CN112307366A

CN112307366A - Information display method and device and computer storage medium

Info

Publication number: CN112307366A
Application number: CN202011193486.7A
Authority: CN
Inventors: 于跃; 张然; 李丕勋; 朱前; 杨大威
Original assignee: Beijing ByteDance Network Technology Co Ltd
Current assignee: Beijing ByteDance Network Technology Co Ltd
Priority date: 2020-10-30
Filing date: 2020-10-30
Publication date: 2021-02-02
Anticipated expiration: 2040-10-30
Also published as: CN112307366B

Abstract

The present disclosure provides a method, an apparatus and a computer storage medium for information display, wherein the method comprises: acquiring and displaying a target content information list; responding to the trigger operation of the description information aiming at any one target clustering result, and acquiring and displaying the detail information corresponding to the target clustering result; wherein the detail information comprises a plurality of aggregation dimensions corresponding to the target clustering result and at least one media content under each aggregation dimension. In the embodiment of the disclosure, a user can directly browse the target content information list and acquire the description information corresponding to the event with higher heat in the preset time period, so that the media content with higher heat can be quickly positioned, the detail information of the event can be acquired, the media content with higher heat can be comprehensively known, the time cost for the user to acquire the information is saved, and the information acquisition efficiency is improved.

Description

Information display method and device and computer storage medium

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a method and an apparatus for displaying information, and a computer storage medium.

Background

With the development of internet technology, the information data presentation of the internet increases exponentially, a user cannot timely and comprehensively know media contents with high popularity, and if the user wants to acquire the media contents with high popularity from mass information, the user needs to browse a large amount of media contents, so that the time cost is high, and the searching efficiency is low.

Disclosure of Invention

The embodiment of the disclosure at least provides an information display method, an information display device and a computer storage medium.

In a first aspect, an embodiment of the present disclosure provides an information displaying method, where the method includes:

acquiring and displaying a target content information list; the target content information list comprises description information of a plurality of target clustering results corresponding to the target content;

responding to the trigger operation of the description information aiming at any one target clustering result, and acquiring and displaying the detail information corresponding to the target clustering result; wherein the detail information comprises a plurality of aggregation dimensions corresponding to the target clustering result and at least one media content under each aggregation dimension.

In one possible implementation, the aggregate dimension includes one or more of an event-related encyclopedia, event details, event party perspectives, event reviews; the aggregate dimension is determined based on attribute information of the target clustering result.

In one possible embodiment, the method further comprises:

displaying push information corresponding to the target clustering result in an information flow; the push information is obtained based on a plurality of media contents corresponding to the target clustering result;

and responding to the trigger operation aiming at the push information in the information flow, and displaying the detail information corresponding to the target clustering result or displaying a target content information list corresponding to the target clustering result.

In one possible implementation manner, the acquiring and displaying a target content information list page includes:

displaying list identifications corresponding to a plurality of target content information lists matched with the user attribute information;

and responding to the triggering operation of any list identification, and acquiring and displaying a target content information list corresponding to the list identification.

In a second aspect, an embodiment of the present disclosure further provides an information displaying method, where the method includes:

acquiring media content corresponding to target information in a preset time period;

clustering the media content to obtain a plurality of clustering results;

selecting a plurality of target clustering results from the clustering results according to the interactive data of the media contents under each clustering result, and determining the description information of each target clustering result;

and generating a target content information list based on the description information of each target clustering result.

In one possible embodiment, clustering the media content to obtain a plurality of clustering results includes:

acquiring any cluster to be clustered; the cluster to be clustered comprises at least one media content;

determining a target cluster based on the characteristic vector and/or keyword information corresponding to the cluster to be clustered; the target cluster is other clusters to be clustered or clustered clusters;

merging the cluster to be clustered and the target cluster to obtain a merged cluster;

and returning to the step of obtaining any cluster to be clustered until all clusters cannot be combined, and taking all clusters as the multiple clustering results.

In a possible implementation manner, determining a target cluster based on the feature vector and/or the keyword information corresponding to the cluster to be clustered includes:

recalling candidate clusters matched with the clusters to be clustered based on the feature vectors and/or keyword information corresponding to the clusters to be clustered;

calculating the vector similarity between the cluster to be clustered and each candidate cluster;

and if the maximum vector similarity between the cluster to be clustered and each candidate cluster is greater than a set similarity threshold, taking the candidate cluster with the maximum vector similarity between the cluster to be clustered as the target cluster.

In a possible implementation manner, recalling the candidate cluster matched with the cluster to be clustered based on the feature vector and/or the keyword information corresponding to the cluster to be clustered includes:

searching a preset number of first candidate clusters with a searching space distance between the first candidate clusters and the cluster to be clustered smaller than a set distance threshold value by adopting a target searching algorithm; and/or the presence of a gas in the gas,

and searching a second candidate cluster having the same keywords with the cluster to be clustered based on at least one keyword corresponding to the cluster to be clustered, wherein the sum of the weights of the same keywords between the second candidate cluster and the cluster to be clustered is greater than a set weight threshold.

In a possible implementation manner, recalling the candidate cluster matched with the cluster to be clustered based on the feature vector and the keyword information corresponding to the cluster to be clustered further includes:

and merging and de-duplicating the first candidate cluster and the second candidate cluster to obtain a candidate cluster matched with the cluster to be clustered.

In a possible implementation manner, after the merging the cluster to be clustered and the target cluster to obtain a merged cluster, the method further includes:

determining feature vectors corresponding to the merged clusters based on the feature vectors respectively corresponding to the clusters to be clustered and the target clusters; and/or the presence of a gas in the gas,

and determining keyword information corresponding to the merged cluster based on the keyword information corresponding to the cluster to be clustered and the target cluster respectively.

In a possible implementation manner, determining a feature vector corresponding to a merged cluster based on feature vectors corresponding to the cluster to be clustered and the target cluster, respectively, includes:

and calculating the average characteristic vector of the characteristic vectors respectively corresponding to the cluster to be clustered and the target cluster, and taking the average characteristic vector as the characteristic vector corresponding to the merged cluster.

In a possible implementation, the weight of the keyword is included in the keyword information; determining keyword information corresponding to the merged cluster based on the keyword information corresponding to the cluster to be clustered and the target cluster respectively, including:

aiming at each keyword corresponding to the merged cluster, determining a weight factor of the keyword based on a first weight of the keyword in the cluster to be clustered, a second weight of the keyword in the target cluster and the inverse document frequency of the keyword in the target cluster;

and determining the weight of each keyword in the merged cluster based on the weight factor corresponding to the keyword.

In a possible implementation manner, in the case that the first weight is an initial weight of the keyword, the initial weight of the keyword in the cluster to be clustered to which the keyword belongs is determined according to the following steps:

determining relevance scores between at least one keyword corresponding to the cluster to be clustered to which the keyword belongs and the media content of the cluster respectively based on a preset relevance algorithm;

determining an initial weight of the keyword based on the relevance score.

In one possible embodiment, selecting a plurality of target clustering results from the clustering results according to the interaction data of the media contents under each clustering result comprises:

determining at least one heat value corresponding to each clustering result according to the interactive data of the media content under each clustering result;

and selecting a target clustering result from the clustering results according to at least one heat value corresponding to each clustering result.

In a possible implementation manner, determining description information of each target clustering result includes:

for each target clustering result, selecting target media content from a plurality of media contents based on attribute information of the plurality of media contents corresponding to the target clustering result;

and extracting title information in the target media content as the description information, and/or extracting keyword information of the target media content, and splicing the keyword information according to a language logic sequence to form the description information.

In a possible embodiment, the at least one heat value includes two heat values, wherein the calculation method for the different heat values is different; selecting a plurality of target clustering results from the clustering results, including:

according to the sequence from high to low of two kinds of heat values corresponding to each clustering result, performing cross sequencing on the clustering results;

and according to the cross sorting result, selecting a preset number of clustering results as the plurality of target clustering results.

In a possible implementation manner, determining at least one heat value corresponding to each clustering result according to the interaction data of the media content under each clustering result includes:

and aiming at each clustering result, determining at least one heat value corresponding to the clustering result based on the first interactive data of the media content browsing user and the second interactive data of the media content publishing user respectively corresponding to a plurality of sub-time periods of the clustering result in a preset time period.

In a possible implementation manner, determining a heat value corresponding to the clustering result based on the first interaction data and the second interaction data respectively corresponding to a plurality of sub-time periods of the clustering result within a latest preset time period includes:

determining a first interaction data difference factor corresponding to each pair of adjacent sub-time periods corresponding to the plurality of sub-time periods according to a first interaction data difference value between first interaction data corresponding to a previous sub-time period and first interaction data corresponding to a next sub-time period; determining a first heat value according to a first interactive data difference value factor corresponding to each pair of adjacent sub-time periods and the first interactive data difference value;

determining a second interaction data difference factor corresponding to each pair of adjacent sub-time periods corresponding to the plurality of sub-time periods according to a second interaction data difference value between second interaction data corresponding to a previous sub-time period and second interaction data corresponding to a next sub-time period in each pair of adjacent sub-time periods corresponding to the plurality of sub-time periods; determining a second heat value according to a second interactive data difference value factor corresponding to each pair of adjacent sub-time periods and the second interactive data difference value;

and determining a heat value corresponding to the clustering result based on the first heat value and the second heat value.

In a possible implementation manner, the first interactive data difference factor and the second interactive data difference factor corresponding to different pairs of adjacent sub-time periods are different, and the absolute value of the first interactive data difference factor and the absolute value of the second interactive data difference factor corresponding to the adjacent sub-time period closer to the current time are larger.

In a possible implementation manner, determining a heat value corresponding to the clustering result based on first interaction data and second interaction data respectively corresponding to a plurality of sub-time periods of the clustering result within a latest preset time period includes:

determining a display coefficient according to a difference value between a first interactive data sum of the clustering result in the latest N sub-time periods in the plurality of sub-time periods and a first interactive data sum of a preset number of sub-time periods before the latest N sub-time period;

determining a third heat value according to the determined display coefficient and the total first interaction data corresponding to the plurality of sub-time periods;

determining a fourth heat value corresponding to the clustering result according to the total second interaction data of the clustering result in the plurality of sub-time periods and a preset text sending coefficient;

and determining a heat value corresponding to the clustering result based on the third heat value and the fourth heat value.

In one possible embodiment, the method further comprises:

for each target clustering result, determining attribute information of the target clustering result according to multimedia content included in the target clustering result;

determining a plurality of aggregation dimensions based on attribute information of the target clustering result;

and generating the aggregated media content corresponding to the target clustering result based on the multiple aggregated dimensions and the multiple media contents corresponding to the target clustering result, and taking the aggregated media content as the detail information corresponding to the description information of the target clustering result.

In one possible implementation, generating the aggregated media content corresponding to the target clustering result based on the plurality of aggregated dimensions and the plurality of media contents corresponding to the target clustering result includes:

for each aggregation dimension, determining media contents in the plurality of media contents under the aggregation dimension;

and generating the aggregated media content according to the determined media content belonging to each aggregation dimension.

In a possible implementation manner, generating a target content information list based on the descriptive information of each target clustering result includes:

and determining target content information lists under each list dimension under a plurality of list dimensions based on the description information of each target clustering result.

In one possible embodiment, the method further comprises:

determining push information corresponding to the target clustering result based on a plurality of media contents corresponding to the target clustering result;

and sending the push information to a user side.

In a third aspect, an embodiment of the present disclosure further provides an information displaying apparatus, where the apparatus includes:

the display module is used for acquiring and displaying the target content information list; the target content information list comprises description information of a plurality of target clustering results corresponding to the target content.

The response module is used for responding to the triggering operation of the description information of any one target clustering result and acquiring and displaying the detail information corresponding to the target clustering result; wherein the detail information comprises a plurality of aggregation dimensions corresponding to the target clustering result and at least one media content under the aggregation dimensions.

In a fourth aspect, an embodiment of the present disclosure further provides an information displaying apparatus, where the apparatus includes:

and the acquisition module is used for acquiring the media content corresponding to the target information in the preset time period.

And the clustering module is used for clustering the media content to obtain a plurality of clustering results.

And the first determining module is used for selecting a plurality of target clustering results from the clustering results according to the interactive data of the media contents under each clustering result and determining the description information of each target clustering result.

And the first generation module is used for generating a target content information list based on the description information of each target clustering result.

In a fifth aspect, an embodiment of the present disclosure further provides a computer device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any one of the possible implementations of the first aspect, or the second aspect, or any one of the possible implementations of the second aspect.

In a sixth aspect, this disclosed embodiment also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor performs the steps in the first aspect, or any one of the possible embodiments of the first aspect, or performs the steps in the second aspect, or any one of the possible embodiments of the second aspect.

According to the information display method, the information display device and the computer storage medium, the target content information list can be directly displayed at the user side, so that the user can directly obtain the description information corresponding to the event with higher heat degree in the preset time period, the media content with higher heat degree can be quickly positioned, the detail information of the event can be obtained by clicking the description information corresponding to the event with higher heat degree, the media content with higher heat degree can be comprehensively known, the time cost for the user to obtain the information is saved, and the information obtaining efficiency is improved.

In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.

FIG. 1 is a flow chart illustrating a method of information presentation provided by an embodiment of the present disclosure;

fig. 2 is a schematic diagram illustrating a presentation page of a default target content information list in the method for information presentation provided by the embodiment of the disclosure;

fig. 3 is a schematic diagram illustrating a display page of a target content information list in the method for displaying information provided by the embodiment of the disclosure;

fig. 4 is a schematic diagram illustrating a display page of detail information corresponding to a target clustering result in the information display method provided by the embodiment of the present disclosure;

fig. 5 is a schematic diagram illustrating a display page of pushed information corresponding to a target clustering result in the information display method provided by the embodiment of the present disclosure;

FIG. 6 illustrates a flow chart of another method of information presentation provided by an embodiment of the present disclosure;

FIG. 7 is a flow chart illustrating a method for clustering media contents in the method for information presentation provided by the embodiment of the present disclosure;

FIG. 8 is a schematic structural diagram illustrating an apparatus for displaying information provided by an embodiment of the present disclosure;

FIG. 9 is a schematic structural diagram of another information presentation apparatus provided by an embodiment of the present disclosure;

fig. 10 shows a schematic structural diagram of a computer device provided by an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

Research shows that, at present, if a user wants to acquire media contents with high popularity from massive information, the user needs to browse a large amount of media contents to comprehensively know the media contents with high popularity, the time cost is high, and the searching efficiency is low.

Based on the above research, according to the information display method, the information display device, and the computer storage medium provided by the embodiments of the present disclosure, a user can directly browse a target content information list at a user side to obtain the description information corresponding to the event with higher heat in a preset time period, so that the media content with higher heat can be quickly located, and the detailed information of the event can be obtained by clicking the description information corresponding to the event with higher heat, so that the media content with higher heat can be comprehensively known, the time cost for the user to obtain information is saved, and the information obtaining efficiency is improved. Here, the generating process of the target content information list may include: the method comprises the steps of clustering media contents corresponding to target information acquired within a preset time period, determining a clustering result corresponding to each media content, selecting a plurality of target clustering results from the clustering results according to interactive data (such as display amount, number of texts and the like) of the media contents under each clustering result, determining description information of each target clustering result, and generating a target content information list based on the determined description information of each target clustering result.

The above-mentioned drawbacks are the results of the inventor after practical and careful study, and therefore, the discovery process of the above-mentioned problems and the solutions proposed by the present disclosure to the above-mentioned problems should be the contribution of the inventor in the process of the present disclosure.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

To facilitate understanding of the present embodiment, first, a detailed description is given to an information displaying method disclosed in an embodiment of the present disclosure, where an execution subject of the information displaying method provided in the embodiment of the present disclosure is generally a computer device with certain computing capability, and the computer device includes, for example: a terminal device, which may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle mounted device, a wearable device, or a server or other processing device. In some possible implementations, the method of information presentation may be implemented by a processor calling computer readable instructions stored in a memory.

Example one

The method for displaying information provided by the embodiment of the present disclosure is described below by taking an execution subject as a user side as an example.

Referring to fig. 1, which is a flowchart of an information displaying method provided in the embodiment of the present disclosure, the method includes steps S101 to S102, where:

s101, obtaining and displaying a target content information list.

The target content information list comprises description information of a plurality of target clustering results corresponding to the target content; here, the description information may be a text description information capable of summarizing the hot event, and may be an event title, for example.

The target content may include national hotspots, local hotspots, interesting content, and the like.

Here, the target clustering result is obtained by clustering the media content; one target clustering result characterizes one hot event.

Here, the target content information list may be a hot menu including description information of a plurality of hot events corresponding to the target content; the target content information list can be a national hot list, a local hot list, an interest list and the like.

Here, the national hotspot list includes description information of a plurality of national hotspot events; the local hotspot list comprises description information of a plurality of local hotspot events; the interest list comprises a plurality of description information of the hot events matched with the user interests; here, the user interest may be determined by analyzing the type of the media content historically browsed by the user, so as to determine an interest list corresponding to the user interest; for example, when the user frequently browses legal media content, the interest of the user is determined to be legal, and the interest list corresponding to the interest of the user is determined to be a list of legal-related content.

In specific implementation, list identifications corresponding to a plurality of target content information lists matched with the user attribute information can be displayed; and responding to the triggering operation of any list identification, and acquiring and displaying a target content information list corresponding to the list identification.

The user attribute information may include current address and location information of the user.

The trigger operation may be a click operation.

Specifically, the user side sends the current address position information of the user to the server, and after receiving the current address position information of the user, the server can determine a local hotspot list matched with the current address position information of the user based on the current address position information of the user, determine the interest of the user based on the type of media content historically browsed by the user, and determine an interest list corresponding to the interest of the user; the national hotspot list, the determined local hotspot list and the interest list are sent to the user side, and after the national hotspot list, the local hotspot list and the interest list are obtained by the user side, list identifications corresponding to the national hotspot list, the local hotspot list and the interest list can be displayed to the user side, and description information of a plurality of hotspot events under a default target content information list can be displayed firstly; fig. 2 shows a display page when the default target content information list is a national hotspot list, taking the user side as a mobile phone as an example.

Specifically, when the user clicks other list identifiers except the list identifier corresponding to the default target content information list in the list identifiers respectively corresponding to the displayed national hotspot list, the local hotspot list and the interest list, description information of a plurality of hotspot events under the target content information list corresponding to the other list identifiers clicked by the user is displayed to the user.

For example, when the list identifications corresponding to the plurality of target content information lists which are displayed by the user side and matched with the user attribute information are respectively: when the national hotspot list, the Beijing hotspot list and the entertainment list are used, the list identifier corresponding to the default target content information list is the national hotspot list, and after the user clicks the Beijing hotspot list, description information of a plurality of hotspot events under the Beijing hotspot list is displayed to the user, wherein a specific display page may be a page shown in fig. 3, and a user side is taken as a mobile phone as an example.

In a specific implementation, after the user side obtains and displays the target content information list based on step S101, the user side may obtain and display detail information of the target clustering result selected by the user according to the triggering operation of the user on the description information of any target clustering result in the target content information list in step S102, which is specifically described as follows.

And S102, responding to the trigger operation of the description information aiming at any one target clustering result, and acquiring and displaying the detail information corresponding to the target clustering result.

The detail information comprises a plurality of aggregation dimensions corresponding to the target clustering result and at least one media content under each aggregation dimension.

Wherein the aggregate dimension may include one or more of an event-related encyclopedia, event details, event party views, event reviews; here, the aggregation dimension may be determined based on attribute information of the target clustering result.

The attribute information may include event type information of the hotspot event; here, the event type may include a variety of entertainment types, social types, civil types, legal types, and the like.

For example, when the event type information of the hot event included in the attribute information of the target clustering result is an entertainment type and the hot event relates to multiple stars, the aggregation dimension corresponding to the hot event may include: the relevant encyclopedias for each star, the event details for the hotspot event, the event party perspective, event reviews, etc.

Specifically, after the user clicks the description information of one target clustering result in the target content information list displayed by the user side, the user side responds to the click operation of the user on the description information of the target clustering result, acquires the detail information of the target clustering result from the server, and displays the detail information containing a plurality of aggregation dimensions.

For example, if the target content information list displayed by the user terminal is as shown in fig. 2: the method includes the steps that description information of a plurality of hot events under a national hot list is obtained, the national hot 1 contains three aggregation dimensions of event details, event party view angles and event comments, after a user clicks the description information of the national hot 1 under the national hot list, the user responds to clicking operation of the user on the description information of the national hot 1, the detail information of the national hot 1 is obtained from a server, media contents under the aggregation dimensions of the event details, the event party view angles and the event comments are displayed, and specific detail information corresponding to the national hot 1 can be as shown in fig. 4, and the user side is taken as a mobile phone as an example.

In a possible implementation manner, the user side may further receive push information corresponding to the target clustering result sent by the server, and display the push information corresponding to the target clustering result in the information stream; and responding to the triggering operation aiming at the push information in the information flow, and displaying the detail information corresponding to the target clustering result or displaying a target content information list corresponding to the target clustering result.

Here, the push information corresponding to the target clustering result may be: analyzing a plurality of media contents corresponding to the target clustering result according to a Front End Engineering Design (FEED) technology to obtain an aggregation card capable of being presented on a page in an information flow presentation mode; here, pictures, text, and the like may be included in the aggregate card.

Wherein, the information flow is fed flow, that is, the multimedia content is presented on the page in a streaming presentation manner.

Specifically, the server may generate push information corresponding to the target clustering result based on the multimedia content corresponding to the target clustering result, and send the push information to the user side; the user side receives the push information corresponding to the target clustering result sent by the server, and displays the push information corresponding to the target clustering result to the user in the form of a polymerization card in the fed stream (a specific display page of the push information corresponding to the target clustering result can be as shown in fig. 5, taking the user side as a mobile phone as an example); the user clicks the push information corresponding to the target aggregation result, and after the user side receives the clicking operation of the user, the user side can display the detail information which is corresponding to the target clustering result and contains a plurality of aggregation dimensions; and displaying a target content information list corresponding to the target clustering result.

In the embodiment of the disclosure, the target content information list can be directly displayed at the user side, so that the user can directly acquire the description information corresponding to the event with higher heat in the preset time period, the media content with higher heat can be quickly positioned, and the detail information of the event can be acquired by clicking the description information corresponding to the event with higher heat, so that the media content with higher heat can be comprehensively known, the time cost for the user to acquire the information is saved, and the information acquisition efficiency is improved.

Example two

The following describes the method for displaying information provided by the embodiments of the present disclosure by taking an execution subject as a server.

Referring to fig. 6, a flowchart of a method for displaying information provided in the embodiment of the present disclosure is shown, where the method includes steps S601 to S604, where:

s601, media content corresponding to the target information in the preset time period is obtained.

Here, since each hotspot event in the hotspot list page is time-efficient, the hotspot event of the hotspot list page may be updated every 1 min. Wherein the preset time period may be 1 min.

The media content may be a text document, a mixed image-text document, a video, an audio, a picture, etc.

In a specific implementation, the server may acquire all media contents within 1min, and process the acquired media contents through the following steps S602 to S604.

S602, clustering the media content to obtain a plurality of clustering results.

Wherein, the clustering result can include a plurality of media contents.

In a specific implementation, the media content may be clustered through the following steps S701 to S704 to obtain a plurality of clustering results, which are specifically described as follows:

s701, obtaining any cluster to be clustered.

Wherein, the cluster to be clustered can contain at least one media content. Here, each media content starts as a cluster to be clustered; on the basis of the existing clustering result, the newly added media content is a cluster to be clustered; in addition, the clusters to be clustered also include clusters to be clustered for the (N +1) th time after being clustered for N times, wherein N is a positive integer.

S702, determining a target cluster based on the characteristic vector and/or the keyword information corresponding to the cluster to be clustered.

The keyword information may include at least one keyword and a weight corresponding to each keyword. Here, the keyword of each media content in the cluster to be clustered may be determined by word segmentation.

If the cluster to be clustered only contains one media content, vectorizing the media content based on a deep learning model to obtain a feature vector of the media content, wherein the feature vector corresponding to the cluster to be clustered is the feature vector of the media content; if the cluster to be clustered contains a plurality of media contents, vectorizing each media content in the cluster to be clustered based on a deep learning model to obtain a feature vector corresponding to each media content, and adding the feature vectors corresponding to each media content to calculate an average value to obtain a feature vector corresponding to the cluster to be clustered, namely the feature vector corresponding to the cluster to be clustered is the average value of the sum of the feature vectors corresponding to each media content.

In a specific implementation, the target cluster corresponding to the cluster to be clustered may be determined by the following method, which is specifically described as follows: recalling candidate clusters matched with the clusters to be clustered based on the feature vectors and/or keyword information corresponding to the clusters to be clustered; calculating the vector similarity between the cluster to be clustered and each candidate cluster; and if the maximum vector similarity between the cluster to be clustered and each candidate cluster is greater than a set similarity threshold, taking the candidate cluster with the maximum vector similarity between the cluster to be clustered and the candidate cluster as a target cluster.

Wherein, the vector similarity may be used to indicate: similarity between the feature vector corresponding to the cluster to be clustered and the feature vector corresponding to the candidate cluster; here, the method for calculating the vector similarity may be to calculate the vector cosine value similarity, that is, calculate the vector cosine value between the cluster to be clustered and the candidate cluster, and the smaller the obtained vector cosine value is, the smaller the included angle is, that is, the closer the distance between the cluster to be clustered and the candidate cluster is, the higher the vector similarity between the cluster to be clustered and the candidate cluster is.

Here, the candidate cluster matched with the cluster to be clustered may be recalled based on the feature vector and/or the keyword information corresponding to the cluster to be clustered by the following method, which is specifically described as follows: searching a preset number of first candidate clusters closest to a search space between the clusters to be clustered by adopting a target search algorithm; and/or searching a second candidate cluster which has the same keywords with the cluster to be clustered and the weight sum of the same keywords is larger than a set weight threshold value based on at least one keyword corresponding to the cluster to be clustered; and merging and de-duplicating the first candidate cluster and the second candidate cluster to obtain a candidate cluster matched with the cluster to be clustered.

Wherein, the target search algorithm may be a hierarchical Navigable Small World map (HNSW) algorithm; the first candidate cluster may contain one or more media content; the second candidate cluster may also include one or more media content therein.

In specific implementation, a spatial map containing clusters to be clustered is constructed based on an HNSW algorithm, the clusters to be clustered are used as search points, the clusters which are closest to the search space between the clusters to be clustered in the spatial map are searched, and the clusters which are closest to the search space between the clusters to be clustered in the spatial map in a preset number are used as first candidate clusters; based on each keyword corresponding to the cluster to be clustered, searching clusters with the same keywords, and taking the clusters with the same keywords and the weight sum of the keywords larger than a preset threshold value as a second candidate cluster; de-duplication and combination are carried out on the first candidate cluster and the second candidate cluster, and a candidate cluster matched with the cluster to be clustered is obtained; vectorizing each media content in the candidate cluster, determining a feature vector corresponding to each media content, adding the feature vectors corresponding to each media content to calculate an average value, and determining the feature vector corresponding to the candidate cluster; calculating a vector cosine value between the cluster to be clustered and the candidate cluster, and determining the vector similarity between the cluster to be clustered and the candidate cluster based on the vector cosine value; and extracting the maximum vector similarity in the vector similarities, comparing the maximum vector similarity with a set similarity threshold, and when the maximum vector similarity is greater than the set similarity threshold, taking the candidate cluster corresponding to the maximum vector similarity as a target cluster, that is, merging the cluster to be clustered into the candidate cluster corresponding to the maximum vector similarity.

And S703, combining the cluster to be clustered with the target cluster to obtain a combined cluster.

In specific implementation, the media content in the cluster to be clustered is merged into the target cluster to obtain a merged cluster.

In the specific implementation, generally, the initial cluster to be clustered, the candidate cluster and the target cluster each include only one media content, and the initial clustering is to aggregate a plurality of media contents together and merge them into one class, which is described in detail as follows: determining a preset number of first candidate clusters closest to the search space between the first candidate clusters and the cluster to be clustered through an HNSW algorithm; determining keywords corresponding to the cluster to be clustered and keywords corresponding to each media content in the database through word segmentation, and determining a relevance score between at least one keyword corresponding to each media content and the media content based on an algorithm (for example, a Best Match (Best Match 25, bm25) for relevance between a preset evaluation keyword (here, the preset evaluation keyword may be a user search keyword corresponding to the media content) and the media content; determining an initial weight of each keyword corresponding to the media content based on the relevance scores between the at least one keyword and the media content respectively; based on the keywords corresponding to the clusters to be clustered, searching media contents with the same keywords as the keywords corresponding to the clusters to be clustered, determining the sum of the weights of the same keywords in the media contents based on the initial weight corresponding to each keyword in each media content, and determining the media contents with the same keywords as the keywords corresponding to the clusters to be clustered as a second candidate cluster when the sum of the weights is greater than a preset threshold; combining and de-duplicating the first candidate cluster and the second candidate cluster, and determining a plurality of candidate clusters matched with the cluster to be clustered; vectorizing the media content in the cluster to be clustered and the media content in each candidate cluster to obtain characteristic vectors corresponding to the cluster to be clustered and each candidate cluster respectively; and calculating a vector cosine value between the cluster to be clustered and each candidate cluster based on the feature vectors respectively corresponding to the cluster to be clustered and each candidate cluster, determining the candidate cluster corresponding to the minimum vector cosine value (namely, the maximum vector similarity), and merging the media content in the cluster to be clustered and the media content in the candidate cluster when the maximum feature similarity is greater than a preset similarity threshold value to obtain a merged cluster.

Exemplarily, a cluster stored in the database only contains one media content, and it is determined by word segmentation that a keyword corresponding to the media content in the cluster to be clustered is four famous works, Shuihu, san Guo Yan, Hongdou dream, and West notes, and it is determined according to the keyword that the media content in the cluster with the same keyword is media content 1 (it is determined by word segmentation that the keyword corresponding to the media content 1 is Shuihu, san Guo Yan, Hongdou dream, movie, literature), and media content 2 (it is determined by word segmentation that the keyword corresponding to the media content 1 is four famous works, literature); according to the bm25 algorithm, keywords in media content 1 are determined: the sum of the weights corresponding to Shuihu Chuan, Sanguo Yangyi and Red dream is 60%, and the keywords in the media content 2 are as follows: the weight corresponding to the four major names is 50%, the set weight threshold value is 50%, and the media content 1 which has the same keywords as the cluster to be clustered and the weight sum of the same keywords is larger than the set weight threshold value is determined as a second candidate cluster; determining a preset number of first candidate clusters closest to the search space distance between the first candidate clusters and the cluster to be clustered as media content 1 and media content 3 through an HNSW algorithm; merging and de-duplicating the first candidate cluster (namely, the media content 1 and the media content 3) and the second candidate cluster (namely, the media content 1), and determining the candidate clusters matched with the cluster to be clustered as the media content 1 and the media content 3; vectorizing the media content, the media content 1 and the media content 3 in the cluster to be clustered respectively to obtain feature vectors corresponding to the media content, the media content 1 and the media content 3 in the cluster to be clustered respectively, and obtaining that the vector similarity between the media content in the cluster to be clustered and the media content 1 is 80% and the vector similarity between the media content in the cluster to be clustered and the media content 3 is 30% by calculating vector cosine values corresponding to the media content in the cluster to be clustered, the media content 1 and the media content 3 respectively; since the maximum vector similarity of 80% is greater than the set similarity threshold of 50%, determining that the media content 1 is a target cluster; and merging the media content in the cluster to be clustered with the media content 1 to obtain a merged cluster.

In a specific implementation, after the merged cluster is obtained, the feature vector corresponding to the merged cluster may be determined by the following method, which is specifically described as follows: and determining the characteristic vector corresponding to the combined cluster based on the characteristic vectors respectively corresponding to the cluster to be clustered and the target cluster.

Specifically, the average feature vector of the feature vectors corresponding to the cluster to be clustered and the target cluster respectively can be calculated, and the average feature vector is used as the feature vector corresponding to the merged cluster, which is specifically described as follows: vectorizing each media content in the cluster to be clustered, vectorizing each media content in the target cluster, determining a feature vector corresponding to each media content in the cluster to be clustered and the target cluster, adding the feature vectors corresponding to each media content, averaging, and determining a feature vector corresponding to the merged cluster.

In a specific implementation, after the merged cluster is obtained, the keyword information corresponding to the merged cluster may be determined by the following method, which is specifically described as follows: and determining keyword information corresponding to the merged cluster based on the keyword information corresponding to the cluster to be clustered and the target cluster respectively.

The keyword information may include at least one keyword and a weight corresponding to each keyword.

Here, the keyword corresponding to the current cluster to be clustered and the keyword corresponding to the target cluster may be determined by a word segmentation method, and the keyword corresponding to the current cluster to be clustered and the keyword corresponding to the target cluster are subjected to keyword de-duplication and combination to determine the keyword corresponding to the combined cluster.

Here, for each keyword corresponding to the merged cluster, a weight factor of the keyword may be determined based on a first weight of the keyword in the cluster to be clustered, a second weight of the keyword in the target cluster, and an inverse document frequency of the keyword in the target cluster; and determining the weight of each keyword in the merged cluster based on the weight factor corresponding to the keyword.

Wherein, the Document may be obtained by an Inverse Document Frequency (IDF) algorithm according to the formula: calculating to obtain the corresponding inverse document frequency of each keyword in the target cluster, wherein the IDF (keyword) is log { (the total number of the media contents in the target cluster)/(the number of the media contents in which the keyword appears +1) }; and according to the formula: the weight factor (keyword) is a first weight (keyword) + a second weight (keyword) + IDF (keyword), and the weight factor corresponding to each keyword is determined.

Generally, the initial cluster to be clustered and the target cluster only contain one media content, so that the first weight corresponding to each keyword in the initial cluster to be clustered is the initial weight of the keyword corresponding to the media content in the cluster to be clustered in the media content, and the second weight of each keyword in the target cluster is the initial weight of the keyword corresponding to the media content in the target cluster in the media content.

Here, the initial weight of each corresponding keyword in the media content may be determined according to the following steps, which are specifically described as follows: determining a relevance score between at least one keyword corresponding to the media content and the media content respectively based on a preset algorithm (such as a Best Match (Best Match 25, bm25) for evaluating the relevance between the keyword and the media content; and determining an initial weight of each keyword corresponding to the media content based on the relevance scores between the at least one keyword and the media content respectively.

The preset evaluation keywords may be keywords corresponding to the title of the media content, or user search keywords corresponding to the media content stored in the database.

Exemplarily, taking an example that a cluster to be clustered includes one media content, determining a keyword corresponding to the media content in the cluster to be clustered by word segmentation includes: the keywords corresponding to the target cluster determined based on the step S702 include: water and enteromorpha biography and literature; determining keywords corresponding to the media contents in the cluster to be clustered according to a bm25 algorithm: the initial weights of Shuihu, the three kingdoms succession and the literature respectively correspond to 33.3 percent, 33.3 percent and 33.3 percent; determining keywords corresponding to the target cluster: the initial weights of the Shuihu and the literature respectively correspond to 50 percent and 50 percent; the keywords corresponding to the merged clusters comprise Shuihu, three kingdoms rehearsal and literature; the first weight corresponding to the keyword "water enterprising" in the merged cluster is 33.3%, the second weight is 50%, and the inverse document frequency is IDF (water enterprising) ═ log (1/2) ═ 0.3, according to the formula: determining that the weight factor corresponding to the keyword 'Shuihu Chuanfu' is 18.3%; the first weight corresponding to the keyword "three kingdoms succession" in the merged cluster is 33.3%, the second weight is 0%, and the inverse document frequency is IDF (water entermorphism) ═ log (1/1) ═ 0, according to the formula: determining that the weight factor corresponding to the keyword 'Shuihu Chuanfu' is 33.3%; the first weight corresponding to the keyword "literature" in the merged cluster is 33.3%, the second weight is 50%, the inverse document frequency is IDF (water enterprising) ═ log (1/2) ═ 0.3, and then the weight factor corresponding to the keyword "water enterprising" ("keyword") is determined to be 18.3% according to the formula weight factor (keyword) ═ first weight (keyword) + second weight (keyword) × IDF (keyword); the weight of the keyword 'Shuihu Chuanzhou' in the merged cluster is 18.3%, the weight of the keyword 'Sanguo' in the merged cluster is 33.3%, and the weight of the keyword 'literature' in the merged cluster is 18.3%.

S704, returning to the step of obtaining any cluster to be clustered until all clusters cannot be combined, and taking all clusters as the multiple clustering results.

In a specific implementation, after the cluster to be clustered and the target cluster are merged, whether the current merged cluster and other clusters in the database can be merged is judged because the feature vector and the keyword information corresponding to the merged cluster are changed, if yes, the merged cluster is merged continuously according to the steps S702 to S703 until all clusters in the database can not be merged, and the clustered cluster is used as an event.

After the media contents of the target information within a preset time period (e.g., within the latest 1 min) are acquired, the media contents representing the same event may be clustered according to the clustering algorithms S701 to S704, and after an event corresponding to each media content is determined, the following step S603 is executed.

S603, selecting a plurality of target clustering results from the clustering results according to the interactive data of the media content under each clustering result, and determining the description information of each target clustering result.

The interactive data may include first interactive data of a media content browsing user and second interactive data of a media content publishing user corresponding to the media content under the clustering result.

Here, the first interaction data of the media content browsing user may include: the number of the media contents to be displayed to the user, the number of clicks, comments, forwarding and praise of the user on the media contents, and the like.

Here, the second interaction data of the media content distribution user is: the number of the corresponding newly added media contents under the event; may include the number of articles published by the user, the number of audio, the number of videos, etc.

In specific implementation, at least one heat value corresponding to each clustering result can be determined according to the interactive data corresponding to the media content under each clustering result; and selecting a target clustering result from the clustering results according to at least one heat value corresponding to each clustering result.

In a specific implementation, for each clustering result, based on the first interaction data of the media content browsing user and the second interaction data of the media content publishing user respectively corresponding to a plurality of sub-time periods of the clustering result within a preset time period, at least one heat value corresponding to the clustering result may be determined.

Here, the preset time period may be 30min, and the preset time period may be divided into 3 sub-time periods, where each sub-time period corresponds to 10 min; wherein the first interactive data of the media content browsing user may include: the number of times that the media content corresponding to the clustering result is pushed to the user in the corresponding sub-time period, the number of times that the user clicks the media content corresponding to the clustering result, the number of times that the user reviews the media content corresponding to the clustering result, the number of times that the user approves the media content corresponding to the clustering result, the number of times that the user forwards the media content corresponding to the clustering result, and the like; the second interactive data of the media content publishing user is the number of the newly added media contents of the clustering result in the corresponding sub-time period, wherein the newly added media contents can be text document media contents, image-text media contents, audio media contents, video media contents and the like.

Here, the at least one kind of heat value may include two kinds of heat values, wherein the calculation methods of the heat values corresponding to the different kinds of heat values are different.

In particular implementations, a calorific value may be calculated by the following method, described in detail below: determining a first interaction data difference value factor corresponding to each pair of adjacent sub-time periods corresponding to the plurality of sub-time periods according to a first interaction data difference value between first interaction data corresponding to a previous sub-time period and first interaction data corresponding to a next sub-time period; determining a first heat value according to the first interactive data difference value factor and the first interactive data difference value corresponding to each pair of adjacent sub-time periods; determining a second interaction data difference factor corresponding to each pair of adjacent sub-time periods corresponding to the plurality of sub-time periods according to a second interaction data difference value between second interaction data corresponding to a previous sub-time period and second interaction data corresponding to a next sub-time period in each pair of adjacent sub-time periods corresponding to the plurality of sub-time periods; determining a second heat value according to a second interactive data difference value factor corresponding to each pair of adjacent sub-time periods and the second interactive data difference value; and determining a heat value corresponding to the clustering result based on the determined first heat value and the second heat value.

The difference factors of the first interactive data and the second interactive data corresponding to different pairs of adjacent sub-time periods are different, and the absolute value of the difference factor of the first interactive data and the absolute value of the difference factor of the second interactive data corresponding to the adjacent sub-time periods which are closer to the current time are larger.

Specifically, a preset sub-time period is divided into 4 sub-time periods, namely a first sub-time period, a second sub-time period, a third sub-time period and a fourth sub-time period, wherein the 4 sub-time periods are sequentially far away from the current time (namely, the first sub-time period is closest to the current time; the fourth sub-time period is farthest from the current time), and a first interactive data difference value between first interactive data of a previous sub-time period and first interactive data of a next sub-time period in every two adjacent sub-time periods is calculated; determining a first interactive data difference value factor corresponding to the first interactive data difference value according to the sub-time period corresponding to the first interactive data difference value; according to the formula: the first interaction data difference factor if (first interaction data of the previous sub-period-first interaction data of the next sub-period >0, 1, -1) log (1+ abs (first interaction data of the previous sub-period-first interaction data of the next sub-period)/1000), and the first interaction data difference factor and the first interaction data difference corresponding to each pair of adjacent sub-periods are substituted into the formula for operation, according to the formula: a first interaction data difference factor 1 x if (first interaction data of the first sub-period-first interaction data of the second sub-period >0, 1, -1) log (1+ abs (first interaction data of the first sub-period-first interaction data of the second sub-period)/1000) + a first interaction data difference factor 2 x if (first interaction data of the second sub-period-first interaction data of the third sub-period >0, 1, -1) log (1+ abs (first interaction data of the second sub-period-first interaction data of the third sub-period)/1000) + a first interaction data difference factor 3 x if (first interaction data of the third sub-period-first interaction data of the fourth sub-period >0, 1, -1) log (1+ abs (first interaction data of the third sub-period-first interaction data of the fourth sub-period)/1000), calculating to obtain a first heat value;

then, according to a second interactive data difference value between second interactive data of a previous sub-time period and second interactive data of a next sub-time period in every two adjacent sub-time periods in each pair of adjacent sub-time periods corresponding to the 4 sub-time periods, determining a second interactive data difference value factor corresponding to the second interactive data difference value according to the sub-time period corresponding to the second interactive data difference value; according to the formula: a second interaction data difference factor if (second interaction data of a previous sub-period-second interaction data of a next sub-period >0, 1, -1) log (1+ abs (second interaction data of a previous sub-period-second interaction data of a next sub-period)/10), and substituting the second interaction data difference factor and the second interaction data difference corresponding to each pair of adjacent sub-periods into the formula operation, according to the formula: a second interaction data difference factor 1 _ if (second interaction data of the first sub-period-second interaction data of the second sub-period >0, 1, -1) > log (1+ abs (second interaction data of the first sub-period-second interaction data of the second sub-period)/10) + a second interaction data difference factor 2 _ if (second interaction data of the second sub-period-second interaction data of the third sub-period >0, 1, -1) > log (1+ abs (second interaction data of the second sub-period-second interaction data of the third sub-period)/10) + a second interaction data difference factor 3 [ -if (second interaction data of the third sub-period-second interaction data of the fourth sub-period >0, 1, -1) > log (1+ abs (second interaction data of the third sub-period-second interaction data of the fourth sub-period)/10), calculating to obtain a second heat value;

then, according to the heat value coefficients respectively corresponding to the first heat value and the second heat value obtained by the calculation and a formula: and determining a heat value corresponding to the clustering result, wherein the heat value is a first heat value coefficient and a first heat value plus a second heat value coefficient and a second heat value.

Wherein, the formula is as follows: if (first interaction data of a previous sub-period-first interaction data of a next sub-period >0, 1, -1) may be used to indicate a change in the first interaction data within a preset sub-period, when a difference value of the first interaction data between the first interaction data of the previous sub-period and the first interaction data of the next sub-period is a positive number, it indicates that the first interaction data continuously rises, and the first heat value is a positive value; when the difference value of the first interaction data between the first interaction data of the previous sub-time period and the first interaction data of the next sub-time period is a negative number, the first interaction data continuously decreases, and the first heat value is a negative value.

Wherein, the formula is as follows: if (second interaction data of the previous sub-time period-second interaction data of the next sub-time period >0, 1, -1) may be used to indicate a rising and falling change of the second interaction data within the preset sub-time period, when a second interaction data difference value between the second interaction data of the previous sub-time period and the second interaction data of the next sub-time period is a positive number, it indicates that the second interaction data continuously rises, and the second heat value is a positive value; when the difference value of the second interactive data between the second interactive data of the previous sub-time period and the second interactive data of the next sub-time period is a negative number, it indicates that the second interactive data continuously decreases, and the second heat value is a negative value.

Wherein abs (first interaction data of a previous sub-period-first interaction data of a next sub-period) represents an absolute value of a first interaction data difference between the first interaction data of the previous sub-period and the first interaction data of the next sub-period; abs (second interactive data of the previous sub-period — second interactive data of the next sub-period) represents an absolute value of a second interactive data difference between the second interactive data of the previous sub-period and the second interactive data of the next sub-period.

Here, it may be determined that the first interaction data difference factor 1 may be 1, the first interaction data difference factor 2 may be 0.77, and the first interaction data difference factor 3 may be 0.33, according to the historical practice statistics; the second interactive data difference factor 1 may be 1, the second interactive data difference factor 2 may be 0.77, and the second interactive data difference factor 3 may be 0.33; the first heat value coefficient may be 0.5, and the second heat value coefficient may be 2.

In particular implementations, another heat value may be calculated by the following method, described in detail below: determining a display coefficient (wherein N is a positive integer) according to a difference value between a first interactive data sum of the clustering result in the most recent N sub-time periods in the plurality of sub-time periods and a first interactive data sum of a preset number of sub-time periods before the most recent N sub-time period; determining a third heat value according to the determined display coefficient and the total first interaction data corresponding to the plurality of sub-time periods; determining a fourth heat value corresponding to the clustering result according to the total second interaction data of the clustering result in a plurality of sub-time periods and a preset text sending coefficient; and determining a heat value corresponding to the clustering result based on the third heat value and the fourth heat value.

Specifically, a preset sub-time period is divided into 4 sub-time periods, which are respectively a first sub-time period, a second sub-time period, a third sub-time period and a fourth sub-time period, wherein the 4 sub-time periods are sequentially far away from the current time (that is, the first sub-time period is closest to the current time; the fourth sub-time period is farthest from the current time), and a first interaction data difference value between a first interaction data sum of the two closest sub-time periods (that is, the first sub-time period and the second sub-time period) in each two adjacent sub-time periods and a first interaction data sum of the two adjacent sub-time periods (that is, the third sub-time period and the fourth sub-time period) is calculated; determining a display coefficient corresponding to the first interactive data difference value according to whether the first interactive data difference value is greater than 0; according to the formula: log (1+ (first interaction data of the first sub-period + first interaction data of the second sub-period + first interaction data of the third sub-period + first interaction data of the fourth sub-period)/10000) × if ((first interaction data of the first sub-period + first interaction data of the second sub-period) - (first interaction data of the third sub-period + first interaction data of the fourth sub-period) >0, 1.2, 0.8), determining a third heat value; according to the formula: presetting a text sending coefficient (log (1+ second interactive data/10 of the first sub-time period) + log (1+ second interactive data/10 of the second sub-time period) + log (1+ second interactive data/10 of the third sub-time period) + log (1+ second interactive data/10 of the fourth sub-time period)), and determining a fourth heat value corresponding to the clustering result; and adding the third heat value and the fourth heat value to determine a heat value corresponding to the clustering result.

Wherein, the formula is as follows: if ((first interaction data of the first sub-period + first interaction data of the second sub-period) >0, 1.2, 0.8) may indicate that the coefficient of exhibition is 1.2 when the sum of the first interaction data between the first interaction data of the first sub-period and the first interaction data of the second sub-period is greater than the sum of the first interaction data between the first interaction data of the third sub-period and the first interaction data of the fourth sub-period; when the sum of the first interactive data between the first interactive data of the first sub-time period and the first interactive data of the second sub-time period is smaller than the sum of the first interactive data between the first interactive data of the third sub-time period and the first interactive data of the fourth sub-time period, the display coefficient is 0.8; here, the preset text coefficient may be 0.5.

In a specific implementation, after at least one heat value corresponding to each clustering result is obtained through calculation by the method, the clustering results meeting the preset heat values are screened out according to the preset heat values, and a plurality of clustering results meeting the preset heat values are selected; the server can cross-sort the plurality of clustering results which accord with the preset heat value according to the sequence of the two corresponding heat values of each clustering result from high to low; and according to the cross sorting result, selecting a preset number of clustering results as the plurality of target clustering results.

In the cross sorting, the same clustering result only appears in one sorting position; and a first clustering result sequenced according to the first heat value is adjacent to a second clustering result sequenced according to the second heat value, the sequence of different first clustering results in the cross sequencing result is the same as the sequence sequenced according to the first heat value, and the sequence of different second clustering results in the cross sequencing result is the same as the sequence sequenced according to the second heat value.

Exemplarily, the clustering result a, the clustering result b, the clustering result c, and the clustering result d are cross-ordered, which is specifically described as follows: the two corresponding heat values of the clustering result a are respectively 7 and 5 (here, the value range of the heat value is 0-10); the two corresponding heat values of the clustering result b are respectively 5 and 7; the two corresponding heat values of the clustering result c are respectively 8 and 2; the two corresponding heat values of the clustering result d are respectively 9 and 8; sequencing the 4 clustering results according to a first heat value to obtain a clustering result d, a clustering result c, a clustering result a and a clustering result b; sorting the 4 clustering results according to a second heat value to obtain a clustering result d, a clustering result b, a clustering result a and a clustering result c, and determining that a cross sorting result is the clustering result d, the clustering result b, the clustering result c and the clustering result a according to the condition that a first clustering result sorted according to the first heat value is adjacent to a second clustering result sorted according to the second heat value; if the number of the clustering results which can be put on the leaderboard is determined to be 3 currently, the target clustering results are determined to be a clustering result d, a clustering result b and a clustering result c according to the determined cross sorting result, and the ranking sequence when putting on the leaderboard is the clustering result d, the clustering result b and the clustering result c.

In specific implementation, after a plurality of target clustering results are selected from the clustering results, description information can be manually configured for each target clustering result, and here, an operator can configure corresponding description information for the target clustering results according to the title information of each media content in the target clustering results; or, configuring description information for each target clustering result automatically, which is described as follows: for each target clustering result, selecting target media content from a plurality of media contents based on the attribute information of the plurality of media contents corresponding to the target clustering result; and extracting title information in the target media content as description information, and/or extracting keyword information of the target media, and splicing the keyword information according to a language logic sequence to form the description information.

The attribute information may include user interaction data and attribute information of a release author; wherein the user interaction data may include: the user click quantity, the user praise quantity, the user comment quantity and the user forwarding quantity; the posting author attribute information may include: publisher authority, publisher influence, etc.

Specifically, when description information is automatically configured for each target clustering result, for user interaction data and attribute information of a release author of a plurality of media contents corresponding to each target clustering result, media contents with larger user interaction data, higher authority of the release author and larger influence of the release author are selected as target media contents; the title information of the target media content can be used as the description information of the target clustering result; the keyword information of the target media content can also be extracted, the extracted keyword information is analyzed, the target keyword information of event information which can represent the description of the target media content is extracted, and the target keyword information is spliced according to a language logic sequence to form the description information of the target clustering result.

And S604, generating a target content information list based on the description information of each target clustering result.

The target content information list comprises description information of a plurality of target clustering results corresponding to the target content; here, the description information may be a text description information capable of summarizing the hot event, for example, an event title.

In a specific implementation, after determining each target clustering result and the ranking order of each target clustering result in the top list, obtaining the description information corresponding to each target clustering result, and generating a target content information list including the description information corresponding to a plurality of target clustering results according to the ranking order of each target clustering result in the top list based on the obtained description information corresponding to each target clustering result.

In the embodiment of the disclosure, media contents corresponding to target information acquired within a preset time period are clustered, a clustering result corresponding to each media content is determined, a plurality of target clustering results are selected from the clustering results according to interactive data (such as display amount, number of texts and the like) of the media contents under each clustering result, description information of each target clustering result is determined, and a target content information list is generated based on the description information of each determined target clustering result, so that a user can directly browse the target content information list at a user terminal to acquire description information corresponding to an event with higher heat in the preset time period, thereby quickly positioning the media contents with higher heat, and can acquire detailed information of the event by clicking the description information corresponding to the event with higher heat, thereby comprehensively knowing the media contents with higher heat, therefore, the time cost for the user to acquire the information is saved, and the information acquisition efficiency is improved.

In a possible implementation manner, the server may further determine, for each target clustering result, attribute information of the target clustering result according to a plurality of media contents included in the target clustering result; determining a plurality of aggregation dimensions based on the attribute information of the target clustering result; and generating aggregated media content corresponding to the target clustering result based on the multiple aggregated dimensions and the multiple media content corresponding to the target clustering result, and taking the aggregated media content as detailed information corresponding to the description information of the target clustering result.

Wherein, the attribute information may include event type information of a hot event corresponding to the target clustering result; here, the event type may include various types such as an entertainment type, a social type, a civil type, a legal type, and the like.

Wherein the aggregate dimension may include one or more of an event-related encyclopedia, event details, event party views, event reviews.

Specifically, the server acquires a plurality of media contents included in each target clustering result, and analyzes the acquired media contents respectively to determine an event type corresponding to each multimedia content; determining an event type corresponding to the target clustering result based on the event type corresponding to each multimedia content; determining a plurality of aggregation dimensions corresponding to the target clustering result based on the event type corresponding to the target clustering result; after determining the multiple aggregation dimensions corresponding to the target clustering result, aggregating the multiple media contents based on the aggregation dimensions and the multiple media contents corresponding to the target clustering result, aggregating the media contents belonging to the same aggregation dimension together to serve as the aggregated media contents corresponding to the target clustering result, and taking the aggregated media contents as the detailed information corresponding to the description information of the target clustering result.

In a possible implementation manner, the server may further determine a target content information list in each list dimension in the multiple list dimensions based on the description information of each target clustering result.

Specifically, the server may determine an event type corresponding to the target clustering result by analyzing the description information of the target clustering result and the plurality of media contents corresponding to the target clustering result, and determine a list dimension to which the target clustering result belongs according to the event type, thereby generating a target content information list under each list dimension.

Here, the event type may include: international type, national type, local type, entertainment type, legal type, financial type, etc.

The list dimensions may include national hotspot dimensions, local hotspot dimensions, interest content dimensions, and other dimensions.

In a possible implementation manner, the server may further analyze, according to a Front End Engineering Design (fed) technology, a plurality of media contents corresponding to the target clustering result to obtain an aggregation card that can be presented on a page in an information stream presentation manner, use the aggregation card as push information corresponding to the target clustering result, and send the push information to the user side.

Here, pictures, text, and the like may be included in the aggregate card.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

Based on the same inventive concept, an information display device corresponding to the information display method is also provided in the embodiments of the present disclosure, and as the principle of solving the problem of the device in the embodiments of the present disclosure is similar to the information display method in the embodiments of the present disclosure, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.

EXAMPLE III

Referring to fig. 8, a schematic structural diagram of an information displaying apparatus 800 according to an embodiment of the present disclosure is shown, where the apparatus includes: the display module 801 is used for acquiring and displaying a target content information list; the target content information list comprises description information of a plurality of target clustering results corresponding to the target content.

A response module 802, configured to respond to a trigger operation for describing information of any one of the target clustering results, and obtain and display detail information corresponding to the target clustering result; wherein the detail information comprises a plurality of aggregation dimensions corresponding to the target clustering result and at least one media content under the aggregation dimensions.

In a possible implementation manner, the displaying module 801 is further configured to display, in an information flow, push information corresponding to the target clustering result; and the push information is obtained based on a plurality of media contents corresponding to the target clustering result.

The response module 802 is further configured to display, in response to the trigger operation for the push information in the information flow, the detail information corresponding to the target clustering result, or display a target content information list corresponding to the target clustering result.

In a possible implementation manner, the presentation module 801 is specifically configured to present list identifiers corresponding to multiple target content information lists matched with the user attribute information; and responding to the triggering operation of any list identification, and acquiring and displaying a target content information list corresponding to the list identification.

According to the method and the device, the target content information list can be directly displayed at the user side, so that the user can directly acquire the description information corresponding to the event with higher heat in the preset time period, the media content with higher heat can be quickly positioned, the detail information of the event can be acquired by clicking the description information corresponding to the event with higher heat, the media content with higher heat can be comprehensively known, the time cost for the user to acquire the information is saved, and the information acquisition efficiency is improved.

Example four

Referring to fig. 9, a schematic structural diagram of an information displaying apparatus 900 provided in an embodiment of the present disclosure is shown, the apparatus including: an obtaining module 901, a clustering module 902, a first determining module 903, and a first generating module 904, wherein:

the obtaining module 901 is configured to obtain media content corresponding to target information in a preset time period.

A clustering module 902, configured to cluster the media content to obtain multiple clustering results.

A first determining module 903, configured to select multiple target clustering results from the clustering results according to the interaction data of the media content in each clustering result, and determine description information of each target clustering result.

A first generating module 904, configured to generate a target content information list based on the description information of each target clustering result.

In a possible implementation, the clustering module 902 is specifically configured to obtain any cluster to be clustered; the cluster to be clustered comprises at least one media content; determining a target cluster based on the characteristic vector and/or keyword information corresponding to the cluster to be clustered; the target cluster is other clusters to be clustered or clustered clusters; merging the cluster to be clustered and the target cluster to obtain a merged cluster; and returning to the step of obtaining any cluster to be clustered until all clusters cannot be combined, and taking all clusters as the multiple clustering results.

In a possible implementation manner, the clustering module 902 is specifically configured to recall a candidate cluster matched with the cluster to be clustered based on a feature vector and/or keyword information corresponding to the cluster to be clustered; calculating the vector similarity between the cluster to be clustered and each candidate cluster; and if the maximum vector similarity between the cluster to be clustered and each candidate cluster is greater than a set similarity threshold, taking the candidate cluster with the maximum vector similarity between the cluster to be clustered as the target cluster.

In a possible implementation manner, the clustering module 902 is specifically configured to search, by using a target search algorithm, a preset number of first candidate clusters, of which the search space distance from the cluster to be clustered is smaller than a set distance threshold; and/or searching a second candidate cluster having the same keywords as the cluster to be clustered based on at least one keyword corresponding to the cluster to be clustered, wherein the sum of the weights of the same keywords between the second candidate cluster and the cluster to be clustered is greater than a set weight threshold.

In a possible implementation manner, the clustering module 902 is specifically configured to perform merging and deduplication processing on the first candidate cluster and the second candidate cluster to obtain a candidate cluster matched with the cluster to be clustered.

In a possible implementation manner, the clustering module 902 is specifically configured to determine, based on feature vectors corresponding to the to-be-clustered cluster and the target cluster, a feature vector corresponding to a merged cluster; and/or determining the keyword information corresponding to the merged cluster based on the keyword information corresponding to the cluster to be clustered and the target cluster respectively.

In a possible implementation manner, the clustering module 902 is specifically configured to calculate average feature vectors of feature vectors corresponding to the cluster to be clustered and the target cluster, respectively, and use the average feature vectors as feature vectors corresponding to the merged cluster.

In a possible implementation, the weight of the keyword is included in the keyword information; the clustering module 902 is further specifically configured to determine, for each keyword corresponding to the merged cluster, a weight factor of the keyword based on a first weight of the keyword in the cluster to be clustered, a second weight of the keyword in the target cluster, and an inverse document frequency of the keyword in the target cluster; and determining the weight of each keyword in the merged cluster based on the weight factor corresponding to the keyword.

In a possible implementation manner, the clustering module 902 is specifically configured to determine, based on a preset relevance algorithm, relevance scores between at least one keyword corresponding to a cluster to be clustered to which the keyword belongs and media content in the cluster; determining an initial weight of the keyword based on the relevance score.

In a possible implementation manner, the first determining module 903 is specifically configured to determine at least one heat value corresponding to each clustering result according to the interactive data of the media content under each clustering result; and selecting a target clustering result from the clustering results according to at least one heat value corresponding to each clustering result.

In a possible implementation manner, the first determining module 903 is specifically configured to select, for each target clustering result, a target media content from a plurality of media contents corresponding to the target clustering result based on attribute information of the plurality of media contents; and extracting title information in the target media content as the description information, and/or extracting keyword information of the target media content, and splicing the keyword information according to a language logic sequence to form the description information.

In a possible embodiment, the at least one heat value includes two heat values, wherein the calculation method for the different heat values is different; the first determining module 903 is specifically configured to perform cross sorting on the multiple clustering results according to a sequence from high to low of two heat values corresponding to each clustering result; and according to the cross sorting result, selecting a preset number of clustering results as the plurality of target clustering results.

In a possible implementation manner, the first determining module 903 is specifically configured to determine, for each clustering result, at least one hotness value corresponding to the clustering result based on first interaction data of a media content browsing user and second interaction data of a media content publishing user, which correspond to a plurality of sub-time periods of the clustering result in a preset time period, respectively.

In a possible implementation manner, the first determining module 903 is specifically configured to determine, according to a first interaction data difference between first interaction data corresponding to a previous sub-time period and first interaction data corresponding to a next sub-time period in each pair of adjacent sub-time periods corresponding to the plurality of sub-time periods, a first interaction data difference factor corresponding to the adjacent sub-time period; determining a first heat value according to a first interactive data difference value factor corresponding to each pair of adjacent sub-time periods and the first interactive data difference value; determining a second interaction data difference factor corresponding to each pair of adjacent sub-time periods corresponding to the plurality of sub-time periods according to a second interaction data difference value between second interaction data corresponding to a previous sub-time period and second interaction data corresponding to a next sub-time period in each pair of adjacent sub-time periods corresponding to the plurality of sub-time periods; determining a second heat value according to a second interactive data difference value factor corresponding to each pair of adjacent sub-time periods and the second interactive data difference value; and determining a heat value corresponding to the clustering result based on the first heat value and the second heat value.

In a possible implementation manner, the first determining module 903 is specifically configured to determine the display coefficient according to a difference between a first interaction data sum of the latest N sub-time periods in the multiple sub-time periods of the clustering result and a first interaction data sum of a preset number of sub-time periods before the latest nth sub-time period; determining a third heat value according to the determined display coefficient and the total first interaction data corresponding to the plurality of sub-time periods; determining a fourth heat value corresponding to the clustering result according to the total second interaction data of the clustering result in the plurality of sub-time periods and a preset text sending coefficient; and determining a heat value corresponding to the clustering result based on the third heat value and the fourth heat value.

In a possible embodiment, the apparatus further comprises:

and the second determining module is used for determining the attribute information of the target clustering result according to the multimedia content included in the target clustering result aiming at each target clustering result.

And the third determining module is used for determining a plurality of aggregation dimensions based on the attribute information of the target clustering result.

And the second generation module is used for generating the aggregated media content corresponding to the target clustering result based on the multiple aggregated dimensions and the multiple media contents corresponding to the target clustering result, and taking the aggregated media content as the detailed information corresponding to the description information of the target clustering result.

In a possible implementation manner, the second generating module is specifically configured to determine, for each aggregation dimension, media contents belonging to the aggregation dimension in the plurality of media contents; and generating the aggregated media content according to the determined media content belonging to each aggregation dimension.

In a possible implementation manner, the first generating module 904 is specifically configured to determine a target content information list in each of multiple list dimensions based on descriptive information of each target clustering result.

In a possible embodiment, the apparatus further comprises:

a fourth determining module, configured to determine, based on the multiple media contents corresponding to the target clustering result, push information corresponding to the target clustering result;

and the sending module is used for sending the push information to the user side.

The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.

Based on the same technical concept, the embodiment of the application also provides computer equipment. Referring to fig. 10, a schematic structural diagram of a computer device 1000 provided in the embodiment of the present application includes a processor 1001, a memory 1002, and a bus 1003. The memory 1002 is used for storing execution instructions, and includes a memory 10021 and an external memory 10022; the memory 10021 is also referred to as an internal memory, and is used for temporarily storing the operation data in the processor 1001 and the data exchanged with the external memory 10022 such as a hard disk, the processor 1001 exchanges data with the external memory 10022 through the memory 10021, and when the computer device 1000 operates, the processor 1001 and the memory 1002 communicate through the bus 1003, so that the processor 1001 executes the following instructions:

acquiring and displaying a target content information list; the target content information list comprises description information of a plurality of target clustering results corresponding to the target content; responding to the trigger operation of the description information aiming at any one target clustering result, and acquiring and displaying the detail information corresponding to the target clustering result; wherein the detail information comprises a plurality of aggregation dimensions corresponding to the target clustering result and at least one media content under each aggregation dimension.

Alternatively, the processor 1001 executes the following instructions:

clustering the media content to obtain a plurality of clustering results;

The specific processing flow of the processor 1001 may refer to the description of the above method embodiment, and is not described herein again.

The embodiments of the present disclosure also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the information presentation method described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

The embodiments of the present disclosure also provide a computer program product, where the computer program product carries a program code, and instructions included in the program code may be used to execute the steps of the information display method in the foregoing method embodiments, which may be referred to specifically for the foregoing method embodiments, and are not described herein again.

The computer program product may be implemented by hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and 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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A method of information presentation, comprising:

2. The method of claim 1, wherein the aggregated dimension comprises one or more of an event-related encyclopedia, event details, event party perspectives, event reviews; the aggregate dimension is determined based on attribute information of the target clustering result.

3. The method according to claim 1 or 2, characterized in that the method further comprises:

4. The method of claim 1, wherein obtaining and presenting a target content information list page comprises:

5. A method of information presentation, comprising:

clustering the media content to obtain a plurality of clustering results;

6. The method of claim 5, wherein clustering the media content to obtain a plurality of clustering results comprises:

7. The method of claim 6, wherein determining a target cluster based on the feature vector and/or keyword information corresponding to the cluster to be clustered comprises:

8. The method according to claim 7, wherein recalling candidate clusters matching the cluster to be clustered based on feature vectors and/or keyword information corresponding to the cluster to be clustered comprises:

9. The method of claim 8, wherein the candidate clusters matching the cluster to be clustered are recalled based on feature vectors and keyword information corresponding to the cluster to be clustered, further comprising:

10. The method according to claim 6, wherein after merging the cluster to be clustered with the target cluster to obtain a merged cluster, the method further comprises:

11. The method according to claim 10, wherein determining the feature vector corresponding to the merged cluster based on the feature vectors corresponding to the cluster to be clustered and the target cluster, respectively, comprises:

12. The method of claim 10, wherein the keyword information includes a weight of the keyword; determining keyword information corresponding to the merged cluster based on the keyword information corresponding to the cluster to be clustered and the target cluster respectively, including:

13. The method according to claim 12, wherein, in the case that the first weight is an initial weight of the keyword, determining the initial weight of the keyword in the cluster to be clustered to which the keyword belongs according to the following steps:

determining an initial weight of the keyword based on the relevance score.

14. The method of claim 5, wherein selecting a plurality of target clustering results from the clustering results according to the interaction data of the media content under each clustering result comprises:

15. The method of claim 14, wherein determining the description information of each target clustering result comprises:

16. The method of claim 15, wherein the at least one heat value comprises two heat values, wherein the different heat values are calculated by different methods; selecting a plurality of target clustering results from the clustering results, including:

17. The method of claim 14, wherein determining at least one heat value corresponding to each clustering result according to the interaction data of the media content under each clustering result comprises:

18. The method of claim 17, wherein determining a heat value corresponding to the clustering result based on the first interactive data and the second interactive data corresponding to a plurality of sub-time periods of the clustering result within a latest preset time period comprises:

19. The method of claim 18, wherein the first interactive data difference factor and the second interactive data difference factor corresponding to different pairs of adjacent sub-time periods are different, and wherein the absolute value of the first interactive data difference factor and the absolute value of the second interactive data difference factor corresponding to adjacent sub-time periods closer to the current time are larger.

20. The method of claim 17, wherein determining a heat value corresponding to the clustering result based on the first interactive data and the second interactive data corresponding to a plurality of sub-time periods of the clustering result within the latest preset time period comprises:

21. The method of claim 5, further comprising:

22. The method of claim 21, wherein generating the aggregated media content corresponding to the target clustering result based on the plurality of aggregated dimensions and a plurality of media contents corresponding to the target clustering result comprises:

23. The method of claim 5, wherein generating a target content information list based on the descriptive information of each of the target clustering results comprises:

24. The method of claim 5, further comprising:

and sending the push information to a user side.

25. An apparatus for information presentation, comprising:

the display module is used for acquiring and displaying the target content information list; the target content information list comprises description information of a plurality of target clustering results corresponding to the target content;

26. An apparatus for information presentation, comprising:

the acquisition module is used for acquiring media content corresponding to the target information in a preset time period;

the clustering module is used for clustering the media content to obtain a plurality of clustering results;

the first determining module is used for selecting a plurality of target clustering results from the clustering results according to the interactive data of the media contents under each clustering result and determining the description information of each target clustering result;

27. A computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when a computer device is run, the machine-readable instructions, when executed by the processor, performing the steps of the method of information presentation of any one of claims 1 to 4 or performing the steps of the method of information presentation of any one of claims 5 to 24.

28. A computer-readable storage medium, characterized in that a computer program is stored thereon, which, when being executed by a processor, performs the steps of the method for information presentation according to any one of claims 1 to 4, or performs the steps of the method for information presentation according to any one of claims 5 to 24.