CN114064163A - Activity content processing and displaying method and device, electronic equipment and storage medium - Google Patents

Activity content processing and displaying method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114064163A
CN114064163A CN202010763268.6A CN202010763268A CN114064163A CN 114064163 A CN114064163 A CN 114064163A CN 202010763268 A CN202010763268 A CN 202010763268A CN 114064163 A CN114064163 A CN 114064163A
Authority
CN
China
Prior art keywords
content
activity
server
related content
participants
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010763268.6A
Other languages
Chinese (zh)
Inventor
董保华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN202010763268.6A priority Critical patent/CN114064163A/en
Publication of CN114064163A publication Critical patent/CN114064163A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/451—Execution arrangements for user interfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/166—Editing, e.g. inserting or deleting
    • G06F40/169—Annotation, e.g. comment data or footnotes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis

Abstract

One or more embodiments of the present specification provide an active content processing and presentation method, apparatus, electronic device, and storage medium; the processing method can comprise the following steps: acquiring activity related content uploaded by at least one activity participant participating in the target activity; clustering the campaign-related content to obtain a plurality of content groupings for the campaign-related content; providing information of the plurality of content packets to the respective activity participants.

Description

Activity content processing and displaying method and device, electronic equipment and storage medium
Technical Field
One or more embodiments of the present disclosure relate to the field of communications technologies, and in particular, to a method and an apparatus for processing and displaying active content, an electronic device, and a storage medium.
Background
Meetings are relatively common activities in the work segment, such as team ko (pick off), annual meetings, staff training, lectures, and so forth. During a meeting activity, meeting participants can post their own opinions on the topic of the meeting discussion or ask questions about the meeting content. For example, the method can be performed by barrage, voting, and asking questions. And the organization party of the conference can summarize the interactive data in the conference process so as to know the ideas of all the conference participants.
Disclosure of Invention
In view of the above, one or more embodiments of the present disclosure provide an active content processing and presenting method, apparatus, electronic device, and storage medium.
To achieve the above object, one or more embodiments of the present disclosure provide the following technical solutions:
according to a first aspect of one or more embodiments of the present specification, there is provided an active content processing method including:
acquiring activity related content uploaded by at least one activity participant participating in the target activity;
clustering the campaign-related content to obtain a plurality of content groupings for the campaign-related content;
providing information of the plurality of content packets to the respective activity participants.
According to a second aspect of one or more embodiments of the present specification, there is provided an active content presentation method including:
uploading activity-related content of a target activity to a server, and clustering the activity-related content uploaded by at least one activity participant participating in the target activity by the server to obtain a plurality of content groups aiming at the activity-related content;
and receiving the information of the plurality of content groups provided by the server and displaying the information of the plurality of content groups.
According to a third aspect of one or more embodiments of the present specification, there is provided an active content processing apparatus including:
the content acquisition unit is used for acquiring activity related content uploaded by at least one activity participant participating in the target activity;
a clustering unit that clusters the activity-related content to obtain a plurality of content groups for the activity-related content;
and a packet return unit that provides information of the plurality of content packets to the respective activity participants.
According to a fourth aspect of one or more embodiments of the present specification, there is provided an active content display apparatus including:
the content uploading unit uploads the activity-related content of the target activity to the server, so that the server clusters the activity-related content uploaded by at least one activity participant participating in the target activity to obtain a plurality of content groups aiming at the activity-related content;
and the grouping receiving unit is used for receiving the information of the content groups provided by the server and displaying the information of the content groups.
According to a fifth aspect of one or more embodiments herein, there is provided an electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor implements the method as in any of the above embodiments by executing the executable instructions.
According to a sixth aspect of one or more embodiments of the present specification, there is provided a computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the method as described in any of the above embodiments.
As can be seen from the above embodiments, in the activity content processing scheme provided by this specification, in an application scenario where a plurality of activity participants exist for a target activity and each activity participant can publish activity-related content for the target activity, a plurality of content groups corresponding to the activity-related content are obtained by clustering the activity-related content uploaded by the activity participants and are displayed by each participant, so that the following beneficial effects can be achieved:
activity-related content with the same or similar semantics can be clustered into the same content group, and finally, the content groups representing different semantics are presented to the activity participants. On one hand, the real distribution situation of the activity-related content can be effectively presented; on the other hand, the method avoids the situation that the user at the activity participant side repeatedly browses the activity related content with the same or similar semantics, is beneficial to the user to intuitively know the various divergent activity related contents, and is beneficial to improving the user experience.
Drawings
FIG. 1 is a block diagram of an active content processing and presentation system according to an exemplary embodiment.
Fig. 2 is a flowchart of an active content processing method according to an exemplary embodiment.
Fig. 3 is an interaction diagram of a processing method of conference speaking content according to an exemplary embodiment.
Fig. 4 is a flowchart of a method for clustering vector data according to an exemplary embodiment.
Fig. 5 is a flowchart of an active content presentation method according to an exemplary embodiment.
Fig. 6 is a schematic structural diagram of an apparatus according to an exemplary embodiment.
Fig. 7 is a block diagram of an active content processing apparatus according to an example embodiment.
Fig. 8 is a schematic structural diagram of another apparatus provided in an exemplary embodiment.
FIG. 9 is a block diagram of an active content presentation device according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of the present specification. Rather, they are merely examples of apparatus and methods consistent with certain aspects of one or more embodiments of the specification, as detailed in the claims which follow.
It should be noted that: in other embodiments, the steps of the corresponding methods are not necessarily performed in the order shown and described herein. In some other embodiments, the method may include more or fewer steps than those described herein. Moreover, a single step described in this specification may be broken down into multiple steps for description in other embodiments; multiple steps described in this specification may be combined into a single step in other embodiments.
FIG. 1 is a block diagram of an active content processing and presentation system according to an exemplary embodiment. As shown in fig. 1, the system may include a server 11, a plurality of electronic devices, such as a mobile phone 12, a mobile phone 13, a computer 14, a computer 15, and the like, and a network 16.
The server 11 may be a physical server comprising a separate host, or the server 11 may be a virtual server hosted by a cluster of hosts. During the operation, the server 11 may run a server-side program of an application to implement a related service function of the application, for example, when the server 11 runs a program for performing an activity, the server may be implemented as a server in this specification. In one or more embodiments of the present disclosure, the server 11 may cooperate with the client running on the electronic devices 12-15 to implement the active content processing and presentation scheme.
For example, the server 11 may run a server-side program of a mobile group office platform, which may provide a conference function for users, and allow communication between participants joining a conference to implement interaction; such as speaking for the conference content, expressing its own perspective. In addition, the participants can further vote for the interactive data of the conference, and the mobile community office platform can also count the voting results and display the voting results to the participants, so that the participants can know the real ideas of other participants. Of course, in addition to the above functions, the server 11 may also be an integrated functional platform with many other functions, for example, processing internal events of the group such as an approval event (e.g., approval event such as leave request, office article application, finance, etc.), an attendance event, a task event, a log event, etc., and further processing external events of the group such as ordering, purchasing, etc., which is not limited in one or more embodiments of the present specification.
Cell phones 12-13, computers 14-15, etc. are just one type of electronic device that a user may use. In fact, it is obvious that the user can also use electronic devices of the type such as: tablet devices, notebook computers, Personal Digital Assistants (PDAs), wearable devices (e.g., smart glasses, smart watches, etc.), etc., which are not limited by one or more embodiments of the present disclosure. During operation, the electronic device may run a client-side program of an application to implement a related service function of the application, for example, when the electronic device runs a program for performing an activity, the electronic device may be implemented as a client in this specification.
The network 16 for interaction between the handsets 12-13, computers 14-15 and the server 11 may include various types of wired or wireless networks. For example, Network 16 may include the Public Switched Telephone Network (PSTN) and the Internet. Taking the mobile phones 12-13 as an example, a long connection can be established between the server 11 and the mobile phones 12-13 through the network 16, so that the server 11 sends data to the mobile phones 12-13 through the long connection. Alternatively, especially in the case where a long connection is not (or cannot be) established between the server 11 and the handsets 12-13, the server 11 may send a message to the corresponding operating system server according to the operating system running on the handsets 12-13, and the operating system server further sends the push message to the handsets 12-13.
Based on the system architecture, the present specification aims to improve the processing mode of the activity content and the display mode after the activity content is processed. Referring to fig. 2, fig. 2 is a flowchart illustrating an active content processing method according to an exemplary embodiment. As shown in fig. 2, the method is applicable to a server and may include the following steps:
step 202, obtaining the activity-related content uploaded by at least one activity participant participating in the target activity.
In this embodiment, a target activity may be created by a user through a client (the client is an organizer), and other users may be organized to join the target activity through their respective clients (the clients of other users are activity participants, and the organizer may also be an activity participant at the same time). Wherein, the activity participant can propose the activity-related content aiming at the target activity to realize the interaction. For example, the target activity is a teleconference, in this scenario, the activity participants are conference members participating in the conference, and each conference member can post its own view, ask questions, vote, and the like for the conference content. The interaction process can be completed through interaction with the server, namely, the activity participants need to upload the acquired activity-related content to the server for processing by the server and send the content to all the activity participants.
Step 204, clustering the activity-related content to obtain a plurality of content groups for the activity-related content.
In this embodiment, each activity participant can upload the acquired activity-related content to the server, and the server forwards the acquired activity-related content to other activity participants, thereby implementing interaction in the activity process. It should be noted that the semantics of the activity-related content uploaded by different activity participants may be different, similar or even the same. For example, for the topic of the meeting, "implementation period of project W", the view of publication by user a is "not more than 2 months", the view of publication by user B is "within 2 months", and the view of publication by user C is "at least 2 months or more"; it can be seen that although the published views of the users a and B are slightly different in form, the actual expressions have substantially the same meaning, and the published view of the user C is completely different from the published views of the users a and B. For the above situation, if the server directly sends the received activity-related content uploaded by each activity participant to all the activity participants for display, each activity participant will indiscriminately display the activity-related content of all the activity participants. On one hand, the display mode cannot intuitively reflect the real distribution situation of the activity-related content. On the other hand, a user on the activity participant side needs to repeatedly browse a plurality of activity-related contents with the same or similar semantics, and the actual requirement is that the user does not need to browse the activity-related contents with the repeated semantics but needs to quickly master the activity-related contents with different semantics, but the display mode enables the user not to quickly know the divergent activity-related contents, so that the browsing efficiency of the user is low, and the user experience is not favorably improved.
Therefore, the server in this specification, for the activity-related content uploaded by the activity participants, does not adopt a mode of directly sending the content to all the activity participants, but first performs clustering on the received activity-related content, and divides the activity-related content with the same or similar semantics into the same content groups, thereby obtaining a plurality of content groups corresponding to the received activity-related content (when the received activity-related content all express the same meaning, only one content group exists). Then, not all the received activity-related content is returned to each activity participant, but the information of the content groups obtained by clustering is returned to each activity participant for displaying.
In this embodiment, there is a difference in text length of the activity-related content uploaded by the activity participants, and for activity-related content with a long text length, when clustering is performed on the activity-related content, the data processing amount is large, and the accuracy of clustering may be affected. Therefore, in order to reduce the data processing amount of the server and improve the accuracy of clustering, a content length threshold for the activity-related content may be preset as a basis for determining whether to abstract the activity-related content. Based on the setting of the content length threshold, for any activity-related content in the received activity-related content, whether the content length of the activity-related content exceeds a preset content length threshold or not can be determined, so that the activity-related content exceeding the preset content length threshold is subjected to abstract extraction to obtain a corresponding content abstract, and then the content abstract can be used for replacing the activity-related content exceeding the preset content length threshold to participate in clustering.
In this embodiment, when clustering the received activity-related content, the activity-related content may be vectorized to obtain corresponding vector data, and then the vector data may be clustered. Furthermore, a language representation model for vectorizing the text can be trained offline, so that when activity-related content needs to be clustered, the language representation model can be called in real time to implement vectorization operation, and the vectorization efficiency is improved. For example, a bert (bidirectional Encoder retrieval from transforms) model may be used as the language representation model in the present specification, and of course, any other model that can be used for vectorizing text may be used, such as a word2vec model, a fasttext classifier, and the like, which is not limited by one or more embodiments of the present specification.
At step 206, information of the plurality of content groupings is provided to the respective activity participants.
Therefore, the following beneficial effects can be achieved by clustering the activity-related content uploaded by the activity participants to obtain a plurality of content groups corresponding to the activity-related content for display by each participant: activity-related content with the same or similar semantics can be clustered into the same content group, and finally, the content groups representing different semantics are presented to the activity participants. On one hand, the real distribution situation of the activity-related content can be effectively presented; on the other hand, the method avoids the situation that the user at the activity participant side repeatedly browses the activity related content with the same or similar semantics, is beneficial to the user to intuitively know the various divergent activity related contents, and is beneficial to improving the user experience.
In the embodiment, the information on the content grouping returned to each activity participant is different according to the corresponding showing mode. In one case, for the clustered content groups, corresponding uniform characterizing content can be generated for activity-related content in each content group, so as to return the uniform characterizing content of each content group to each activity participant; correspondingly, as the unified representation content can uniformly express the meanings of the activity-related content contained in the corresponding content group, each activity participant can display the unified representation content corresponding to each content group, so that the display mode is simple and the user experience is good. In another case, for the clustered content groups, at least a portion of the activity-related content contained by each content group may be returned to each activity participant. For example, all the activity-related content included in the content packet may be returned to each activity participant for presentation, or a portion of the activity-related content may be selected therefrom and returned to each activity participant for presentation. Of course, the specific selection rule can be flexibly set according to the actual requirement, and one or more embodiments of the present disclosure are not limited thereto. For example, one or more activity-related content items with the most content and the most complete expression can be selected from the content group through semantic analysis to return to each activity participant. In this embodiment, based on the content groups obtained by processing the activity content, after browsing the information of the content groups, the users on the activity participants can further select the content groups that meet their own conditions from the content groups to express the semantic opinion represented by the content groups. Taking a conference scenario as an example, the activity-related content is the speaking content of the members participating in the conference, and the speaking content of the members can be divided into a plurality of content groups with different meanings through the above-mentioned step 202 and 206, where each content group represents a different type of conference view, that is, the speaking content contained in the same content group represents the same type of conference view. Then all conference members may further vote on these content groups, expressing support for their own complimentary conference view. It should be noted that not all users need to speak, nor do all users need to vote on the conference perspective.
After receiving information (the unified representation content or at least part of the activity related content) of the content grouping provided by the server, each activity participant can use the information as a voting option for voting by users at each activity participant side. Further, an editing function may be provided for the voting choices, and the user may manually edit the specific contents of the voting choices. For example, a user with an editing right (e.g., an initiator of a conference) may modify the textual description of the voting option online (the modified textual description is sent to the server to be updated by the server and provided to all users), so that the textual description is more personalized or more consistent with the meaning of the actual expression, thereby increasing the interest of the voting process and the interactivity between the voting participants. As another example, the voting pattern may be extended. For example, in addition to selecting the voting option, the voting participants may further express support for the selected voting option through words, pictures and the like, and draw a vote through the manner. The data is sent to the server along with the selection information for the voting options, so that the data is sent to all voting participants by the server for display, for example, in the form of a bullet screen. In one case, the server may collect the selection information of all the activity participants for the plurality of content groups, and then count the selection conditions in a unified manner. For example, when the server returns the information of the plurality of content groups to each activity participant, an effective selection time period for the plurality of content groups may be set in association, so that the selection information uploaded by each activity participant in the effective time period is effective, and further, the effective selection information is counted; and for the selected information which is not uploaded in the effective time period, the final statistical result is not counted.
In this case, all the users on the activity participant side can select the displayed content group, so that the activity participant sends corresponding selection information to the server. Wherein the selection information is used for indicating the content groups selected by the user; for example, the method can be implemented by sending a selection instruction for the content packet, wherein the selection instruction includes the packet identifier of the content packet selected by the user. Then, the server may obtain the selection information uploaded by all the activity participants for the plurality of content groups, determine the statistical result of the selection condition of all the activity participants for the activity-related content based on the selection information, and then return the statistical result to each activity participant for being displayed by each activity participant. And the client used by the conference members can send corresponding voting information to the server, so that the server directly counts the voting number of each conference viewpoint and returns a voting result.
In another case, the server may obtain the selection information of each activity participant for the plurality of content groups in real time, perform statistics on the selection conditions in real time, and return the current statistics result to each activity participant in real time, so that the user at the activity participant side can know the selection conditions for the content groups in real time.
In this case, the user at each activity participant side can select the displayed content group, so that the activity participant sends corresponding selection information to the server. Similarly, the selection information is used to indicate the content packets selected by the user; for example, the method can be implemented by sending a selection instruction for the content packet, wherein the selection instruction includes the packet identifier of the content packet selected by the user. Then, the server may respectively obtain the selection information for the plurality of content groups uploaded by each activity participant, determine a statistical result of the selection condition of each activity participant for any content group based on the currently obtained selection information for any content group and the number of activity-related content currently contained in any content group, and then return the statistical result to each activity participant in real time to be displayed by each activity participant in real time. And after checking different conference views obtained by clustering, each conference member can vote the conference views, and the client used by the conference members can send corresponding voting information to the server so that the server counts the current voting number of each conference view in real time and returns the voting result in real time for the client to display.
Aiming at the mode of returning the current statistical result in real time, when counting the selection result, because the actual semantics are the same and only the activity-related contents with differences in the expression mode are divided into the same content group, the number of the activity-related contents currently contained in the content group and the selection number aiming at the content group are taken as the basis together, and the selection condition of the user at the activity participant side for the corresponding meaning of the content group can be accurately reflected. Specifically, for any content group, the server may determine, according to the currently acquired selection information for the any content group, the number of participants who currently and cumulatively select the any content group, so that the sum of the number of participants and the number of activity-related content currently included in the any content group is used as a statistical result currently corresponding to the any content group.
Also taking the conference scenario as an example, for any conference view (with type distinction, conference view points and content groups in one-to-one correspondence), the server can count the number of speech contents contained in the content group corresponding to the conference view point into the number of votes; in other words, the final number of votes is the sum of the number of votes currently and cumulatively selected from the conference viewpoint and the number of speech contents included in the content packet corresponding to the conference viewpoint. By the above method for calculating the voting result, even if a user does not vote after presenting the speech content for the conference, the speech content of the user is voted for a conference view corresponding to the speech content, so that the final voting result can accurately reflect the real distribution of the view proposed by the user for the conference.
For the convenience of understanding, the following describes the process of processing, presenting the conference speaking content and voting for the conference content in the following by taking the conference scenario as an example.
Referring to fig. 3, fig. 3 is an interaction diagram of a processing method of conference speaking content according to an exemplary embodiment. As shown in fig. 3, the interactive process may include the following steps:
in step 302A, the client 31 obtains the speech content input by the user a.
In step 302B, the client 32 obtains the speech content input by the user B.
In the present embodiment, it is assumed that the user a joins the conference through the client terminal 31 so that the client terminal 31 acts as a conference participant; user B joins the conference through client 32, so that client 32 acts as a conference participant. Of course, the number of conference participants depends on the actual situation and can be flexibly set, and the clients 31-32 are taken as an example for explanation.
User A, B may enter his own speech content in an input area presented by the respective client for uploading by the respective client to server 33 for processing.
In step 304A, the client 31 uploads the speech content.
In step 304B, client 32 uploads the talk content.
Step 306, the server 33 extracts and preprocesses the abstract of the speech content.
In this embodiment, in order to reduce the data processing amount of the server 33 and improve the accuracy of subsequent clustering, a text length threshold for the utterance content may be set as a basis for determining whether to abstract the utterance content. When the text length of the obtained speech content exceeds the threshold value, the server judges that the speech content is a long text, abstract extraction (only view extraction) needs to be carried out on the long text, a short text which is shorter in length and can express the original meaning of the long text is obtained, and then the short text is preprocessed. Of course, when the text length of the obtained utterance content does not exceed the threshold, it can be determined that the utterance content is a short text, and thus, the utterance content does not need to be abstracted and can be directly preprocessed.
The speech content can be abstracted by adopting a keyword extraction algorithm of any natural language. For example, TF-IDF (Term Frequency/Inverse Document Frequency), TextRank, etc. algorithms may be used, and one or more embodiments of the present disclosure are not limited thereto.
The example is TextRank. The TextRank algorithm divides a text into a plurality of composition units (words and sentences), establishes a graph model, and sorts important components in the text by using a voting mechanism, so that extraction of keywords can be completed only by using the information of a single document. Specifically, the TextRank constructs a network through adjacent relations among words, then calculates the rank value of each node by using the iteration principle of PageRank, and the keywords can be obtained by sorting the rank values. PageRank can be used for solving the problem of webpage ranking, the link relation between webpages is represented by the edges of a graph, and an iterative calculation formula is as follows:
Figure BDA0002613677550000111
PR (Vi) represents rank value of node Vi, in (Vi) represents predecessor node set of node Vi, out (Vj) represents successor node set of node Vj, and d is damping factor for smoothing. In the PageRank algorithm, the link relationships between web pages can be represented graphically. Similarly, TextRank constructs a graph by using adjacent nodes of word nodes in a sentence (a certain word has graph adjacency relation with the previous N words and the next N words). Specifically, a sliding window with the length of N can be set, all words in the window are regarded as adjacent nodes of word nodes, and therefore the word graph constructed by the TextRank is an undirected graph. Considering that different word pairs may have different co-occurrence (co-occurrence), the TextRank takes the co-occurrence as a weight of the undirected graph edge. Then, the iterative calculation formula of TextRank is as follows:
Figure BDA0002613677550000121
as can be seen, the formula has only one more weight term W than the PageRankjiWhich is used to indicate the different degrees of importance of the edge connection between two nodes. Based on the above formula, the keyword extraction application is further described below.
The algorithm used by TextRank for keyword extraction is as follows:
1) segmenting a given text T into complete sentences, i.e.
T＝[S1,S2,……,Sm]。
2) For each sentence Si belonging to T, performing word segmentation and part-of-speech tagging, filtering out stop words, and only keeping words with specified part-of-speech, such as nouns, verbs, adjectives and the like, namely
Si＝[ti,1,ti,2,……,ti,n]；
Where ti, j are the reserved candidate keywords.
3) And (V, E) constructing a candidate keyword graph G, wherein V is a node set and is composed of the candidate keywords generated in the step 2), and then constructing an edge between any two points by adopting a co-occurrence relationship (co-occurrence), wherein the edges exist between the two nodes only when the corresponding vocabularies co-occur in a window with the length of K, and K represents the size of the window, namely, at most K words co-occur.
4) And (4) iteratively propagating the weight of each node according to the formula (2) until convergence.
5) And carrying out reverse ordering on the node weights, thereby obtaining the most important T words as candidate keywords.
6) The most important T words are obtained in the step 5), the original text is marked, and if adjacent phrases are formed, the keywords are combined to form the multi-word keywords. At this point, the process of extracting the keywords is completed.
The preprocessing process can include operations such as wrong character correction, special character processing, sensitive word filtering, synonym rewriting and the like, so that the standardized speaking content is obtained. Of course, the specific operation of the pre-processing can be flexibly set according to the actual situation, and one or more embodiments of the present specification do not limit this.
In step 308, the server 33 calls the language characterization model to convert the content digest into vector data.
In this embodiment, the language representation model for vectorizing the text may be trained offline, so that when the speech content needs to be clustered, the language representation model may be called in real time to implement vectorization, thereby improving vectorization efficiency. For example, a bert (bidirectional Encoder retrieval from transforms) model may be used as the language representation model in the present specification, and of course, any other model that can be used for vectorizing text may be used, such as a word2vec model, a fasttext classifier, and the like, which is not limited by one or more embodiments of the present specification.
Taking the BERT model as an example, the BERT model may be trained in advance, and the trained BERT model may be deployed on another platform (different from the other platform of the current conference platform), so as to be called in real time through an online request.
In step 310, the server 33 clusters the vector data to obtain a content packet.
In this embodiment, a one-pass clustering algorithm may be adopted, and the one-pass clustering algorithm may complete clustering only by traversing the data set once, and has the characteristics of simplicity and high efficiency, and is relatively suitable for being used in a scene (such as a conference scene) with high requirements for incremental clustering and timeliness. Of course, any other clustering algorithm may be used, such as dbscan, hierarchical clustering, etc., and one or more embodiments of the present disclosure are not limited thereto.
The one-pass cluster algorithm is taken as an example for explanation. The flow of the one-pass cluster algorithm is as follows:
1) initially reading a new object from the data set;
2) constructing a new cluster with the object;
3) if the end of the data set is reached, the step 6) is carried out; otherwise, a new object is read in, the distance between the object and each existing cluster is calculated, and the cluster with the minimum distance to the object is selected.
4) If the minimum distance exceeds a given threshold value r, turning to step 2); otherwise, merging the object into the minimum cluster, updating the cluster center, and turning to the step 3);
5) the loop is ended.
The distance between the node and the cluster center can be calculated by adopting an Euclidean distance formula, so that whether the currently acquired object is combined into the existing cluster or not is determined. The Euclidean distance formula is as follows:
Figure BDA0002613677550000141
n represents the number of objects in the dataset.
Of course, clustering can also be performed by calculating cosine similarity (cosine similarity) between vectors. The process of clustering is described in detail below with reference to fig. 4. Referring to fig. 4, fig. 4 is a flowchart illustrating a method for clustering vector data according to an exemplary embodiment. As shown in fig. 4, the method applied to the server may include the following steps:
in step 402, similarity clustering is performed on vector data.
In step 404, determining whether the similarity exceeds a similarity threshold; if yes, go to step 406, otherwise go to step 410.
In this embodiment, a similarity threshold (cosine similarity threshold) may be set, and the similarity threshold is used to measure whether two vectors are similar to each other, i.e. whether the two vectors can be merged into the same content packet. Specifically, for the currently acquired vector data, the cosine value of the included angle between the vector data and the vector center corresponding to each existing content group can be calculated, and the similarity between the vector data and the existing content groups is sequentially evaluated. And when the calculated cosine value of the included angle with a certain vector center exceeds a similarity threshold value, dividing the speech content corresponding to the vector data into content groups corresponding to the vector center, and correspondingly updating the vector center. And when the cosine values of the included angles of the vector centers corresponding to all the existing content groups do not exceed the similarity threshold, adding a content group, and dividing the speech content corresponding to the vector data into the added content group.
In step 406, the utterance content corresponding to the vector data is divided into existing content packets.
In step 408, the vector center corresponding to the existing content packet is updated and returns to step 402.
In step 410, a content packet is added, the speaking content corresponding to the vector data is divided into the added content packet, and the process returns to step 402.
In step 312A, the server 33 returns a content packet to the client 31.
In step 312B, the server 33 returns the content packet to the client 32.
In step 314A, the client 31 presents the content package.
In step 314B, the client 32 presents the content package.
In one case, for the divided content groups, uniform representation contents which can represent the expressed meanings of all the content of the speech in the group can be generated for the speech content in each content group. Then, when the server 33 returns the information of the content packets (i.e. the conference viewpoint representing the content packets) to the clients 31-32, it is sufficient to return the uniform representation content of each content packet for being displayed by the clients 31-32, and the display manner is simple and the user experience is good.
In another case, for the divided content packets, at least part of the speaking content contained in each content packet may be returned to the clients 31-32. For example, all the speech content contained in the content packet can be returned to the client terminal 31-32 for presentation, and the user at the client terminal 31-32 side can also confirm the speech content published by itself to ensure that the speech content published by itself is divided into the correct content packets. Alternatively, for each content group, a portion of the speech content may be selected therefrom and returned to the client 31-32 for presentation. Of course, the specific selection rule can be flexibly set according to the actual requirement, and one or more embodiments of the present disclosure are not limited thereto. For example, semantic analysis may be performed to select one or more utterance contents with the longest text length and the most complete expression from the content packet.
In step 316A, the client 31 obtains voting information of the user a for the content packet.
In step 316B, the client 32 obtains voting information for the content packet from user B.
In this embodiment, the user on the client side may vote for a meeting point of view corresponding to the presented content group to indicate support for the meeting point of view. Further, the server 33 may show the voting situation, so as to let the users participating in the conference know what they want. For example, a top question list may be derived from the number of votes statistics for presentation by the clients 31-32.
In step 318A, the client 31 uploads the voting information.
In step 318B, the client 32 uploads the voting information.
In step 320, the server 33 counts the voting information.
In one case, the server 33 may collect the voting information uploaded by all the clients, and then count the voting conditions in a unified manner. For example, the voting time may be set to 2 minutes, and after the voting is initiated, the information of each content group is in a voteable state within 2 minutes, and after more than 2 minutes, the information of each content group is in an unselected state, and the voting cannot be performed on the information. In this case, after obtaining the voting information uploaded by all the clients, the service end 33 may determine the voting result for each content group directly based on the voting information, that is, the number of votes for each content group is the final voting result. And then, returning the voting results to each client for showing.
For example, assume that a content packet includes a, b, c, etc., corresponding votes and vote results such as
Table 1 shows:
content grouping Number of votes Voting result
Content packet a 15 15
Content packet b 20 20
Content packet c 9 9
…… …… ……
TABLE 1
In another case, the server may obtain the voting information uploaded by each client in real time, perform statistics on the voting conditions in real time, and return the current statistical results to each client in real time, so that the user at the client side can know the voting conditions for the content grouping in real time. Aiming at the mode of returning the current voting result in real time, when the voting result is counted, because the actual semantics are the same and only the speaking contents with differences in the expression mode are all divided into the same content group, the number of the speaking contents currently contained in the content group and the voting number aiming at the content group are taken as the basis together, and the voting condition of the user at the client side for the corresponding meaning of the content group can be accurately reflected.
For example, assume that the content packet includes a, b, c, etc., and the corresponding voting result is calculated as
Shown in Table 2:
content grouping Number of speech contents contained Number of votes Voting result
Content packet a 4 15 19
Content packet b 5 20 25
Content packet c 2 9 11
…… …… …… ……
TABLE 2
In step 322A, the server 33 returns the voting result to the client 31.
In step 322B, the server 33 returns the voting result to the client 32.
In step 324A, the client 31 displays the voting result.
In step 324B, the client 32 presents the voting results.
It should be noted that, the above descriptions are all given by taking a conference scenario as an example, and the technical solution of the present specification can also be applied to any other application scenarios that can post related content for an activity. For example, in a social scenario, the target activity is debate on a topic, opinion solicitation on a question, people election, and so forth. Taking character selection as an example, the target activity is specifically a singing game, and the vermicelli for watching the game can give a notice to the contestants or the game links. After the opinions published by the fans are clustered to obtain the grouping of various opinions, a voting link can be initiated to the fans, and the fans vote for various opinions.
Corresponding to the above embodiment of the server side, the present specification also provides an embodiment of a method for presenting active content on the client side, and the description related to the embodiment of the server side may also be applied to the embodiment of the method for presenting active content on the client side, which is not described in detail below.
Accordingly, fig. 5 is a flowchart of an active content presentation method according to an exemplary embodiment. As shown in FIG. 5, the method applied to an activity participant engaged in a target activity may include the steps of:
step 502, uploading activity-related content of a target activity to a server, so that the server clusters the activity-related content uploaded by at least one activity participant participating in the target activity to obtain a plurality of content groups for the activity-related content;
step 504, receiving the information of the plurality of content packets provided by the server, and displaying the information of the plurality of content packets.
As mentioned above, the activity-related content exceeding the preset content length threshold is abstracted by the server to obtain a content abstract, and the content abstract is used to replace the activity-related content exceeding the preset content length threshold to participate in the clustering.
As mentioned above, the activity-related content uploaded by at least one activity participant of the target activity is converted into corresponding vector data by the server invoking a pre-configured language representation model, and the vector data is used for participating in clustering.
As described above, the activity participants may upload selection information for the plurality of content groups to the server, so that the server determines, based on the selection information uploaded by all the activity participants, statistical results of all the activity participants regarding the selection of the activity-related content; and then, receiving and displaying the statistical result provided by the server.
As described above, the active participants may upload the selection information for the plurality of content groups to the server, so that the server determines, based on the currently acquired selection information for any content group and the number of activity-related content currently contained in any content group, a statistical result of the current selection condition of each active participant for any content group; and then, receiving and displaying the statistical result provided by the server.
As previously mentioned, the statistics corresponding to any of the content packets include: the sum of the number of the participants who select the any content group and the number of the activity-related content contained in the any content group is accumulated currently, and the number of the participants is determined by the server according to the currently acquired selection information aiming at the any content group.
As described above, the activity participants may receive the uniform characterization content provided by the server and generated for the activity-related content in each content group; alternatively, the activity participants may receive at least part of the activity-related content contained in each content packet provided by the server.
As previously described, the target activity comprises a conference activity, and the activity-related content comprises interaction data of activity participants for the conference activity.
In correspondence with the above method embodiments, the present specification also provides embodiments of an active content processing apparatus.
FIG. 6 is a schematic block diagram of an apparatus provided in an exemplary embodiment. Referring to fig. 6, at the hardware level, the apparatus includes a processor 602, an internal bus 604, a network interface 606, a memory 608 and a non-volatile memory 610, but may also include hardware required for other services. The processor 602 reads the corresponding computer program from the non-volatile memory 610 into the memory 608 and runs it, forming an active content processing apparatus on a logical level. Of course, besides software implementation, the one or more embodiments in this specification do not exclude other implementations, such as logic devices or combinations of software and hardware, and so on, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.
Referring to fig. 7, in a software implementation, the apparatus for processing active content, applied to a server, may include:
a content acquisition unit 71 that acquires activity-related content uploaded by at least one activity participant participating in the target activity;
a clustering unit 72 for clustering the activity-related content to obtain a plurality of content groups for the activity-related content;
a packet return unit 73 that provides information of the plurality of content packets to the respective activity participants.
Optionally, the apparatus further comprises:
and the abstract extracting unit 74 determines that the content length of any activity-related content exceeds a preset content length threshold, and extracts the abstract of the activity-related content exceeding the preset content length threshold to obtain a content abstract, wherein the content abstract is used for replacing the activity-related content exceeding the preset content length threshold to participate in clustering.
Optionally, the clustering unit 72 is specifically configured to:
calling a pre-configured language characterization model to convert the activity-related content into corresponding vector data;
and clustering the vector data.
Optionally, the method further includes:
a first information acquisition unit 75 that acquires selection information of all the activity participants with respect to the plurality of content groups;
the first statistical unit 76 determines the statistical result of the selection of the activity-related content by all the activity participants based on the selection information.
Optionally, the method further includes:
a second information obtaining unit 77 that obtains selection information of each activity participant for the plurality of content groups, respectively;
the second statistical unit 78 determines a statistical result of the selection condition of each current activity participant for any content group based on the currently acquired selection information for any content group and the number of activity-related content currently contained in any content group.
Optionally, the second statistical unit 78 is specifically configured to:
determining the number of participants who select any content group accumulatively at present according to the currently acquired selection information for any content group;
and taking the sum of the number of the participants and the number of the activity-related content currently contained in any content group as a statistical result currently corresponding to any content group.
Optionally, the packet returning unit 73 is specifically configured to:
generating corresponding uniform representation content aiming at the activity related content in each content group, and providing the uniform representation content of each content group for each activity participant; alternatively, the first and second electrodes may be,
at least a portion of the activity-related content contained in each content group is provided to each activity participant.
Optionally, the target activity includes a conference activity, and the activity-related content includes interaction data of activity participants for the conference activity.
FIG. 8 is a schematic block diagram of an apparatus provided in an exemplary embodiment. Referring to fig. 8, at the hardware level, the apparatus includes a processor 802, an internal bus 804, a network interface 806, a memory 808, and a non-volatile memory 810, but may also include hardware required for other services. The processor 802 reads the corresponding computer program from the non-volatile memory 810 into the memory 808 and then runs the computer program to form the active content presentation apparatus on a logical level. Of course, besides software implementation, the one or more embodiments in this specification do not exclude other implementations, such as logic devices or combinations of software and hardware, and so on, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.
Referring to fig. 9, in a software implementation, the apparatus for presenting active content, applied to an active participant participating in a target activity, may include:
the content uploading unit 91 uploads the activity-related content of the target activity to the server, so that the server clusters the activity-related content uploaded by at least one activity participant participating in the target activity to obtain a plurality of content groups for the activity-related content;
the packet receiving unit 92 receives the information of the plurality of content packets provided by the server, and displays the information of the plurality of content packets.
Optionally, the activity-related content exceeding the preset content length threshold is extracted by the server to obtain a content abstract, and the content abstract is used for replacing the activity-related content exceeding the preset content length threshold to participate in clustering.
Optionally, the server side invokes a pre-configured language representation model to convert the activity-related content uploaded by at least one activity participant of the target activity into corresponding vector data, where the vector data is used for participating in clustering.
Optionally, the method further includes:
a first information uploading unit 93, configured to upload, to the server, selection information for the plurality of content groups, so that the server determines, based on the selection information uploaded by all activity participants, a statistical result of selection conditions of all activity participants for the activity-related content;
the first result receiving unit 94 receives and displays the statistical result provided by the server.
Optionally, the method further includes:
a second information uploading unit 95, configured to upload, to the server, selection information for the plurality of content groups, so that the server determines, based on the currently acquired selection information for any content group and the number of currently-included activity-related content in any content group, a statistical result of a selection condition of each current activity participant for any content group;
the second result receiving unit 96 receives and displays the statistical result provided by the server.
Optionally, the statistical result corresponding to any content packet includes: the sum of the number of the participants who select the any content group and the number of the activity-related content contained in the any content group is accumulated currently, and the number of the participants is determined by the server according to the currently acquired selection information aiming at the any content group.
Optionally, the packet receiving unit 92 is specifically configured to:
receiving uniform representation content which is provided by the server and generated aiming at activity related content in each content group; alternatively, the first and second electrodes may be,
and receiving at least part of activity-related content contained in each content packet provided by the server.
Optionally, the target activity includes a conference activity, and the activity-related content includes interaction data of activity participants for the conference activity.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.
In a typical configuration, a computer includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in one or more embodiments of the present description to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of one or more embodiments herein. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
The above description is only for the purpose of illustrating the preferred embodiments of the one or more embodiments of the present disclosure, and is not intended to limit the scope of the one or more embodiments of the present disclosure, and any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the one or more embodiments of the present disclosure should be included in the scope of the one or more embodiments of the present disclosure.

Claims (34)

1. An active content processing method, comprising:
acquiring activity related content uploaded by at least one activity participant participating in the target activity;
clustering the campaign-related content to obtain a plurality of content groupings for the campaign-related content;
providing information of the plurality of content packets to the respective activity participants.
2. The method of claim 1, further comprising:
determining that the content length of any activity-related content exceeds a preset content length threshold;
and performing abstract extraction on the activity-related content exceeding the preset content length threshold to obtain a content abstract, wherein the content abstract is used for replacing the activity-related content exceeding the preset content length threshold to participate in clustering.
3. The method of claim 1, wherein clustering the activity-related content comprises:
calling a pre-configured language characterization model to convert the activity-related content into corresponding vector data;
and clustering the vector data.
4. The method of claim 1, further comprising:
acquiring selection information of all activity participants aiming at the plurality of content groups;
and determining the statistical result of all activity participants aiming at the selection condition of the activity-related content based on the selection information.
5. The method of claim 1, further comprising:
respectively acquiring selection information of each activity participant aiming at the plurality of content groups;
and determining the statistical result of the selection condition of each current activity participant for any content group based on the currently acquired selection information for any content group and the number of the activity-related content currently contained in any content group.
6. The method according to claim 5, wherein the determining the statistical result of the selection condition of each current activity participant for any content group based on the currently acquired selection information for any content group and the number of activity-related content currently contained in any content group comprises:
determining the number of participants who select any content group accumulatively at present according to the currently acquired selection information for any content group;
and taking the sum of the number of the participants and the number of the activity-related content currently contained in any content group as a statistical result currently corresponding to any content group.
7. The method of claim 1, wherein providing information of the plurality of content packets to the respective activity participants comprises:
generating corresponding uniform representation content aiming at the activity related content in each content group, and providing the uniform representation content of each content group for each activity participant; alternatively, the first and second electrodes may be,
at least a portion of the activity-related content contained in each content group is provided to each activity participant.
8. The method of claim 1, wherein the target activity comprises a conference activity, and wherein the activity-related content comprises interaction data of activity participants for the conference activity.
9. A method for presenting active content, comprising:
uploading activity-related content of a target activity to a server, and clustering the activity-related content uploaded by at least one activity participant participating in the target activity by the server to obtain a plurality of content groups aiming at the activity-related content;
and receiving the information of the plurality of content groups provided by the server and displaying the information of the plurality of content groups.
10. The method according to claim 9, wherein the activity-related content exceeding the preset content length threshold is summarized by the server to obtain a content summary, and the content summary is used to replace the activity-related content exceeding the preset content length threshold to participate in the clustering.
11. The method of claim 9, wherein the activity-related content uploaded by at least one activity participant of the target activity is converted by the server invoking a pre-configured language characterization model into corresponding vector data, the vector data being used for participating in clustering.
12. The method of claim 9, further comprising:
uploading selection information for the plurality of content groups to the server, and determining a statistical result of selection conditions of all activity participants for the activity-related content by the server based on the selection information uploaded by all the activity participants;
and receiving and displaying the statistical result provided by the server.
13. The method of claim 9, further comprising:
uploading selection information aiming at the plurality of content groups to the server, so that the server determines the statistical result of the selection condition of each current activity participant aiming at any content group based on the currently acquired selection information aiming at any content group and the quantity of activity related content currently contained in any content group;
and receiving and displaying the statistical result provided by the server.
14. The method of claim 13, wherein the statistics corresponding to any of the content packets comprise: the sum of the number of the participants who select the any content group and the number of the activity-related content contained in the any content group is accumulated currently, and the number of the participants is determined by the server according to the currently acquired selection information aiming at the any content group.
15. The method of claim 9, wherein the receiving information of the plurality of content packets provided by the server comprises:
receiving uniform representation content which is provided by the server and generated aiming at activity related content in each content group; alternatively, the first and second electrodes may be,
and receiving at least part of activity-related content contained in each content packet provided by the server.
16. The method of claim 9, wherein the target activity comprises a conference activity, and wherein the activity-related content comprises interaction data of activity participants for the conference activity.
17. An active content processing apparatus, comprising:
the content acquisition unit is used for acquiring activity related content uploaded by at least one activity participant participating in the target activity;
a clustering unit that clusters the activity-related content to obtain a plurality of content groups for the activity-related content;
and a packet return unit that provides information of the plurality of content packets to the respective activity participants.
18. The apparatus of claim 17, further comprising:
and the abstract extracting unit is used for determining that the content length of any activity-related content exceeds a preset content length threshold value, and extracting the abstract of the activity-related content exceeding the preset content length threshold value to obtain a content abstract, wherein the content abstract is used for replacing the activity-related content exceeding the preset content length threshold value to participate in clustering.
19. The apparatus according to claim 17, wherein the clustering unit is specifically configured to:
calling a pre-configured language characterization model to convert the activity-related content into corresponding vector data;
and clustering the vector data.
20. The apparatus of claim 17, further comprising:
the first information acquisition unit is used for acquiring the selection information of all the activity participants aiming at the plurality of content groups;
and the first statistical unit is used for determining the statistical result of all activity participants aiming at the selection condition of the activity related content based on the selection information.
21. The apparatus of claim 17, further comprising:
the second information acquisition unit is used for respectively acquiring the selection information of each activity participant aiming at the plurality of content groups;
and the second statistical unit is used for determining the statistical result of the selection condition of each current activity participant for any content group based on the currently acquired selection information for any content group and the number of the activity-related content currently contained in any content group.
22. The apparatus according to claim 21, wherein the second statistical unit is specifically configured to:
determining the number of participants who select any content group accumulatively at present according to the currently acquired selection information for any content group;
and taking the sum of the number of the participants and the number of the activity-related content currently contained in any content group as a statistical result currently corresponding to any content group.
23. The apparatus according to claim 17, wherein the packet returning unit is specifically configured to:
generating corresponding uniform representation content aiming at the activity related content in each content group, and providing the uniform representation content of each content group for each activity participant; alternatively, the first and second electrodes may be,
at least a portion of the activity-related content contained in each content group is provided to each activity participant.
24. The apparatus of claim 17, wherein the target activity comprises a conference activity, and wherein the activity-related content comprises interaction data of activity participants for the conference activity.
25. An activity content presentation device, comprising:
the content uploading unit uploads the activity-related content of the target activity to the server, so that the server clusters the activity-related content uploaded by at least one activity participant participating in the target activity to obtain a plurality of content groups aiming at the activity-related content;
and the grouping receiving unit is used for receiving the information of the content groups provided by the server and displaying the information of the content groups.
26. The apparatus of claim 25, wherein the activity-related content exceeding the preset content length threshold is summarized by the server to obtain a content summary, and the content summary is used to replace the activity-related content exceeding the preset content length threshold to participate in the clustering.
27. The apparatus of claim 25, wherein the activity-related content uploaded by at least one activity participant of the target activity is converted by the server invoking a pre-configured language characterization model into corresponding vector data, and the vector data is used for participating in clustering.
28. The apparatus of claim 25, further comprising:
the first information uploading unit uploads the selection information for the plurality of content groups to the server, so that the server determines the statistical result of the selection condition of all activity participants for the activity-related content based on the selection information uploaded by all activity participants;
and the first result receiving unit is used for receiving and displaying the statistical result provided by the server.
29. The apparatus of claim 25, further comprising:
the second information uploading unit uploads the selection information aiming at the plurality of content groups to the server, so that the server determines the statistical result of the selection condition of each current activity participant aiming at any content group based on the currently acquired selection information aiming at any content group and the quantity of activity related content currently contained in any content group;
and the second result receiving unit is used for receiving and displaying the statistical result provided by the server.
30. The apparatus of claim 29, wherein the statistics corresponding to the any content packet comprise: the sum of the number of the participants who select the any content group and the number of the activity-related content contained in the any content group is accumulated currently, and the number of the participants is determined by the server according to the currently acquired selection information aiming at the any content group.
31. The apparatus of claim 25, wherein the packet receiving unit is specifically configured to:
receiving uniform representation content which is provided by the server and generated aiming at activity related content in each content group; alternatively, the first and second electrodes may be,
and receiving at least part of activity-related content contained in each content packet provided by the server.
32. The apparatus of claim 25, wherein the target activity comprises a conference activity, and wherein the activity-related content comprises interaction data of activity participants for the conference activity.
33. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor implements the method of any one of claims 1-16 by executing the executable instructions.
34. A computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, carry out the steps of the method according to any one of claims 1 to 16.
CN202010763268.6A 2020-07-31 2020-07-31 Activity content processing and displaying method and device, electronic equipment and storage medium Pending CN114064163A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010763268.6A CN114064163A (en) 2020-07-31 2020-07-31 Activity content processing and displaying method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010763268.6A CN114064163A (en) 2020-07-31 2020-07-31 Activity content processing and displaying method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114064163A true CN114064163A (en) 2022-02-18

Family

ID=80227908

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010763268.6A Pending CN114064163A (en) 2020-07-31 2020-07-31 Activity content processing and displaying method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114064163A (en)

Similar Documents

Publication Publication Date Title
US10380158B2 (en) System for determining and optimizing for relevance in match-making systems
US8447640B2 (en) Device, system and method of handling user requests
US9471883B2 (en) Hybrid human machine learning system and method
US7421429B2 (en) Generate blog context ranking using track-back weight, context weight and, cumulative comment weight
US10469275B1 (en) Clustering of discussion group participants
US20170011029A1 (en) Hybrid human machine learning system and method
US20120016661A1 (en) System, method and device for intelligent textual conversation system
US20130018968A1 (en) Automatic profiling of social media users
US20120197993A1 (en) Skill ranking system
KR20160055930A (en) Systems and methods for actively composing content for use in continuous social communication
WO2018040069A1 (en) Information recommendation system and method
US8874559B1 (en) Ranking and ordering items in user-streams
CN109284502B (en) Text similarity calculation method and device, electronic equipment and storage medium
US9779169B2 (en) System for ranking memes
Samuel et al. That message went viral?! exploratory analytics and sentiment analysis into the propagation of tweets
US20170052761A1 (en) Expert signal ranking system
CN108804456B (en) Chat sessions based on object-specific knowledge base
US8954451B2 (en) Selecting microblog entries based on web pages, via path similarity within hierarchy of categories
EP3996373A2 (en) Method and apparatus of generating bullet comment, device, and storage medium
US20180349347A1 (en) Measuring Phrase Association on Online Social Networks
CN110188248A (en) Data processing method, device and electronic equipment based on news question and answer interactive system
US11095601B1 (en) Connection tier structure defining for control of multi-tier propagation of social network content
CN108600083B (en) Message reminding method and device
Mastykash et al. Internet social environmental platforms data representation
CN113407677B (en) Method, apparatus, device and storage medium for evaluating consultation dialogue quality

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination