CN109271509B - Live broadcast room topic generation method and device, computer equipment and storage medium - Google Patents
Live broadcast room topic generation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109271509B CN109271509B CN201810969224.1A CN201810969224A CN109271509B CN 109271509 B CN109271509 B CN 109271509B CN 201810969224 A CN201810969224 A CN 201810969224A CN 109271509 B CN109271509 B CN 109271509B
- Authority
- CN
- China
- Prior art keywords
- topic
- title
- live broadcast
- broadcast room
- room
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a method and a device for generating topics of a live broadcast room, computer equipment and a storage medium. The method comprises the following steps: acquiring a published document meeting the attention degree condition in at least one information publishing platform; adopting similarity matching conditions to collect the title information of the published documents into corresponding title sets; and determining title keywords corresponding to the title set, and constructing the live broadcast topic according to the title keywords. The technical scheme of the embodiment of the invention overcomes the technical defects that the existing topic library construction mode is time-consuming and labor-consuming, has higher labor cost and certain information hysteresis, constructs the topic of the live broadcast room through the published document of the information platform, and realizes the method for constructing the artificial topic.
Description
Technical Field
The embodiment of the invention relates to the technical field of data mining, in particular to a live broadcast room topic generation method and device, computer equipment and a storage medium.
Background
The live broadcast software is used as an entertainment tool to provide a participating entertainment mode for users, and the live broadcast software is rapidly favored and pursued by the broad masses of users due to the characteristics of good real-time performance and strong interactivity. Currently, in the live broadcast process, the interaction between the main broadcast and the audience generally takes a certain topic as a main line.
The interactive topics of the live broadcast room can be set by the anchor through voice interaction during broadcasting, and can also be selected from a topic library by the anchor. Accordingly, a library of questions needs to be set up and completed before the live broadcast. In the prior art, the topic library is generally manually input by a worker.
In the process of implementing the invention, the inventor finds that the prior art has the following defects: when the topic library is established, the contents in the topic library are all manually input by workers, the labor cost is high, and the selected topics have certain information hysteresis.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for generating a live broadcast topic, a computer device, and a storage medium, so as to optimize an existing live broadcast topic generation method.
In a first aspect, an embodiment of the present invention provides a method for generating a live broadcast topic, including:
acquiring a published document meeting the attention degree condition in at least one information publishing platform;
collecting the title information of the issued document into a corresponding title set by adopting a similarity matching condition;
and determining title keywords corresponding to the title set, and constructing the topic of the live broadcast room according to the title keywords.
In the above method, optionally, the attention condition includes at least one of:
the reading amount is greater than or equal to the reading number threshold, the comment amount is greater than or equal to the comment number threshold, and the praise amount is greater than or equal to the praise number threshold.
In the above method, optionally, determining the title keyword corresponding to the title set includes:
performing word segmentation processing on at least one piece of title information included in the title set to obtain at least two word segments;
calculating the word frequency of each participle;
and sequencing each participle according to the word frequency, and acquiring the title key words corresponding to the title set according to a sequencing result.
In the above method, optionally, before calculating the word frequency of each word segmentation, the method further includes:
and filtering the common words of each participle according to a common word bank.
In the above method, optionally, constructing a live-room topic according to the title keyword includes:
sending the title keywords to a label determination platform, and acquiring word attribute labels corresponding to the title keywords, which are fed back by the label determination platform;
acquiring a standard topic sentence pattern corresponding to the word attribute label, wherein the standard topic sentence pattern comprises blank items for filling title keywords;
and combining the title key words with the standard topic sentence patterns to obtain the live broadcast topic.
In the above method, optionally, after constructing the live-room topic according to the title keyword, the method further includes:
sending the live broadcast room topic to an auditing platform for topic auditing;
if receiving an examination passing response fed back by the examination platform, storing the topic of the live broadcast room in a topic library;
the topics stored in the topic library are used for being provided for a main broadcasting terminal to select, so that the target topic selected by the main broadcasting terminal is displayed in the corresponding live broadcasting room.
In a second aspect, an embodiment of the present invention provides an apparatus for generating a live broadcast topic, including:
the document acquisition module is used for acquiring published documents meeting the attention degree condition in at least one information publishing platform;
the title collecting module is used for collecting the title information of the published document into a corresponding title set by adopting a similarity matching condition;
and the live broadcasting room topic construction module is used for determining the title key words corresponding to the title set and constructing the live broadcasting room topic according to the title key words.
In the above apparatus, optionally, the attention condition includes at least one of:
the reading amount is greater than or equal to the reading number threshold, the comment amount is greater than or equal to the comment number threshold, and the praise amount is greater than or equal to the praise number threshold.
In a third aspect, an embodiment of the present invention provides a computer device, where the computer device includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method according to any one of the embodiments of the invention.
In a fourth aspect, embodiments of the present invention provide a storage medium containing computer-executable instructions for performing a method according to any one of the embodiments of the present invention when executed by a computer processor.
The embodiment of the invention provides a method and a device for generating a topic in a live broadcast room, computer equipment and a storage medium.
Drawings
Fig. 1 is a flowchart of a method for generating a live broadcast topic according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for generating a live broadcast topic according to a second embodiment of the present invention;
fig. 3 is a flowchart of a method for generating a live broadcast topic according to a third embodiment of the present invention;
fig. 4 is a structural diagram of a live broadcast topic generation device according to a fourth embodiment of the present invention;
fig. 5 is a structural diagram of a computer device according to a fifth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in further detail below with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention.
It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1 is a flowchart of a method for generating a live broadcast topic according to an embodiment of the present invention, where the method of this embodiment may be executed by a device for generating a live broadcast topic, and the device may be implemented in a hardware and/or software manner, and may be generally integrated in a server, an intelligent mobile terminal, and other devices. The method of the embodiment specifically includes:
s101, acquiring a published document meeting the attention degree condition in at least one information publishing platform.
In this embodiment, the information publishing platform may specifically be a news website, a news application, a microblog platform, a wechat application, and the like. The attention degree condition specifically refers to a condition to be satisfied by data representing the attention degree of a user who issues a document. The attention condition may specifically be a condition that is satisfied by the number of reads, the number of comments, the number of forwards, the number of likes, or the number of favorites of the published document, or may be a condition that is satisfied by multiple data (e.g., the number of reads and the number of comments) at the same time.
It is understood that the information publishing platform will typically publish the latest, hottest and socially more influential documents in a timely manner, and that these latest, hottest and socially more influential documents will also be of high interest to the user. Therefore, the published documents meeting the attention condition acquired from the information publishing platform should be documents with higher popularity and popularity at present, so that the popularity and popularity of the topic of the live broadcast room determined according to the acquired published documents can be higher, and the topic can be better matched with the live broadcast application and used as the topic discussed in the live broadcast room (especially the voice live broadcast room).
S102, adopting similarity matching conditions to collect the title information of the published documents into corresponding title sets.
In this embodiment, after the published documents meeting the attention degree condition are acquired from the information publishing platform, similarity matching is performed on the title information of each acquired published document, and then the acquired title information of the published documents is collected and divided into one or more title sets according to the matching result and the similarity matching condition.
In this embodiment, the similarity matching of the obtained header information of the published document may specifically determine the similarity between two header information by using a calculation method such as an euclidean distance, a cosine similarity, a minkowski distance, and a manhattan distance. The similarity matching condition may specifically be that the text similarity of the header information of the two published documents is greater than a set threshold value, and the like.
It can be understood that, the higher the above-mentioned set threshold is set, the higher the similarity of all the title information in a title set is, and the fewer the number of different title keywords contained in all the title information in the title set is.
It will be further appreciated that in order to reduce the relevance of the live-room topic (i.e., the similarity between different live-room topics should be low), for two title keywords with higher similarity, one of the title keywords may be discarded, and the live-room topic may be constructed only for the other title keyword. Therefore, the set threshold is not easily set too high, otherwise, the similarity of the title keywords determined from different title sets may be too high, and the correlation of the topic in the live broadcast may be too high.
In this embodiment, the method for collecting the title information of the published document may specifically be to select one title information as the information to be matched, and collect all the title information whose similarity with the title information satisfies the similarity matching condition and the title information into one title information set.
S103, determining title keywords corresponding to the title set, and constructing the topic of the live broadcast room according to the title keywords.
In the present embodiment, after dividing the title information of the published document into title sets, the title keyword corresponding to each title set is determined. One title set may correspond to one title keyword or may correspond to a plurality of title keywords. The title keyword may be a word with the highest occurrence frequency among all the title information in the title set, or a word with the occurrence frequency greater than a set threshold.
Further, after determining the title keywords, the live room topics can be constructed according to the content of the title keywords, and one title keyword can specifically construct one or more live room topics. For example, if the title keyword is "clothing", the live room topic constructed from "clothing" may be specifically "what style of clothing you like", "brand of clothing you buy frequently", and so on.
The embodiment of the invention provides a method for generating a topic in a live broadcast room, which comprises the steps of firstly collecting the title information of a published document meeting the attention degree condition into a title set, and then constructing the topic in the live broadcast room according to keywords corresponding to the title set, so that the technical defects that the existing topic library construction mode is time-consuming and labor-consuming, high in labor cost and certain in information hysteresis are overcome, the topic in the live broadcast room is constructed through the published document of an information platform, an artificial topic construction method is realized, manual participation is not needed, the topic can be constructed quickly, conveniently and high in real-time, and the constructed topic is high in timeliness.
Example two
Fig. 2 is a flowchart of a method for generating a live broadcast topic according to a second embodiment of the present invention. In this embodiment, a specific keyword determination method is provided, and meanwhile, a common word filtering step is added, and a specific implementation manner of a specific live broadcast topic construction method is provided.
Correspondingly, the method of the embodiment specifically includes:
s201, acquiring a published document meeting the attention degree condition in at least one information publishing platform.
S202, adopting similarity matching conditions to collect the title information of the published documents into corresponding title sets.
S203, performing word segmentation processing on at least one piece of title information included in the title set to obtain at least two word segments.
In the present embodiment, the determination process of the title keyword is embodied in steps 203 to 206.
Since the title information in the title set satisfies the similarity matching condition, it can be known that the similarity of the text content in all the title information belonging to one title set is high, in this embodiment, only one title information in one title set may be used to determine one or more title keywords corresponding to the title set, and certainly, in order to improve the accuracy of the title keywords, it is preferable to use a plurality of or all the title information to determine one or more title keywords corresponding to the title set.
Further, if the plurality of pieces of title information are used to determine one or more title keywords corresponding to the title set, the plurality of pieces of title information may be specifically randomly selected from the title set, or may be selected according to the similarity, and the like, which is not limited in this embodiment.
Typically, all the title information included in the title set may be subjected to word segmentation processing, and word segmentation results corresponding to the title information may be obtained.
And S204, filtering the common words of each participle according to the common word bank.
It is understood that the word frequency of the common words appearing in the title information is high, and thus the common words may be erroneously determined as the title keywords. Therefore, in the present embodiment, after the word segmentation is performed on the header information, the filtering of the common words is performed on the word segmentation first. The common word bank can be one or more of an adverb bank, a conjunctive bank, a preposition bank and an assistant bank.
Typically, the adverb lexicon includes: the common adverbs such as "has", "at", "time" or "most"; the word bank comprises: the use of the conjunction of "with," "in place of," "about," "with," or "and" the like; the preposition word library comprises: the common prepositions of "from", "to", "towards" or "and the like; the auxiliary word library comprises: the common auxiliary words such as "get", "only", "give" or "also" are used.
And S205, calculating the word frequency of each participle after the common word is filtered.
In this embodiment, the title keyword is determined according to the word frequency of each participle obtained after the participle of the title information is participled, so after the participle is filtered by the common word, the word frequency of each participle is counted, that is, the occurrence frequency of each participle in the participle result respectively corresponding to each title information is counted.
S206, sequencing the participles according to the word frequency, and acquiring the title key words corresponding to the title set according to the sequencing result.
In this embodiment, the participles are sorted according to the word frequency from large to small or from small to large, and then only the participle with the highest word frequency may be selected as the title keyword, or all the participles with the word frequency greater than the set word frequency threshold may be selected as the title keyword.
And S207, sending the title keywords to a label determination platform, and acquiring word attribute labels corresponding to the title keywords and fed back by the label determination platform.
In this embodiment, steps 207 to 209 embody a method of constructing a live-room topic from the title keyword.
In this embodiment, a set of standard topic sentence patterns is associated with a word attribute tag, so that after the word attribute tag associated with the title keyword is determined, the live broadcast topic associated with the title keyword can be easily constructed. The term attribute tag may specifically be a person name, a place name, a clothing brand, a cosmetic brand, and the like.
Illustratively, if the term attribute label is "place name," then the corresponding set of standard topic sentence patterns may include: "do you like XXX? "," do you go past XXX? "," do you feel XXX? "and the like. Where the blank position of "XXX" is used to fill the title key.
And S208, acquiring a standard topic sentence pattern corresponding to the word attribute label, wherein the standard topic sentence pattern comprises blank items for filling the title key words.
S209, combining the title keywords with the standard topic sentence pattern to obtain the topic in the live broadcast room.
In this embodiment, the title keyword may be specifically combined with all the standard topic sentence patterns to obtain all the live broadcast room topics corresponding to the title keyword. Further, if the number of the live broadcast topic is limited, the number of the live broadcast topic required to be formed by each title keyword can be determined according to the number of the title keywords and the number of the standard topic periods corresponding to each type of word attribute tags.
And S210, sending the live broadcast room topics to an auditing platform for topic auditing.
In order to ensure that the live broadcast topic is healthy, in this embodiment, the constructed live broadcast topic is sent to an auditing platform for topic auditing. The topic auditing mode may specifically be auditing by a worker, or auditing by matching with a bad word, and the like, which is not limited in this embodiment.
And S211, if an audit passing response fed back by the audit platform is received, storing the topics of the live broadcast room in a topic library, wherein the topics stored in the topic library are used for being provided for the anchor terminal to select, so that the target topics selected by the anchor terminal are displayed in the corresponding live broadcast room.
The embodiment of the invention provides a method for generating a topic in a live broadcast room, which embodies a method for determining a keyword and improves the accuracy of extracting a title keyword. Meanwhile, the step of filtering common words is added, the bad interference of the common words on the extraction of the title key words is avoided, the method for constructing the topic in the live broadcast room is specified, and the topic in the live broadcast room is quickly, simply and effectively constructed according to the title key words.
On the basis of the foregoing embodiments, the attention condition may specifically include at least one of the following: the reading amount is greater than or equal to the reading number threshold, the comment amount is greater than or equal to the comment number threshold, and the praise amount is greater than or equal to the praise number threshold.
The benefits of this arrangement are: the published documents with higher attention can be correctly and effectively screened out.
EXAMPLE III
Fig. 3 is a flowchart of a method for generating a live broadcast topic according to a third embodiment of the present invention. The embodiment is optimized based on the above embodiment, and in this embodiment, a specific implementation manner for increasing the live broadcast topic setting process is provided.
Correspondingly, the method of the embodiment specifically includes:
s301, in at least one information publishing platform, a publishing document meeting the attention degree condition is obtained.
S302, adopting similarity matching conditions to collect the title information of the published documents into corresponding title sets.
S303, determining title keywords corresponding to the title set, and constructing the topic of the live broadcast room according to the title keywords.
And S304, storing all the live broadcast topics in a set storage area to form a topic library.
S305, the server obtains an alternative topic set from the topic library and feeds the alternative topic set back to the anchor terminal according to the topic setting instruction of the live broadcast room sent by the anchor terminal.
In this embodiment, the anchor terminal may specifically be a terminal device such as an intelligent mobile terminal and a tablet computer used by an anchor in a live broadcast room. The live broadcast room specifically refers to a virtual room established by the anchor using a live broadcast application program and provided for a user (viewer) in the live broadcast room to enter, and typically may be a voice live broadcast room or a video live broadcast room. The topic library includes a plurality of legal topics for discussion in the live broadcast.
In this embodiment, the topic setting instruction may specifically be a topic setting instruction for adding a topic, and may also be a topic setting instruction for replacing a topic, and the like. Specifically, the anchor in the live broadcast room can enable the anchor to send a topic setting instruction for adding topics to the server by selecting the topic setting control during broadcasting, and can also enable the anchor to send a topic setting instruction for changing topics to the server by selecting the topic changing control during the live broadcast.
It can be understood that, when a user uses a live broadcast application program and enters a live broadcast room, most of the situations are that the live broadcast room is already played for a period of time, so that the user cannot know the topic of current communication of the live broadcast room just before entering the live broadcast room, and the user is difficult to quickly merge into the live broadcast room. Therefore, in this embodiment, the anchor sends a topic setting instruction to the server through the anchor end when the live broadcast is broadcast, and then the server enables the anchor to display the target topic in the live broadcast through the live broadcast topic setting method formed in steps 305 to 307.
In this embodiment, the manner in which the server acquires the candidate topic sets from the topic library may be that the server randomly selects a certain number of candidate topics from the topic library to form the candidate topic sets, or the server acquires a set number of candidate topics from the candidate topic sets according to the number of topics or the generation time of the topics in the descending order or ascending order. Typically, the server may record each alternative topic in the set of alternative topics pushed to the same anchor to avoid the same alternative topic being pushed to the same anchor multiple times.
The set number may be a fixed value set by a system, a user-defined value freely set by the anchor terminal, a value dynamically changing according to changes in display modes and positions of alternative topics of different anchor terminals, and the like, and the comparison in this embodiment is not limited.
Further, the alternative topics included in the topic library may be pre-entered by staff of the live broadcast platform, may also be provided by a plurality of anchor broadcasters (for example, anchor broadcasters with certain authority), may also be filtered from network hotwords, and the like, and certainly, the alternative topics may also be obtained by any two or all three of the above three alternative topic obtaining manners, which is not limited in this embodiment.
S306, the server receives the target topic determined by the anchor terminal according to the fed back alternative topic set.
In this embodiment, after receiving the alternative topic set fed back by the server, the anchor terminal displays the alternative topic set, so that the anchor in the live broadcast room can select an interested topic, that is, a target topic from the alternative topic set. After the anchor determines and selects the target topic, the anchor end sends the target topic selected by the anchor to the server.
S307, the server pushes the target topic to a live broadcast room to be displayed.
In this embodiment, after receiving the target topic, the server may push the target topic to the live broadcast room, so that all users of the live broadcast room corresponding to the live broadcast room can view the target topic. Typically, the target topic can be directly pushed to all the user terminals associated with the anchor terminal, so as to instruct the user terminals to display the target topic at the set display positions of the corresponding user side display interface.
Furthermore, the target topic can be synchronously pushed to the anchor side so as to instruct the anchor side to display the target topic at the set display position of the corresponding anchor side display interface.
It should be noted that, in this embodiment, steps 301 to 307 may be executed by the same server, or may be executed by different servers. If steps 301 to 307 in this embodiment are executed by different servers, steps 301 to 304 are executed by the same server, and steps 305 to 307 are executed by the same server.
The embodiment of the invention provides a method for generating a topic of a live broadcast room, which increases a process for setting the topic of the live broadcast room, solves the technical defect that a user needs to spend a large amount of time to find an interested live broadcast room in the prior art, enables the user to know the communication topic of the live broadcast room in time after entering the live broadcast room through the real-time display of the communication topic of the live broadcast room, greatly reduces the time for the user to determine whether to reside in the live broadcast room or not, and further shortens the time for the user to find the interested live broadcast room. In addition, the technical scheme of the embodiment can also enable the user who just enters the live broadcast room to quickly integrate into the topic being discussed in the live broadcast room, and improve the use experience of the user.
Example four
Fig. 4 is a configuration diagram of a live broadcast topic generation device according to a fourth embodiment of the present invention. As shown in fig. 4, the apparatus includes: a document acquisition module 401, a title collection module 402, and a live broadcast topic construction module 403, wherein:
a document obtaining module 401, configured to obtain, in at least one information publishing platform, a publishing document that meets a concern condition;
a title collecting module 402, configured to collect the title information of the published document in a corresponding title set by using a similarity matching condition;
and a live broadcast topic constructing module 403, configured to determine a title keyword corresponding to the title set, and construct a live broadcast topic according to the title keyword.
The embodiment of the invention provides a device for generating a topic in a live broadcast room, which comprises a document acquisition module, a topic collection module, a topic construction module and a topic generation module, wherein the document acquisition module is used for acquiring a published document meeting an attention degree condition in at least one information publishing platform, the topic collection module is used for collecting the topic information of the published document into a corresponding topic collection by adopting a similarity matching condition, and the topic construction module is used for determining a topic keyword corresponding to the topic collection and constructing the topic in the live broadcast room according to the topic keyword.
The device solves the technical defects that the existing topic library construction mode is time-consuming and labor-consuming, the labor cost is high and certain information hysteresis is provided, constructs the topic of the live broadcast room through the published document of the information platform, and realizes an artificial topic construction method.
On the basis of the above embodiments, the attention condition may include at least one of the following:
the reading amount is greater than or equal to the reading number threshold, the comment amount is greater than or equal to the comment number threshold, and the praise amount is greater than or equal to the praise number threshold.
On the basis of the foregoing embodiments, the live broadcast topic construction module 403 may include:
the word segmentation unit is used for performing word segmentation processing on at least one piece of title information included in the title set to obtain at least two word segments;
the word frequency calculating unit is used for calculating the word frequency of each participle;
and the title keyword acquisition unit is used for sequencing each participle according to the word frequency and acquiring the title keyword corresponding to the title set according to the sequencing result.
On the basis of the above embodiments, the method may further include:
and the common word filtering unit is used for filtering the common words of the participles according to the common word bank before calculating the word frequency of the participles.
On the basis of the foregoing embodiments, the live broadcast topic construction module 403 may further include:
the word attribute label acquisition unit is used for sending the title key words to the label determination platform and acquiring word attribute labels which are fed back by the label determination platform and correspond to the title key words;
a standard topic sentence pattern obtaining unit, configured to obtain a standard topic sentence pattern corresponding to the word attribute tag, where the standard topic sentence pattern includes a blank item for filling the title keyword;
and the live broadcast room topic determining unit is used for combining the title key words and the standard topic sentence patterns to obtain the live broadcast room topic.
On the basis of the above embodiments, the method may further include:
the topic sending module is used for sending the live broadcast room topic to the auditing platform for topic auditing after the live broadcast room topic is constructed according to the title key words;
the topic storage module is used for storing the topics of the live broadcast room in the topic library if receiving the auditing passing response fed back by the auditing platform;
the topics stored in the topic library are used for being provided for the anchor terminal to select, so that the target topic selected by the anchor terminal is displayed in the corresponding live broadcasting room.
The device for generating the live broadcast topic provided by the embodiment of the invention can be used for executing the method for generating the live broadcast topic provided by any embodiment of the invention, has corresponding functional modules, and realizes the same beneficial effects.
EXAMPLE five
Fig. 5 is a schematic structural diagram of a computer device according to a fifth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in FIG. 5 is only an example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 5, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing a method for creating a live-talk question library provided by an embodiment of the present invention. Namely: acquiring a published document meeting the attention degree condition in at least one information publishing platform; collecting the title information of the issued document into a corresponding title set by adopting a similarity matching condition; and determining title keywords corresponding to the title set, and constructing the topic of the live broadcast room according to the title keywords.
EXAMPLE six
The sixth embodiment of the present invention further provides a storage medium containing computer-executable instructions, where the computer-executable instructions are executed by a computer processor to implement the method for establishing a live broadcast title library according to the sixth embodiment of the present invention. Namely: acquiring a published document meeting the attention degree condition in at least one information publishing platform; collecting the title information of the issued document into a corresponding title set by adopting a similarity matching condition; and determining title keywords corresponding to the title set, and constructing the topic of the live broadcast room according to the title keywords.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (8)
1. A method for generating a topic of a live broadcast room is characterized by comprising the following steps:
acquiring a published document meeting the attention degree condition in at least one information publishing platform;
collecting the title information of the issued document into a corresponding title set by adopting a similarity matching condition;
screening title keywords according to a set threshold;
determining title keywords corresponding to the title set, and constructing a live broadcast topic according to the title keywords;
storing all the live broadcast room topics to a set storage area to form a topic library;
setting an instruction according to a topic of a live broadcast room sent by a main broadcast end, and obtaining an alternative topic set from a topic library and feeding back the alternative topic set to the main broadcast end;
receiving a target topic determined by the anchor terminal according to the fed back alternative topic set;
wherein the attention condition comprises at least one of:
the reading amount is greater than or equal to the reading number threshold, the comment amount is greater than or equal to the comment number threshold, and the praise amount is greater than or equal to the praise number threshold.
2. The method of claim 1, wherein determining title keywords corresponding to the set of titles comprises:
performing word segmentation processing on at least one piece of title information included in the title set to obtain at least two word segments;
calculating the word frequency of each participle;
and sequencing each participle according to the word frequency, and acquiring the title key words corresponding to the title set according to a sequencing result.
3. The method of claim 2, further comprising, prior to calculating the word frequency for each of the participles:
and filtering the common words of each participle according to a common word bank.
4. The method of any of claims 1-3, wherein constructing a live-room topic from the title key comprises:
sending the title keywords to a label determination platform, and acquiring word attribute labels corresponding to the title keywords, which are fed back by the label determination platform;
acquiring a standard topic sentence pattern corresponding to the word attribute label, wherein the standard topic sentence pattern comprises blank items for filling title keywords;
and combining the title key words with the standard topic sentence patterns to obtain the live broadcast topic.
5. The method of any of claims 1-3, further comprising, after constructing a live room topic from the title key,:
sending the live broadcast room topic to an auditing platform for topic auditing;
if receiving an examination passing response fed back by the examination platform, storing the topic of the live broadcast room in a topic library;
the topics stored in the topic library are used for being provided for a main broadcasting terminal to select, so that the target topic selected by the main broadcasting terminal is displayed in the corresponding live broadcasting room.
6. An apparatus for generating a live room topic, comprising:
the document acquisition module is used for acquiring published documents meeting the attention degree condition in at least one information publishing platform;
the title collecting module is used for collecting the title information of the published document into a corresponding title set by adopting a similarity matching condition; screening title keywords according to a set threshold;
the live broadcast room topic construction module is used for determining title keywords corresponding to the title set and constructing a live broadcast room topic according to the title keywords;
storing all the live broadcast room topics to a set storage area to form a topic library;
setting an instruction according to a topic of a live broadcast room sent by a main broadcast end, and obtaining an alternative topic set from a topic library and feeding back the alternative topic set to the main broadcast end;
receiving a target topic determined by the anchor terminal according to the fed back alternative topic set;
wherein the attention condition comprises at least one of:
the reading amount is greater than or equal to the reading number threshold, the comment amount is greater than or equal to the comment number threshold, and the praise amount is greater than or equal to the praise number threshold.
7. A computer device, characterized in that the computer device comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.
8. A storage medium containing computer-executable instructions for performing the method of any one of claims 1-5 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810969224.1A CN109271509B (en) | 2018-08-23 | 2018-08-23 | Live broadcast room topic generation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810969224.1A CN109271509B (en) | 2018-08-23 | 2018-08-23 | Live broadcast room topic generation method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109271509A CN109271509A (en) | 2019-01-25 |
| CN109271509B true CN109271509B (en) | 2021-05-28 |
Family
ID=65154193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810969224.1A Active CN109271509B (en) | 2018-08-23 | 2018-08-23 | Live broadcast room topic generation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109271509B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110769270B (en) * | 2019-11-08 | 2021-10-26 | 网易（杭州）网络有限公司 | Live broadcast interaction method and device, electronic equipment and storage medium |
| CN112199578B (en) * | 2020-08-28 | 2022-04-22 | 贝壳找房(北京)科技有限公司 | Information processing method and apparatus, electronic device, and storage medium |
| CN113411618B (en) * | 2020-11-26 | 2024-03-22 | 腾讯科技（深圳）有限公司 | Data processing method and device based on social application and computer storage medium |
| CN113099253A (en) * | 2021-03-30 | 2021-07-09 | 北京达佳互联信息技术有限公司 | Data generation method and device and electronic equipment |
| CN113691825A (en) * | 2021-08-20 | 2021-11-23 | 上海哔哩哔哩科技有限公司 | Service processing method and device |
| CN114125492B (en) * | 2022-01-24 | 2022-07-15 | 阿里巴巴（中国）有限公司 | Live content generation method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915447A (en) * | 2015-06-30 | 2015-09-16 | 北京奇艺世纪科技有限公司 | Method and device for tracing hot topics and confirming keywords |
| CN106503030A (en) * | 2015-09-03 | 2017-03-15 | 卡西欧计算机株式会社 | Session control, dialog control method |
| CN107276985A (en) * | 2017-05-16 | 2017-10-20 | 德基网络科技南京有限公司 | One kind is based on e-commerce platform Online Video management method |
| CN107562843A (en) * | 2017-08-25 | 2018-01-09 | 贵州耕云科技有限公司 | A kind of hot news Phrase extraction method based on title high frequency cutting |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9646057B1 (en) * | 2013-08-05 | 2017-05-09 | Hrl Laboratories, Llc | System for discovering important elements that drive an online discussion of a topic using network analysis |
| CN103617169B (en) * | 2013-10-23 | 2017-04-05 | 杭州电子科技大学 | A kind of hot microblog topic extracting method based on Hadoop |
| CN105488196B (en) * | 2015-12-07 | 2019-01-22 | 中国人民大学 | A kind of hot topic automatic mining system based on interconnection corpus |
| CN106874448B (en) * | 2017-02-10 | 2020-03-06 | 中国农业大学 | Method and device for mining earthquake subject term from microblog |
| CN107526819A (en) * | 2017-08-29 | 2017-12-29 | 江苏飞搏软件股份有限公司 | A kind of big data the analysis of public opinion method towards short text topic model |
| CN107894994A (en) * | 2017-10-18 | 2018-04-10 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus for detecting much-talked-about topic classification |
| CN108009149A (en) * | 2017-11-23 | 2018-05-08 | 东软集团股份有限公司 | A kind of keyword extracting method, extraction element, medium and electronic equipment |
-
2018
- 2018-08-23 CN CN201810969224.1A patent/CN109271509B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915447A (en) * | 2015-06-30 | 2015-09-16 | 北京奇艺世纪科技有限公司 | Method and device for tracing hot topics and confirming keywords |
| CN106503030A (en) * | 2015-09-03 | 2017-03-15 | 卡西欧计算机株式会社 | Session control, dialog control method |
| CN107276985A (en) * | 2017-05-16 | 2017-10-20 | 德基网络科技南京有限公司 | One kind is based on e-commerce platform Online Video management method |
| CN107562843A (en) * | 2017-08-25 | 2018-01-09 | 贵州耕云科技有限公司 | A kind of hot news Phrase extraction method based on title high frequency cutting |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109271509A (en) | 2019-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271509B (en) | Live broadcast room topic generation method and device, computer equipment and storage medium | |
| US10546005B2 (en) | Perspective data analysis and management | |
| CN112115299A (en) | Video searching method and device, recommendation method, electronic device and storage medium | |
| CN108197198B (en) | Interest point searching method, device, equipment and medium | |
| US20140067842A1 (en) | Information processing method and apparatus | |
| CN109275047B (en) | Video information processing method and device, electronic equipment and storage medium | |
| CN109558513B (en) | Content recommendation method, device, terminal and storage medium | |
| CN107193974B (en) | Regional information determination method and device based on artificial intelligence | |
| CN111506771B (en) | Video retrieval method, device, equipment and storage medium | |
| CN108573393B (en) | Comment information processing method and device, server and storage medium | |
| CN111428049A (en) | Method, device, equipment and storage medium for generating event topic | |
| CN108932218B (en) | Instance extension method, device, equipment and medium | |
| CN108920649B (en) | Information recommendation method, device, equipment and medium | |
| US20130125008A1 (en) | Systems And Methods For Providing Content Streams | |
| CN110737824B (en) | Content query method and device | |
| US11423219B2 (en) | Generation and population of new application document utilizing historical application documents | |
| CN112969079A (en) | Anchor resource allocation method and device, computer equipment and storage medium | |
| CN112307318B (en) | Content publishing method, system and device | |
| CN110633404A (en) | Application message pushing method and device, storage medium and terminal equipment | |
| CN110209780B (en) | Question template generation method and device, server and storage medium | |
| US10042913B2 (en) | Perspective data analysis and management | |
| CN109670080A (en) | A kind of determination method, apparatus, equipment and the storage medium of video display label | |
| CN113672758A (en) | Singing list generation method, device, medium and computing equipment | |
| CN110287338B (en) | Industry hotspot determination method, device, equipment and medium | |
| CN111556326A (en) | Public class video clip pushing method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |