software, microcode etc.), or the form that hardware and software combines.

According to the embodiment of the present invention, it is proposed that a kind of method of information processing, system, medium and computing device.

In addition, any number of elements in attached drawing is used to example and unrestricted, and any name is only used for distinguishing, Without any restrictions implication.

Below with reference to some representative embodiments of the present invention, the principle of the present invention and spirit are explained in detail.

Summary of the invention

During the embodiment of the present invention is realized, inventor has found：During personalized recommendation, do not consider Difference to user to the tolerance of media content quality.

Embodiments of the present invention provide a kind of information processing method.The information processing method includes：Obtain for First feedback information of the media content of push, wherein, the first feedback information is used to reflect appearance of the user to media content quality Degree of bearing；According to the first feedback information, tolerance of the user to media content quality is determined；Obtain at least one media content；With And the media content to match with user to the tolerance of media content quality is selected from least one media content.Pass through One feedback information, determines tolerance of the user to media content quality, and method of the invention causes the process in personalized recommendation In, difference of the different user to media content quality tolerance is taken into account, in the media that user recommends and tolerance matches Hold, bring more preferable reading experience for user, and reduce the complaint related with media quality.

After the basic principle of the present invention is described, lower mask body introduces the various non-limiting embodiment party of the present invention Formula.

Application scenarios overview

The environment that can be implemented within of the embodiment of the present invention is elaborated with reference first to Fig. 1.

As shown in Figure 1, the environment 100 that can be implemented within of the embodiment of the present invention can include terminal device 101,102, 103, network 104 and server 105.Network 104 is logical to be provided between terminal device 101,102,103 and server 105 Believe the medium of link.Network 104 can include various connection types, such as wired, wireless communication link etc..

User can be interacted with using terminal equipment 101,102,103 by network 104 with server 105, to receive or send out Send message etc..Various client applications can be installed on terminal device 101,102,103, can be with by various client applications Publication medium content, can issue comment, such as follow-up, for example, forum's class application, web browser applications, news category application, (merely illustrative) such as instant messaging tools, mailbox client, social platform softwares.

Terminal device 101,102,103 can be had display screen and support to apply the various electronics of the various operations of APP Equipment, includes but not limited to smart mobile phone, tablet computer, pocket computer on knee and desktop computer etc..

Server 105 can be to provide the server of various services, such as utilize terminal device 101,102,103 to user The media content commented on provides the back-stage management server (merely illustrative) supported.Back-stage management server can be to receiving The data such as user comment analyze etc. processing, and by handling result (such as according to user's acquisition request or the webpage of generation, Information or data etc.) feed back to terminal device.

It should be noted that the information processing method that the embodiment of the present disclosure is provided can be performed by server 105.Or Can also be by other servers or server cluster execution different from server 105.Correspondingly, the embodiment of the present disclosure is provided Information processing system can be arranged in server 105, or be arranged at different from other servers of server 105 or service In device cluster.Certainly, the information processing method that the embodiment of the present disclosure is provided can also be held by terminal device 101,102 or 103 OK.Or can also be by the other-end equipment execution different from terminal device 101,102 or 103.Correspondingly, the disclosure is implemented The information processing system that example is provided can be arranged in terminal device 101,102 or 103, or is arranged at different from terminal device 101st, in 102 or 103 other-end equipment.

It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need Will, can have any number of terminal device, network and server.

It should be noted that present invention could apply to several scenes, for convenience of description, hereafter will be with a certain news visitor Family end is carrier, and user elaborates the present invention exemplified by being fed back for the media content of the news client push, and simultaneously The non-restriction to this clearly demarcated embodiment.

Illustrative methods

The environment 100 that can be implemented within reference to the embodiment of the present invention of Fig. 1, comes with reference to figure 2, Fig. 3 A~Fig. 3 J The method for describing the information processing of illustrative embodiments according to the present invention.It should be noted that above application scene be only for Readily appreciate spirit and principles of the present invention and show, embodiments of the present invention are unrestricted in this regard.On the contrary, Embodiments of the present invention can be applied to applicable any scene.

An embodiment of the present invention provides a kind of method of information processing.

Fig. 2 schematically shows the flow chart of information processing method according to an embodiment of the invention.

As shown in Fig. 2, the information processing method can include operation S210~S240, wherein：

In operation S210, the first feedback information for the media content pushed is obtained.

In operation S220, according to the first feedback information, tolerance of the user to media content quality is determined.

In operation S230, at least one media content is obtained.

In operation S240, select from least one media content and match with user to the tolerance of media content quality Media content.

According to an exemplary embodiment of the present, media content can be with the media table such as text, picture, audio or video Show one or more combining forms in form to present, do not limit herein.

According to an exemplary embodiment of the present, the first feedback information can be that user utilizes a variety of of news client offer Feedback conduit, for the feedback information for having pushed media content, as content quality is poor, title party, wrong word, content typesetting are poor, Picture improper fit etc..

Since the first feedback information directly reacts tolerance of the user to media content quality, can be according to first Feedback information determines tolerance of the user to media content quality, as the first feedback information of user A shows the user to media The tolerance of content quality is higher, and the first feedback information of user B show the user to the tolerance of media content quality compared with It is low.

When personalized recommendation is done, to the user of different tolerances, according to each user to media content quality Tolerance, selects the tolerance phase with the user to media content quality from the recommendation pond comprising at least one media content The media content matched somebody with somebody, the result of recommendation can accomplish to vary with each individual.

By the embodiment of the present invention, during personalized recommendation, take into account different user and media content quality is held The difference for degree of bearing, the media content for recommending to match with its tolerance to user, more preferable reading experience is brought for user, and And reduce the complaint related with media quality.

Fig. 3 A schematically show according to an embodiment of the invention according to the first feedback information, determine user to media The flow chart of the tolerance of content quality.

As shown in Figure 3A, this method can include operation S311~S315, wherein：

S311 is being operated, is determining the feedback conduit of the first feedback information.

In operation S312, according to the feedback conduit determined, the weighted value of the first feedback information is determined.

In operation S313, tolerance prediction model is loaded.

In operation S314, weighted value is inputted into tolerance prediction model, to obtain corresponding with the first feedback information first Tolerate angle value.

In operation S315, based on the first tolerance angle value, tolerance of the user to media content quality is determined.

According to an exemplary embodiment of the present, the feedback conduit of the first feedback information can have a variety of, such as client application Negative-feedback function, user's follow-up etc., do not limit herein possessed by user feedback entrance, every news in " setting " function It is fixed.The user feedback content reported by above three channel, can be changed, manages and be classified by such as " user feedback platform " Related data, specific implementation are not the emphasis that the present invention discusses, details are not described herein., can will be with based on user feedback system The relevant customer complaint problem of content quality does following classification (as shown in table 1).

Table 1

Channel	Question Classification
		User feedback entrance	Wrong word, figure is improper, typesetting is poor, title party, news content difference etc.
Negative-feedback	Content quality is poor, title party etc.
		Follow-up post	Title party, have wrong word, the fact not to be inconsistent

In view of the factor of user's operation cost, according to an exemplary embodiment of the present, by the feedback information of different channels Different weighted values is assigned, such as user feedback entrance：Complaint reason in once feeding back belongs to one or more Question Classifications, " content quality is poor " weighted value Score weightings 1.Negative-feedback：No matter one or two Question Classification is hit in a negative-feedback, " content quality is poor " weighted value Score only weights 0.5.Follow-up post：One or more Question Classifications are matched in follow-up post, " content quality is poor " weighted value Score only weights 0.5, the value range of the weighted value Score of content quality difference be [0 ,+ ∞]。

Tolerance prediction model is loaded, tolerance prediction model is that training obtains in advance using special user's training sample And local or high in the clouds are stored in, when use, is loaded directly into.The weighted value of definite content quality difference is inputted into tolerance Prediction model is spent, the first tolerance angle value of user can be obtained.Exemplary embodiments of the present invention are with tolerance model 0.8^Score ⁺¹Exemplified by illustrate, the feedback conduit determined according to the weighted value Score of content quality difference and it is definite, it is different Content quality difference weighted value Score corresponding content qualities tolerance angle value it is as shown in table 2.The weighted value of content quality difference The value range of Score is [0 ,+∞], and the weighted value of content quality difference is bigger, tolerance model 0.8^Score+1Value range Successively decrease since 0.8, i.e., it is more and more lower to ropy content tolerance.

Table 2

Content quality difference weighted value	Score	0.5	1	1.5	2	2.5	3	3.5
									Weighted value conversion process	Score+1	1.5	2	2.5	3	3.5	4	4.5
Content quality tolerance	0.8^Score+1	0.72	0.64	0.57	0.51	0.46	0.41	0.37
									Content quality difference weighted value	Score	4	4.5	5	5.5	6	6.5	7
Weighted value conversion process	Score+1	5	5.5	6	6.5	7	7.5	8
									Content quality tolerance	0.8^Score+1	0.33	0.29	0.26	0.23	0.21	0.19	0.17

By the embodiment of the present invention, due to using the channel according to the first feedback information, determining weighted value, utilizing weighted value Technical solution of the user to the tolerance of media content quality is determined with tolerance prediction model so that the prediction knot of tolerance Fruit is more accurate, while the foundation of tolerance prediction model can realize the purpose handled extensive information, reaches letter Change flow, improve the technique effect of forecasting efficiency.

Fig. 3 B schematically show according to an embodiment of the invention selected from least one media content and user The flow chart of the media content to match to the tolerance of media content quality.

As shown in Figure 3B, this method can include operation S321~S322, wherein：

S321 is being operated, is determining the performance figure of each bar media content at least one media content, wherein, performance figure For reflecting the quality level of media content.

In operation S322, the distribution situation of the performance figure based on each bar media content, from least one media content Select the media content to match with user to the tolerance of media content quality.

According to an exemplary embodiment of the present, be incorporated herein article rest mass index (hereinafter referred to as performance figure) this Concept, it is mainly from article readability, negative characteristics (such as three customs, title party), high-quality news sources, the several angles of editor's mark quality Degree is calculated, and specific calculating logic is not the emphasis being discussed herein, and is repeated no more.

According to the performance figure of each bar media content in the recommendation pond (including at least one media content) of media content and Its distribution situation, is selected from least one media content in the media to match with user to the tolerance of media content quality Hold, user A such as higher to the tolerance of media content quality, the media content of less high-quality volume index can be recommended, and it is right The relatively low user B of the tolerance of media content quality, can recommend the media content of more high-quality volume index, and concrete condition can be with The tolerance of media content quality is determined with reference to user, details are not described herein.

By the embodiment of the present invention, due to the distribution situation using the performance figure based on each bar media content, from least The technical solution of the media content to match with user to the tolerance of media content quality is selected in one media content, is being done During personalized recommendation, while considering user to the tolerance of media content quality, the matter of each bar media content is taken into account The distribution situation of volume index so that the quantity that can recall media content is guaranteed, and recommendation results have diversity.

Fig. 3 C schematically show point of the performance figure according to an embodiment of the invention based on each bar media content Cloth situation, selects the media content that matches with user to the tolerance of media content quality from least one media content Flow chart.

As shown in Figure 3 C, this method can include operation S331~S334, wherein：

In operation S331, according to the distribution situation of the performance figure of each bar media content, performance figure threshold value is determined, its In, performance figure is defined as high quality media content higher than the media content of performance figure threshold value.

In operation S332, based on performance figure threshold value, determine to include at least one media content all high-quality Measure media content.

The matchmaker of predetermined quantity is pushed in operation S333, the tolerance according to user to media content quality, true directional user Accounting of the high quality media content in the media content of predetermined quantity when holding in vivo.

In operation S334, selected based on accounting from least one media content corresponding media content as with user couple The media content that the tolerance of media content quality matches.

According to an exemplary embodiment of the present, herein by ten decile of value range [0,1] of media content performance figure simultaneously Check the corresponding media content quantity in each section, it is assumed that it is distributed as shown in fig. 3d.

Based on the distribution situation of media content performance figure, and the accuracy and diversity of recommendation results are considered, by 0.75 It is set to and distinguishes line (in figure shown in dotted line), is i.e. content of the performance figure more than or equal to 0.75 is set to high quality media content, is less than 0.75 is set to non-high quality media content.Therefore, at least needed more than or equal to 0.75 content recalling stage rest mass index Accounting 1-0.8^Score+1, physical relationship is as shown in table 3.

Table 3

Content quality difference weighted value	Score	0.5	1	1.5	2	2.5	3	3.5
									Weighted value conversion process	Score+1	1.5	2	2.5	3	3.5	4	4.5
Content quality tolerance	0.8^Score+1	0.72	0.64	0.57	0.51	0.46	0.41	0.37
									High quality media content accounting	1-0.8^Score+1	28%	36%	43%	49%	54%	59%	63%
Content quality difference weighted value	Score	4	4.5	5	5.5	6	6.5	7
									Weighted value conversion process	Score+1	5	5.5	6	6.5	7	7.5	8
Content quality tolerance	0.8^Score+1	0.33	0.29	0.26	0.23	0.21	0.19	0.17
									High quality media content accounting	1-0.8^Score+1	67%	71%	74%	77%	79%	81%	83%

It should be noted that in order to ensure to there are enough media contents to recall, media content weighted value Score of poor quality Threshold value can be 7, i.e., when Score >=7, handled according to Score=7.When Score=0, meaning is used Feedback information is submitted in family not over above-mentioned data channel, therefore tolerance model has no effect recommendation results.

By the embodiment of the present invention, due to the distribution situation using the performance figure based on each bar media content, from least The technical solution of the media content to match with user to the tolerance of media content quality is selected in one media content so that The media content recommended to user is combined with the tolerance of user, on the basis of accurately personalized recommendation, can also be reached Diversity and rich technique effect to recommendation, the usage experience of user are more preferable.

Fig. 3 E are schematically shown according to an embodiment of the invention to be selected based on accounting from least one media content Go out flow chart of the corresponding media content as the media content to match with user to the tolerance of media content quality.

As shown in FIGURE 3 E, this method can include operation S341~S345, wherein：

S341 is being operated, is obtaining the predetermined number value of the media content pushed to user.

In operation S342, high quality media content number when pushing the media content of predetermined quantity based on the true directional user of accounting The threshold value of amount.

In operation S343, determined according to the threshold value of quantity in the high quality media selected from least one media content The first quantitative value held.

In operation S344, according to predetermined number value and the first quantitative value, determine what is selected from least one media content Second quantitative value of non-high quality media content.

In operation S345, using the high quality media content of the first quantity and the non-high quality media content of the second quantity as The media content to match with user to the tolerance of media content quality.

It should be noted that the first quantitative value is not less than the threshold value of high quality media content quantity, the second quantitative value is The difference of predetermined number value and the first quantitative value, performance figure are defined as non-height less than the media content of performance figure threshold value Quality image content.

As shown in table 3, if the weighted value that the first feedback information determines is 4, input tolerance prediction model draws user couple The tolerance of media content quality be 0.33, then recall stage quality index more than 0.75 this threshold value media content extremely Few accounting is 67%, i.e., in the case where the predetermined number value of the media content pushed to user is 100, in high quality media It is at least 67 to hold, accordingly, it may be determined that going out the quantity of non-high quality media content.

By the embodiment of the present invention, due to using the tolerance according to user, in the media content of true directional user push Predetermined number value in the case of, high quality media content when pushing the media content of predetermined quantity based on the true directional user of accounting The threshold value of quantity, correspondingly, selects the technical solution of the media content of the non-high quality of corresponding number so that personalized recommendation During, not only ensured the quantity of high quality media content, but also can greatly meet user to the accuracys of recommendation results and Rich demand.

Fig. 3 F schematically show the flow chart of information processing method according to another embodiment of the present invention.

As illustrated in Figure 3 F, this method can include operation S351~S352, wherein：

In operation S351, after the media content of predetermined quantity is pushed to user, the media for predetermined quantity are obtained Second feedback information of content.

In operation S352, based on the second feedback information, tolerance of the user to media content quality is repaired.

It may change in view of user to the tolerance of media content quality with the migration of time, according to this Invention exemplary embodiment, not only by the media to match with user to the tolerance of media content quality of predetermined quantity Appearance is pushed to user, and after recommendation, also catches the feedback information of user in time, and tolerance is repaired, to realize Adjustment in real time.

By the embodiment of the present invention, due to using the feedback information according to user, the technical side repaired to tolerance Case so that user can adjust the tolerance of media content quality in real time according to the feedback information of user, ensure to recommend As a result optimality.

Fig. 3 G schematically show the media content according to another embodiment of the present invention for obtaining and being directed to predetermined quantity The flow chart of second feedback information.

As shown in Figure 3 G, this method can include operation S361~S362, wherein：

In operation S361, the matchmaker that performance figure in the media content for predetermined quantity is less than performance figure threshold value is obtained Hold situation about being operated in vivo.

In operation S362, the matchmaker based on performance figure in the media content for predetermined quantity less than performance figure threshold value Hold situation about being operated in vivo, determine the second feedback information.

According to an exemplary embodiment of the present, no matter the tolerance of user is higher or relatively low, there is certain probability Media content of the performance figure less than the threshold value of high quality media content quantity is read, if showing at this time positive emerging Interest, repairs content quality tolerance model, performance figure in the media content for predetermined quantity can be less than matter The situation that the media content of volume index threshold value is operated, determines the second feedback information.

By the embodiment of the present invention, due to being less than performance figure using for performance figure in the media content of predetermined quantity The situation that the media content of threshold value is operated, to determine the technical solution of the second feedback information so as to media content quality Tolerance can do appropriate adjustment to the feedback information of the media content of non-high quality according to user, real-time update, ensures The optimality of recommendation results.

As a kind of optional embodiment, performance figure less than the media content of performance figure threshold value operated including In the case of the operation of at least one of, the second feedback information is determined：Performance figure is less than the media of performance figure threshold value At least one media content in content is performed sharing operation；Performance figure is less than in the media content of performance figure threshold value At least one media content be performed collection operation；Performance figure is less than in the media content of performance figure threshold value at least One media content is performed reading operations；And performance figure is less than at least one in the media content of performance figure threshold value Bar media content is performed preservation operation.

According to an exemplary embodiment of the present, user is less than the media content of performance figure threshold value for performance figure Operation can include but is not limited to share, and collect, and preserve, and media content reads progress >=60% etc..Due in top information flow In, media content quality cannot be judged well based on media content title, therefore put aside and will click on as positive behavior.

By the embodiment of the present invention, due to being less than the media content of performance figure threshold value for performance figure using user Operational circumstances determine the technical solution of the second feedback information, fully take into account influence user's tolerance model it is many-sided because Element so that the second feedback information can be directly perceived, accurately reflects the tolerance situation of change of user, ensures the optimal of recommendation results Property.

Fig. 3 H schematically show it is according to another embodiment of the present invention be based on the second feedback information, repair user to matchmaker The flow chart of the tolerance of body content quality.

As shown in figure 3h, this method can include operation S371~S374, wherein：

In operation S371, based on the second feedback information, determine to repair the tolerance of media content quality user Draft reparation value.

In operation S372, the repairing condition that the tolerance set in advance to media content quality is repaired is obtained.

In operation S373, according to repairing condition, determine to draft the corresponding target reparation value of reparation value.

In operation S374, tolerance of the user to media content quality is repaired according to target reparation value.

According to an exemplary embodiment of the present, based on the second feedback information, the appearance to user to media content quality is determined It is R that what degree of bearing was repaired, which drafts reparation value,.

The repairing condition that tolerance set in advance to media content quality is repaired can be according to actual needs certainly Row definition, is herein to trigger the critical condition of weighted value Score reparation operations：Drafting the integral multiple that reparation value is R >=0.5 is Example, illustrates the exemplary embodiment of the present invention, but is not to limit.For example, certain user tolerance weighted value Score=7, such as It is 0.6 at this time that fruit, which drafts reparation value as R, can determine that target reparation value is 0.5 according to critical condition, then tolerance weighted value Score is changed into 6.5 (noticing that result is not 6.4) from 7；Or it is 1.2 to draft recovery value R, mesh can be determined according to critical condition It is 1 to mark reparation value, then tolerance weighted value Score is changed into 6 (noticing that result is not 5.8) from 7.Complete after once repairing operation, Reparation value R is restored to 0 immediately.In addition, it can be seen that user may not only rise to one grade in once recovering, amplitude is specifically risen to As shown in table 4.

Table 4

Rise to amplitude	1	2	3	4	＞ 4
						Reparation value	0.5≤R ＜ 1	1≤R ＜ 1.5	1.5≤R ＜ 2	2≤R ＜ 2.5	And so on

By the embodiment of the present invention, the reparation bar repaired according to the tolerance set in advance to media content quality Part, determines to draft the corresponding target reparation value of reparation value, tolerance is repaired, and ensure that the reasonability of reparation and operable Property.

Fig. 3 I schematically show it is according to another embodiment of the present invention be based on the second feedback information, determine to user couple What the tolerance of media content quality was repaired drafts the flow chart of reparation value.

As shown in fig. 31, this method can include operation S381~S383, wherein：

In operation S381, the corresponding operation behavior data of the second feedback information are determined.

In operation S382, according to operation behavior data, determine to repair the tolerance of media content quality user Reparation weighted value.

In operation S383, based on weighted value is repaired, determine what user repaired the tolerance of media content quality Draft reparation value.

According to an exemplary embodiment of the present, quality is less than to performance figure in the media content of predetermined quantity according to user The situation that the media content of index threshold value is operated, the second feedback information determined can be according to corresponding operation behavior Data determine to repair weighted value accordingly, and the recovery such as once shared or collected to weighted value Score of poor quality is 0.1, and is expired It is once 0.05 etc. that sufficient article, which reads recovery of the behavior of progress to Score,.

By the embodiment of the present invention, due to determining that what tolerance was repaired drafts using according to different operation behaviors Repair the technical solution of value so that the reparation to tolerance is more reasonable, meets the real tolerance situation of change of user.

Fig. 3 J schematically show it is according to another embodiment of the present invention based on repair weighted value, determine to user to matchmaker What the tolerance of body content quality was repaired drafts the flow chart of reparation value.

As shown in figure 3j, this method can include operation S391~S393, wherein：

In operation S391, obtain and repair weighted value acceleration model, wherein, the weighted value of acceleration model and the first feedback information It is related.

In operation S392, the weighted value of the first feedback information is inputted into acceleration model, determines to add to repairing weighted value The acceleration figure of speed.

In operation S393, based on repairing weighted value and repairing the acceleration figure of weighted value, determine to user to media content matter What the tolerance of amount was repaired drafts reparation value.

According to an exemplary embodiment of the present, influenced by user content quality tolerance is different, in a predetermined quantity Recommendation results in the probability of article of reading to content quality index ＜ 0.75 be different.Therefore, for different user Content quality tolerance, it is necessary to different acceleration is multiplied by, to ensure that the positive behavior of user can act on oneself in time Tolerance model.Definition accelerates function F herein, as shown in table 5.

Table 5

By taking the user of Score=7 as an example, based on the mapping table of table 5, its content quality tolerance is 0.17, by Score bands Enter acceleration model function F=1.26^ScoreAs a result it was 5.0 (retaining a decimal).If this user collects or has shared one The article of piece content rest mass ＜ 0.75, then it is 0.1*5.0 that Score, which drafts reparation value R, i.e., 0.5；Or this user reads The article and reading progress of one content rest mass ＜ 0.75 is higher than 60%, then it is 0.05*5.0 that Score, which drafts reparation value R, I.e. 0.25.It is clear that as Score=7, if user collects or has shared 0.75 article of content rest mass ＜, Or read 2 0.75 articles of content rest mass ＜ and read progress and be all higher than 60%, then its weighted value Score can be by 7 Recover to 6.5.

By the embodiment of the present invention, due to the technical solution using acceleration model so that what tolerance was repaired drafts Reparation value, from the influence of user's tolerance variations, can ensure the positive behavior of user can act on the appearance with oneself in time Degree of bearing model, ensure that the correctness of reparation.

Exemplary system

After the method for exemplary embodiment of the invention is described, next, with reference to figure 4, Fig. 5 A~Fig. 5 G to this Invention illustrative embodiments, the system that is used for realization information processing is described in detail.

An embodiment of the present invention provides a kind of information processing system.

Fig. 4 schematically shows the block diagram of information processing system according to an embodiment of the invention.

As shown in figure 4, the information processing system 400 can be obtained including the first acquisition module 410, determining module 420, second Modulus block 430 and selecting module 440.Wherein：First acquisition module 410 is used to obtain first for the media content pushed Feedback information, wherein, the first feedback information is used to reflect tolerance of the user to media content quality.Determining module 420 is used for According to the first feedback information, tolerance of the user to media content quality is determined.Second acquisition module 430 is used to obtain at least one Bar media content.Selecting module 440 is used to select from least one media content and tolerance of the user to media content quality Spend the media content to match.

Fig. 5 A schematically show the block diagram of determining module according to an embodiment of the invention.

As shown in Figure 5A, determining module 420 can include the first determination unit 511, the second determination unit 512, loading list Member 513,514 and the 3rd determination unit 515 of input unit.Wherein, the first determination unit 511 is used to determine the first feedback information Feedback conduit.Second determination unit 512 is used for the weighted value for according to the feedback conduit determined, determining the first feedback information.Add Carrier unit 513 is used to load tolerance prediction model.Input unit 514 is used to weighted value inputting tolerance prediction model, with Obtain the first tolerance angle value corresponding with the first feedback information.3rd determination unit 515 is used to, based on the first tolerance angle value, determine Tolerance of the user to media content quality.

Fig. 5 B schematically show the block diagram of selecting module according to an embodiment of the invention.

As shown in Figure 5 B, selecting module 440 can include the 4th determination unit 521 and selecting unit 522.Wherein：4th Determination unit 521 is used for the performance figure for determining each bar media content at least one media content, wherein, performance figure is used for Reflect the quality level of media content.Selecting unit 522 is used for the distribution situation of the performance figure based on each bar media content, from The media content to match with user to the tolerance of media content quality is selected at least one media content.

Fig. 5 C schematically show the block diagram of selecting unit according to an embodiment of the invention.

As shown in Figure 5 C, selecting unit 522 can include the first determination subelement 531, the second determination subelement 532, the Three determination subelements 533 and selection subelement 534.Wherein：First determination subelement 531 is used for the matter according to each bar media content The distribution situation of volume index, determines performance figure threshold value, wherein, performance figure is higher than the media content of performance figure threshold value It is defined as high quality media content.Second determination subelement 532 is used to be based on performance figure threshold value, determines at least one All high quality media contents included in media content.3rd determination subelement 533 is used for according to user to media content matter The tolerance of amount, high quality media content is in the media of predetermined quantity when true directional user pushes the media content of predetermined quantity Accounting in appearance.Selection subelement 534 is used to select corresponding media content work from least one media content based on accounting For the media content to match with user to the tolerance of media content quality.

As a kind of optional embodiment, subelement 534 is selected to be additionally operable to：Obtain the pre- of the media content to user's push Fixed number value；The threshold of high quality media content quantity when pushing the media content of predetermined quantity based on the true directional user of accounting Value；First quantitative value of the high quality media content for determining to select from least one media content according to the threshold value of quantity, Wherein, the first quantitative value is not less than the threshold value of quantity；According to predetermined number value and the first quantitative value, determine from least one matchmaker Second quantitative value of the non-high quality media content selected in holding in vivo, wherein, the second quantitative value is predetermined number value and first The difference of quantitative value, performance figure are defined as non-high quality media content less than the media content of performance figure threshold value；With And using the high quality media content of the first quantity and the non-high quality media content of the second quantity as with user to media content The media content that the tolerance of quality matches.

Fig. 5 D schematically show the block diagram of information processing system according to another embodiment of the present invention.

As shown in Figure 5 D, which further includes：3rd acquisition module 450 and repair module 460.Wherein：3rd obtains Module 450 is used for after the media content of predetermined quantity is pushed to user, obtains the of the media content for predetermined quantity Two feedback informations.Repair module 460 is used to be based on the second feedback information, repairs tolerance of the user to media content quality.

Fig. 5 E schematically show the block diagram of the 3rd acquisition module according to another embodiment of the present invention.

As shown in fig. 5e, the 3rd acquisition module 450 can include 551 and the 5th determination unit 552 of first acquisition unit.Its In：First acquisition unit 551 is used to obtain performance figure in the media content for predetermined quantity and is less than performance figure threshold value Media content situation about being operated.5th determination unit 552 is used to refer to based on quality in the media content for predetermined quantity Number determines the second feedback information less than the situation that the media content of performance figure threshold value is operated.

Fig. 5 F schematically show the block diagram of repair module according to another embodiment of the present invention.

As illustrated in figure 5f, it is true can to include the 6th determination unit 561, second acquisition unit the 562, the 7th for repair module 460 Order member 563 and reparation unit 564.Wherein：6th determination unit 561 is used to be based on the second feedback information, determines to user couple What the tolerance of media content quality was repaired drafts reparation value.It is set in advance right that second acquisition unit 562 is used to obtain The repairing condition that the tolerance of media content quality is repaired.7th determination unit 563 is used for according to repairing condition, determines to intend The corresponding target reparation value of periodical repair complex value.Unit 564 is repaired to be used to repair user to media content quality according to target reparation value Tolerance.

Fig. 5 G schematically show the block diagram of the 6th determination unit according to another embodiment of the present invention.

As depicted in fig. 5g, the 6th determination unit 561 can include the 4th determination subelement 571, the 5th determination subelement 572 With the 6th determination subelement 573.Wherein：4th determination subelement 571 is used to determine the corresponding operation behavior of the second feedback information Data.5th determination subelement 572 is used for according to operation behavior data, determine to user to the tolerance of media content quality into The reparation weighted value that row is repaired.6th determination subelement 573 is used to, based on weighted value is repaired, determine to user to media content matter What the tolerance of amount was repaired drafts reparation value.

As a kind of optional embodiment, the 6th determination subelement 573 is additionally operable to：Obtain and repair weighted value acceleration model, Wherein, acceleration model is related to the weighted value of the first feedback information；The weighted value of first feedback information is inputted into acceleration model, really The fixed acceleration figure accelerated to repairing weighted value；And the acceleration figure based on reparation weighted value and reparation weighted value, definite pair What user repaired the tolerance of media content quality drafts reparation value.

Exemplary media

After the system of exemplary embodiment of the invention is described, next, with reference to figure 6 to the exemplary reality of the present invention Medium applying mode, being used for realization information processing is described in detail.

An embodiment of the present invention provides a kind of medium, is stored with computer executable instructions, above-metioned instruction is processed single Member makes processing unit perform any one of above method embodiment above-mentioned information processing method when performing.

In some possible embodiments, various aspects of the invention are also implemented as a kind of shape of program product Formula, it includes program code, and when described program product is being run in equipment, said program code is used to perform the equipment The information processing side of illustrative embodiments various according to the present invention described in above-mentioned " illustrative methods " part of this specification Operation (or step) in method, for example, the equipment can perform operation S210 as shown in Figure 2：Obtain to be directed to and pushed Media content the first feedback information, wherein, the first feedback information be used for reflect tolerance of the user to media content quality. Operate S220：According to the first feedback information, tolerance of the user to media content quality is determined.Operate S230：Obtain at least one Bar media content.Operate S240：The tolerance phase to media content quality with user is selected from least one media content The media content matched somebody with somebody.

Described program product can use any combination of one or more computer-readable recording mediums.Computer-readable recording medium can be readable letter Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example may be-but not limited to-electricity, magnetic, optical, electromagnetic, red The system of outside line or semiconductor, system or device, or any combination above.The more specifically example of readable storage medium storing program for executing (non exhaustive list) includes：Electrical connection, portable disc with one or more conducting wires, hard disk, random access memory (RAM), read-only storage (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc Read memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.

As shown in fig. 6, describing the program product 60 of information processing according to the embodiment of the present invention, it can be used Portable compact disc read only memory (CD-R0M) and including program code, and can be run in equipment, such as PC. However, the program product not limited to this of the present invention, in this document, readable storage medium storing program for executing can be any include or storage program Tangible medium, the program can be commanded execution system, system either device use or it is in connection.

Exemplary computer device

After the method, system and medium of exemplary embodiment of the invention is described, next, being introduced with reference to figure 7 The computing device of the information processing of an illustrative embodiments according to the present invention.

The embodiment of the present invention additionally provides a kind of computing device.The computing device includes：Processing unit；And storage is single Member, is stored with computer executable instructions, and above-metioned instruction is used for realization in above method embodiment when processed unit performs The above-mentioned information processing method of any one.

Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or Program product.Therefore, various aspects of the invention can be implemented as following form, i.e.,：It is complete hardware embodiment, complete The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.), or hardware and software, can unite here Referred to as " circuit ", " module " or " system ".

In some possible embodiments, the computing device of information processing according to the present invention can include at least at least One processing unit and at least one storage unit.Wherein, the storage unit has program stored therein code, works as described program When code is performed by the processing unit so that the processing unit performs to be retouched in above-mentioned " illustrative methods " part of this specification Operation (or step) in the information processing method for the illustrative embodiments various according to the present invention stated.For example, the processing Unit can perform operation S210 as shown in Figure 2：The first feedback information for the media content pushed is obtained, its In, the first feedback information is used to reflect tolerance of the user to media content quality.Operate S220：According to the first feedback information, Determine tolerance of the user to media content quality.Operate S230：Obtain at least one media content.Operate S240：From at least The media content to match with user to the tolerance of media content quality is selected in one media content.

The computing device 70 of the information processing of this embodiment according to the present invention is described referring to Fig. 7.Such as Fig. 7 Shown computing device 70 is only an example, should not bring any limit to the function and use scope of the embodiment of the present invention System.

As shown in fig. 7, computing device 70 is showed in the form of universal computing device.The component of computing device 70 can include But it is not limited to：Above-mentioned at least one processing unit 701, above-mentioned at least one storage unit 702, connection different system component (bag Include storage unit 702 and processing unit 701) bus 703.

Bus 703 includes address bus, controlling bus and data/address bus.

Storage unit 702 can include volatile memory, such as random access memory (RAM) 7021 and/or high speed Buffer memory 7022, can further include read-only storage (ROM) 7023.

Storage unit 702 can also include program/utility with one group of (at least one) program module 7024 7025, such program module 7024 includes but not limited to：Operating system, one or more application program, other program moulds Block and routine data, may include the realization of network environment in each or certain combination in these examples.

Computing device 70 can also be with one or more external equipments 704 (such as keyboard, sensing equipment, bluetooth equipment etc.) Communication, this communication can be carried out by input/output (I/O) interface 705.Also, computing device 70 can also pass through network Adapter 706 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network, such as because of spy Net) communication.As shown in the figure, network adapter 706 is communicated by bus 703 with other modules of computing device 70.It should be understood that Although not shown in the drawings, can combine computing device 70 uses other hardware and/or software module, include but not limited to：Micro- generation Code, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup are deposited Storage system etc..

It should be noted that although some units/modules of the system for information processing are referred in above-detailed Or subelement/submodule, but it is this division be merely exemplary it is not enforceable.It is in fact, real according to the present invention Mode is applied, the feature and function of two or more above-described units/modules can embody in a units/modules. Conversely, the feature and function of an above-described units/modules can be further divided into by multiple units/modules Lai specific Change.

In addition, although in the accompanying drawings with the operation of particular order the invention has been described method, still, this do not require that or Hint must perform these operations according to the particular order, or the operation having to carry out shown in whole could realize it is desired As a result.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and performed by some steps, and/or by one Step is decomposed into execution of multiple steps.

Although by reference to some embodiments the spirit and principle that the invention has been described, it should be appreciated that, this Invention is not limited to disclosed embodiment, and the division to each side does not mean that the feature in these aspects cannot yet Combination is to be benefited, and this division is merely to the convenience of statement.It is contemplated that cover appended claims spirit and In the range of included various modifications and equivalent arrangements.

Claims

1. a kind of information processing method, including：

The first feedback information for the media content pushed is obtained, wherein, first feedback information is used to reflect user To the tolerance of media content quality；

According to first feedback information, tolerance of the user to media content quality is determined；

Obtain at least one media content；And

The media to match with the user to the tolerance of media content quality are selected from least one media content Content.

2. according to the method described in claim 1, wherein, according to first feedback information, determine the user in media Holding the tolerance of quality includes：

Determine the feedback conduit of first feedback information；

According to the feedback conduit determined, the weighted value of first feedback information is determined；

Load tolerance prediction model；

The weighted value is inputted into the tolerance prediction model, to obtain the first tolerance corresponding with first feedback information Angle value；And

Based on the described first tolerance angle value, tolerance of the user to media content quality is determined.

3. according to the method described in claim 1, wherein, selected from least one media content with the user to matchmaker The media content that the tolerance of body content quality matches includes：

Determine the performance figure of each bar media content at least one media content, wherein, the performance figure is used for anti- Reflect the quality level of media content；And

The distribution situation of performance figure based on each bar media content, is selected and institute from least one media content State the media content that user matches the tolerance of media content quality.

4. according to the method described in claim 3, wherein, the distribution situation of the performance figure based on each bar media content, The media content to match with the user to the tolerance of media content quality is selected from least one media content Including：

According to the distribution situation of the performance figure of each bar media content, performance figure threshold value is determined, wherein, performance figure Media content higher than the performance figure threshold value is defined as high quality media content；

Based on the performance figure threshold value, determine in all high quality media for being included at least one media content Hold；

Tolerance according to the user to media content quality, when determining the media content to user push predetermined quantity Accounting of the high quality media content in the media content of the predetermined quantity；And

Selected based on the accounting from least one media content corresponding media content as with the user to matchmaker The media content that the tolerance of body content quality matches.

5. according to the method described in claim 4, wherein, selected based on the accounting from least one media content pair The media content answered includes as the media content to match with the user to the tolerance of media content quality

Obtain the predetermined number value of the media content pushed to the user；

It is described based on the accounting determine to the user push predetermined quantity media content when the high quality media content The threshold value of quantity；

The of the high quality media content for determining to select from least one media content according to the threshold value of the quantity One quantitative value, wherein, first quantitative value is not less than the threshold value of the high quality media content quantity；

According to the predetermined number value and first quantitative value, the non-height selected from least one media content is determined Second quantitative value of quality image content, wherein, second quantitative value is the predetermined number value and first quantitative value Difference, performance figure is defined as non-high quality media content less than the media content of the performance figure threshold value；And

Using the high quality media content of first quantity and the non-high quality media content of second quantity as with it is described The media content that user matches the tolerance of media content quality.

6. according to the method described in claim 4, wherein, the method further includes：

After the media content of the predetermined quantity is pushed to the user, the media content for the predetermined quantity is obtained The second feedback information；And

Based on second feedback information, tolerance of the user to media content quality is repaired.

7. method according to claim 6, wherein, second feedback information bag of the acquisition for the media content of the predetermined quantity Include：

Obtain the media content that performance figure in the media content for the predetermined quantity is less than the performance figure threshold value Situation about being operated；And

It is less than the media content of the performance figure threshold value based on performance figure in the media content for the predetermined quantity Situation about being operated, determines second feedback information.

8. a kind of information processing system, including：

First acquisition module, for obtaining the first feedback information for the media content pushed, wherein, first feedback Information is used to reflect tolerance of the user to media content quality；

Determining module, for according to first feedback information, determining tolerance of the user to media content quality；

Second acquisition module, for obtaining at least one media content；And

Selecting module, for selecting the tolerance with the user to media content quality from least one media content The media content to match.

9. a kind of computer-readable recording medium, is stored thereon with executable instruction, described instruction, which is processed when unit performs, to be made The processing unit performs the information processing method according to any one of claim 1-7.

10. a kind of electronic equipment, including：

Processing unit；And

Storage unit, is stored thereon with executable instruction, and described instruction makes the processing unit when being performed by the processing unit Perform the information processing method according to any one of claim 1-7.