CN112765336B - Barrage management method and device, terminal equipment and storage medium - Google Patents
Barrage management method and device, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN112765336B CN112765336B CN202110124655.XA CN202110124655A CN112765336B CN 112765336 B CN112765336 B CN 112765336B CN 202110124655 A CN202110124655 A CN 202110124655A CN 112765336 B CN112765336 B CN 112765336B
- Authority
- CN
- China
- Prior art keywords
- live broadcast
- information
- record
- live
- question
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 37
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000011218 segmentation Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application is applicable to the technical field of artificial intelligence, and provides a barrage management method, a barrage management device, terminal equipment and a storage medium, wherein the barrage management method comprises the following steps: generating a live broadcast record and live broadcast recommendation information according to key information in the live broadcast information, and displaying the live broadcast record and the live broadcast recommendation information in a live broadcast manner; acquiring a bullet screen questioning, and respectively carrying out association calculation on the bullet screen questioning and live broadcast record and live broadcast recommendation information to obtain an association score; and if the association score is greater than the score threshold, carrying out question reply on the barrage question by using live broadcast records or live broadcast recommendation information corresponding to the association score. According to the live broadcast prompt query method and device based on the generated live broadcast record and the live broadcast recommendation information, the live broadcast prompt query can be automatically replied, the phenomenon that a host can not reply to the live broadcast prompt query of a user when the live broadcast record and the live broadcast recommendation information are more is prevented, and the live broadcast watching experience of the user is improved. Furthermore, the present application relates to blockchain techniques.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to a barrage management method, device, terminal equipment, and storage medium.
Background
At present, due to the influence of epidemic situation, a great number of activities (such as production, creation and the like) in the scene under the line have the requirement of switching to live broadcast on the line. Because of the specificity of the online live broadcast scene, a host (host) always carries out live broadcast explanation on a screen independently, and a user watching live broadcast can only carry out communication interaction with the host through a live broadcast room barrage, so that the barrage management problem of the live broadcast room is more and more valued for guaranteeing the smoothness of live broadcast communication between the host and the user.
In the existing barrage management process, barrages are managed in a manual mode by a host, but when the barrage information is more, the host cannot respond to questions sent by users in time, and further the experience of watching live broadcast by the users is reduced.
Disclosure of Invention
In view of the above, the embodiments of the present application provide a barrage management method, device, terminal device, and storage medium, so as to solve the problem in the barrage management process in the prior art that, because barrage information is more, a host can not respond in time to a question sent by a user, resulting in low user watching live broadcast experience.
A first aspect of an embodiment of the present application provides a barrage management method, including:
acquiring live broadcast information and extracting key information in the live broadcast information;
generating a live broadcast record and live broadcast recommendation information according to the key information, and displaying the live broadcast record and the live broadcast recommendation information in a live broadcast manner, wherein at least one product to be recommended is stored in the live broadcast recommendation information;
acquiring a barrage question, and carrying out association calculation on the barrage question and the live broadcast record and the live broadcast recommendation information respectively to obtain an association score, wherein the association score is used for representing the association degree between the barrage question and the live broadcast record or the association degree between the barrage question and the live broadcast recommendation information;
and if the association score is greater than a score threshold, carrying out question reply on the live broadcast record or the live broadcast recommendation information corresponding to the association score.
Further, the extracting key information in the live broadcast information includes:
converting the text of the live broadcast information to obtain text information, wherein the text information at least comprises a text sentence,
and matching a preset keyword with the text sentence, and extracting the text sentence matched with the preset keyword to obtain the key information.
Further, the generating live broadcast record and live broadcast recommendation information according to the key information includes:
acquiring the corresponding live time of the key information in the live information, and correspondingly storing the live time and the corresponding key information to obtain the live record;
extracting live keywords in the live record, and acquiring vocabulary types of the live keywords;
and determining the data pointed by the vocabulary category as recommendation data corresponding to the live broadcast information, and setting the product pointed by the key information in the recommendation data as the product to be recommended to obtain the live broadcast recommendation information.
Further, the performing association calculation on the barrage question and the live broadcast record and the live broadcast recommendation information respectively to obtain an association score includes:
extracting semantic keywords in the barrage question, and determining the type pointed by the semantic keywords as the question type of the barrage question;
if the question type of the bullet screen question is a record query type, word segmentation is carried out on the record information in the live broadcast record to obtain record word segmentation;
calculating an association value between the semantic keyword and the record word, wherein the association value is used for representing the association degree between the semantic keyword and the record word, and summing the association values corresponding to different record word in the same record information to obtain the association score corresponding to the record information;
and if the question type of the barrage question is a product query type, querying a product category corresponding to the semantic keyword, and respectively calculating the similarity between the queried product category and the recommended product in the live broadcast recommendation information to obtain the association score.
Further, after the bullet screen question is acquired, the method further comprises:
matching a preset shielding word with the vocabulary in the barrage question;
if the preset shielding word is matched with the vocabulary in the barrage question, inquiring a live broadcasting room corresponding to the live broadcasting information, and acquiring a live broadcasting title of the live broadcasting room;
and replacing the vocabulary matched with the preset shielding word in the bullet screen question with the obtained live title.
Further, the method further comprises:
inquiring a live broadcasting room corresponding to the live broadcasting information, and acquiring the number of online people in the live broadcasting room;
if the number of online persons is smaller than the threshold number of persons, setting live broadcast records and/or bullet screen characters pointed by the live broadcast recommendation information as active bullet screens, and displaying the queried active bullet screens on the live broadcast room, wherein the active bullet screens are preset bullet screen characters.
Further, after the bullet screen question is acquired, the method further comprises:
acquiring the question asking times of the barrage questions within a preset time interval;
and if the question asking times of the bullet screen questions are larger than the times threshold, highlighting the bullet screen questions, wherein the highlighting marks are used for highlighting the bullet screen questions.
A second aspect of an embodiment of the present application provides a barrage management device, including:
the information extraction unit is used for acquiring live broadcast information and extracting key information in the live broadcast information;
the information generation unit is used for generating a live broadcast record and live broadcast recommendation information according to the key information, and displaying the live broadcast record and the live broadcast recommendation information in a live broadcast mode, wherein at least one product to be recommended is stored in the live broadcast recommendation information;
the association calculation unit is used for acquiring a bullet screen question, carrying out association calculation on the bullet screen question and the live broadcast record and the live broadcast recommendation information respectively to obtain an association score, wherein the association score is used for representing the association degree between the bullet screen question and the live broadcast record or the association degree between the bullet screen question and the live broadcast recommendation information;
and the question replying unit is used for replying the live broadcast record or the live broadcast recommendation information corresponding to the association score to the bullet screen question if the association score is larger than a score threshold.
A third aspect of the embodiments of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the terminal device, where the processor implements the steps of the barrage management method provided in the first aspect when the processor executes the computer program.
A fourth aspect of the embodiments of the present application provides a storage medium storing a computer program which, when executed by a processor, implements the steps of the barrage management method provided by the first aspect.
The bullet screen management method, the bullet screen management device, the terminal equipment and the storage medium provided by the embodiment of the application have the following beneficial effects:
according to the bullet screen management method provided by the embodiment of the application, the key information in the live broadcast information is extracted, the live broadcast record and the live broadcast recommendation information are generated according to the key information, the live broadcast content record and the inquiry of the product to be recommended can be effectively carried out in the live broadcast process, the live broadcast record and the live broadcast recommendation information are subjected to live broadcast display, the live broadcast information and the product to be recommended are conveniently checked by a user watching live broadcast, the bullet screen question is acquired, the bullet screen question is respectively associated with the live broadcast record and the live broadcast recommendation information, whether the acquired bullet screen question can be automatically replied based on the live broadcast record or the live broadcast recommendation information can be effectively judged, if the association score is larger than the score threshold value, the bullet screen question is automatically replied by the live broadcast record or the live broadcast recommendation information corresponding to the association score, the phenomenon that the user cannot be replied to the bullet screen question by a host when the bullet screen information is more is effectively prevented, and the live broadcast watching experience of the user is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of an implementation of a barrage management method according to an embodiment of the present application;
FIG. 2 is a flowchart illustrating a method for barrage management according to another embodiment of the present application;
FIG. 3 is a block diagram of a barrage management device according to an embodiment of the present application;
fig. 4 is a block diagram of a terminal device according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The barrage management method according to the embodiment of the present application may be executed by a control device or a terminal (hereinafter referred to as a "mobile terminal").
Referring to fig. 1, fig. 1 shows a flowchart of an implementation of a barrage management method according to an embodiment of the present application, including:
step S10, acquiring live broadcast information and extracting key information in the live broadcast information.
In this embodiment, a target live broadcast identifier is pre-stored, where the target live broadcast identifier is used to represent a corresponding target anchor or a target live broadcast room, and when the target live broadcast identifier represents the corresponding target anchor, the target anchor obtains live broadcast voice of the target anchor in the live broadcast room to obtain the live broadcast information;
when the target live broadcast identification characterizes the corresponding target live broadcast room, and when any anchor is in the target live broadcast room to conduct live broadcast, live broadcast voice in the target live broadcast room is obtained, and the live broadcast information is obtained.
Specifically, the key information is used for representing key content in corresponding live broadcast information, for example, the key information can be price, preferential strength or discount information of commodities in the live broadcast information, and in the step, the accuracy of the subsequent live broadcast record and live broadcast recommendation information generation is effectively improved by extracting the key information in the live broadcast information.
Specifically, in this step, the extracting key information in the live broadcast information includes:
the live broadcast information is subjected to text conversion to obtain text information, wherein the text information at least comprises a text sentence, optionally, the live broadcast information can be subjected to text conversion based on a voice recognition model to obtain the text information corresponding to the live broadcast information, so as to achieve the effect of converting live broadcast voice into live broadcast text, facilitate the extraction and display of subsequent key information,
and matching a preset keyword with the text sentence, and extracting the text sentence matched with the preset keyword to obtain the key information, wherein the preset keyword can be set according to requirements, for example, the preset keyword can be provided with words such as discount strength, preferential price or production place, and when any word in the text sentence is the same as the preset keyword, the text sentence is extracted to obtain the key information.
And step S20, generating a live broadcast record and live broadcast recommendation information according to the key information, and displaying the live broadcast record and the live broadcast recommendation information in a live broadcast mode.
At least one product to be recommended is stored in the live broadcast recommendation information, and the live broadcast content can be effectively recorded and the product to be recommended can be effectively inquired in the live broadcast process by extracting key information in the live broadcast information and generating live broadcast record and live broadcast recommendation information according to the key information.
Specifically, in this step, the generating the live broadcast record and the live broadcast recommendation information according to the key information includes:
acquiring the corresponding live time of the key information in the live information, and correspondingly storing the live time and the corresponding key information to obtain the live record, wherein the live time and the corresponding key information are correspondingly stored, so that the key information in the live information is effectively stored, and the display accuracy of the live record is improved;
extracting a live keyword in the live broadcast record, and acquiring the vocabulary category of the live keyword, wherein the live broadcast record can be subjected to semantic analysis through a semantic analysis model to obtain the live keyword, the live keyword is matched with a pre-stored category lookup table to obtain the vocabulary category corresponding to the live keyword, and the category lookup table stores the corresponding relation between different keywords and the corresponding vocabulary category;
and determining the data pointed by the vocabulary category as recommendation data corresponding to the live broadcast information, and setting the product pointed by the key information in the recommendation data as the product to be recommended to obtain the live broadcast recommendation information.
And step S30, acquiring a bullet screen question, and carrying out association calculation on the bullet screen question, the live broadcast record and the live broadcast recommendation information respectively to obtain an association score.
The association score is used for representing the association degree between the barrage question and the live broadcast record or representing the association degree between the barrage question and the live broadcast recommendation information, and in the step, the barrage question can be acquired in a random acquisition or detection mode based on preset times.
Specifically, in this step, when the acquiring of the barrage question is performed based on the mode of detecting the preset times, if the number of times of sending any barrage question in the preset time is greater than the preset times, the barrage question is acquired, where the preset time and the preset times can be set according to requirements, for example, the preset time can be set to 10 seconds, 20 seconds or 1 minute, and the preset times can be set to 10 times, 15 times or 20 times.
Optionally, in this step, after the acquiring the barrage question, the method further includes:
matching a preset shielding word with a vocabulary in the barrage question, wherein the preset shielding word can be set according to requirements, for example, the preset shielding word can be set into a vocabulary such as "purchase instead" or "borrow" and the like;
if the preset shielding word is matched with the vocabulary in the barrage question, inquiring a live broadcasting room corresponding to the live broadcasting information, and acquiring a live broadcasting title of the live broadcasting room;
and replacing the vocabulary matched with the preset shielding word in the live broadcasting title in the live broadcasting question, wherein the vocabulary matched with the preset shielding word in the live broadcasting title in the live broadcasting question is replaced, so that illegal vocabularies in the live broadcasting question are effectively prevented, and the safety of bullet screen management is improved.
And step S40, if the association score is larger than a score threshold, carrying out question reply on the live broadcast record or the live broadcast recommendation information corresponding to the association score.
The score threshold can be set according to requirements, the score threshold is used for judging whether bullet screen questions corresponding to the association score can be automatically replied based on live broadcast records or live broadcast recommendation information, if the association score between the bullet screen questions and the live broadcast records or the live broadcast recommendation information is larger than the score threshold, the bullet screen questions can be automatically replied, and further, the phenomenon that when bullet screens in a live broadcast room are too many, and live broadcast cannot timely reply to the questions, user watching experience is improved is prevented.
Specifically, in the step, answers corresponding to the barrage questions in the live broadcast records or the live broadcast recommendation information are extracted, question replies corresponding to the barrage questions are generated based on the extracted answers, and automatic answers are carried out on the barrage questions based on the generated question replies.
In the embodiment, by extracting the key information in the live broadcast information and generating the live broadcast record and the live broadcast recommended information according to the key information, the record of live broadcast content and the inquiry of the product to be recommended can be effectively carried out in the live broadcast process, live broadcast display is carried out on the live broadcast record and the live broadcast recommended information, the live broadcast information and the product to be recommended are conveniently watched by a user watching live broadcast, the live broadcast record and the live broadcast recommended information are respectively associated and calculated by acquiring a live broadcast question, whether the acquired live broadcast question can be automatically replied based on the live broadcast record or the live broadcast recommended information can be effectively judged, if the association score is larger than the score threshold value, the live broadcast record or the live broadcast recommended information corresponding to the association score is automatically replied to the live broadcast question, the phenomenon that the live broadcast question cannot be replied to the user when the live broadcast information is more is effectively prevented, and the live broadcast watching live broadcast experience is improved.
Referring to fig. 2, fig. 2 is a flowchart illustrating an implementation of a barrage management method according to another embodiment of the present application. Compared to the embodiment of fig. 1, the barrage management method provided in this embodiment is used for further refining step S30 in the embodiment of fig. 1, and includes:
and S31, extracting semantic keywords in the barrage question, and determining the type pointed by the semantic keywords as the question type of the barrage question.
The method comprises the steps that semantic analysis can be conducted on a bullet screen questioning based on a preset semantic analysis model to obtain semantic keywords in the bullet screen questioning, the semantic keywords are matched with a prestored questioning type lookup table to obtain the questioning type of the bullet screen questioning, the corresponding relation between different semantic keywords and corresponding questioning types is stored in the questioning type lookup table, and preferably, the questioning types of the bullet screen questioning comprise a record query type and a product query type.
And step S32, if the question type of the bullet screen question is a record query type, the record information in the live broadcast record is segmented to obtain record segmentation.
When the questioning type of the bullet screen questioning is a record inquiring type, the questioning requirement of the bullet screen questioning is judged to be inquiring information of the live broadcast record, and the record information in the live broadcast record is segmented, so that the calculation of the association score between the subsequent semantic keywords and the record information is effectively facilitated.
Optionally, in the step, the record word segmentation is obtained by matching the record information in the live broadcast record with a designated vocabulary, and word segmentation is performed on the record information based on a matching result, wherein a preset designated vocabulary is stored in the designated vocabulary, and when the vocabulary in the record information is matched with any designated vocabulary, the matched vocabulary in the record information is segmented to obtain the record word segmentation.
And step S33, calculating the association value between the semantic keyword and the record word, and summing the association values corresponding to different record word in the same record information to obtain the association score corresponding to the record information.
The association value is used for representing the association degree between the semantic keywords and the record segmentation words, in the step, the semantic keywords and different record segmentation words are respectively combined to obtain combined words, the combined words are matched with a pre-stored association value lookup table to obtain association values between the semantic keywords and the record segmentation words, and the association value lookup table stores corresponding relations between different combined words and corresponding association values.
And step S34, if the question type of the bullet screen question is a product query type, querying a product category corresponding to the semantic keyword, and respectively calculating the similarity between the queried product category and the recommended product in the live broadcast recommendation information to obtain the association score.
When the questioning type of the barrage questioning is a product query type, determining that the questioning requirement of the barrage questioning is to query recommended products in the live broadcast recommended information, and in the step, calculating the similarity between the queried product types and the recommended products in the live broadcast recommended information respectively through querying the product types corresponding to the semantic keywords to obtain the association score between the barrage questioning and the live broadcast recommended information.
Optionally, in this embodiment, the method further includes:
inquiring a live broadcasting room corresponding to the live broadcasting information, and acquiring the number of online people in the live broadcasting room;
the method comprises the steps of extracting live broadcast identifiers in live broadcast information, matching the live broadcast identifiers with a pre-stored live broadcast list to obtain a live broadcast room corresponding to the live broadcast information, wherein the live broadcast identifiers are used for representing corresponding anchor or live broadcast rooms, corresponding relations between different live broadcast identifiers and corresponding live broadcast rooms are stored in the live broadcast list, in the step, inquiring the number of online watching persons in the inquired live broadcast room to obtain the number of online persons, and the number of online persons is used for representing the activity degree of the corresponding live broadcast room;
if the number of the online persons is smaller than a threshold value of the number of the online persons, setting live broadcast records and/or barrage characters pointed by the live broadcast recommendation information as active barrages, and displaying the queried active barrages on the live broadcasting room;
the live barrage is preset barrage characters, the number threshold can be set according to requirements, the number threshold can be set to be 1 kilo, 1 ten thousand or 10 ten thousand, and the number threshold is used for judging whether live broadcasting room atmosphere is needed to be lively or not.
In the step, live broadcast records and/or live broadcast recommendation information are/is pointed to be the live barrage, and the live broadcast room is barraged by the queried live barrage, so that the live barrage can be effectively and automatically sent out to be active in atmosphere when the number of live broadcast watching users is small, the effects of relieving tension and enhancing explanation confidence are achieved for a host broadcast, and the attention of the live broadcast watching users to the live broadcast room is improved.
In this embodiment, a barrage database is pre-stored, and the barrage database stores corresponding relations between different live broadcast records and/or live broadcast recommendation information and corresponding barrage characters, so that the live broadcast records and/or live broadcast recommendation information corresponding to the live broadcast information are matched with the barrage database to obtain barrage characters pointed by the live broadcast records and/or live broadcast recommendation information.
Further, in this embodiment, after the bullet screen question is acquired, the method further includes:
acquiring the question asking times of the barrage questions within a preset time interval;
and if the number of questions asked by the barrage is greater than the number threshold, highlighting the barrage questions, wherein the highlighting is used for highlighting the barrage questions, and when the number of questions asked by the same barrage in a preset time interval is greater than the number threshold, judging that the barrage questions are not replied by the host, and prompting the host by highlighting the barrage questions.
In the embodiment, the accuracy of the association calculation between the barrage question and the live broadcast record and the live broadcast recommendation information is effectively improved by extracting the semantic keywords in the barrage question and determining the type pointed by the semantic keywords as the question type of the barrage question, the calculation of the association score between the subsequent semantic keywords and the record information is effectively facilitated by segmenting the record information in the live broadcast record, and the association score between the barrage question and the live broadcast recommendation information can be effectively obtained by inquiring the product category corresponding to the semantic keywords and respectively calculating the similarity between the inquired product category and the recommended product in the live broadcast recommendation information.
In all embodiments of the present application, the association score is obtained based on an association calculation between the barrage quiz and the live recording and live recommendation information, in particular, the association score is obtained by an association calculation between the barrage quiz and the live recording and live recommendation information. Uploading the association scores to the blockchain may ensure its security and fair transparency to the user. The user device may download the association score from the blockchain to verify whether the association score has been tampered with. The blockchain referred to in this example is a novel mode of application for computer technology such as distributed data storage, point-to-point transmission, consensus mechanisms, encryption algorithms, and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Referring to fig. 3, fig. 3 is a block diagram illustrating a barrage management apparatus 100 according to an embodiment of the application. The bullet screen management apparatus 100 in this embodiment includes units for performing the steps in the embodiments corresponding to fig. 1, 2, and 3. Refer specifically to fig. 1 and fig. 2, and the related descriptions in the embodiments corresponding to fig. 1 and fig. 2. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to fig. 3, the bullet screen management apparatus 100 includes: an information extraction unit 10, an information generation unit 11, an association calculation unit 12, and a question reply unit 13, wherein:
and the information extraction unit 10 is used for acquiring the live broadcast information and extracting key information in the live broadcast information.
Wherein the information extraction unit 10 is further configured to: converting the text of the live broadcast information to obtain text information, wherein the text information at least comprises a text sentence,
and matching the preset keywords with the text sentences, and extracting the text sentences matched with the preset keywords to obtain the key messages.
And the information generating unit 11 is configured to generate a live broadcast record and live broadcast recommendation information according to the key information, and perform live broadcast display on the live broadcast record and the live broadcast recommendation information, where at least one product to be recommended is stored in the live broadcast recommendation information.
Wherein the information generating unit 11 is further configured to: acquiring the corresponding live time of the key information in the live information, and correspondingly storing the live time and the corresponding key information to obtain the live record;
extracting live keywords in the live record, and acquiring vocabulary types of the live keywords;
and determining the data pointed by the vocabulary category as recommendation data corresponding to the live broadcast information, and setting the product pointed by the key information in the recommendation data as the product to be recommended to obtain the live broadcast recommendation information.
And the association calculation unit 12 is used for acquiring a bullet screen question, and performing association calculation on the bullet screen question and the live broadcast record and the live broadcast recommendation information respectively to obtain an association score, wherein the association score is used for representing the association degree between the bullet screen question and the live broadcast record or the association degree between the bullet screen question and the live broadcast recommendation information.
Wherein the association calculation unit 12 is further configured to: extracting semantic keywords in the barrage question, and determining the type pointed by the semantic keywords as the question type of the barrage question;
if the question type of the bullet screen question is a record query type, word segmentation is carried out on the record information in the live broadcast record to obtain record word segmentation;
calculating an association value between the semantic keyword and the record word, wherein the association value is used for representing the association degree between the semantic keyword and the record word, and summing the association values corresponding to different record word in the same record information to obtain the association score corresponding to the record information;
and if the question type of the barrage question is a product query type, querying a product category corresponding to the semantic keyword, and respectively calculating the similarity between the queried product category and the recommended product in the live broadcast recommendation information to obtain the association score.
Optionally, the association calculation unit 12 is further configured to: matching a preset shielding word with the vocabulary in the barrage question;
if the preset shielding word is matched with the vocabulary in the barrage question, inquiring a live broadcasting room corresponding to the live broadcasting information, and acquiring a live broadcasting title of the live broadcasting room;
and replacing the vocabulary matched with the preset shielding word in the bullet screen question with the obtained live title.
Further, the association calculating unit 12 is further configured to: acquiring the question asking times of the barrage questions within a preset time interval;
and if the question asking times of the bullet screen questions are larger than the times threshold, highlighting the bullet screen questions, wherein the highlighting marks are used for highlighting the bullet screen questions.
And the question replying unit 13 is configured to reply a question to the barrage question by using the live broadcast record or the live broadcast recommendation information corresponding to the association score if the association score is greater than a score threshold.
Preferably, in this embodiment, the barrage management device 100 further includes:
the barrage active unit 14 is used for inquiring the live broadcasting room corresponding to the live broadcasting information and acquiring the number of online people in the live broadcasting room;
if the number of online persons is smaller than the threshold number of persons, setting live broadcast records and/or bullet screen characters pointed by the live broadcast recommendation information as active bullet screens, and displaying the queried active bullet screens on the live broadcast room, wherein the active bullet screens are preset bullet screen characters.
In the embodiment, by extracting the key information in the live broadcast information and generating the live broadcast record and the live broadcast recommended information according to the key information, the record of live broadcast content and the inquiry of the product to be recommended can be effectively carried out in the live broadcast process, live broadcast display is carried out on the live broadcast record and the live broadcast recommended information, the live broadcast information and the product to be recommended are conveniently watched by a user watching live broadcast, the live broadcast record and the live broadcast recommended information are respectively associated and calculated by acquiring a live broadcast question, whether the acquired live broadcast question can be automatically replied based on the live broadcast record or the live broadcast recommended information can be effectively judged, if the association score is larger than the score threshold value, the live broadcast record or the live broadcast recommended information corresponding to the association score is automatically replied to the live broadcast question, the phenomenon that the live broadcast question cannot be replied to the user when the live broadcast information is more is effectively prevented, and the live broadcast watching live broadcast experience is improved.
Fig. 4 is a block diagram of a terminal device 2 according to another embodiment of the present application. As shown in fig. 4, the terminal device 2 of this embodiment includes: a processor 20, a memory 21 and a computer program 22, such as a program of a barrage management method, stored in the memory 21 and executable on the processor 20. The steps of the embodiments of the bullet screen management method described above, such as S10 to S40 shown in fig. 1 or S31 to S34 shown in fig. 2, are implemented by the processor 20 when executing the computer program 23. Alternatively, the processor 20 may implement the functions of each unit in the embodiment corresponding to fig. 3, for example, the functions of the units 10 to 14 shown in fig. 3, when executing the computer program 22, and the detailed description of the embodiment corresponding to fig. 4 will be referred to herein, which is omitted.
Illustratively, the computer program 22 may be partitioned into one or more units that are stored in the memory 21 and executed by the processor 20 to complete the present application. The one or more units may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program 22 in the terminal device 2. For example, the computer program 22 may be divided into an information extraction unit 10, an information generation unit 11, an association calculation unit 12, a question reply unit 13, and a barrage activity unit 14, each unit functioning specifically as described above.
The terminal device may include, but is not limited to, a processor 20, a memory 21. It will be appreciated by those skilled in the art that fig. 4 is merely an example of the terminal device 2 and does not constitute a limitation of the terminal device 2, and may include more or less components than illustrated, or may combine certain components, or different components, e.g., the terminal device may further include an input-output device, a network access device, a bus, etc.
The processor 20 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 21 may be an internal storage unit of the terminal device 2, such as a hard disk or a memory of the terminal device 2. The memory 21 may be an external storage device of the terminal device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal device 2. Further, the memory 21 may also include both an internal storage unit and an external storage device of the terminal device 2. The memory 21 is used for storing the computer program as well as other programs and data required by the terminal device. The memory 21 may also be used for temporarily storing data that has been output or is to be output.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (8)
1. A method of barrage management comprising:
acquiring live broadcast information and extracting key information in the live broadcast information;
generating a live broadcast record and live broadcast recommendation information according to the key information, and displaying the live broadcast record and the live broadcast recommendation information in a live broadcast manner, wherein at least one product to be recommended is stored in the live broadcast recommendation information;
acquiring a barrage question, and carrying out association calculation on the barrage question and the live broadcast record and the live broadcast recommendation information respectively to obtain an association score, wherein the association score is used for representing the association degree between the barrage question and the live broadcast record or the association degree between the barrage question and the live broadcast recommendation information;
if the association score is greater than a score threshold, carrying out question reply on the live broadcast record or the live broadcast recommendation information corresponding to the association score;
the generating live broadcast record and live broadcast recommendation information according to the key information comprises the following steps:
acquiring the corresponding live time of the key information in the live information, and correspondingly storing the live time and the corresponding key information to obtain the live record;
extracting live keywords in the live record, and acquiring vocabulary types of the live keywords;
determining the data pointed by the vocabulary category as recommendation data corresponding to the live broadcast information, and setting the product pointed by the key information in the recommendation data as the product to be recommended to obtain the live broadcast recommendation information;
the step of performing association calculation on the bullet screen questioning and the live broadcast record and the live broadcast recommendation information respectively to obtain an association score comprises the following steps:
extracting semantic keywords in the barrage question, and determining the type pointed by the semantic keywords as the question type of the barrage question;
if the question type of the bullet screen question is a record query type, word segmentation is carried out on the record information in the live broadcast record to obtain record word segmentation;
calculating an association value between the semantic keyword and the record word, wherein the association value is used for representing the association degree between the semantic keyword and the record word, and summing the association values corresponding to different record word in the same record information to obtain the association score corresponding to the record information;
and if the question type of the barrage question is a product query type, querying a product category corresponding to the semantic keyword, and respectively calculating the similarity between the queried product category and the recommended product in the live broadcast recommendation information to obtain the association score.
2. The barrage management method of claim 1, wherein the extracting key information in the live information comprises:
converting the text of the live broadcast information to obtain text information, wherein the text information at least comprises a text sentence,
and matching a preset keyword with the text sentence, and extracting the text sentence matched with the preset keyword to obtain the key information.
3. The barrage management method of claim 1, further comprising, after the obtaining the barrage question:
matching a preset shielding word with the vocabulary in the barrage question;
if the preset shielding word is matched with the vocabulary in the barrage question, inquiring a live broadcasting room corresponding to the live broadcasting information, and acquiring a live broadcasting title of the live broadcasting room;
and replacing the vocabulary matched with the preset shielding word in the bullet screen question with the obtained live title.
4. The barrage management method of claim 1, further comprising:
inquiring a live broadcasting room corresponding to the live broadcasting information, and acquiring the number of online people in the live broadcasting room;
if the number of online persons is smaller than the threshold number of persons, setting live broadcast records and/or bullet screen characters pointed by the live broadcast recommendation information as active bullet screens, and displaying the queried active bullet screens on the live broadcast room, wherein the active bullet screens are preset bullet screen characters.
5. The barrage management method of claim 1, further comprising, after the obtaining the barrage question:
acquiring the question asking times of the barrage questions within a preset time interval;
and if the question asking times of the bullet screen questions are larger than the times threshold, highlighting the bullet screen questions, wherein the highlighting marks are used for highlighting the bullet screen questions.
6. A bullet screen management apparatus comprising:
the information extraction unit is used for acquiring live broadcast information and extracting key information in the live broadcast information;
the information generation unit is used for generating a live broadcast record and live broadcast recommendation information according to the key information, and displaying the live broadcast record and the live broadcast recommendation information in a live broadcast mode, wherein at least one product to be recommended is stored in the live broadcast recommendation information;
the association calculation unit is used for acquiring a bullet screen question, carrying out association calculation on the bullet screen question and the live broadcast record and the live broadcast recommendation information respectively to obtain an association score, wherein the association score is used for representing the association degree between the bullet screen question and the live broadcast record or the association degree between the bullet screen question and the live broadcast recommendation information;
the questioning and replying unit is used for replying the live broadcast record or the live broadcast recommendation information corresponding to the association score to the barrage questioning if the association score is larger than a score threshold;
wherein, the information generating unit is specifically configured to: acquiring the corresponding live time of the key information in the live information, and correspondingly storing the live time and the corresponding key information to obtain the live record;
extracting live keywords in the live record, and acquiring vocabulary types of the live keywords;
determining the data pointed by the vocabulary category as recommendation data corresponding to the live broadcast information, and setting the product pointed by the key information in the recommendation data as the product to be recommended to obtain the live broadcast recommendation information;
the association calculation unit is specifically configured to: extracting semantic keywords in the barrage question, and determining the type pointed by the semantic keywords as the question type of the barrage question;
if the question type of the bullet screen question is a record query type, word segmentation is carried out on the record information in the live broadcast record to obtain record word segmentation;
calculating an association value between the semantic keyword and the record word, wherein the association value is used for representing the association degree between the semantic keyword and the record word, and summing the association values corresponding to different record word in the same record information to obtain the association score corresponding to the record information;
and if the question type of the barrage question is a product query type, querying a product category corresponding to the semantic keyword, and respectively calculating the similarity between the queried product category and the recommended product in the live broadcast recommendation information to obtain the association score.
7. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 5 when the computer program is executed.
8. A storage medium storing a computer program which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110124655.XA CN112765336B (en) | 2021-01-29 | 2021-01-29 | Barrage management method and device, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110124655.XA CN112765336B (en) | 2021-01-29 | 2021-01-29 | Barrage management method and device, terminal equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112765336A CN112765336A (en) | 2021-05-07 |
| CN112765336B true CN112765336B (en) | 2023-12-05 |
Family
ID=75707488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110124655.XA Active CN112765336B (en) | 2021-01-29 | 2021-01-29 | Barrage management method and device, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112765336B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113301376B (en) * | 2021-05-24 | 2023-04-07 | 成都威爱新经济技术研究院有限公司 | Live broadcast interaction method and system based on virtual reality technology |
| CN113641937B (en) * | 2021-08-17 | 2023-06-30 | 杭州时趣信息技术有限公司 | Comment automatic reply method, comment automatic reply system and storage medium |
| CN114390306A (en) * | 2021-12-27 | 2022-04-22 | 中国电信股份有限公司 | Live broadcast interactive abstract generation method and device |
| CN114363650B (en) * | 2021-12-31 | 2024-02-06 | 广州方硅信息技术有限公司 | Live broadcast room public screen text display method, electronic equipment and storage medium |
| CN115065833A (en) * | 2022-05-12 | 2022-09-16 | 广州方硅信息技术有限公司 | Live broadcast room comment display method, server, electronic terminal and storage medium |
| CN115334362B (en) * | 2022-07-16 | 2023-09-26 | 珠海格力电器股份有限公司 | Barrage problem processing method, barrage problem processing device, barrage problem storage medium, barrage problem service equipment and barrage problem service system |
| CN115170372B (en) * | 2022-09-06 | 2022-12-09 | 江西兴智教育科技有限公司 | Interactive education platform system and method based on Internet |
| CN116582694B (en) * | 2023-06-14 | 2023-10-31 | 杭州蚊子会数字营销有限公司 | Live broadcast data processing method based on character recognition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011053992A (en) * | 2009-09-02 | 2011-03-17 | Nippon Telegr & Teleph Corp <Ntt> | Question recommending device, method and program |
| CN105435453A (en) * | 2015-12-22 | 2016-03-30 | 网易（杭州）网络有限公司 | Bullet screen information processing method, device and system |
| WO2019174428A1 (en) * | 2018-03-15 | 2019-09-19 | 腾讯科技（深圳）有限公司 | Method and device for obtaining reply information |
| CN111680133A (en) * | 2019-03-11 | 2020-09-18 | 阿里巴巴集团控股有限公司 | Live broadcast question and answer method and device |
| CN111695974A (en) * | 2020-06-18 | 2020-09-22 | 上海适享文化传播有限公司 | Method for using retail knowledge database at any time and any place in live broadcast |
-
2021
- 2021-01-29 CN CN202110124655.XA patent/CN112765336B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011053992A (en) * | 2009-09-02 | 2011-03-17 | Nippon Telegr & Teleph Corp <Ntt> | Question recommending device, method and program |
| CN105435453A (en) * | 2015-12-22 | 2016-03-30 | 网易（杭州）网络有限公司 | Bullet screen information processing method, device and system |
| WO2019174428A1 (en) * | 2018-03-15 | 2019-09-19 | 腾讯科技（深圳）有限公司 | Method and device for obtaining reply information |
| CN111680133A (en) * | 2019-03-11 | 2020-09-18 | 阿里巴巴集团控股有限公司 | Live broadcast question and answer method and device |
| CN111695974A (en) * | 2020-06-18 | 2020-09-22 | 上海适享文化传播有限公司 | Method for using retail knowledge database at any time and any place in live broadcast |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112765336A (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112765336B (en) | Barrage management method and device, terminal equipment and storage medium | |
| CN107393541B (en) | Information verification method and device | |
| US20160162794A1 (en) | Decision tree data structures generated to determine metrics for child nodes | |
| US20140257995A1 (en) | Method, device, and system for playing video advertisement | |
| CN108810642B (en) | Bullet screen display method and device and electronic equipment | |
| CN109460503B (en) | Answer input method, answer input device, storage medium and electronic equipment | |
| US20210193187A1 (en) | Apparatus for video searching using multi-modal criteria and method thereof | |
| CN110895568B (en) | Method and system for processing court trial records | |
| CN111860377A (en) | Live broadcast method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN111599359A (en) | Man-machine interaction method, server, client and storage medium | |
| CN110569502A (en) | Method and device for identifying forbidden slogans, computer equipment and storage medium | |
| CN111128233B (en) | Recording detection method and device, electronic equipment and storage medium | |
| CN110858353A (en) | Method and system for obtaining case referee result | |
| CN113873088B (en) | Interactive method and device for voice call, computer equipment and storage medium | |
| Rossi et al. | Are Deep Learning-Generated Social Media Profiles Indistinguishable from Real Profiles? | |
| CN112434144A (en) | Method, device, electronic equipment and computer readable medium for generating target problem | |
| CN117114475A (en) | Comprehensive capability assessment system based on multidimensional talent assessment strategy | |
| CN117370512A (en) | Method, device, equipment and storage medium for replying to dialogue | |
| CN114363650B (en) | Live broadcast room public screen text display method, electronic equipment and storage medium | |
| CN112949305A (en) | Negative feedback information acquisition method, device, equipment and storage medium | |
| CN114186048A (en) | Question-answer replying method and device based on artificial intelligence, computer equipment and medium | |
| Lopresti et al. | Adapting the turing test for declaring document analysis problems solved | |
| CN114390306A (en) | Live broadcast interactive abstract generation method and device | |
| CN113868401A (en) | Digital human interaction method and device, electronic equipment and computer storage medium | |
| CN114095738A (en) | Video and live broadcast processing method, live broadcast system, electronic device, terminal and 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 |