CN107992548B

CN107992548B - Information processing method, system, medium, and computing device

Info

Publication number: CN107992548B
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: 2021-08-03
Anticipated expiration: 2037-11-27
Also published as: CN107992548A

Abstract

The embodiment of the invention provides an information processing method. The information processing method includes: acquiring first feedback information aiming at the pushed media content, wherein the first feedback information is used for reflecting the tolerance of a user on the quality of the media content; determining the tolerance of the user to the media content quality according to the first feedback information; obtaining at least one piece of media content; and selecting media content from the at least one piece of media content that matches the user's tolerance to the quality of the media content. The method ensures that the difference of the tolerance of different users to the quality of the media content is considered in the personalized recommendation process, recommends the media content matched with the tolerance for the users, brings better reading experience for the users and reduces complaints related to the media quality. Furthermore, embodiments of the present invention provide an information processing system, a medium, and a computing device.

Description

Information processing method, system, medium, and computing device

Technical Field

Embodiments of the present invention relate to the field of information processing, and more particularly, to an information processing method, system, medium, and computing device.

Background

This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.

In the whole information processing field, users can interact and generate a large amount of information through various clients installed on intelligent equipment. In order to establish brand image and enhance user stickiness, recommending personalized content for users according to the preferences of the users has become one of the essential functions of news clients, but the recommended media content quality may be uneven, so that the 'poor content quality' becomes a problem which is often mentioned and accounts for a large proportion in user feedback information, such as a title party, old and old repetition, wrongly written characters, poor content typesetting, improper picture adaptation and the like. For users with feedback behaviors, most users are active and core users of products, and for the feedback, the main processing mode is to do no processing or reply meaningless, such as the feedback is received and can be solved as soon as possible, and when the user is lost, part of users can select other channels, and further negative effects are generated on the products. Therefore, high-quality media content is recommended to the user during personalized recommendation, feedback of 'poor content quality' of the user can be reduced, and positive effects on establishment of brand images and retention of core users can be achieved.

At present, some methods for recommending high-quality media content to a user during personalized recommendation have appeared, such as simply improving the quality standard of entering the recommended content pool, however, in the process of implementing the disclosed concept, the inventors found that at least the following problems exist in the related art:

different users have different tolerances on the quality of the same media content, and the difference of the tolerances on the quality of the media content of the users is not considered in the process of personalized recommendation.

In view of the above problems in the related art, no effective solution has been proposed at present.

Disclosure of Invention

As mentioned above, since different users have different tolerances for the same media content, that is, a user a with a higher tolerance value may tolerate a media content with a lower content quality for the same media content, and a user B with a relatively lower tolerance value may not tolerate the media content with a lower content quality, and may give feedback information of "poor content quality" or even a complaint.

Therefore, in the prior art, the difference of tolerance of the user on the quality of the media content is not considered in the process of making personalized recommendation, which is a very annoying process.

Therefore, an improved information processing method is highly needed, so that in the process of making personalized recommendation, the difference of tolerance of the user on the quality of the media content is considered, and the recommendation result meets the personalized requirements of the user in terms of accuracy and richness.

In this context, embodiments of the present invention are intended to provide an information processing method and a system thereof.

In a first aspect of embodiments of the present invention, there is provided an information processing method including: acquiring first feedback information aiming at pushed media content, wherein the first feedback information is used for reflecting the tolerance of a user on the quality of the media content; determining the tolerance of the user to the quality of the media content according to the first feedback information; obtaining at least one piece of media content; and selecting the media content matched with the tolerance of the user on the quality of the media content from the at least one piece of media content.

In a second aspect of embodiments of the present invention, there is provided an information processing system including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring first feedback information aiming at the pushed media content, and the first feedback information is used for reflecting the tolerance of a user on the quality of the media content; a determining module, configured to determine, according to the first feedback information, tolerance of the user to media content quality; the second acquisition module is used for acquiring at least one piece of media content; and the selection module is used for selecting the media content matched with the tolerance of the user on the quality of the media content from the at least one piece of media content.

In a third aspect of embodiments of the present invention, there is provided a computer-readable storage medium having stored thereon executable instructions that, when executed by a processing unit, cause the processing unit to perform the information processing method of any one of the above embodiments.

In a fourth aspect of embodiments of the present invention, there is provided a computing device comprising: a processing unit; and a storage unit having computer-executable instructions stored thereon, which, when executed by the processing unit, cause the processing unit to perform the information processing method according to any one of the above embodiments.

According to the information processing method and the system thereof, the tolerance of the user to the quality of the media content is determined through the first feedback information, the method of the invention gives consideration to the difference of the tolerances of different users to the quality of the media content in the personalized recommendation process, and can ensure the accuracy and richness of the personalized recommendation result while recommending the media content matched with the tolerance to the user, thereby bringing better reading experience to the user and reducing complaints related to the media quality.

Drawings

The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:

FIG. 1 schematically illustrates an environment in which embodiments of the invention may be implemented;

FIG. 2 schematically shows a flow diagram of an information processing method according to an embodiment of the invention;

FIG. 3A schematically illustrates a flow chart for determining a user's tolerance to media content quality based on first feedback information, according to an embodiment of the invention;

FIG. 3B is a flow diagram that schematically illustrates selecting media content from at least one piece of media content that matches a user's tolerance for media content quality, in accordance with an embodiment of the present invention;

fig. 3C is a flow chart schematically illustrating a process of selecting media contents matching with the user's tolerance for the quality of the media contents from at least one piece of media contents based on the distribution of the quality indexes of the media contents according to an embodiment of the present invention;

FIG. 3D schematically shows a distribution diagram of quality indices of media content according to an embodiment of the invention;

FIG. 3E is a flow diagram that schematically illustrates selecting corresponding media content from at least one piece of media content based on dominance as media content that matches a user's tolerance for media content quality, in accordance with an embodiment of the present invention;

FIG. 3F schematically shows a flow chart of an information processing method according to another embodiment of the invention;

FIG. 3G schematically shows a flow diagram for obtaining second feedback information for a predetermined number of media content according to another embodiment of the invention;

FIG. 3H schematically shows a flow chart for fixing the user's tolerance to the quality of the media content based on the second feedback information according to another embodiment of the present invention;

FIG. 3I schematically shows a flowchart for determining a proposed repair value for repairing the user's tolerance to the quality of the media content based on the second feedback information, according to another embodiment of the present invention;

FIG. 3J schematically illustrates a flow diagram for determining a proposed repair value for repairing the user's tolerance to media content quality based on repair weight values, according to another embodiment of the invention;

FIG. 4 schematically shows a block diagram of an information handling system according to an embodiment of the invention;

FIG. 5A schematically illustrates a block diagram of the determination module according to an embodiment of the invention;

FIG. 5B schematically shows a block diagram of a selection module according to an embodiment of the invention;

FIG. 5C schematically shows a block diagram of a selection unit according to an embodiment of the invention;

FIG. 5D schematically shows a block diagram of an information handling system according to another embodiment of the invention;

FIG. 5E schematically illustrates a block diagram of a third acquisition module in accordance with another embodiment of the present invention;

FIG. 5F schematically illustrates a block diagram of a repair module according to another embodiment of the invention;

fig. 5G schematically shows a block diagram of a sixth determination unit according to another embodiment of the invention;

FIG. 6 schematically shows a schematic view of a computer-readable storage medium product according to an embodiment of the invention; and

FIG. 7 schematically shows a block diagram of a computing device according to an embodiment of the invention.

In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

Detailed Description

The principles and spirit of the present invention will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

As will be appreciated by one skilled in the art, embodiments of the present invention may be embodied as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.

According to an embodiment of the invention, a method, a system, a medium and a computing device for information processing are provided.

Moreover, any number of elements in the drawings are by way of example and not by way of limitation, and any nomenclature is used solely for differentiation and not by way of limitation.

The principles and spirit of the present invention are explained in detail below with reference to several representative embodiments of the invention.

Summary of The Invention

In the process of implementing the embodiment of the present invention, the inventors found that: in the process of personalized recommendation, the difference of tolerance of the user to the media content quality is not considered.

The embodiment of the invention provides an information processing method. The information processing method includes: acquiring first feedback information aiming at the pushed media content, wherein the first feedback information is used for reflecting the tolerance of a user on the quality of the media content; determining the tolerance of the user to the media content quality according to the first feedback information; obtaining at least one piece of media content; and selecting media content from the at least one piece of media content that matches the user's tolerance to the quality of the media content. The method ensures that the difference of the tolerance of different users to the quality of the media content is considered in the personalized recommendation process, recommends the media content matched with the tolerance for the users, brings better reading experience for the users and reduces complaints related to the media quality.

Having described the general principles of the invention, various non-limiting embodiments of the invention are described in detail below.

Application scene overview

Reference is first made to FIG. 1 for a detailed description of an environment in which embodiments of the invention may be practiced.

As shown in FIG. 1, an environment 100 in which embodiments of the invention may be implemented may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, and so forth.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various client applications may be installed on the

terminal devices

101, 102, and 103, through which media content may be published, comments may be published, such as postings, etc., for example, forum-like applications, web browser applications, news-like applications, instant messaging tools, mailbox clients, social platform software, etc. (just an example).

The

terminal devices

101, 102, 103 may be various electronic devices having display screens and supporting various operations of the application APP, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for media content that is reviewed by the user with the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user comment, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to a user request) to the terminal device.

It should be noted that the information processing method provided by the embodiment of the present disclosure may be executed by the server 105. Or may be performed by a server or cluster of servers other than server 105. Accordingly, the information processing system provided by the embodiment of the present disclosure may be disposed in the server 105, or disposed in another server or server cluster different from the server 105. Of course, the information processing method provided by the embodiment of the present disclosure may also be executed by the

terminal device

101, 102, or 103. Or may be performed by other terminal devices than

terminal devices

101, 102 or 103. Accordingly, the information processing system provided by the embodiment of the present disclosure may be provided in the

terminal device

101, 102, or 103, or in another terminal device different from the

terminal device

101, 102, or 103.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

It should be noted that the present invention can be applied to various scenarios, and for convenience of description, the following will use a certain news client as a carrier, and the user performs feedback on media content pushed by the news client as an example to describe the present invention in detail, but not limit the present invention.

Exemplary method

A method of information processing according to an exemplary embodiment of the present invention is described below with reference to fig. 2, 3A-3J, in conjunction with environment 100 of fig. 1 in which an embodiment of the present invention may be implemented. It should be noted that the above application scenarios are merely illustrated for the convenience of understanding the spirit and principles of the present invention, and the embodiments of the present invention are not limited in this respect. Rather, embodiments of the present invention may be applied to any scenario where applicable.

The embodiment of the invention provides an information processing method.

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

As shown in fig. 2, the information processing method may include operations S210 to S240, in which:

in operation S210, first feedback information for the pushed media content is acquired.

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

In operation S230, at least one piece of media content is acquired.

In operation S240, media content that matches the tolerance of the user for the quality of the media content is selected from the at least one piece of media content.

According to an exemplary embodiment of the present invention, the media content may be presented in one or more combinations of various media representations such as text, pictures, audio or video, and is not limited herein.

According to an exemplary embodiment of the present invention, the first feedback information may be feedback information for the pushed media content, such as poor content quality, a party with a title, wrongly written characters, poor content layout, improper picture adaptation, and the like, by using a plurality of feedback channels provided by the news client.

Since the first feedback information directly reflects the tolerance of the user to the quality of the media content, the tolerance of the user to the quality of the media content can be determined according to the first feedback information, for example, the first feedback information of the user a indicates that the tolerance of the user to the quality of the media content is high, and the first feedback information of the user B indicates that the tolerance of the user to the quality of the media content is low.

When personalized recommendation is made, for users with different tolerances, according to the tolerance of each user to the quality of the media content, the media content matched with the tolerance of the user to the quality of the media content is selected from a recommendation pool containing at least one piece of media content, and the recommendation result can be different from person to person.

According to the embodiment of the invention, in the process of personalized recommendation, the difference of different users on the media content quality tolerance is taken into consideration, the media content matched with the tolerance is recommended to the users, better reading experience is brought to the users, and complaints related to the media quality are reduced.

Fig. 3A schematically shows a flow chart for determining a user's tolerance to the quality of the media content according to the first feedback information according to an embodiment of the present invention.

As shown in fig. 3A, the method may include operations S311 to S315, in which:

in operation S311, a feedback channel of the first feedback information is determined.

In operation S312, a weight value of the first feedback information is determined according to the determined feedback channel.

In operation S313, a tolerance prediction model is loaded.

In operation S314, the weight value is input into the tolerance prediction model to obtain a first tolerance value corresponding to the first feedback information.

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

According to an exemplary embodiment of the present invention, the feedback channel of the first feedback information may be various, such as a user feedback entry in a "setting" function of the client application, a negative feedback function possessed by each piece of news, a user posting, and the like, and is not limited herein. The user feedback contents reported through the three channels can be converted, managed and classified into related data through a user feedback platform, and the specific implementation is not the focus of the discussion of the invention and is not repeated herein. Based on the user feedback system, the user complaint questions related to the content quality can be classified as follows (as shown in table 1).

TABLE 1

Channel for irrigation	Problem classification
		User feedback portal	Wrongly written characters, improper matching of drawings, bad typesetting, tolerance in the title party and news, etc
Negative feedback	Poor quality of content, title party, etc
		Follow paste	The title party, wrongly written characters, inconsistent facts, etc

Considering the factor of the operation cost of the user, according to the exemplary embodiment of the present invention, feedback information of different channels is given different weight values, such as: the complaint reasons in the primary feedback belong to one or more question categories, and the "poor content" weight value Score weighs 1. Negative feedback: the "poor content" weight Score weighs only 0.5 whether one or two question categories hit in a negative feedback. Follow-up pasting: one or more question classifications are matched in the one-time post-posting, the weighted values Score of the poor content quality are weighted by only 0.5, and the value range of the weighted values Score of the poor content quality is [0, + ∞ ].

And loading a tolerance prediction model, wherein the tolerance prediction model is obtained by using a special user training sample to train in advance and is stored in the local or cloud end, and the tolerance prediction model can be directly loaded when in use. And inputting the determined weight value with poor content quality into a tolerance prediction model to obtain a first tolerance value of the user. Exemplary embodiments of the invention model tolerance 0.8^Score ⁺¹For example, the weight value Score with poor content quality is determined according to the determined feedback channel, and content quality tolerance values corresponding to different weight values Score with poor content quality are shown in table 2. The weighted value Score with poor content quality has a value range of [0, + ∞ [ ]]Tolerance model 0.8 for higher weight value of poor content quality^Score+1The value range of (a) is decreased from 0.8, namely, the content tolerance of the quality difference is lower and lower.

TABLE 2

Poor weight of content quality	Score	0.5	1	1.5	2	2.5	3	3.5
									Weight value conversion processing	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
									Poor weight of content quality	Score	4	4.5	5	5.5	6	6.5	7
Weight value conversion processing	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

According to the embodiment of the invention, the technical scheme that the weighted value is determined according to the channel of the first feedback information, and the tolerance of the user to the media content quality is determined by utilizing the weighted value and the tolerance prediction model is adopted, so that the prediction result of the tolerance is more accurate, and meanwhile, the purpose of processing large-scale information can be realized by establishing the tolerance prediction model, and the technical effects of simplifying the process and improving the prediction efficiency are achieved.

Fig. 3B schematically shows a flow chart of selecting media content from at least one piece of media content that matches the tolerance of the user to the quality of the media content according to an embodiment of the present invention.

As shown in fig. 3B, the method may include operations S321 to S322, in which:

in operation S321, a quality index of each of the at least one piece of media content is determined, wherein the quality index is used to reflect a quality level of the media content.

In operation S322, media content matching the tolerance of the user on the quality of the media content is selected from the at least one piece of media content based on the distribution of the quality index of each piece of media content.

According to the exemplary embodiment of the present invention, the concept of static quality index (hereinafter referred to as quality index) of an article is introduced, which is mainly calculated from the aspects of readability of the article, negative characteristics (such as trivia, title party), high-quality news source and editing and labeling quality, and the specific calculation logic is not the key point discussed herein and is not repeated.

According to the quality indexes and the distribution conditions of the media contents in the recommendation pool of the media contents (including at least one piece of media contents), the media contents matched with the tolerance of the user to the quality of the media contents are selected from the at least one piece of media contents, for example, the user A with higher tolerance to the quality of the media contents can recommend the media contents with less high quality indexes, the user B with lower tolerance to the quality of the media contents can recommend the media contents with more high quality indexes, the specific conditions can be determined by combining the tolerance of the user to the quality of the media contents, and the detailed description is omitted.

According to the embodiment of the invention, because the technical scheme that the media content matched with the tolerance of the user to the quality of the media content is selected from at least one piece of media content based on the distribution condition of the quality index of each piece of media content is adopted, the distribution condition of the quality index of each piece of media content is considered while the tolerance of the user to the quality of the media content is considered in the process of personalized recommendation, so that the quantity of media content which can be recalled is ensured, and the recommendation result has diversity.

Fig. 3C is a flow chart schematically illustrating a process of selecting media content matching with the user's tolerance for the quality of the media content from at least one piece of media content according to an embodiment of the present invention.

As shown in fig. 3C, the method may include operations S331 to S334, in which:

in operation S331, a quality index threshold value is determined according to a distribution of quality indexes of the respective media contents, wherein the media contents having a quality index higher than the quality index threshold value are defined as high-quality media contents.

In operation S332, all high-quality media contents included in the at least one piece of media content are determined based on the quality index threshold value.

In operation S333, a percentage of the high-quality media content among the predetermined number of media contents when the predetermined number of media contents are pushed to the user is determined according to the tolerance of the user to the quality of the media contents.

In operation S334, corresponding media content is selected from the at least one piece of media content based on the occupation ratio as media content matching with the tolerance of the user on the quality of the media content.

According to an exemplary embodiment of the present invention, the value range [0, 1] of the media content quality index is divided into ten equal parts and the number of media contents corresponding to each interval is checked, assuming that the distribution is as shown in fig. 3D.

Based on the distribution of the quality index of the media content and considering the accuracy and diversity of the recommendation result, 0.75 is defined as a division line (shown by a dotted line in the figure), i.e., the content with the quality index of 0.75 or more is defined as high-quality media content, and the content with the quality index of less than 0.75 is defined as non-high-quality media content. Therefore, the content with the static quality index of more than or equal to 0.75 needs to account for at least 1-0.8 in the recall stage^Score+1The specific relationship is shown in table 3.

TABLE 3

Poor weight of content quality	Score	0.5	1	1.5	2	2.5	3	3.5
									Weight value conversion processing	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 ratio	1-0.8^Score+1	28％	36％	43％	49％	54％	59％	63％
Poor weight of content quality	Score	4	4.5	5	5.5	6	6.5	7
									Weight value conversion processing	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 ratio	1-0.8^Score+1	67％	71％	74％	77％	79％	81％	83％

It should be noted that, in order to ensure that there is enough media content to recall, the threshold of the media content quality difference weighted value Score may be 7, that is, when Score ≧ 7, the Score is treated as 7. When Score is 0, the user does not submit feedback information through the data channel, and therefore the tolerance model does not have any influence on the recommendation result.

According to the embodiment of the invention, because the technical scheme that the media content matched with the tolerance of the user to the quality of the media content is selected from at least one piece of media content based on the distribution condition of the quality index of each piece of media content is adopted, the media content recommended to the user is combined with the tolerance of the user, the technical effects of diversity and richness of the recommended content can be achieved on the basis of accurate personalized recommendation, and the use experience of the user is better.

Fig. 3E schematically shows a flowchart of selecting corresponding media content from at least one piece of media content based on the occupation ratio as media content matching with the tolerance of the user on the quality of the media content according to an embodiment of the present invention.

As shown in fig. 3E, the method may include operations S341 to S345, in which:

in operation S341, a predetermined number of values of media content pushed to a user is acquired.

In operation S342, a threshold value of the amount of high-quality media content when a predetermined amount of media content is pushed to the user is determined based on the occupancy ratio.

In operation S343, a first quantity value of high-quality media contents selected from the at least one piece of media contents is determined according to the threshold value of the quantity.

In operation S344, a second quantitative value of non-high quality media content selected from the at least one piece of media content is determined according to the predetermined quantitative value and the first quantitative value.

In operation S345, the first amount of high-quality media content and the second amount of non-high-quality media content are treated as media content matching the tolerance of the user for the quality of the media content.

It should be noted that the first quantity value is not less than the threshold value of the quantity of the high-quality media content, the second quantity value is the difference between the predetermined quantity value and the first quantity value, and the media content with the quality index lower than the threshold value of the quality index is defined as the non-high-quality media content.

As shown in table 3, if the weighted value determined by the first feedback information is 4 and the input tolerance prediction model indicates that the tolerance of the user to the quality of the media content is 0.33, the percentage of the media content with the quality index greater than the threshold value of 0.75 in the recall stage is at least 67%, that is, in the case that the predetermined number of the media content to be pushed to the user is 100, the number of the high-quality media content is at least 67, and accordingly, the number of the non-high-quality media content can be determined.

According to the embodiment of the invention, under the condition that the preset number value of the media content pushed to the user is determined according to the tolerance of the user, the threshold value of the number of the high-quality media content when the preset number of the media content is pushed to the user is determined based on the ratio, and correspondingly, the technical scheme of selecting the corresponding number of the non-high-quality media content is adopted, so that the number of the high-quality media content is ensured, and the appeal of the user on the accuracy and richness of the recommendation result can be greatly met in the personalized recommendation process.

Fig. 3F schematically shows a flowchart of an information processing method according to another embodiment of the present invention.

As shown in FIG. 3F, the method may include operations S351-S352, wherein:

in operation S351, after a predetermined number of media contents are pushed to the user, second feedback information for the predetermined number of media contents is acquired.

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

Considering that the tolerance of the user to the quality of the media content may change along with the migration of time, according to the exemplary embodiment of the present invention, not only a predetermined number of media contents matching the tolerance of the user to the quality of the media content are pushed to the user, but also after recommendation, the feedback information of the user is captured in time, and the tolerance is repaired, so as to realize real-time adjustment.

According to the embodiment of the invention, because the technical scheme of repairing the tolerance according to the feedback information of the user is adopted, the tolerance of the user to the quality of the media content can be adjusted in real time according to the feedback information of the user, and the optimality of the recommendation result is ensured.

Fig. 3G schematically shows a flowchart for obtaining second feedback information for a predetermined number of media contents according to another embodiment of the present invention.

As shown in fig. 3G, the method may include operations S361 to S362, in which:

in operation S361, a case where media contents having a quality index lower than a quality index threshold value among a predetermined number of media contents are operated is acquired.

In operation S362, second feedback information is determined based on a case where media contents having a quality index lower than a quality index threshold value are operated for a predetermined number of media contents.

According to the exemplary embodiment of the present invention, no matter whether the tolerance of the user is high or low, there is a certain probability that the media content with the quality index lower than the threshold value of the number of the high-quality media content is read, and if the forward interest is shown at this time, the content quality tolerance model is repaired, and the second feedback information may be determined for the case where the media content with the quality index lower than the threshold value of the quality index is operated in the predetermined number of media contents.

According to the embodiment of the invention, the technical scheme of determining the second feedback information aiming at the condition that the media content with the quality index lower than the quality index threshold value in the preset number of media contents is operated is adopted, so that the tolerance of the quality of the media content can be properly adjusted and updated in real time according to the feedback information of the non-high-quality media content by a user, and the optimality of the recommendation result is ensured.

As an alternative embodiment, in case the media content having a quality index below a quality index threshold is operated comprising at least one of the following operations, determining the second feedback information: at least one piece of media content with the quality index lower than the quality index threshold value is shared; at least one piece of media content with the quality index lower than the quality index threshold value is subjected to collection operation; at least one piece of media content with the quality index lower than the quality index threshold value is read; and at least one piece of media content in the media content with the quality index lower than the quality index threshold value is subjected to storage operation.

According to an exemplary embodiment of the present invention, the user's operation on the media content with the quality index lower than the quality index threshold value may include, but is not limited to, sharing, collecting, saving, and the media content reading progress is greater than or equal to 60%. Since the quality of the media contents cannot be judged well based on the titles of the media contents in the header information stream, the click is not considered for the moment as a forward behavior.

According to the embodiment of the invention, as the technical scheme that the user determines the second feedback information according to the operation condition of the media content with the quality index lower than the quality index threshold value is adopted, the factors influencing the tolerance model of the user are fully considered, so that the second feedback information can visually and accurately reflect the tolerance change condition of the user, and the optimality of the recommendation result is ensured.

Fig. 3H schematically shows a flowchart for fixing the tolerance of the user to the quality of the media content based on the second feedback information according to another embodiment of the present invention.

As shown in fig. 3H, the method may include operations S371 to S374, in which:

in operation S371, a proposed repair value for repairing the tolerance of the user to the media content quality is determined based on the second feedback information.

In operation S372, a repair condition for repairing a tolerance for media content quality, which is set in advance, is obtained.

In operation S373, a target repair value corresponding to the proposed repair value is determined according to the repair condition.

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

According to the exemplary embodiment of the present invention, the proposed repair value for repairing the tolerance of the user to the media content quality is determined to be R based on the second feedback information.

The preset repair condition for repairing the tolerance of the media content quality can be defined according to the actual requirement, and the critical condition for triggering the weight value Score repair operation is as follows: the exemplary embodiment of the present invention will be described by taking the example of the repair value being an integer multiple of R.gtoreq.0.5, but not limited thereto. For example, if a user tolerance weight Score is 7, and if the proposed repair value is R, which is 0.6 at this time, and the target repair value can be determined to be 0.5 according to the critical condition, the tolerance weight Score changes from 7 to 6.5 (note that the result is not 6.4); or if the recovery value R is drawn to be 1.2, and the target recovery value can be determined to be 1 according to the critical condition, the tolerance weight value Score is changed from 7 to 6 (note that the result is not 5.8). After completing one repair operation, the repair value R is immediately reduced to 0. In addition, it can be seen that the user may not only jump one gear in one recovery, but the specific jump amplitude is shown in table 4.

TABLE 4

Amplitude of jump	1	2	3	4	＞4
						Repair value	0.5≤R＜1	1≤R＜1.5	1.5≤R＜2	2≤R＜2.5	By analogy with that

According to the embodiment of the invention, the target repair value corresponding to the planned repair value is determined according to the preset repair condition for repairing the tolerance of the media content quality, the tolerance is repaired, and the repair rationality and operability are ensured.

Fig. 3I schematically shows a flowchart for determining a proposed repair value for repairing the tolerance of the user to the media content quality based on the second feedback information according to another embodiment of the present invention.

As shown in fig. 3I, the method may include operations S381 to S383, in which:

in operation S381, operation behavior data corresponding to the second feedback information is determined.

In operation S382, a repair weight value for repairing the tolerance of the user to the media content quality is determined according to the operation behavior data.

In operation S383, a proposed repair value for repairing the tolerance of the user to the media content quality is determined based on the repair weight value.

According to the exemplary embodiment of the present invention, according to the condition that the user operates the media content with the quality index lower than the quality index threshold value in the predetermined number of media contents, the determined second feedback information may determine the corresponding restoration weight value according to the corresponding operation behavior data, for example, the restoration of the quality difference weight value Score for one sharing or collection is 0.1, and the restoration of the behavior meeting the article reading progress for Score is 0.05 once, and so on.

According to the embodiment of the invention, the technical scheme of determining the planned repair value for repairing the tolerance according to different operation behaviors is adopted, so that the repair of the tolerance is more reasonable, and the actual tolerance change condition of a user is met.

Fig. 3J schematically illustrates a flow chart for determining a proposed repair value for repairing the user's tolerance to media content quality based on the repair weight values according to another embodiment of the present invention.

As shown in fig. 3J, the method may include operations S391 to S393, wherein:

in operation S391, a repair weight value acceleration model is obtained, where the acceleration model is related to a weight value of the first feedback information.

In operation S392, the weight value of the first feedback information is input to the acceleration model, and an acceleration value for accelerating the repair weight value is determined.

In operation S393, a pseudo-fixed repair value for repairing the tolerance of the user to the media content quality is determined based on the repair weight value and the acceleration value of the repair weight value.

According to an exemplary embodiment of the present invention, the probability of viewing an article having a content quality index < 0.75 in a predetermined number of recommendations at a time is different, subject to different user content quality tolerances. Therefore, different accelerations need to be multiplied for the content quality tolerances of different users to ensure that the forward behavior of the user can act on the tolerance model of the user in time. An acceleration function F is defined here, as shown in table 5.

TABLE 5

Take the user with Score of 7 as an example, based on the mapping table in table 5, with content quality tolerance of 0.17, Score is substituted into the acceleration model function F of 1.26^ScoreThe result was 5.0 (one decimal fraction remained). If the user collects or shares an article with the content static quality less than 0.75, the Score fitting restoration value R is 0.1 x 5.0, namely 0.5; or the user reads an article with content static quality < 0.75 and reading progress higher than 60%, the Score fitting repair value R is 0.05 x 5.0, i.e. 0.25. Obviously, when Score is 7, if the user collects or shares one article with a content static quality of < 0.75, or reads 2 articles with a content static quality of < 0.75 and the reading progress is higher than 60%, the weighted value Score is restored from 7 to 6.5.

According to the embodiment of the invention, due to the adoption of the technical scheme of the acceleration model, the quasi-fixed restoration value for restoring the tolerance can not be influenced by the tolerance difference of the user, the forward behavior of the user can be ensured to act on the tolerance model of the user in time, and the correctness of restoration is ensured.

Exemplary System

Having described the method of the exemplary embodiment of the present invention, a system for implementing information processing of the exemplary embodiment of the present invention will be described in detail with reference to fig. 4, 5A to 5G.

The embodiment of the invention provides an information processing system.

FIG. 4 schematically shows a block diagram of an information handling system according to an embodiment of the invention.

As shown in fig. 4, the information processing system 400 may include a first obtaining module 410, a determining module 420, a second obtaining module 430, and a selecting module 440. Wherein: the first obtaining module 410 is configured to obtain first feedback information for the pushed media content, where the first feedback information is used to reflect tolerance of a user on quality of the media content. The determining module 420 is configured to determine tolerance of the user to the quality of the media content according to the first feedback information. The second obtaining module 430 is configured to obtain at least one piece of media content. The selection module 440 is configured to select media content from the at least one piece of media content that matches the tolerance of the user to the quality of the media content.

FIG. 5A schematically illustrates a block diagram of the determination module according to an embodiment of the invention.

As shown in fig. 5A, the determination module 420 may include a first determination unit 511, a second determination unit 512, a loading unit 513, an input unit 514, and a third determination unit 515. The first determining unit 511 is configured to determine a feedback channel of the first feedback information. The second determining unit 512 is configured to determine a weight value of the first feedback information according to the determined feedback channel. The loading unit 513 is used to load the tolerance prediction model. The input unit 514 is configured to input the weight value into the tolerance prediction model to obtain a first tolerance value corresponding to the first feedback information. The third determining unit 515 is configured to determine tolerance of the user to the quality of the media content based on the first tolerance value.

FIG. 5B schematically shows a block diagram of a selection module according to an embodiment of the invention.

As shown in fig. 5B, the selection module 440 may include a fourth determination unit 521 and a selection unit 522. Wherein: the fourth determination unit 521 is configured to determine a quality index of each media content of the at least one media content, where the quality index is used to reflect a quality level of the media content. The selecting unit 522 is configured to select media content matching the tolerance of the user on the quality of the media content from the at least one piece of media content based on the distribution of the quality index of each piece of media content.

Fig. 5C schematically shows a block diagram of a selection unit according to an embodiment of the invention.

As shown in fig. 5C, the selection unit 522 may include a first determination subunit 531, a second determination subunit 532, a third determination subunit 533, and a selection subunit 534. Wherein: the first determining subunit 531 is configured to determine a quality index threshold according to a distribution of quality indexes of the media contents, where media contents with quality indexes higher than the quality index threshold are defined as high-quality media contents. The second determining subunit 532 is configured to determine all high-quality media contents included in the at least one piece of media content based on the quality index threshold. The third determining subunit 533 is configured to determine, according to the tolerance of the user to the quality of the media content, a proportion of the high-quality media content in the predetermined number of media contents when the predetermined number of media contents are pushed to the user. The selecting subunit 534 is configured to select, based on the occupation ratio, a corresponding media content from the at least one piece of media content as a media content that matches the tolerance of the user for the quality of the media content.

As an alternative embodiment, the selection subunit 534 is further configured to: obtaining a predetermined number of values of media content pushed to a user; determining a threshold value for the amount of high quality media content when a predetermined amount of media content is pushed to the user based on the occupancy ratio; determining a first quantity value of high-quality media contents selected from the at least one piece of media contents according to the threshold value of the quantity, wherein the first quantity value is not less than the threshold value of the quantity; determining a second quantity value of non-high quality media content selected from the at least one piece of media content according to the predetermined quantity value and the first quantity value, wherein the second quantity value is a difference value of the predetermined quantity value and the first quantity value, and the media content with the quality index lower than the quality index threshold value is defined as the non-high quality media content; and using the first amount of high-quality media content and the second amount of non-high-quality media content as media content that matches the user's tolerance for media content quality.

FIG. 5D schematically shows a block diagram of an information handling system according to another embodiment of the invention.

As shown in fig. 5D, the system 400 further includes: a third acquisition module 450 and a repair module 460. Wherein: the third obtaining module 450 is configured to obtain second feedback information for a predetermined number of media contents after pushing the predetermined number of media contents to the user. The restoration module 460 is configured to restore the tolerance of the user to the media content quality based on the second feedback information.

FIG. 5E schematically shows a block diagram of a third acquisition module according to another embodiment of the invention.

As shown in fig. 5E, the third acquisition module 450 may include a first acquisition unit 551 and a fifth determination unit 552. Wherein: the first acquisition unit 551 is configured to acquire a case where media content having a quality index lower than a quality index threshold value is operated for a predetermined number of media content. The fifth determining unit 552 is configured to determine the second feedback information based on a case where media contents having a quality index lower than a quality index threshold value are operated for a predetermined number of media contents.

FIG. 5F schematically shows a block diagram of a repair module according to another embodiment of the invention.

As shown in fig. 5F, the repair module 460 may include a sixth determination unit 561, a second acquisition unit 562, a seventh determination unit 563, and a repair unit 564. Wherein: the sixth determining unit 561 is configured to determine a proposed repair value for repairing the tolerance of the user to the media content quality based on the second feedback information. The second obtaining unit 562 is configured to obtain a preset repair condition for repairing the tolerance of the media content quality. The seventh determining unit 563 is configured to determine, according to the repair condition, a target repair value corresponding to the proposed repair value. The repair unit 564 is configured to repair the tolerance of the user to the quality of the media content according to the target repair value.

Fig. 5G schematically shows a block diagram of a sixth determination unit according to another embodiment of the invention.

As shown in fig. 5G, the sixth determination unit 561 may include a fourth determination subunit 571, a fifth determination subunit 572, and a sixth determination subunit 573. Wherein: the fourth determining subunit 571 is configured to determine the operation behavior data corresponding to the second feedback information. The fifth determining subunit 572 is configured to determine, according to the operation behavior data, a repair weight value for repairing the tolerance of the user to the media content quality. The sixth determining subunit 573 is configured to determine a proposed repair value for repairing the tolerance of the user to the media content quality based on the repair weight value.

As an alternative embodiment, the sixth determining subunit 573 is further configured to: acquiring a restoration weighted value acceleration model, wherein the acceleration model is related to the weighted value of the first feedback information; inputting the weight value of the first feedback information into an acceleration model, and determining an acceleration value for accelerating the repair weight value; and determining a planned restoration value for restoring the tolerance of the user to the media content quality based on the restoration weight value and the acceleration value of the restoration weight value.

Exemplary Medium

Having described the system of the exemplary embodiment of the present invention, a medium for implementing information processing of the exemplary embodiment of the present invention will be described in detail with reference to fig. 6.

An embodiment of the present invention provides a medium storing computer-executable instructions that, when executed by a processing unit, cause the processing unit to perform any one of the above-described information processing methods in the above-described method embodiments.

In some possible embodiments, aspects of the present invention may also be implemented in the form of a program product including program code for causing a device to perform operations (or steps) in the information processing methods according to various exemplary embodiments of the present invention described in the above section "exemplary methods" of this specification when the program product is run on the device, for example, the device may perform operation S210: first feedback information aiming at the pushed media content is obtained, wherein the first feedback information is used for reflecting the tolerance of a user on the quality of the media content. Operation S220: and determining the tolerance of the user to the media content quality according to the first feedback information. Operation S230: at least one piece of media content is obtained. Operation S240: and selecting the media content which is matched with the tolerance of the user on the quality of the media content from the at least one piece of media content.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

As shown in fig. 6, an information processing program product 60 according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-R0M) and include program code, and may be run on a device, such as a personal computer. However, the program product of the present invention is not limited in this respect, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device.

Exemplary computing device

Having described the method, system, and media of exemplary embodiments of the present invention, a computing device for information processing according to an exemplary embodiment of the present invention is next described with reference to FIG. 7.

The embodiment of the invention also provides the computing equipment. The computing device includes: a processing unit; and a storage unit storing computer-executable instructions for implementing the information processing method of any one of the above method embodiments when executed by the processing unit.

As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

In some possible embodiments, an information processing computing device according to the present invention may include at least one processing unit, and at least one storage unit. Wherein the storage unit stores program code that, when executed by the processing unit, causes the processing unit to perform operations (or steps) in the information processing method according to various exemplary embodiments of the present invention described in the above-mentioned "exemplary method" section of this specification. For example, the processing unit may perform operation S210 as shown in fig. 2: first feedback information aiming at the pushed media content is obtained, wherein the first feedback information is used for reflecting the tolerance of a user on the quality of the media content. Operation S220: and determining the tolerance of the user to the media content quality according to the first feedback information. Operation S230: at least one piece of media content is obtained. Operation S240: and selecting the media content which is matched with the tolerance of the user on the quality of the media content from the at least one piece of media content.

The information processing computing device 70 according to this embodiment of the present invention is described below with reference to fig. 7. The computing device 70 shown in FIG. 7 is only one example and should not be taken to limit the scope of use and functionality of embodiments of the present invention.

As shown in fig. 7, computing device 70 is embodied in the form of a general purpose computing device. Components of computing device 70 may include, but are not limited to: the at least one processing unit 701, the at least one memory unit 702, and a bus 703 that couples various system components including the memory unit 702 and the processing unit 701.

The bus 703 includes an address bus, a control bus, and a data bus.

The storage unit 702 can include volatile memory, such as Random Access Memory (RAM)7021 and/or cache memory 7022, and can further include Read Only Memory (ROM) 7023.

Storage unit 702 may also include a program/utility 7025 having a set (at least one) of program modules 7024, such program modules 7024 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Computing device 70 may also communicate with one or more external devices 704 (e.g., keyboard, pointing device, bluetooth device, etc.), which may be through an input/output (I/O) interface 705. Moreover, computing device 70 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) through network adapter 706. As shown, network adapter 706 communicates with the other modules of computing device 70 via bus 703. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with computing device 70, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

It should be noted that although in the above detailed description several units/modules or sub-units/sub-modules of a system for information processing are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module according to embodiments of the invention. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.

Moreover, while the operations of the method of the invention are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.

While the spirit and principles of the invention have been described with reference to several particular embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, nor is the division of aspects, which is for convenience only as the features in such aspects may not be combined to benefit. The invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. An information processing method comprising:

acquiring first feedback information aiming at pushed media content, wherein the first feedback information is used for reflecting the tolerance of a user on the quality of the media content, and the first feedback information is fed back by the user through at least one of a plurality of feedback channels;

determining the tolerance of the user to the media content quality according to the first feedback information;

obtaining at least one piece of media content; and

selecting media content from the at least one piece of media content that matches the user's tolerance to media content quality;

wherein, according to the first feedback information, determining the tolerance of the user to the media content quality comprises:

determining a feedback channel of the first feedback information;

determining a weight value of the first feedback information according to the determined feedback channel;

loading a tolerance prediction model;

inputting the weight value into the tolerance prediction model to obtain a first tolerance value corresponding to the first feedback information; and

determining the tolerance of the user to the media content quality based on the first tolerance value;

wherein selecting media content from the at least one piece of media content that matches the user's tolerance for media content quality comprises:

determining a quality index of each of the at least one piece of media content, wherein the quality index is used for reflecting the quality level of the media content; and

selecting media contents matched with the tolerance of the user on the quality of the media contents from the at least one piece of media contents based on the distribution condition of the quality indexes of the media contents;

selecting media contents matched with the tolerance of the user on the quality of the media contents from the at least one piece of media contents based on the distribution condition of the quality indexes of the media contents comprises the following steps:

determining a quality index threshold value according to the distribution condition of the quality index of each piece of media content, wherein the media content with the quality index higher than the quality index threshold value is defined as high-quality media content;

determining all high-quality media contents contained in the at least one piece of media content based on the quality index threshold value;

determining the proportion of the high-quality media content in a predetermined number of media contents when the predetermined number of media contents are pushed to the user according to the tolerance of the user on the quality of the media contents; and

and selecting corresponding media content from the at least one piece of media content based on the occupation ratio as media content matched with the tolerance of the user on the quality of the media content.

2. The method of claim 1, wherein selecting corresponding media content from the at least one piece of media content based on the duty as media content that matches the user's tolerance for media content quality comprises

Obtaining a predetermined number of values of media content pushed to the user;

the threshold value of the number of high-quality media contents is determined when a preset number of media contents are pushed to the user based on the occupation ratio;

determining a first quantity value of high-quality media content selected from the at least one piece of media content according to the threshold value of the quantity, wherein the first quantity value is not less than the threshold value of the quantity of the high-quality media content;

determining a second quantity value of non-high quality media content selected from the at least one piece of media content according to the predetermined quantity value and the first quantity value, wherein the second quantity value is a difference value of the predetermined quantity value and the first quantity value, and the media content with the quality index lower than the quality index threshold value is defined as the non-high quality media content; and

and using the first quantity of high-quality media content and the second quantity of non-high-quality media content as media content matched with the tolerance of the user on the quality of the media content.

3. The method of claim 1, wherein the method further comprises:

after the predetermined number of media contents are pushed to the user, second feedback information aiming at the predetermined number of media contents is obtained; and

and repairing the tolerance of the user to the media content quality based on the second feedback information.

4. The method of claim 3, wherein obtaining second feedback information for the predetermined amount of media content comprises:

acquiring the condition that the media content with the quality index lower than the quality index threshold value in the preset number of media contents is operated; and

determining the second feedback information based on a condition that media contents with quality indexes lower than the quality index threshold value are operated in the preset number of media contents.

5. The method of claim 4, wherein the second feedback information is determined in case the media content having the quality index below the quality index threshold is operated on comprising at least one of:

at least one piece of media content of the media content with the quality index lower than the quality index threshold value is subjected to sharing operation;

at least one piece of media content in the media content with the quality index lower than the quality index threshold value is subjected to collection operation;

at least one piece of media content of the media content with the quality index lower than the quality index threshold value is read; and

at least one piece of media content in the media content with the quality index lower than the quality index threshold value is subjected to storage operation.

6. The method of claim 3, wherein repairing the user's tolerance to media content quality based on the second feedback information comprises:

determining a planned restoration value for restoring the tolerance of the user to the media content quality based on the second feedback information;

acquiring a preset repair condition for repairing the tolerance of the media content quality;

determining a target restoration value corresponding to the quasi-fixed restoration value according to the restoration condition; and

and repairing the tolerance of the user to the media content quality according to the target repairing value.

7. The method of claim 6, wherein determining, based on the second feedback information, a proposed repair value to repair the user's tolerance to media content quality comprises:

determining operation behavior data corresponding to the second feedback information;

determining a repair weight value for repairing the tolerance of the user to the media content quality according to the operation behavior data; and

and determining a planned restoration value for restoring the tolerance of the user to the media content quality based on the restoration weight value.

8. The method of claim 7, wherein determining, based on the repair weight value, a proposed repair value to repair the user's tolerance to media content quality comprises:

acquiring the restoration weight value acceleration model, wherein the acceleration model is related to the weight value of the first feedback information;

inputting the weight value of the first feedback information into the acceleration model, and determining an acceleration value for accelerating the repair weight value; and

and determining a planned restoration value for restoring the tolerance of the user to the media content quality based on the restoration weight value and the acceleration value of the restoration weight value.

9. An information processing system comprising:

the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring first feedback information aiming at the pushed media content, the first feedback information is used for reflecting the tolerance of a user on the quality of the media content, and the first feedback information is fed back by the user through at least one of a plurality of feedback channels;

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

the second acquisition module is used for acquiring at least one piece of media content; and

the selection module is used for selecting the media content matched with the tolerance of the user on the quality of the media content from the at least one piece of media content;

wherein the determining module comprises:

the first determining unit is used for determining a feedback channel of the first feedback information;

the second determining unit is used for determining a weight value of the first feedback information according to the determined feedback channel;

the loading unit is used for loading the tolerance prediction model;

an input unit, configured to input the weight value into the tolerance prediction model to obtain a first tolerance value corresponding to the first feedback information; and

a third determining unit, configured to determine tolerance of the user on media content quality based on the first tolerance value;

wherein the selection module comprises:

a fourth determining unit, configured to determine a quality index of each media content in the at least one piece of media content, where the quality index is used to reflect a quality level of the media content; and

a selecting unit, configured to select, based on a distribution of the quality indexes of the media contents, a media content that matches with the tolerance of the user on the quality of the media content from the at least one piece of media content;

wherein the selection unit includes:

a first determining subunit, configured to determine a quality index threshold according to a distribution of quality indexes of the media contents, where a media content with a quality index higher than the quality index threshold is defined as a high-quality media content;

a second determining subunit, configured to determine, based on the quality index threshold value, all high-quality media contents included in the at least one piece of media content;

a third determining subunit, configured to determine, according to tolerance of the user to quality of the media content, a ratio of the high-quality media content to a predetermined number of media contents when the predetermined number of media contents are pushed to the user; and

and the selecting subunit is used for selecting corresponding media content from the at least one piece of media content based on the occupation ratio as the media content matched with the tolerance of the user on the quality of the media content.

10. The system of claim 9, wherein the selection subunit is further operable to:

obtaining a predetermined number of values of media content pushed to the user;

determining a first quantity value of high-quality media content selected from the at least one piece of media content according to the threshold value of the quantity, wherein the first quantity value is not less than the threshold value of the quantity;

11. The system of claim 9, wherein the system further comprises:

the third obtaining module is used for obtaining second feedback information aiming at the media contents in the preset number after the media contents in the preset number are pushed to the user; and

and the repairing module is used for repairing the tolerance of the user on the quality of the media content based on the second feedback information.

12. The system of claim 11, wherein the third acquisition module comprises:

a first acquisition unit configured to acquire a case where a media content having a quality index lower than the quality index threshold value among the predetermined number of media contents is operated; and

a fifth determining unit configured to determine the second feedback information based on a case where media contents having a quality index lower than the quality index threshold value among the predetermined number of media contents are operated.

13. The system of claim 12, wherein the second feedback information is determined in the event that the media content having the quality index below the quality index threshold is manipulated comprises at least one of:

14. The system of claim 11, wherein the repair module comprises:

a sixth determining unit, configured to determine, based on the second feedback information, a proposed repair value for repairing the tolerance of the user to the media content quality;

a second obtaining unit, configured to obtain a preset repair condition for repairing the tolerance of the media content quality;

a seventh determining unit, configured to determine, according to the repair condition, a target repair value corresponding to the proposed repair value; and

and the repairing unit is used for repairing the tolerance of the user to the media content quality according to the target repairing value.

15. The system of claim 14, wherein the sixth determination unit comprises:

the fourth determining subunit is configured to determine operation behavior data corresponding to the second feedback information;

a fifth determining subunit, configured to determine, according to the operation behavior data, a repair weight value for repairing a tolerance of the user to the media content quality; and

and the sixth determining subunit is configured to determine, based on the repair weight value, a proposed repair value for repairing the tolerance of the user to the media content quality.

16. The system of claim 15, wherein the sixth determining subunit is further configured to:

17. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processing unit, cause the processing unit to perform the information processing method according to any one of claims 1-8.

18. An electronic device, comprising:

a processing unit; and

a storage unit having stored thereon executable instructions which, when executed by the processing unit, cause the processing unit to perform the information processing method according to any one of claims 1-8.