CN113297464A

CN113297464A - Media file processing method and device and electronic equipment

Info

Publication number: CN113297464A
Application number: CN202010432702.2A
Authority: CN
Inventors: 周银达; 王炜; 许艳; 王兴勇
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2020-05-20
Filing date: 2020-05-20
Publication date: 2021-08-24

Abstract

The embodiment of the application discloses a method and a device for processing a media file and electronic equipment, wherein the method comprises the following steps: collecting the topic words associated with the published media files and generating a topic word library; according to the target recommendation dimension, storing and updating attribute information of the subject words in the subject word bank related to the target recommendation dimension; determining attribute information of the published media file on the target recommendation dimension according to attribute information of the topic word associated with the published media file and the target recommendation dimension; and providing a published media file list to a client according to the attribute information of the published media file on the target recommendation dimension. According to the embodiment of the application, simpler and more effective information recommendation can be realized.

Description

Media file processing method and device and electronic equipment

Technical Field

The present application relates to the field of media file information processing technologies, and in particular, to a method and an apparatus for processing a media file, and an electronic device.

Background

In some news-like applications, the main function is to push some news-like media file information to the user, and the main form may include articles, videos, and the like. Specifically, how to recommend the media file information, that is, how to filter or sort the mass media information for a specific user, so that the pushed information can arouse the reading interest of the user, which is a very critical problem, and may affect the system indexes such as the residence time of the user.

The popular push scheme in the prior art is a Wide & Deep model scheme, and the core idea is to combine the memory capability of a linear model and the generalization capability of a DNN (Deep Neural Networks) model, and simultaneously optimize the parameters of the two models in the training process, thereby optimizing the prediction capability of the whole model. Wherein, the memory ability finds the correlation between the objects or the characteristics from the historical data. The generalization capability, i.e., the passing of correlations, finds new combinations of features that appear little or nothing in the historical data.

Although the scheme has an obvious effect, the problems of high model complexity, extremely complex engineering characteristics, high engineering deployment difficulty and the like exist. In addition, in an implemented application scenario, it may be difficult to obtain and capture data of attributes, behaviors, habits and the like of some users, and particularly in an early stage of recommendation, there is a problem of sparse user data and the like, so that the Wide & Deep model is difficult to function.

Therefore, how to implement more simple and effective information recommendation becomes a technical problem to be solved by those skilled in the art.

Disclosure of Invention

The application provides a media file processing method and device and electronic equipment, and simpler and more effective information recommendation can be realized.

The application provides the following scheme:

a method of processing a media file, comprising:

collecting the topic words associated with the published media files and generating a topic word library;

according to the target recommendation dimension, storing and updating attribute information of the subject words in the subject word bank related to the target recommendation dimension;

determining attribute information of the published media file on the target recommendation dimension according to attribute information of the topic word associated with the published media file and the target recommendation dimension;

and providing a published media file list to a client according to the attribute information of the published media file on the target recommendation dimension.

A method of processing a media file, comprising:

acquiring media file list information, wherein the media file list information is generated according to attribute information of a published media file in a target recommendation dimension, and the attribute information of the published media file in the target recommendation dimension is determined according to attribute information of a subject word associated with the published media file and the target recommendation dimension;

and displaying the media file list information.

A method of processing a media file, comprising:

collecting published media files, storing and updating time attribute information of the published media files, wherein the published media files are endowed with initial time attribute values when being published and are reduced according to time lapse;

collecting the subject term associated with the published media file, storing and updating the time attribute information of the subject term, wherein the subject term is endowed with an initial time attribute value when appearing for the first time and is reduced according to the time lapse;

determining attribute information of the media file in a time dimension according to a current time attribute value of a published media file and a current time attribute value of at least one subject term corresponding to the media file;

and providing the media file to the client according to the attribute information on the time dimension.

A method of processing a media file, comprising:

collecting the subject term associated with the published media file, storing and updating the occurrence frequency information of the subject term;

determining heat information of the media file according to the occurrence frequency information of at least one subject term corresponding to the published media file;

and providing the published media file to a client according to the popularity information.

A method of processing a media file, comprising:

collecting the subject term associated with the published media file, storing and updating the attribute value of the association degree between the subject term and the user personalized preference corresponding to the client;

determining an association degree attribute value of the media file and the user personalized preference corresponding to the client according to the association degree attribute value of at least one subject term corresponding to the published media file;

and providing the issued media file to the client according to the association degree attribute value of the media file and the user personalized preference corresponding to the client.

A media file information presentation page is provided,

the page comprises a plurality of tabs which are respectively used for displaying media file lists generated according to different recommendation dimensions, wherein the recommendation dimensions comprise: attribute information, heat and association information between the media files and users corresponding to the client in the time dimension;

the media file list is determined according to attribute information of published media files in corresponding recommendation dimensions, and the attribute information of the published media files in corresponding recommendation dimensions is determined according to attribute information of subject words related to the published media files and related to the corresponding recommendation dimensions.

A group session message processing method in an instant communication system comprises the following steps:

collecting a plurality of group messages generated in a target group session in an instant messaging system;

extracting subject words from the plurality of group messages to generate a subject word bank;

clustering the group messages according to the difference of the associated subject terms to generate a plurality of group message categories;

determining attribute information of a corresponding group message category on the target recommendation dimension according to the attribute information of the subject term related to the target recommendation dimension;

and providing the group message content of the corresponding category to the client according to the attribute information of the group message category on the target recommendation dimension.

A media file processing apparatus, comprising:

the theme word collecting unit is used for collecting theme words related to published media files and generating a theme word bank;

the subject word attribute storage unit is used for storing and updating attribute information of the subject words in the subject word bank related to the target recommendation dimension according to the target recommendation dimension;

the media file attribute determining unit is used for determining attribute information of the published media file in the target recommendation dimension according to attribute information of a subject word associated with the published media file and the target recommendation dimension;

and the media file providing unit is used for providing a published media file list for the client according to the attribute value of the published media file on the target recommendation dimension.

A media file processing apparatus, comprising:

the information acquisition unit is used for acquiring media file list information, the media file list information is generated according to attribute information of a published media file in a target recommendation dimension, and the attribute information of the published media file in the target recommendation dimension is determined according to attribute information of a subject word associated with the published media file and the target recommendation dimension;

and the information display unit is used for displaying the media file list information.

A media file processing apparatus, comprising:

the media file attribute storage unit is used for collecting published media files and maintaining the time attribute information of the published media files, wherein the published media files are endowed with initial time attribute values when being published and are reduced according to the time lapse;

a topic word attribute storage unit, configured to collect topic words associated with the published media file, and store and update time attribute information of the topic words, where the topic words are given an initial time attribute value when appearing for the first time and are reduced according to time lapse;

the time dimension attribute determining unit is used for determining attribute information of the media file in the time dimension according to the current time attribute value of the published media file and the current time attribute value of at least one subject term corresponding to the media file;

and the media file providing unit is used for providing the media file to the client according to the attribute information on the time dimension.

A media file processing apparatus, comprising:

the theme word attribute storage unit is used for collecting the theme words associated with the published media file, and storing and updating the occurrence frequency information of the theme words;

the system comprises a popularity information determining unit, a popularity information determining unit and a popularity information determining unit, wherein the popularity information determining unit is used for determining popularity information of a published media file according to the occurrence frequency information of at least one subject term corresponding to the media file;

and the media file providing unit is used for providing the published media files to the client according to the popularity information.

A media file processing apparatus, comprising:

the theme word attribute storage unit is used for collecting the theme words associated with the published media files, and storing and updating the theme words and the association degree attribute values of the personalized preferences of the user corresponding to the client;

the association degree information determining unit is used for determining an association degree attribute value of the media file and the user personalized preference corresponding to the client according to the association degree attribute value of at least one subject term corresponding to the published media file;

and the media file providing unit is used for providing the issued media file to the client according to the association degree attribute value information of the media file and the user personalized preference corresponding to the client.

A group session message processing apparatus in an instant communication system, comprising:

the group message collecting unit is used for collecting a plurality of group messages generated in a target group session in the instant communication system;

the subject word extracting unit is used for extracting subject words from the plurality of group messages and generating a subject word library;

the group message classification unit is used for clustering the group messages according to the difference of the associated subject terms to generate a plurality of group message categories;

the subject word attribute processing unit is used for storing and updating attribute information of the subject words in the subject word bank related to the target recommendation dimension according to the target recommendation dimension;

the group message category attribute processing unit is used for determining attribute information of a corresponding group message category on the target recommendation dimension according to the attribute information of the subject term related to the target recommendation dimension;

and the group message recommending unit is used for providing the group message content of the corresponding category to the client according to the attribute information of the group message category on the target recommendation dimension.

According to the specific embodiments provided herein, the present application discloses the following technical effects:

according to the embodiment of the application, the attribute information of the media file in the corresponding recommendation dimension can be determined by using the subject term associated with the media file and the attribute information of the subject term in the target recommendation dimension, and the recommendation list is generated according to the attribute information so as to be provided for the client side to display. According to the scheme, the recommendation process of the media file is simplified by utilizing the attribute information of the subject term, the dependence on data such as user behaviors, attributes and habits is reduced, and effective recommendation can be realized under the condition that the accumulation of the user data is less at the initial deployment stage of the system.

Of course, it is not necessary for any product to achieve all of the above-described advantages at the same time for the practice of the present application.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a schematic diagram of a first application provided in an embodiment of the present application;

FIG. 2 is a flow chart of a first method provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of a second application provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of a third application provided by an embodiment of the present application;

FIG. 5 is a flow chart of a second method provided by embodiments of the present application;

FIG. 6 is a flow chart of a third method provided by embodiments of the present application;

FIG. 7 is a flow chart of a fourth method provided by embodiments of the present application;

FIG. 8 is a flow chart of a fifth method provided by embodiments of the present application;

FIG. 9 is a flow chart of a sixth method provided by embodiments of the present application;

FIG. 10 is a schematic diagram of a first apparatus provided by an embodiment of the present application;

FIG. 11 is a schematic diagram of a second apparatus provided by an embodiment of the present application;

FIG. 12 is a schematic diagram of a third apparatus provided by an embodiment of the present application;

FIG. 13 is a schematic diagram of a fourth apparatus provided by an embodiment of the present application;

FIG. 14 is a schematic diagram of a fifth apparatus provided by an embodiment of the present application;

FIG. 15 is a schematic view of a sixth apparatus provided by an embodiment of the present application;

fig. 16 is a schematic diagram of an electronic device provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments that can be derived from the embodiments given herein by a person of ordinary skill in the art are intended to be within the scope of the present disclosure.

In the embodiment of the application, a lightweight media file information recommendation method is provided, in which published media files (which may include articles, videos, and the like) may be collected first, and topic words may be extracted for the published media files to generate a topic word library. The extraction of the subject term can be realized by adopting the prior art, and after the specific subject term is extracted, how to reasonably utilize the subject term information to recommend the media file is a problem which needs to be solved. Specifically, in the embodiment of the present application, the attribute information of the topic word may be maintained in dimensions such as freshness, heat, and association with the user, and then when recommendation is specifically needed, the attribute information of the media file in the dimension may be determined according to the attribute information of the topic word associated with the published media file in the corresponding dimension, and recommendation is performed to a specific client according to the attribute information of the published media file. By the scheme, the recommendation process of the media file can be simplified by reasonably utilizing the attribute information of the subject term, the dependence on data such as user behaviors, attributes and habits is reduced, and effective recommendation can be realized under the condition of less user data accumulation at the initial deployment stage of the system and the like. Furthermore, since the information in dimensions such as freshness, heat, and relevance can be taken into consideration, the recommended information can be made highly effective.

In specific implementation, from the perspective of system architecture, referring to fig. 1, the embodiment of the present application may relate to a client and a server corresponding to a media file recommendation function, where for a mobile terminal, the client may exist in the form of an application program (App) alone, or may exist in the form of a function module in a certain comprehensive application program. The client is mainly used for displaying front-end pages and interacting with users, and the server can be used for collecting published media files, extracting subject terms, maintaining the media files and subject term attribute information, generating a final recommendation list and the like.

The following describes in detail a specific technical solution provided in an embodiment of the present application.

Example one

First, in the first embodiment, from the perspective of the server, a method for processing a media file is provided, and referring to fig. 2, the method may specifically include:

s210: and collecting the topic words associated with the published media files and generating a topic word library.

The published media file may be an article, a video, etc. published by a specific publisher in an information publication system. For a specific media file, after the media file is distributed in the information distribution system, the system side can extract the subject term of the media file by using a technology such as NLP (Natural Language Processing). The subject term is a term, phrase or the like that expresses the subject matter of the media file. For media files of the articles, NLP processing can be directly performed on text contents in the articles, for videos, audios and the like, speech recognition can be performed first, and then NLP processing can be performed based on speech recognition results, and the like. In addition, a specific publisher may also specify a specific topic word for a media file when publishing the media file, and so on.

S220: according to the target recommendation dimension, storing and updating attribute information of the subject words in the subject word bank related to the target recommendation dimension;

a media file may be associated with one or more subject terms, and how to implement recommendations for the media file using these subject terms is a consideration. In this embodiment of the present application, first, attribute information of a subject term in the subject thesaurus, which is related to a target recommendation dimension (e.g., a degree of heat, a degree of association with a user, etc.), may be saved and updated (may be updated in real time or periodically). For example, attributes such as the degree of hotness of the subject word and the degree of association with the user. That is, a target recommendation dimension is set in advance, and then attribute information of a subject word in such a recommendation dimension is determined, which may change with the passage of time, the release of a new media file, the addition of a new subject word, and the like.

S230: determining attribute information of the published media file on the target recommendation dimension according to attribute information of the topic word associated with the published media file and the target recommendation dimension;

on the basis of maintaining the attribute information of the subject words on a plurality of recommendation dimensions, specifically when recommending the media files to the user, the attribute information of the published media files on the target recommendation dimension can be determined according to the attribute information of the subject words related to the specific media files on the target recommendation dimension.

The method and the device can calculate the published media file attribute information when the media file is required to be provided to the client. For example, the published media file list may be provided to the client after receiving a refresh request from the client, and at this time, the published media file attribute information is calculated to generate the list. Alternatively, the server may push the published media file list to the client. For example, a periodic (push once per hour, etc.) push may be performed, or a push may be performed when the number of newly published media files reaches a certain number, and so on.

Specifically, the target recommendation dimension may include a time dimension (for example, may be referred to as freshness, etc.), and in this case, the attribute information of the topic word related to the target recommendation dimension may include: time attribute information of the subject term. In a specific implementation, in order to dimension the time attribute value of the subject word, an initial time attribute value may be assigned to the subject word when the subject word first appears in the subject word bank, for example, the initial value may be 10, and so on; the temporal attribute value of the subject word may then be reduced by the passage of time. The time step for adjusting the time attribute value of the subject term may be varied, for example, it may be adjusted once a day, at this time, when the subject term first appears, its time attribute value may be 10, and then, the time step is decreased by one every day until it is 0. Specifically, it can be expressed by the following formula:

wherein q represents the qth subject term,

is the initial value of the time attribute value;

a time attribute value representing the current day of the corresponding subject word,

representing the time attribute value of the corresponding subject word on the previous day. If a media file is associated with a plurality of subject terms, the time attribute values corresponding to the plurality of subject terms can be added to determine the freshness of the media file.

Or, in another way, the freshness of a particular media file may be related to the time attribute value of the media file itself, which may depend on its release time, in addition to the time attribute value of the topic word. For example, time attribute information for the published media file may be maintained, wherein the published media file may be assigned an initial time attribute value when published and decreased over time. In this way, the attribute information of the media file in the time dimension can be determined according to the current time attribute value of the published media file and the current time attribute value of at least one subject term corresponding to the media file.

That is, for a media file, the publication time may be different from the time that its associated subject word appears in the subject thesaurus. For example, a media file is published 3/7, its associated subject term includes "epidemic" and the like, and the subject term may have appeared in the subject thesaurus 3/1 because the subject term was included in other articles published earlier. Thus, although the media file may be released at a new time, possibly including some new content, its subject matter may already be "old" and thus, may not be particularly fresh for its entirety. For this reason, the freshness of the media file can be comprehensively determined by combining the time attribute of the media file itself and the time attribute of the subject term.

For example, the time attribute information of the media file may be expressed as:

wherein p represents the pth media file;

an initial value representing a time attribute of the corresponding media file;

a current value representing a time attribute of the corresponding media file;

indicating the time attribute value of the corresponding media file on the previous day.

Thus, when information of a certain media file in the time dimension needs to be calculated, the calculation can be performed according to the following formula:

wherein,

attribute information representing the media file in the time dimension,

a value of a time attribute representing the media file,

a time attribute value representing a subject term associated with the media file.

In addition to recommending media files in the time dimension, recommendations may also be made from a popularity perspective of media files. Specifically, the dimension may also be first performed on the attribute information of the subject term in the heat dimension, and in the specific implementation, the attribute value information of the subject term related to the heat may include: and the occurrence frequency attribute value information of the subject term. That is, if a topic word appears in the topic lexicon more frequently, it means that the topic word is repeatedly mentioned by a plurality of media files, and therefore, the popularity is higher. Specifically, the occurrence frequency of the subject term in the subject term library may be counted, and the occurrence frequency attribute value of the subject term may be determined.

Specifically, assume that when the articles in the chapter library have [ A, B, C, D, E, F, G ] articles, each article has one or more subject words. For example, the subject word of article A is [ a, B ], the subject word of article B is [ C, D ], the subject label of article C is [ a, e, f ], the subject word of article D is [ f, C ], etc. Firstly, calculating the frequency k of each subject word in the whole subject word bank, wherein the statistical result is shown in table 1,

TABLE 1

Subject term	Frequency of
		A	3
B	3
		C	2
D	2
		E	1
F	3

Then the heat of each article is calculated by summing the frequencies of the included subject words, as shown in the following equation:

wherein,

indicating the heat of the media file, p indicating the p-th article, n indicating that the article has n subject words, k_nIndicating the frequency of the nth subject term. Finally, the heat of each article was calculated as shown in table 2:

TABLE 2

In addition, recommendations can be made in a user association dimension in addition to freshness and heat. At this time, the attribute value information of the specific topic word related to the target recommendation dimension may include: and the attribute value of the degree of association between the theme words and the personalized preferences of the user corresponding to the client. For example, in one mode, a plurality of subject words in a subject word bank can be provided to the client at a time when the user uses the subject words for the first time, so that the corresponding user submits personalized preference information by selecting one or more subject words, and at this time, the association degree attribute value between the subject word in the subject word bank and the personalized preference of the corresponding user can be determined according to the one or more subject words selected by the user. For example, as shown in fig. 3, the topic words provided to the client may include: operational optimization, algorithms, evolutionary algorithms, deep learning, AI chips, natural language processing, machine learning, machine vision, reinforcement learning, and the like. The user's check results may include: machine vision, reinforcement learning, natural language processing, and the like. If an article contains machine vision, reinforcement learning, and natural language processing these several subject words, the association between the article and the user will be higher.

Or, in another mode, statistics may be performed on the historical browsing records of the user corresponding to the client; and determining the association degree attribute value of the subject word in the subject word bank and the personalized preference of the corresponding user according to the subject word associated with the media file browsed by the corresponding user. For example, the published media files include media files related to educational training. At this time, the learned degree of the corresponding user for the content related to the subject term may be determined according to the subject term associated with the media file browsed by the corresponding user, and then the association degree between the subject term in the subject term library and the personalized preference of the corresponding user may be determined according to the learned degree, and so on. For example, if a user learns less about content related to a topic word, the media file related to the topic word may be determined as a media file with a higher degree of association with the user, and it is necessary to recommend the media file to the user for browsing, and so on.

Alternatively, the above two ways may be combined, that is, assuming that all subject words are associated with the user at the time of system initialization

Is 0, then, if a certain subject word is selected by the user, the association degree of the subject word and the user is added with 1, that is,

if a subject word appears in an article browsed by the user, the association degree of the subject word and the user continues to be increased by 1. The process can be maintained in real time. Specifically, when recommendation needs to be performed to the user, the association degree between the article and the user may be calculated, specifically, the association degree between the subject word corresponding to the article and the user may be summed up:

wherein,

identifying the relevance between the media file and the user, wherein N represents that the article has N subject terms, and the relevance of the corresponding subject terms is

Of course, in the specific implementation, in addition to the recommendation dimensions such as freshness, heat and association with the user, recommendations may be made from other dimensions, that is, the specific recommendation dimension may be expanded, which is not listed here.

S240: and providing a published media file list to a client according to the attribute information of the published media file on the target recommendation dimension.

After determining the attribute information of the specific published media file in the specific recommendation dimension, a recommendation list can be formed according to the sequence of the attribute values of the published media file in the specific recommendation dimension from high to low, and the recommendation list is provided for the client to be displayed. In specific implementation, a plurality of media file lists can be generated from the published media files according to a plurality of target recommendation dimensions and provided to the client, so that the client can display the published media files from the plurality of target recommendation dimensions. For example, three recommendation lists are generated according to three dimensions of freshness, heat and association with the user, and at this time, as shown in fig. 4, the client may provide three different tabs in the page for presenting the media files from the three dimensions. Therefore, the user can view the specific media file list from three visual angles of freshness, heat and relevance, and the user can view from the interested visual angle or switch to other visual angles to view.

During specific implementation, the theme words associated with the published media file can be provided so as to be displayed at the client and be set to be in an interactive state. In this way, after receiving the interactive information related to the target subject term, a published media file list associated with the target subject term may be provided.

In a word, according to the embodiment of the application, the attribute information of the media file in the corresponding recommendation dimension can be determined by using the subject term associated with the media file and the attribute information of the subject term in the target recommendation dimension, and a recommendation list is generated according to the attribute information so as to be provided for the client side to display. According to the scheme, the attribute information of the subject term is reasonably utilized to simplify the recommendation process of the media file, the dependence on data such as user behaviors, attributes and habits is reduced, and effective recommendation can be realized under the condition that the accumulation of user data is less at the initial deployment stage of a system.

Example two

The second embodiment corresponds to the first embodiment, and provides a method for processing a media file from the perspective of a client, and referring to fig. 5, the method may specifically include:

s510: acquiring media file list information, wherein the media file list information is generated according to attribute information of a published media file in a target recommendation dimension, and the attribute information of the published media file in the target recommendation dimension is determined according to attribute information of a subject word associated with the published media file and the target recommendation dimension;

s520: and displaying the media file list information.

In a specific implementation, the target recommendation dimensions may be multiple and respectively correspond to different media file lists, at this time, multiple tabs may be provided in a page and respectively correspond to multiple target recommendation dimensions, so that multiple different media file lists corresponding to the multiple target recommendation dimensions are respectively displayed in the multiple tabs.

EXAMPLE III

The third embodiment is separately introduced for the specific implementation of the recommendation in the freshness dimension. Referring to fig. 6, a third embodiment provides a method for processing a media file, where the method may specifically include:

s610: collecting published media files, storing and updating time attribute information of the published media files, wherein the published media files are endowed with initial time attribute values when being published and are reduced according to time lapse;

s620: collecting the subject term associated with the published media file, storing and updating the time attribute information of the subject term, wherein the subject term is endowed with an initial time attribute value when appearing for the first time and is reduced according to the time lapse;

s630: determining attribute information of the media file in a time dimension according to a current time attribute value of a published media file and a current time attribute value of at least one subject term corresponding to the media file;

s640: and providing the media file to the client according to the attribute information on the time dimension.

Example four

The fourth embodiment is described separately for the specific implementation of the recommendation in the hotness dimension. Referring to fig. 7, a fourth embodiment provides a method for processing a media file, where the method may specifically include:

s710: collecting the subject term associated with the published media file, storing and updating the occurrence frequency information of the subject term;

s720: determining heat information of the media file according to the occurrence frequency information of at least one subject term corresponding to the published media file;

s730: and providing the published media file to a client according to the popularity information.

EXAMPLE five

The fifth embodiment is separately introduced for a specific implementation scheme for recommending in the user association degree dimension. Referring to fig. 8, a fifth embodiment provides a method for processing a media file, where the method may specifically include:

s810: collecting the subject term associated with the published media file, storing and updating the attribute value of the association degree between the subject term and the user personalized preference corresponding to the client;

s820: determining an association degree attribute value of the media file and the user personalized preference corresponding to the client according to the association degree attribute value of at least one subject term corresponding to the published media file;

s830: and providing the issued media file to the client according to the association degree attribute value of the media file and the user personalized preference corresponding to the client.

EXAMPLE six

The sixth embodiment further provides a media file information presentation page, where the page includes multiple tabs, and the multiple tabs are respectively used to present media file lists generated according to different recommendation dimensions, where the recommendation dimensions include: the freshness and the heat of the media files and the association degree information between the media files and the corresponding users of the client; the media file list is determined according to attribute values of published media files in corresponding recommendation dimensions, and the attribute values of the published media files in the corresponding recommendation dimensions are determined according to attribute value information of subject words associated with the published media files and the corresponding recommendation dimensions.

EXAMPLE seven

In practical application, the scheme provided by the embodiment of the application can also be used in other application scenarios. For example, in an instant messaging scenario, a user may join multiple groups, and to avoid interference from excessive group messages, a "message interference free" mode may be activated, so that when a new group message is generated, the user is not prompted, and the user may view the new group message at an idle time. However, if the number of new messages in a group is too large, the user may not be able to look up the messages one by one, but at the same time fear that the user may miss the content of interest. One possible solution is to subscribe to a group message topic of interest, but this solution is more mechanical. According to the scheme provided by the embodiment of the application, the group messages of the user can be collected, the subject words are extracted, and then the group messages can be clustered according to the subject words. In addition, attribute information of the subject word on a target recommendation dimension can be maintained, so that attribute information corresponding to the group message type is determined, and recommendation is further performed on the user according to the type. In this way, the user is given the opportunity to obtain the content of the group message in which he is interested, without being disturbed by too many group messages.

Specifically, referring to fig. 9, a seventh embodiment provides a group session message processing method in an instant messaging system, where the method specifically includes:

s910: collecting a plurality of group messages generated in a target group session in an instant messaging system;

s920: extracting subject words from the plurality of group messages to generate a subject word bank;

s930: clustering the group messages according to the difference of the associated subject terms to generate a plurality of group message categories;

s940: according to the target recommendation dimension, storing and updating attribute information of the subject words in the subject word bank related to the target recommendation dimension;

s950: determining attribute information of a corresponding group message category on the target recommendation dimension according to the attribute information of the subject term related to the target recommendation dimension;

s960: and providing the group message content of the corresponding category to the client according to the attribute information of the group message category on the target recommendation dimension.

For the parts of the second to seventh embodiments that are not described in detail, reference may be made to the description of the first embodiment, which is not repeated herein.

It should be noted that, in the embodiments of the present application, the user data may be used, and in practical applications, the user-specific personal data may be used in the scheme described herein within the scope permitted by the applicable law, under the condition of meeting the requirements of the applicable law and regulations in the country (for example, the user explicitly agrees, the user is informed, etc.).

Corresponding to the first embodiment, an embodiment of the present application further provides a device for processing a media file, and referring to fig. 10, the device may specifically include:

a topic word collecting unit 1010, configured to collect topic words associated with published media files, and generate a topic word library;

a topic word attribute storing unit 1020, configured to store and update attribute information of topic words in the topic word library, which is related to a target recommendation dimension, according to the target recommendation dimension;

a media file attribute determining unit 1030, configured to determine attribute information of the published media file in the target recommendation dimension according to attribute information of a topic word associated with the published media file and the target recommendation dimension;

the media file providing unit 1040 is configured to provide a published media file list to the client according to the attribute information of the published media file in the target recommendation dimension.

Wherein the target recommendation dimension comprises a time dimension, and the attribute information related to the target recommendation dimension comprises: time attribute information of the subject term;

the topic word attribute maintenance unit may be specifically configured to: when the subject word appears in the subject word bank for the first time, giving an initial time attribute value to the subject word; and reducing the time attribute value of the subject word according to the time passage.

In a specific implementation, the apparatus may further include:

a media file time attribute storage unit for storing and updating the time attribute information of the published media file, wherein the published media file is given an initial time attribute value when being published and is reduced according to the time lapse;

the media file attribute determining unit may be specifically configured to:

and determining attribute information of the media file in a time dimension according to the current time attribute value of the published media file and the current time attribute value of at least one subject term corresponding to the media file.

Or, the target recommendation dimension may also include a heat degree, and the attribute value information related to the target recommendation dimension includes: the occurrence frequency of the subject term;

in this case, the topic word attribute storage unit may be specifically configured to:

and counting the occurrence frequency of the subject words in the subject word bank, and determining the occurrence frequency of the subject words.

Or, the target recommendation dimension includes a user association degree, and the attribute value information related to the target recommendation dimension includes: and the association degree of the theme words and the personalized preferences of the user corresponding to the client.

Specifically, the topic word attribute storage unit may be specifically configured to:

providing the subject terms in the subject term library to the client, so that the corresponding user submits the personalized preference information of the corresponding user by selecting one or more subject terms;

and determining the association degree of the subject words in the subject word bank and the personalized preferences of the corresponding user according to the one or more subject words selected by the user.

Alternatively, the topic word attribute storage unit may be specifically configured to:

counting the historical browsing records of the user corresponding to the client;

and determining the association degree of the subject words in the subject word bank and the personalized preferences of the corresponding user according to the subject words associated with the media files browsed by the corresponding user.

Wherein the published media file comprises: media files related to educational training;

the topic word attribute storage unit may be specifically configured to:

determining the learned degree of the corresponding user to the content related to the subject term according to the subject term related to the media file browsed by the corresponding user;

and determining the association degree of the subject words in the subject word bank and the personalized preferences of the corresponding users according to the learned degree.

In a specific implementation, if there are a plurality of topic words associated with the published media file, the media file attribute determining unit may specifically be configured to:

and determining the attribute information of the published media file on the target recommendation dimension by integrating the attribute information of the plurality of subject terms on the target recommendation dimension.

The media file providing unit may specifically be configured to:

and respectively generating a plurality of media file lists for the published media files according to a plurality of target recommendation dimensions, and providing the media file lists for the client so that the client can display the published media files from the plurality of target recommendation dimensions.

Specifically, the media file providing unit may specifically be configured to:

and after receiving a refreshing request of the client, providing the published media file list to the client.

Or, the media file providing unit may specifically be configured to:

and pushing the published media file list to the client.

In a specific implementation, the apparatus may further include:

the theme word providing unit is used for providing the theme words related to the published media file so as to be displayed at a client side and set to be in an interactive state;

and the interaction unit is used for providing a published media file list associated with the target subject term after receiving the interaction information related to the target subject term.

Corresponding to the second embodiment, an embodiment of the present application further provides a device for processing a media file, and referring to fig. 11, the device may specifically include:

an information obtaining unit 1110, configured to receive media file list information provided by a server, where the media file list information is generated according to attribute information of a published media file in a target recommendation dimension, and the attribute information of the published media file in the target recommendation dimension is determined according to attribute information of a subject word associated with the published media file and the target recommendation dimension;

an information presentation unit 1120, configured to present the media file list information.

The target recommendation dimensions are multiple and respectively correspond to different media file lists;

the information presentation unit may be specifically configured to:

providing a plurality of tabs in a page, wherein the tabs respectively correspond to a plurality of target recommendation dimensions, so that a plurality of different media file lists corresponding to the target recommendation dimensions are respectively displayed in the tabs.

Corresponding to the embodiment, the embodiment of the present application further provides a device for processing a media file, referring to fig. 12, where the device specifically includes:

a media file attribute saving unit 1210 configured to collect published media files and maintain time attribute information of the published media files, where the published media files are given initial time attribute values when being published and decrease with time;

a topic word attribute storage unit 1220, configured to collect topic words associated with the published media file, and maintain time attribute information of the topic words, where the topic words are given an initial time attribute value when they first appear, and decrease with time;

a time dimension attribute information determining unit 1230, configured to determine attribute information of the media file in a time dimension according to a current time attribute value of the published media file and a current time attribute value of at least one topic word corresponding to the media file;

a media file providing unit 1240, configured to provide the media file to the client according to the attribute information in the time dimension.

Corresponding to the fourth embodiment, an embodiment of the present application further provides a device for processing a media file, and referring to fig. 13, the device may specifically include:

a topic word attribute storage unit 1310, configured to collect topic words associated with published media files, and maintain frequency of occurrence information of the topic words;

a popularity information determining unit 1320, configured to determine popularity information of the media file according to an occurrence frequency attribute value of at least one topic word corresponding to the published media file;

a media file providing unit 1330, configured to provide the published media file to the client according to the popularity information.

Corresponding to the fifth embodiment, an embodiment of the present application further provides a device for processing a media file, and referring to fig. 14, the device may specifically include:

a topic word attribute storage unit 1410, configured to collect topic words associated with published media files, and maintain attribute values of the relevance degrees between the topic words and the personalized preferences of the user corresponding to the client;

the relevance information determining unit 1420 is configured to determine, according to the relevance attribute value of at least one topic word corresponding to a published media file, a relevance attribute value of a user personalized preference corresponding to the media file and a client;

the media file providing unit 1430 is configured to provide the published media file to the client according to the association attribute value information of the media file and the user personalized preference corresponding to the client.

Corresponding to the seventh embodiment, an embodiment of the present application further provides a group session message processing apparatus in an instant messaging system, and referring to fig. 15, the apparatus may include:

a group message collection unit 1510 configured to collect a plurality of group messages generated in a target group session in the instant messaging system;

a topic word extraction unit 1520, configured to extract topic words from the plurality of group messages and generate a topic word library;

a group message classification unit 1530, configured to cluster the group messages according to different associated subject terms, so as to generate multiple group message categories;

a topic word attribute processing unit 1540, configured to store and update attribute information of a topic word in the topic word library, which is related to a target recommendation dimension, according to the target recommendation dimension;

the group message category attribute processing unit 1550 is configured to determine attribute information of a corresponding group message category in the target recommendation dimension according to the attribute information of the subject term related to the target recommendation dimension;

and a group message recommending unit 1560, configured to provide the group message content of the corresponding category to the client according to the attribute information of the group message category in the target recommendation dimension.

In addition, the present application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the method described in any of the preceding method embodiments.

And an electronic device comprising:

one or more processors; and

a memory associated with the one or more processors for storing program instructions that, when read and executed by the one or more processors, perform the steps of the method of any of the preceding method embodiments.

Where fig. 16 illustratively shows the architecture of an electronic device, for example, device 1600 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, an aircraft, or the like.

Referring to fig. 16, device 1600 may include one or more of the following components: processing component 1602, memory 1604, power component 1606, multimedia component 1608, audio component 1610, input/output (I/O) interface 1612, sensor component 1614, and communications component 1616.

The processing component 1602 generally controls overall operation of the device 1600, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. Processing element 1602 may include one or more processors 1620 to execute instructions to perform all or some of the steps of the methods provided by the disclosed embodiments. Further, the processing component 1602 can include one or more modules that facilitate interaction between the processing component 1602 and other components. For example, the processing component 1602 can include a multimedia module to facilitate interaction between the multimedia component 1608 and the processing component 1602.

The memory 1604 is configured to store various types of data to support operation at the device 1600. Examples of such data include instructions for any application or method operating on device 1600, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 1604 may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

A power supply component 1606 provides power to the various components of the device 1600. The power components 1606 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 1600.

The multimedia component 1608 includes a screen that provides an output interface between the device 1600 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1608 comprises a front-facing camera and/or a rear-facing camera. The front-facing camera and/or the back-facing camera may receive external multimedia data when device 1600 is in an operational mode, such as a capture mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 1610 is configured to output and/or input an audio signal. For example, audio component 1610 includes a Microphone (MIC) configured to receive external audio signals when device 1600 is in an operational mode, such as a call mode, recording mode, and voice recognition mode. The received audio signal may further be stored in the memory 1604 or transmitted via the communications component 1616. In some embodiments, audio component 1610 further includes a speaker for outputting audio signals.

The I/O interface 1612 provides an interface between the processing component 1602 and peripheral interface modules, such as keyboards, click wheels, buttons, and the like. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

Sensor assembly 1614 includes one or more sensors for providing status assessment of various aspects of device 1600. For example, sensor assembly 1614 can detect an open/closed state of device 1600, the relative positioning of components, such as a display and keypad of device 1600, a change in position of device 1600 or a component of device 1600, the presence or absence of user contact with device 1600, orientation or acceleration/deceleration of device 1600, and a change in temperature of device 1600. The sensor assembly 1614 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1614 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1614 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

Communications component 1616 is configured to facilitate communications between device 1600 and other devices in a wired or wireless manner. The device 1600 may access a wireless network based on a communication standard, such as WiFi, or a mobile communication network such as 2G, 3G, 4G/LTE, 5G, etc. In an exemplary embodiment, the communication unit 1616 receives a broadcast signal or broadcast associated information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communications component 1616 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the device 1600 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 1604 comprising instructions, executable by the processor 1620 of the device 1600 to perform the methods provided by the disclosed aspects is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

The method, the apparatus and the electronic device for processing a media file provided by the present application are introduced in detail, and a specific example is applied in the description to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, the specific embodiments and the application range may be changed. In view of the above, the description should not be taken as limiting the application.

Claims

1. A method for processing a media file, comprising:

2. The method of claim 1,

the target recommendation dimension comprises a time dimension, and the attribute information related to the target recommendation dimension comprises: time attribute information of the subject term;

the maintaining of the attribute information of the subject term in the subject term library related to the target recommendation dimension includes:

when the subject word appears in the subject word bank for the first time, giving an initial time attribute value to the subject word;

and reducing the time attribute value of the subject word according to the time passage.

3. The method of claim 2, further comprising:

storing and updating time attribute information of the published media file, wherein the published media file is given an initial time attribute value when being published and is reduced according to time lapse;

the determining the attribute information of the published media file in the target recommendation dimension according to the attribute information of the topic word associated with the published media file in the target recommendation dimension includes:

4. The method of claim 1,

the target recommendation dimension comprises a heat degree, and the attribute information related to the target recommendation dimension comprises: the occurrence frequency of the subject term;

the storing and updating of attribute information of the subject term in the subject term library related to the target recommendation dimension includes:

5. The method of claim 1,

the target recommendation dimension comprises a user association degree, and the attribute information related to the target recommendation dimension comprises: and the association degree of the theme words and the personalized preferences of the user corresponding to the client.

6. The method of claim 5,

7. The method of claim 5,

8. The method of claim 7,

the published media file comprises: media files related to educational training;

the determining the association degree of the subject term in the subject term library and the personalized preference of the corresponding user according to the subject term associated with the media file browsed by the corresponding user comprises the following steps:

9. The method according to any one of claims 1 to 8,

if the published media file is associated with a plurality of topic words, the determining the attribute information of the published media file in the target recommendation dimension includes:

10. The method according to any one of claims 1 to 8,

the providing the published media file to the client comprises:

11. The method according to any one of claims 1 to 8,

the providing the published media file list to the client comprises:

12. The method according to any one of claims 1 to 8,

the providing the published media file list to the client comprises:

and pushing the published media file list to the client.

13. The method of any one of claims 1 to 8, further comprising:

providing the subject term associated with the published media file for display at a client and setting the subject term in an interactive state;

after receiving the interactive information related to the target subject term, a published media file list associated with the target subject term is provided.

14. A method for processing a media file, comprising:

and displaying the media file list information.

15. The method of claim 14,

the displaying the media file list information includes:

16. A method for processing a media file, comprising:

17. A method for processing a media file, comprising:

18. A method for processing a media file, comprising:

19. A media file information presentation page, characterized in that,

20. A group session message processing method in an instant messaging system is characterized by comprising the following steps:

21. An apparatus for processing a media file, comprising:

22. An apparatus for processing a media file, comprising:

23. An apparatus for processing a media file, comprising:

24. An apparatus for processing a media file, comprising:

25. An apparatus for processing a media file, comprising:

26. A group session message processing apparatus in an instant messaging system, comprising:

27. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 20.

28. An electronic device, comprising:

one or more processors; and

a memory associated with the one or more processors for storing program instructions that, when read and executed by the one or more processors, perform the steps of the method of any of claims 1 to 20.