Live broadcast room information distribution method and device, electronic equipment and storage medium

Abstract

The invention provides a live broadcast room information distribution method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the fields of NLP, big data, intelligent search, intelligent e-commerce and the like. According to the specific implementation scheme, in response to received query information, candidate live broadcast content text information matched with the query information is determined from multiple pieces of live broadcast content text information, and the live broadcast content text information is associated with a live broadcast link of a corresponding live broadcast room; according to a candidate live broadcast link associated with the candidate live broadcast content text information, candidate live broadcast room information is distributed, and the candidate live broadcast room information represents information of a broadcast live broadcast room obtained based on the candidate live broadcast link.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the fields of NLP (Natural Language Processing), big data, intelligent search, intelligent e-commerce, and specifically to a method, device, electronic device and storage medium for distributing information in a live broadcast room. Background Art

[0002] As one of the emerging forms of information transmission, the live broadcast room has many characteristics that traditional media do not have. The most notable one is its immediacy, which allows users and anchors to share information and experience at the same time. In addition, the interactivity of the live broadcast room is also an important feature. Users can communicate and interact with anchors or other users in real time through bullet screens, comments or praise. This sense of participation and interactivity enhances the user's viewing experience. Summary of the invention

[0003] The present invention provides a method, device, electronic device and storage medium for distributing live broadcast room information.

[0004] According to one aspect of the present disclosure, a live content distribution method is provided, comprising: in response to receiving query information, determining candidate live content text information matching the query information from multiple live content text information, the live content text information being associated with a live link corresponding to an already-launched live broadcast room; and distributing candidate live broadcast room information according to the candidate live broadcast link associated with the candidate live content text information, the candidate live broadcast room information representing information of the already-launched live broadcast room obtained based on the candidate live broadcast link.

[0005] According to another aspect of the present disclosure, a live broadcast room information distribution device is provided, including: a candidate live broadcast content text information determination module, which is used to determine, in response to receiving query information, candidate live broadcast content text information matching the query information from multiple live broadcast content text information, the live broadcast content text information is associated with the live broadcast link of the corresponding live broadcast room that has been launched; and a live broadcast room information distribution module, which is used to distribute candidate live broadcast room information according to the candidate live broadcast link associated with the candidate live broadcast content text information, the candidate live broadcast room information representing information of the live broadcast room that has been launched based on the candidate live broadcast link.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the live content distribution method of the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the live content distribution method of the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program is stored on at least one of a readable storage medium and an electronic device, and when the computer program is executed by a processor, the live content distribution method of the present disclosure is implemented.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 An exemplary system architecture to which the method and device for distributing live broadcast room information according to an embodiment of the present disclosure can be applied is schematically shown;

[0012] Figure 2 A flowchart of a method for distributing live broadcast room information according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 3 A schematic diagram of generating QC information according to an embodiment of the present disclosure is schematically shown;

[0014] Figure 4 A schematic diagram of generating a QC page according to an embodiment of the present disclosure is schematically shown;

[0015] Figure 5 A schematic diagram of building an information database based on a QC page according to an embodiment of the present disclosure is schematically shown;

[0016] Figure 6 A schematic diagram of implementing real-time question and answer according to an embodiment of the present disclosure is schematically shown;

[0017] Figure 7 A schematic diagram of a product form for implementing real-time question and answer in a live broadcast room according to an embodiment of the present disclosure is shown;

[0018] Figure 8 The overall flow chart of the live broadcast room information distribution method according to the embodiment of the present disclosure is schematically shown;

[0019] Fig. 9 A block diagram schematically shows a live broadcast room information distribution device according to an embodiment of the present disclosure; and

[0020] Fig.10 A schematic block diagram of an electronic device that can be used to implement an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0022] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0023] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0024] Since the content of the live broadcast room is constantly changing, new information may be generated at any moment, making the real-time update of the content extremely critical. During the distribution process, the live broadcast room faces a challenge: it is difficult to meet the user's demand for real-time search. When users are looking for specific information, they may find that it is difficult to quickly meet their needs due to the immediacy and unstructured characteristics of the live broadcast content. This not only makes it impossible to maximize the value of the content, but also makes it difficult to achieve large-scale and accurate distribution of live broadcast rooms.

[0025] In the process of distributing relevant live broadcast rooms, the information is mainly based on the title of the live broadcast room and the information of the anchor, and the information is generalized to a certain extent. When users search, the generalized information is associated with the live broadcast room address, thereby guiding users to enter the live broadcast room to meet their retrieval needs.

[0026] In the process of implementing the concept of the present disclosure, the inventors discovered that during the distribution of related live broadcast rooms, the user's search needs may not be strongly related to the content of the live broadcast room.

[0027] The present disclosure provides a method, device, electronic device and storage medium for distributing live broadcast room information, including: in response to receiving query information, determining candidate live broadcast content text information matching the query information from multiple live broadcast content text information, the live broadcast content text information is associated with the live broadcast link of the corresponding live broadcast room that has been launched; distributing the candidate live broadcast room information according to the candidate live broadcast link associated with the candidate live broadcast content text information, the candidate live broadcast room information represents the information of the live broadcast room that has been launched based on the candidate live broadcast link.

[0028] Figure 1 An exemplary system architecture to which the method and apparatus for distributing live broadcast room information according to an embodiment of the present disclosure can be applied is schematically illustrated.

[0029] It should be noted that Figure 1 The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, an exemplary system architecture to which the live broadcast room information distribution method and apparatus can be applied may include a terminal device, but the terminal device may implement the live broadcast room information distribution method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0030] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0031] The user may use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only as examples).

[0032] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0033] The server 105 may be a server that provides various services, such as a background management server that provides support for the content browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (for example only). The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0034] It should be noted that the live broadcast room information distribution method provided in the embodiment of the present disclosure can generally be executed by the first terminal device 101, the second terminal device 102 or the third terminal device 103. Correspondingly, the live broadcast room information distribution device provided in the embodiment of the present disclosure can also be set in the first terminal device 101, the second terminal device 102 or the third terminal device 103.

[0035] Alternatively, the live broadcast room information distribution method provided in the embodiment of the present disclosure may also be generally executed by the server 105. Accordingly, the live broadcast room information distribution device provided in the embodiment of the present disclosure may generally be set in the server 105. The live broadcast room information distribution method provided in the embodiment of the present disclosure may also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the live broadcast room information distribution device provided in the embodiment of the present disclosure may also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0036] For example, when a user reads an e-book online, the first terminal device 101, the second terminal device 102, and the third terminal device 103 can obtain the target content in the e-book pointed by the user's sight, and then send the obtained target content to the server 105, and the server 105 analyzes the target content to determine the characteristic information of the target content; predicts the content that the user is interested in based on the characteristic information of the target content; and extracts the content that the user is interested in. Alternatively, a server or server cluster that can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105 analyzes the target content and finally extracts the content that the user is interested in.

[0037] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0038] Figure 2 The flowchart of the live broadcast room information distribution method according to the embodiment of the present disclosure is schematically shown.

[0039] like Figure 2 As shown, the method includes operations S210 to S220.

[0040] In operation S210, in response to receiving the query information, candidate live content text information matching the query information is determined from a plurality of live content text information, and the live content text information is associated with a live link of a corresponding live broadcast room that has been launched.

[0041] According to an embodiment of the present disclosure, query information may represent the content entered by the user in the search box of the live broadcast software, and may be used to retrieve information about the live broadcast room that the user is interested in. Live broadcast content text information may represent textual description information of live broadcast content related to the live broadcast room that has been launched. For each live broadcast room that has been launched, one or more textual description information may be analyzed to form the live broadcast content text information of the live broadcast room that has been launched. The live broadcast content text information may be mounted on the live broadcast link corresponding to the live broadcast room that has been launched, so as to establish an association relationship between the live broadcast content text information and the live broadcast link corresponding to the live broadcast room that has been launched.

[0042] In operation S220, candidate live broadcast room information is distributed according to the candidate live broadcast link associated with the candidate live broadcast content text information, and the candidate live broadcast room information represents information of the live broadcast room that has been launched based on the candidate live broadcast link.

[0043] According to the embodiments of the present disclosure, based on the established association between the live content text information and the live link corresponding to the live broadcast room, the candidate live link can be located according to the obtained candidate live content text information. By distributing the live broadcast room information corresponding to the candidate live broadcast link, the distributed live broadcast rooms can all be live broadcast rooms that match the query information.

[0044] Through the above-mentioned embodiments of the present disclosure, by associating the live broadcast content text information with the live broadcast link of the corresponding live broadcast room that has been launched, the candidate live broadcast room information that matches the query information can be located more accurately by matching the query information with the live broadcast content text information, thereby effectively improving the correlation between the user's search needs and the retrieved candidate live broadcast rooms, thereby improving the accuracy of the distribution of the live broadcast room information, and the distributed candidate live broadcast room information can better meet the interests of users.

[0045] In conjunction with specific embodiments, Figure 2 The method shown is further explained.

[0046] According to an embodiment of the present disclosure, the above operation S220 may include: reading candidate live broadcast room information according to the candidate live broadcast link, sending the candidate live broadcast room information to a front-end page for display, wherein the candidate live broadcast content text information is hidden on the front-end page.

[0047] According to an embodiment of the present disclosure, the live content text information may be used only to provide search conditions for query information, and may not be displayed as a search result.

[0048] For example, when a user enters query information in the search box of the live broadcast software, after matching it with multiple live content text information on the back end, only the matched candidate live broadcast room information can be displayed on the front end page, without displaying the matched candidate live content text information.

[0049] It should be noted that, according to actual business needs, the candidate live content text information can also be displayed on the front-end page together with the corresponding candidate live room information, which is not limited here.

[0050] Through the above-mentioned embodiments of the present disclosure, on the basis of retrieving candidate live broadcast room information of interest to the user based on the live broadcast content text information, the candidate live broadcast room information can be displayed intuitively and concisely on the front-end page, so that the search content that is strongly related to the query information can be guided to the live broadcast room for answers.

[0051] In the process of implementing the concept disclosed in the present invention, the inventors also found that the amount of information used for distribution during the distribution of related live broadcast rooms is small, the traffic that can be associated is small, and the cost of updating the live broadcast room title based on manual updates is high.

[0052] According to an embodiment of the present disclosure, before at least the above operation S210, the live content text information of each live broadcast room that has been launched can be first generated. The method may include: in response to receiving a broadcast signal of a live broadcast room to be launched, obtaining the anchor information, live broadcast script information, and historical live broadcast information related to the anchor information of the live broadcast room to be launched. Based on the anchor information, live broadcast script information, and historical live broadcast information, the live content text information of the live broadcast room to be launched is generated.

[0053] According to the embodiments of the present disclosure, at the beginning of each live broadcast room that has already started broadcasting, the live broadcast system can first detect the broadcast signal of the live broadcast room to be broadcasted, indicating that a certain live broadcast room is about to start broadcasting. After the live broadcast room to be broadcasted starts broadcasting, it is the live broadcast room that has started broadcasting. The anchor information can represent the image, attributes, type and other information of the anchor in the live broadcast room to be broadcasted, and is not limited to this. The historical live broadcast information can represent the information of the corresponding anchor's historical live broadcasts and the interaction information with the users who watched the live broadcast during the historical live broadcast process, and is not limited to this. The live broadcast script information can represent the script of speech based on which the content of this live broadcast is based.

[0054] For example, after obtaining the anchor information, live broadcast script information and historical live broadcast information, the anchor information, live broadcast script information and historical live broadcast information can be combined to obtain the live broadcast content text information.

[0055] It should be noted that users are aware of and agree to the acquisition and use of anchor information, live broadcast script information and historical live broadcast information, and they all comply with relevant laws and regulations and do not violate good practices.

[0056] Through the above embodiments of the present disclosure, by combining the anchor information, live broadcast script information and historical live broadcast information to construct live broadcast content text information, it is beneficial to obtain more complete search information for each live broadcast room to be broadcasted, construct more information for distribution, and improve the accuracy of subsequent search results. In addition, the above method of reading relevant information to construct live broadcast content text information can effectively reduce the update cost compared to the manual operation update method.

[0057] According to an embodiment of the present disclosure, generating the live content text information of the live broadcast room to be broadcasted based on the anchor information, the live broadcast script information and the historical live broadcast information may include: extracting question information based on at least one of the historical live broadcast information and the live broadcast script information. Based on the question information, performing a first natural language processing on the historical live broadcast information to generate live content text information related to the question information.

[0058] According to an embodiment of the present disclosure, question information can represent user-related question information involved in the live broadcast process of the anchor. For example, when a historical user inputs historical query information into the search box, obtains historical live broadcasts through queries, and enters historical live broadcasts, question information can be obtained based on the historical live broadcast information by extracting historical query questions carried by historical users when entering historical live broadcasts. Question information can also represent information related to the anchor's live broadcast content. For example, question information can be converted based on the content said by the anchor in the historical live broadcast. Question information can also be extracted based on the live broadcast script information of the live broadcast room to be broadcasted, etc. The method for extracting question information may not be limited to this.

[0059] According to an embodiment of the present disclosure, the first natural language processing is used to extract content information strongly related to the question information from the historical live broadcast information based on the question information. The first natural language processing can be performed using the first large language model. For example, the historical live broadcast information can be used as the prompt (prompt information) of the first large language model, and the question information (query) can be used as the input of the first large language model. After being processed by the first large language model, live content text information (content) strongly related to the query is generated.

[0060] According to the embodiment of the present disclosure, after the above processing, QC information for retrieval can be generated according to the question information (query) and the live content text information (content).

[0061] Figure 3 The schematic diagram of generating QC information according to an embodiment of the present disclosure is schematically shown.

[0062] like Figure 3 As shown, when any live broadcast room starts broadcasting, the broadcasting information 310 of the corresponding live broadcast room can be obtained first. The broadcasting information 310 may include live broadcast script information 311, anchor information 312, historical live broadcast information 313, etc., but is not limited thereto. Then, the live broadcast script information 311, anchor information 312, historical live broadcast information 313, etc. can be input into the first large language model 320 for first natural language processing, and the first QC information 330 can be obtained.

[0063] Through the above-mentioned embodiments of the present disclosure, combined with natural language processing, the generated live content text information can be made more concise and natural, which is conducive to improving retrieval efficiency.

[0064] According to the embodiments of the present disclosure, the live content text information may be in hypertext markup language, or in other formats, such as .txt, .doc, etc., which are not limited here.

[0065] According to an embodiment of the present disclosure, when the live content text information is in hypertext markup language, the method for generating the live content text information of each live broadcast room that has been broadcast may also include: extracting title information and summary information from the live content text information. Based on the title information, summary information and live content text information, a hypertext markup language page of the live content text information is constructed.

[0066] According to an embodiment of the present disclosure, after obtaining the live content text information (content), the content can be first extracted into titles and summaries. Then, the extracted titles and summaries can be rearranged according to HTML (Hypertext Markup Language) tags. For example, the title information is written under the title tag, the summary information is written under the article1 tag, the live content text information is written under the article2 tag, etc., to generate a hypertext markup language page, also known as a QC page. Through this method, the content machine-related content corresponding to each query can be combined into a QC page.

[0067] Figure 4 A schematic diagram of generating a QC page according to an embodiment of the present disclosure is schematically shown.

[0068] like Figure 4 As shown, after obtaining the second QC information 410, the second QC information 410 can be input into the third language model 420 to obtain title information 421, summary information 422, content information 423, etc. Then, the title information 421, summary information 422, content information 423, etc. can be combined with the HTML structure to construct a QC page 430.

[0069] It should be noted that the third largest language model and the first largest language model may be the same large language model or different large language models, which is not limited here.

[0070] Through the above-mentioned embodiments of the present disclosure, since a hypertext markup language page is constructed based on information such as a title and a summary, the text information of the live content can be further simplified, which helps to further improve the retrieval efficiency.

[0071] Based on the above method, a QC page can be generated in response to receiving a start signal. Multiple QC pages can be produced for different queries. For each QC page, it can be mounted on the live link of the corresponding live broadcast room, so as to establish an association between the live content text information and the live link of the corresponding live broadcast room. The multiple QC pages can be stored in a retrieval database for retrieval when the user enters query information in the search box.

[0072] According to an embodiment of the present disclosure, in response to receiving a shutdown signal of a live broadcast room that has been broadcast, the delivered live content text information is deleted from the search database. The delivered live content text information represents the live content text information determined based on the live broadcast room that has been broadcast.

[0073] Figure 5 A schematic diagram of building an information database based on a QC page according to an embodiment of the present disclosure is schematically shown.

[0074] like Figure 5 As shown, when a start signal 510 is detected, the QC pages generated by the live broadcast room that generates the start signal can be searched and stored in the search database 520 for retrieval by the page search system 530. When a stop signal 540 is detected, all QC pages stored in the search database 520 can be searched, and the QC pages related to the live broadcast room that generates the stop signal can be deleted.

[0075] Through the above-mentioned embodiments of the present disclosure, the search information in the search database can be dynamically updated according to the switch status of the live broadcast room, useless information can be deleted, and the search accuracy can be guaranteed.

[0076] In the process of implementing the concept disclosed in the present invention, the inventors also found that the delay after the distribution of the relevant live broadcast room is high, and users need to ask questions again and wait for the host to reply, but the high delay will cause users to leave the live broadcast room before waiting for a reply.

[0077] According to an embodiment of the present disclosure, the above-mentioned live broadcast room information distribution method may further include: in response to determining that the target object has entered the target live broadcast room, performing a second natural language processing on at least one of the target live broadcast content text information and the object identification information of the target object used to determine the target live broadcast room and the query information to obtain the anchor answer style information, the target live broadcast room representing any candidate live broadcast room that has been distributed. Send the anchor answer style information to the anchor of the target live broadcast room.

[0078] According to an embodiment of the present disclosure, the object identification information may represent the nickname information used by the target object when entering the target live broadcast room. The anchor's answer style information may represent the reply information generated by the anchor in the target live broadcast room for the target object entering the target live broadcast room. The reply information may include a first type of reply that represents making the target object wait or a second type of reply that directly answers the query questions of the target object. For example, a first type of reply may be expressed as: Welcome XX to the live broadcast room, currently answering YY's questions, and your questions will be answered later. A second type of reply may be expressed as: The calculation method of AAAA will be explained soon: BBBB...

[0079] According to an embodiment of the present disclosure, the second natural language processing is used to combine the object identification information and the query information to generate a type of reply speech. The second natural language processing can also be used to combine the target live content text information and the query information to generate a second type of reply speech. The second natural language processing can be performed using the second largest language model. For example, after the target object enters the live broadcast room, the query information of the target object can be brought in through the target link bound to the target QC page information used when retrieving the target live broadcast room, and the query information of the target object and the target QC page information can be combined into the aforementioned first type of reply speech or second type of reply speech using the second largest language model. The corresponding reply speech is then sent to the anchor of the target live broadcast room, and the anchor can answer the query information of the target object according to the speech.

[0080] It should be noted that the acquisition and use of nickname information are known and agreed by the target object, and are in compliance with relevant laws and regulations and do not violate process ethics. The target QC page information can be recorded for subsequent multiple rounds of questions and answers.

[0081] Through the above-mentioned embodiments of the present disclosure, the anchor can promptly pay attention to the target objects entering the target live broadcast room, thereby reducing the loss rate of the target objects.

[0082] According to an embodiment of the present disclosure, in response to determining that the target object has entered the target live broadcast room, the target live broadcast content text information is displayed in the live broadcast window of the target live broadcast room.

[0083] According to an embodiment of the present disclosure, when a target object enters a target live broadcast room and the host uses a type of reply speech to broadcast live, the target live broadcast content text information can be displayed in the live broadcast window of the target live broadcast room.

[0084] Figure 6 A schematic diagram of implementing real-time question and answer according to an embodiment of the present disclosure is schematically shown.

[0085] like Figure 6 As shown, after the user enters query information 610 in the search box and clicks search, the page retrieval system can retrieve the target QC page information 630 matching the query information 610 from the retrieval database 620 storing the QC page information. The target QC page information 630 may include target title information 631, target summary information 632, target content information 633, etc. Afterwards, the query information 610 and the target title information 631, target summary information 632, target content information 633, etc. can be input into the second language model 640, and the second natural language processing is performed by the second language model 640 to obtain a text answer 641 or a spoken answer 642 corresponding to the first type of reply speech or the second type of reply speech.

[0086] It should be noted that the second largest language model and the first largest language model may be the same large language model or different large language models, which is not limited here.

[0087] Figure 7 A product form diagram for implementing real-time question and answer in a live broadcast room according to an embodiment of the present disclosure is schematically shown.

[0088] like Figure 7 As shown, after user XX enters the live broadcast room, the anchor plays the message "Welcome XX to the live broadcast room, we are currently answering YY's questions, and your questions will be answered later" in a spoken broadcast mode, and the second type of reply information generated for user XX can be displayed in the live broadcast window 700 in the form of a partially hidden first page 710. The display position may include the bottom, side, and top, which is not limited here. User XX clicks on the partially hidden first page 710 to expand it to obtain the second page 720, which displays the second type of reply information more completely.

[0089] Through the above-mentioned embodiments of the present disclosure, it is possible to provide a real-time answer to the query information of the target object after the target object enters the target live broadcast room.

[0090] According to an embodiment of the present disclosure, the live broadcast room that has been broadcasted may include a digital human live broadcast room. Since each digital human live broadcast room has a fixed virtual image and broadcast content, when the above method is applied to the digital human live broadcast room, the distribution volume and distribution accuracy of the digital human live broadcast room of the relevant information can be effectively improved.

[0091] It should be noted that the above method can also be applied to real-person live broadcast rooms. In this case, the responding anchor users are aware of and agree to the acquisition and use of relevant data in the real-person live broadcast room, and all comply with the provisions of relevant laws and regulations and do not violate good practices.

[0092] Figure 8 The overall flow chart of the live broadcast room information distribution method according to an embodiment of the present disclosure is schematically shown.

[0093] like Figure 8As shown, on the basis of generating the third QC information 810 for the live broadcast room, the third QC information 801 can be first stored in the pre-storage database 810. Then, prompt 811 can be generated based on the third QC information 801 stored in the pre-storage database 810, input into the AI ​​(Artificial Intelligence) model 820, generate title information and summary information, and the title information and summary information can be supplemented and written into the pre-storage database 810 to generate QC page information based on the third QC information 801 stored in the pre-storage database 810 and the corresponding title information and summary information. In response to detecting the broadcast start signal, the data push script 830 can read the QC page information of the live broadcast room to be broadcasted from the pre-storage database 810, and store the read QC page information in the retrieval database 850 through the queue 840.

[0094] According to the embodiments of the present disclosure, QC information can be generated in real time in response to the broadcast signal and stored in the retrieval database. It can also be generated in advance for each type of digital human live broadcast room before the broadcast of each type of digital human live broadcast room, and pre-stored in the pre-storage database, and then read from the pre-storage database in response to the broadcast signal and written into the retrieval database for subsequent retrieval. Its implementation details can also be adjusted according to business needs and are not limited here.

[0095] It should be noted that the first QC information 330 , the second QC information 410 , and the third QC information 810 may express the same QC information or different QC information, which is not limited here.

[0096] Through the above-mentioned embodiments of the present disclosure, a distribution method for a live broadcast room based on retrieval of QC page information is realized. Based on the QC page information, the amount of information used for retrieval in the live broadcast room can be effectively increased, and the distribution volume and distribution accuracy of the live broadcast room can be effectively improved.

[0097] Fig. 9 A block diagram of a live broadcast room information distribution device according to an embodiment of the present disclosure is schematically shown.

[0098] like Fig. 9 As shown, the live broadcast room information distribution device 900 includes a candidate live broadcast content text information determination module 910 and a live broadcast room information distribution module 920.

[0099] The candidate live content text information determination module 910 is used to determine candidate live content text information matching the query information from multiple live content text information in response to receiving the query information, and the live content text information is associated with the live link of the corresponding live broadcast room.

[0100] The live broadcast room information distribution module 920 is used to distribute the candidate live broadcast room information according to the candidate live broadcast link associated with the candidate live broadcast content text information. The candidate live broadcast room information represents the information of the live broadcast room that has been launched based on the candidate live broadcast link.

[0101] According to an embodiment of the present disclosure, the live broadcast room information distribution module includes a candidate live broadcast room information reading unit and a candidate live broadcast room information display unit.

[0102] The candidate live broadcast room information reading unit is used to read the candidate live broadcast room information according to the candidate live broadcast link.

[0103] The candidate live broadcast room information display unit is used to send the candidate live broadcast room information to the front-end page for display, wherein the candidate live broadcast content text information is hidden on the front-end page.

[0104] According to an embodiment of the present disclosure, the live broadcast room information distribution device also includes an information acquisition module and a live broadcast content text information generation module.

[0105] The information acquisition module is used to obtain the anchor information, live broadcast script information and historical live broadcast information related to the anchor information of the live broadcast room to be started in response to receiving the start signal of the live broadcast room to be started.

[0106] The live broadcast content text information generation module is used to generate the live broadcast content text information of the live broadcast room to be broadcasted based on the anchor information, live broadcast script information and historical live broadcast information.

[0107] According to an embodiment of the present disclosure, the live content text information generation module includes a question information extraction unit and a first natural language processing unit.

[0108] The question information extraction unit is used to extract question information based on at least one of the historical live broadcast information and the live broadcast script information.

[0109] The first natural language processing unit is used to perform first natural language processing on the historical live broadcast information according to the question information, and generate live broadcast content text information related to the question information.

[0110] According to an embodiment of the present disclosure, the live broadcast room information distribution device also includes an extraction module and a hypertext markup language page construction module.

[0111] The extraction module is used to extract title information and summary information from the live content text information.

[0112] The hypertext markup language page construction module is used to construct a hypertext markup language page of the live content text information according to the title information, summary information and live content text information.

[0113] According to an embodiment of the present disclosure, the live broadcast room information distribution device also includes a second natural language processing module and a sending module.

[0114] The second natural language processing module is used to respond to determining that the target object has entered the target live broadcast room, perform second natural language processing on at least one of the target live broadcast content text information and the object identification information of the target object used to determine the target live broadcast room, and the query information to obtain the host's answer style information. The target live broadcast room represents any candidate live broadcast room that has been distributed.

[0115] The sending module is used to send the anchor's answer style information to the anchor in the target live broadcast room.

[0116] According to an embodiment of the present disclosure, the live broadcast room information distribution device also includes a display module.

[0117] The display module is used to display the target live content text information in the live broadcast window of the target live broadcast room in response to determining that the target object has entered the target live broadcast room.

[0118] According to an embodiment of the present disclosure, a plurality of live content text information is stored in a search database. The live broadcast room information distribution device also includes a deletion module.

[0119] The deletion module is used to delete the delivered live content text information from the retrieval database in response to receiving a shutdown signal from the live broadcast room that has been broadcasted. The delivered live content text information represents the live content text information determined based on the live broadcast room that has been broadcasted.

[0120] According to an embodiment of the present disclosure, the live broadcast room that has been launched includes a digital human live broadcast room.

[0121] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0122] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method of the present disclosure.

[0123] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method of the present disclosure.

[0124] According to an embodiment of the present disclosure, a computer program product includes a computer program, wherein the computer program is stored in at least one of a readable storage medium and an electronic device, and the computer program implements the method of the present disclosure when executed by a processor.

[0125] Fig.10 A schematic block diagram of an electronic device that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0126] like Fig.10 As shown, the device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0127] A number of components in the device 1000 are connected to an input / output (I / O) interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0128] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1001 performs the various methods and processes described above, such as a live content distribution method. For example, in some embodiments, the live content distribution method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the live content distribution method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute the live content distribution method in any other appropriate manner (eg, by means of firmware).

[0129] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0130] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0131] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0132] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0133] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0134] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0135] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0136] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for distributing live content, comprising: In response to receiving the query information, determining candidate live content text information matching the query information from a plurality of live content text information, wherein the live content text information is associated with a live link corresponding to a live broadcast room that has been broadcast; as well as The candidate live broadcast room information is distributed according to the candidate live broadcast link associated with the candidate live broadcast content text information, and the candidate live broadcast room information represents the information of the live broadcast room that has been started based on the candidate live broadcast link.

2. The method according to claim 1, wherein: The distributing the candidate live broadcast room information according to the candidate live broadcast link associated with the candidate live broadcast content text information includes: According to the candidate live broadcast link, read the candidate live broadcast room information; The candidate live broadcast room information is sent to a front-end page for display, wherein the candidate live broadcast content text information is hidden on the front-end page.

3. The method according to claim 1 or 2, further comprising: In response to receiving a start signal of a live broadcast room to be started, acquiring the anchor information, live broadcast script information and historical live broadcast information related to the anchor information of the live broadcast room to be started; as well as The live broadcast content text information of the live broadcast room to be broadcasted is generated according to the anchor information, the live broadcast script information and the historical live broadcast information.

4. The method according to claim 3, wherein: The generating of the live broadcast content text information of the live broadcast room to be broadcasted according to the anchor information, the live broadcast script information and the historical live broadcast information comprises: Extracting question information according to at least one of the historical live broadcast information and the live broadcast script information; and According to the question information, a first natural language processing is performed on the historical live broadcast information to generate live broadcast content text information related to the question information.

5. The method according to any one of claims 1 to 4, further comprising: Extracting title information and summary information from the live content text information; A hypertext markup language page of the live content text information is constructed according to the title information, the summary information and the live content text information.

6. The method according to any one of claims 1 to 5, further comprising: In response to determining that the target object has entered the target live broadcast room, performing a second natural language processing on at least one of the target live broadcast content text information and the object identification information of the target object used to determine the target live broadcast room and the query information to obtain anchor answer style information, wherein the target live broadcast room represents any of the candidate live broadcast rooms that have been distributed; and The anchor's answer style information is sent to the anchor of the target live broadcast room.

7. The method according to claim 6, further comprising: In response to determining that the target object has entered the target live broadcast room, the target live broadcast content text information is displayed in the live broadcast window of the target live broadcast room.

8. The method according to any one of claims 1 to 7, wherein: The plurality of live content text information are stored in a retrieval database; the method further comprises: In response to receiving a shut-down signal from the live broadcast room that has already started broadcasting, the delivered live broadcast content text information is deleted from the retrieval database, where the delivered live broadcast content text information represents the live broadcast content text information determined based on the live broadcast room that has already started broadcasting.

9. The method according to any one of claims 1 to 8, wherein: The live broadcast room that has been launched includes the digital human live broadcast room.

10. A live broadcast room information distribution device, comprising: A candidate live content text information determination module, configured to determine, in response to receiving query information, candidate live content text information matching the query information from a plurality of live content text information, wherein the live content text information is associated with a live link corresponding to a live broadcast room that has been broadcast; as well as The live broadcast room information distribution module is used to distribute the candidate live broadcast room information according to the candidate live broadcast link associated with the candidate live broadcast content text information, and the candidate live broadcast room information represents the information of the live broadcast room that has been launched based on the candidate live broadcast link.

11. The device according to claim 10, wherein: The live broadcast room information distribution module includes: A candidate live broadcast room information reading unit, used to read the candidate live broadcast room information according to the candidate live broadcast link; The candidate live broadcast room information display unit is used to send the candidate live broadcast room information to the front-end page for display, wherein the candidate live broadcast content text information is hidden in the front-end page.

12. The device according to claim 10 or 11, further comprising: An information acquisition module, configured to, in response to receiving a start signal of a live broadcast room to be started, acquire the anchor information, live broadcast script information, and historical live broadcast information related to the anchor information of the live broadcast room to be started; as well as The live broadcast content text information generation module is used to generate the live broadcast content text information of the live broadcast room to be broadcasted according to the anchor information, the live broadcast script information and the historical live broadcast information.

13. The device according to claim 12, wherein: The live content text information generation module includes: a question information extraction unit, configured to extract question information according to at least one of the historical live broadcast information and the live broadcast script information; and The first natural language processing unit is used to perform a first natural language processing on the historical live broadcast information according to the question information, and generate live broadcast content text information related to the question information.

14. The device according to any one of claims 10 to 13, further comprising: An extraction module, used to extract title information and summary information from the live content text information; The hypertext markup language page construction module is used to construct a hypertext markup language page of the live content text information according to the title information, the summary information and the live content text information.

15. The device according to any one of claims 10 to 14, further comprising: A second natural language processing module is used for, in response to determining that the target object has entered the target live broadcast room, performing a second natural language processing on at least one of the target live broadcast content text information and the object identification information of the target object used to determine the target live broadcast room and the query information to obtain anchor answer style information, wherein the target live broadcast room represents any of the candidate live broadcast rooms that have been distributed; as well as A sending module is used to send the anchor's answer style information to the anchor in the target live broadcast room.

16. The apparatus according to claim 15, further comprising: A display module is used to display the target live content text information in the live broadcast window of the target live broadcast room in response to determining that the target object has entered the target live broadcast room.

17. The device according to any one of claims 10 to 16, wherein: The plurality of live content text information are stored in a retrieval database; the device further comprises: The deletion module is used to delete the delivered live content text information from the retrieval database in response to receiving a shutdown signal from the live broadcast room that has been broadcasted, wherein the delivered live content text information represents the live content text information determined based on the live broadcast room that has been broadcasted.

18. The device according to any one of claims 10 to 17, wherein: The live broadcast room that has been launched includes the digital human live broadcast room.

19. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

21. A computer program product, comprising a computer program, wherein the computer program is stored on at least one of a readable storage medium and an electronic device, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images