CN114765701A

CN114765701A - Information processing method and device based on live broadcast room

Info

Publication number: CN114765701A
Application number: CN202110057950.8A
Authority: CN
Inventors: 韩卫生; 万玉龙; 高杰
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2021-01-15
Filing date: 2021-01-15
Publication date: 2022-07-19

Abstract

An embodiment of the specification provides a live broadcast room-based information processing method and device, and a specific implementation manner of the method comprises the following steps: under the condition that a target live broadcast room is in a first live broadcast mode currently, target comment sentences submitted in the target live broadcast room are obtained; converting the target comment sentence into comment voice; and providing comment voice to the anchor of the target live broadcast room.

Description

Information processing method and device based on live broadcast room

Technical Field

The embodiment of the specification relates to the technical field of computers, in particular to a method and a device for processing information based on a live broadcast room, a method and a device for processing information based on an e-commerce live broadcast room, a method and a device for processing information based on a government affair live broadcast room, a method and a device for processing information based on an education live broadcast room, and a method and a device for processing information based on a conference live broadcast room.

Background

With the rapid development of the live broadcast industry, various types of live broadcast platforms are more and more, more and more people are put into the live broadcast industry, and the development situation of 'all flowers are in order' is presented. In the current live broadcast scene, the anchor mainly acquires user feedback information according to the subtitles, so that the anchor needs to pay attention to the subtitle information in real time in the live broadcast process, and the anchor has higher working strength.

Therefore, a reasonable and reliable scheme is urgently needed, which not only can effectively reduce the workload of the anchor, but also can enable the anchor to acquire the user feedback information.

Disclosure of Invention

The embodiment of the specification provides a live broadcast room-based information processing method and device, an e-commerce live broadcast room-based information processing method and device, a government affair live broadcast room-based information processing method and device, an education live broadcast room-based information processing method and device, and a conference live broadcast room-based information processing method and device.

In a first aspect, an embodiment of the present specification provides an information processing method based on a live broadcast room, including: under the condition that a target live broadcast room is in a first live broadcast mode currently, obtaining comment sentences which are submitted in the target live broadcast room and meet broadcast screening conditions, and using the comment sentences as target comment sentences, wherein the broadcast screening conditions are set for the target live broadcast room; converting the target comment sentence into comment voice; and providing the comment voice to the anchor of the target live broadcast room.

In some embodiments, the execution subject of the method includes a main broadcast version APP in which the target live broadcast room is located; and the providing the comment voice to the anchor of the target live broadcast room comprises: and playing the comment voice to the anchor.

In some embodiments, the execution subject of the method comprises a server; and the providing of the comment voice to the anchor of the target live broadcast room comprises: and sending the comment voice to an anchor version APP where the target live broadcast room is located, so that the anchor version APP plays the comment voice to the anchor.

In some embodiments, the obtaining of comment statements submitted in the target live broadcast room and meeting the broadcast screening condition includes: acquiring a plurality of comment sentences submitted in the target live broadcast room in the previous period of the current period; and selecting the comment sentences meeting the broadcast screening condition from the comment sentences.

In some embodiments, the broadcast screening condition includes a preset value related to a live broadcast topic of the target live broadcast room and before the occurrence frequency is ranked; and the selecting of the comment sentences meeting the broadcast screening condition from the plurality of comment sentences comprises: acquiring the occurrence frequency of different comment sentences in the comment sentences and the correlation degree of the comment sentences and the live topic; and selecting the comment sentences meeting the broadcast screening conditions from the different comment sentences according to the acquired occurrence frequency and the acquired relevancy.

In some embodiments, after the obtaining, as the target comment statement, the comment statement that meets the report filtering condition and is submitted in the target live broadcast room, the method further includes: providing the target comment statement to the anchor.

In some embodiments, the method further comprises: and responding to the received broadcast screening conditions set aiming at the target live broadcast room, and correspondingly storing the received broadcast screening conditions and the identification information of the target live broadcast room.

In some embodiments, the method further comprises: and under the condition that the target live broadcasting room is currently in a first live broadcasting mode, providing prompt voice to the anchor broadcast in response to detecting that a viewer user enters the target live broadcasting room, wherein the prompt voice indicates that the viewer user enters the live broadcasting room.

In some embodiments, prior to said providing a prompt voice to said anchor, said method further comprises: generating first prompt information according to the user identification of the audience user and a prompt information template; and converting the first prompt message into the prompt voice.

In some embodiments, in playing the voice to the anchor, an acoustic echo cancellation algorithm is used to cancel the echo of the played voice.

In some embodiments, after the comment sentences meeting the broadcast screening condition and submitted in the target live broadcast room are obtained and used as the target comment sentences, the method further comprises the steps of determining whether the target comment sentences are comment sentences of a praise class or not; and the acoustic echo cancellation algorithm is adopted to cancel the echo of the played voice, and the method comprises the following steps: and in response to the target comment statement not being a comment statement of the praise class, eliminating the echo of the comment voice by adopting an acoustic echo elimination algorithm.

In some embodiments, in a case that the target live broadcasting room is currently in the first live broadcasting mode, before the comment sentences meeting the broadcast screening condition and submitted in the target live broadcasting room are obtained as target comment sentences, the method further includes: responding to a starting instruction of an anchor version APP where the target live broadcast room is located, and providing second prompt information for the anchor, wherein the second prompt information is used for prompting whether the first live broadcast mode is started or not.

In some embodiments, the method further comprises: and in response to receiving first feedback information indicating that the first direct broadcasting mode is started, setting the current direct broadcasting mode of the target direct broadcasting room to be the first direct broadcasting mode.

In some embodiments, the method further comprises: and in response to receiving second feedback information indicating that the first live broadcasting mode is not started, setting the current live broadcasting mode of the target live broadcasting room to be a second live broadcasting mode, wherein the second live broadcasting mode represents common live broadcasting.

In some embodiments, the method further comprises: responding to a closing instruction aiming at the first live broadcast mode, and setting the current live broadcast mode of the target live broadcast room to be a second live broadcast mode or quitting an anchor version APP where the target live broadcast room is located according to the closing instruction, wherein the second live broadcast mode represents common live broadcast.

In some embodiments, after the responding to the shutdown instruction for the first direct broadcast mode, the method further comprises: providing third prompt information to the anchor, wherein the third prompt information is used for prompting whether to quit the live broadcast; and the current live broadcast mode of the target live broadcast room is set to be a second live broadcast mode or the main broadcast version APP where the target live broadcast room is located is quitted according to the closing instruction, and the method comprises the following steps: in response to receiving third feedback information indicating that the live broadcast does not exit, setting the current live broadcast mode of the target live broadcast room to be a second live broadcast mode; and exiting the main broadcast APP in response to receiving fourth feedback information indicating exiting the live broadcast.

In a second aspect, an embodiment of the present specification provides an information processing method based on a live broadcast room, including: under the condition that a target live broadcast room is in a first live broadcast mode currently, acquiring target comment sentences submitted in the target live broadcast room; converting the target comment sentence into comment voice; and providing the comment voice to the anchor of the target live broadcast room.

In a third aspect, an embodiment of the present specification provides an information processing method based on a live broadcast room, including: acquiring two paths of voice signals acquired by a voice acquisition device, wherein the terminal equipment where the voice acquisition device is located further comprises a voice playing device and an anchor version APP, the anchor version APP opens a target live broadcast room, the first path of voice signal in the two paths of voice signals is the anchor voice of the target live broadcast room, and the second path of voice signal is the output signal of the voice playing device; and selectively eliminating or reserving the second path of voice signals.

In a fourth aspect, an embodiment of the present specification provides an information processing method based on an e-commerce live broadcast room, including: under the condition that a live telecast room is in a first live telecast mode currently, acquiring target comment sentences submitted in the live telecast room; converting the target comment sentence into comment voice; and providing the comment voice to a main broadcasting of the E-commerce live broadcast room.

In a fifth aspect, an embodiment of the present specification provides an information processing method based on a government affair live broadcast room, including: under the condition that a government affair live broadcasting room is in a first live broadcasting mode currently, acquiring target comment sentences submitted in the government affair live broadcasting room; converting the target comment sentence into comment voice; and providing the comment voice to a host of the government affair live broadcast room.

In a sixth aspect, an embodiment of the present specification provides an information processing method based on an education live broadcast room, including: under the condition that an education live broadcasting room is in a first live broadcasting mode currently, target comment sentences submitted in the education live broadcasting room are obtained; converting the target comment sentence into comment voice; and providing the comment voice to a main broadcasting of the education live broadcasting room.

In a seventh aspect, an embodiment of the present specification provides an information processing method based on a conference live room, including: under the condition that a conference live broadcast room is in a first live broadcast mode currently, acquiring target comment sentences submitted in the conference live broadcast room; converting the target comment sentence into comment voice; and providing the comment voice to a host of the conference live room.

In an eighth aspect, an embodiment of the present specification provides a live broadcast room-based information processing apparatus, including: the device comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire comment sentences which are submitted in a target live broadcast room and meet broadcast screening conditions as target comment sentences under the condition that the target live broadcast room is currently in a first live broadcast mode, and the broadcast screening conditions are set for the target live broadcast room; a voice conversion unit configured to convert the target comment sentence into a comment voice; a voice providing unit configured to provide the comment voice to a host of the target live broadcast room.

In a ninth aspect, an embodiment of the present specification provides a live broadcast room-based information processing apparatus, including: the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire a target comment statement submitted in a target live broadcast room under the condition that the target live broadcast room is currently in a first live broadcast mode; a voice conversion unit configured to convert the target comment sentence into a comment voice; a voice providing unit configured to provide the comment voice to a host of the target live broadcast room.

In a tenth aspect, an embodiment of the present specification provides a live broadcast room-based information processing apparatus, including: the device comprises an acquisition unit, a voice playing unit and a broadcasting unit, wherein the acquisition unit is configured to acquire two paths of voice signals acquired by the voice acquisition unit, the terminal equipment where the voice acquisition unit is located further comprises the voice playing unit and is provided with a broadcasting-master APP, a target live broadcasting room is opened by the broadcasting-master APP, the first path of voice signal in the two paths of voice signals is the broadcasting-master voice of the target live broadcasting room, and the second path of voice signal is the output signal of the voice playing unit; and the echo cancellation unit is configured to selectively cancel or reserve the second path of voice signals.

In an eleventh aspect, an embodiment of the present specification provides an information processing apparatus based on an e-commerce live broadcast room, including: the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire a target comment statement submitted in a live telecast room under the condition that the live telecast room is currently in a first live broadcasting mode; a voice conversion unit configured to convert the target comment sentence into a comment voice; a voice providing unit configured to provide the comment voice to a host of the live telecast.

In a twelfth aspect, an embodiment of the present specification provides an information processing apparatus based on a government affair live broadcast room, including: the obtaining unit is configured to obtain the target comment sentences submitted in the government affair live broadcasting room under the condition that the government affair live broadcasting room is in a first direct broadcasting mode currently; a voice conversion unit configured to convert the target comment sentence into a comment voice; a voice providing unit configured to provide the comment voice to a host of the government affair live broadcast room.

In a thirteenth aspect, an embodiment of the present specification provides an information processing apparatus based on an education live broadcast room, including: an acquisition unit configured to acquire a target comment sentence submitted in an education live broadcast room in a case where the education live broadcast room is currently in a first live broadcast mode; a voice conversion unit configured to convert the target comment sentence into a comment voice; a voice providing unit configured to provide the comment voice to a host of the education live room.

In a fourteenth aspect, an embodiment of the present specification provides an information processing apparatus based on a live conference room, including: the conference live broadcasting system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire a target comment statement submitted in a conference live broadcasting room under the condition that the conference live broadcasting room is currently in a first live broadcasting mode; a voice conversion unit configured to convert the target comment sentence into a comment voice; a voice providing unit configured to provide the comment voice to a host of the live conference room.

In a fifteenth aspect, the present specification provides a computer readable storage medium, on which a computer program is stored, wherein when the computer program is executed in a computer, the computer is caused to execute the method described in any implementation manner of the first to seventh aspects.

In a sixteenth aspect, the present specification provides a computing device, including a memory and a processor, where the memory stores executable code, and the processor executes the executable code to implement the method described in any one of the implementation manners of the first aspect to the seventh aspect.

In the information processing method and apparatus based on the live broadcast room provided by the above embodiments of the present specification, when the target live broadcast room is currently in the first live broadcast mode, the target comment statements submitted in the target live broadcast room are acquired, then the target comment statements are converted into comment voices, and then the comment voices are provided to the anchor broadcast in the target live broadcast room, so that the anchor broadcast does not need to pay attention to subtitle information in real time during the live broadcast process, and user comments can be obtained through the played comment voices. Therefore, the work load of the anchor can be effectively reduced, and the anchor can acquire the user feedback information.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments disclosed in the present specification, the drawings needed to be used in the description of the embodiments will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments disclosed in the present specification, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.

FIG. 1 is an exemplary system architecture diagram to which some embodiments of the present description may be applied;

FIG. 2 is a flow diagram of one embodiment of a live-room based information processing method in accordance with the present description;

FIG. 3 is a schematic diagram of a screening process of target review statements;

FIG. 4 is a flow diagram of one embodiment of a live telecast based information processing method according to the present description;

FIG. 5 is a flow diagram of one embodiment of a government affairs live room based information processing method according to the present description;

FIG. 6 is a flow diagram of one embodiment of a method for information processing based on an educational direct broadcast room in accordance with the present description;

FIG. 7 is a flow diagram for one embodiment of a live conference room-based information processing method in accordance with the present description;

FIG. 8a is a schematic illustration of a main broadcast version of a live interface;

FIG. 8b is a diagram illustrating the effect of a target comment sentence;

FIG. 8c is a diagram of the effect of the presentation of the target comment sentence;

FIG. 8d is a diagram of the effect of the presentation of the target comment sentence;

FIG. 9 is a flow diagram of one embodiment of a live-room based information processing method in accordance with the present description;

FIG. 10 is a flow diagram of one embodiment of a live room-based information processing method according to the present description;

FIG. 11 is a schematic diagram of the start-up flow of the live mode of the target live room;

fig. 12 is a schematic diagram of a shutdown procedure of the first direct broadcasting mode;

FIG. 13a is a diagram of a main version live interface in a light live mode;

FIG. 13b is a schematic diagram illustrating the effect of displaying the third prompt message;

FIG. 13c is a schematic diagram of a anchor version of a live interface in normal live mode;

fig. 14 is a schematic configuration diagram of a live-air-room-based information processing apparatus according to the present specification;

fig. 15 is a schematic configuration diagram of a live-air-room-based information processing apparatus according to the present specification;

fig. 16 is a schematic configuration diagram of a live-air-room-based information processing apparatus according to the present specification;

fig. 17 is a schematic configuration diagram of an information processing apparatus based on a live telecast room according to the present specification;

fig. 18 is a schematic view of a structure of an information processing apparatus based on a government affairs live room according to the present specification;

fig. 19 is a schematic view of a configuration of an information processing apparatus based on an education live room according to the present specification;

fig. 20 is a schematic diagram of a configuration of an information processing apparatus based on a live conference room according to the present specification.

Detailed Description

The present specification will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. The described embodiments are only a subset of the embodiments described herein and not all embodiments described herein. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without making any creative effort belong to the protection scope of the present application.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present description may be combined with each other without conflict.

As described above, in a current live broadcast scene, a anchor mainly obtains user feedback information according to subtitles, which requires the anchor to pay attention to subtitle information in real time during a live broadcast process, and the anchor has a high working strength.

Based on this, some embodiments of the present specification provide a live broadcast room-based information processing method, by which not only can the workload of the anchor be effectively reduced, but also the anchor can acquire user feedback information. In particular, FIG. 1 illustrates an exemplary system architecture diagram suitable for use with these embodiments.

As shown in fig. 1,

terminal devices

101, 102, 104 and a server 103 are shown. The

terminal devices

101 and 102 are respectively installed with audience version APPs (applications), the terminal device 104 is installed with a main broadcast version APP, and the server 103 is a background server supporting these two APPs.

It should be noted that the terminal device may be various electronic devices, which may include, but are not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, and the like, and is not limited in particular herein.

The audience version APP may be an APP for use by an audience user watching a live broadcast. Further, the APP category of the audience version APP may be, for example, a shopping APP, a social APP, a game APP, an education APP, a government APP, a conference APP, or a live APP, and is not limited herein. When audience version APP belongs to the live broadcast type APP, the audience version APP can be called as a live broadcast audience version APP.

The anchor version APP may be an APP for use by the anchor. Generally, a user who performs live broadcasting by using a live broadcasting room opened in the anchor version APP is called an anchor. In practice, the application category of the anchor version APP may be consistent with that of the viewer version APP, and is not specifically limited herein. When the anchor version APP belongs to the live broadcast type APP, the anchor version APP can be called a live broadcast anchor version APP.

Note that the anchor version APP in this specification can provide a variety of live modes to the anchor. The plurality of live modes may include, but are not limited to, a first live mode and a second live mode. In this specification, a live broadcast room that can enter any of the plurality of live broadcast modes may be referred to as a target live broadcast room.

In different live scenes, the target live room may have different designations. For example, in an educational live scenario, the target live room may be referred to as an educational live room. In a conference live scenario, the target live room may be referred to as a conference live room. In the E-commerce live broadcast scene, the target live broadcast room can be called an E-commerce live broadcast room. In a government affair live broadcasting scene, the target live broadcasting room can be called as a government affair live broadcasting room.

In this specification, the first live mode may be referred to as a light live mode. As the name suggests, the live broadcast scheme in the live broadcast mode can reduce the work load of the anchor. The second live mode may be referred to as a normal live mode. The live broadcast scheme in the normal live broadcast mode is a scheme generally known by people.

Generally, audience users in a target live broadcast room can enter the target live broadcast room by using an audience version APP and submit comment sentences in the target live broadcast room. As an example, the target live broadcast room opened in the main broadcast APP installed on the terminal device 104 is a live broadcast room a. The audience user to which the terminal device 101 belongs may open an audience version live interface of the live broadcast room a in an audience version APP installed on the terminal device 101, then input a comment statement 1 in a comment area of the interface, and trigger (e.g., click) a submit button, so that the audience version APP sends the comment statement 1 to the server 103. The audience user to which the terminal device 102 belongs may open an audience version live interface of the live broadcast room a in an audience version APP installed on the terminal device 102, then input the comment statement 2 in a comment area of the interface, and trigger (e.g., click) a submit button, so that the audience version APP sends the comment statement 2 to the server 103. Wherein, audience version live interface is the live interface in audience version APP. It should be understood that the comment sentence 1 and the comment sentence 2 are only exemplary comment sentences, and the specification does not set any limit to the specific comment content of the comment sentence.

The server can respectively send the received comment sentences, such as comment sentence 1 and comment sentence 2, to the anchor version APP where the live broadcast room A is located, so that the received comment sentences 1 and comment sentences 2 are respectively displayed in the comment display area of the anchor version APP on the anchor version live broadcast interface of the live broadcast room A. And the anchor version live interface is a live interface in the anchor version APP.

It should be understood that, in addition to displaying the comment sentence in the comment display area, other information related to the comment sentence, such as a nickname, an avatar of a viewer user who sent the comment sentence, and/or a sending time of the comment sentence, etc., may be displayed, and is not particularly limited herein.

When the target live broadcast room is in the second live broadcast mode, the anchor is generally required to pay attention to the subtitle information in real time during the live broadcast process, for example, to comment statements in a comment display area.

When the target live broadcasting room is in the first live broadcasting mode, voice broadcasting can be carried out on the target comment sentences, so that the anchor broadcast obtains user feedback information in a voice listening mode without staring at the screen in real time, intervention can be carried out only when feedback to audience users is judged to be needed according to broadcasting contents, and workload can be effectively relieved.

The target comment sentence may be any comment sentence received in real time, or a comment sentence screened out from comment sentences received in real time or comment sentences received within a certain period of time according to a broadcast screening condition set for the target live broadcast room, which is not specifically limited herein.

Continuing to take the comment statement 1 and the comment statement 2 as an example, assuming that the comment statement 1 and the comment statement 2 are submitted under the condition that the live broadcast room a is in the first live broadcast mode, the anchor APP or the server 103 on the terminal device 104 may determine a target comment statement from the comment statement 1 and/or the comment statement 2, convert the determined target comment statement into comment voice, and provide the comment voice for the anchor of the live broadcast room a. Specifically, when the server 103 side performs voice conversion, the server 103 may send the comment voice to the anchor version APP where the live broadcast room a is located, so that the anchor version APP plays the comment voice to the anchor. When voice conversion is performed on the anchor version APP side on the terminal device 104, the anchor version APP can directly play comment voice to the anchor after converting the target comment sentence into the comment voice. Note that fig. 1 only shows a case where speech conversion is performed on the anchor version APP side on the terminal device 104.

It should be understood that the number of terminal devices and servers in fig. 1 is merely illustrative. There may be any number of terminal devices and servers, as desired for implementation.

The following describes specific implementation steps of the above method with reference to specific examples.

Referring to fig. 2, a flow 200 of one embodiment of a live-room based information processing method is shown. The execution subject of the method may be a main broadcast APP installed on the server 103, the terminal device 104, or the terminal device 104 shown in fig. 1. The method comprises the following steps:

step 211, under the condition that the target live broadcast room is currently in the first live broadcast mode, acquiring target comment statements submitted in the target live broadcast room;

step 212, converting the target comment sentence into comment voice;

step 213, providing comment voice to the anchor of the target live broadcast room.

Through the execution of the step 211 and the step 213, the anchor broadcast does not need to pay attention to the subtitle information in real time in the live broadcast process, and the comment of the user can be obtained through the played comment voice. Therefore, the work load of the anchor can be effectively reduced, and the anchor can acquire the user feedback information.

The above steps are further explained below.

In step 211, as one implementation, the comment statement submitted by the audience user in the target live broadcast may be treated as a target comment statement in response to receiving the comment statement.

As another implementation manner, if the target live broadcast room is provided with the broadcast screening condition, step 211 may further include: step 2111, obtaining the comment sentences which are submitted in the target live broadcast room and meet the broadcast screening conditions, and using the comment sentences as target comment sentences. Among them, a Natural Language Processing (NLP) technique may be adopted to screen out comment sentences that satisfy the broadcast screening conditions. It should be noted that the broadcast screening condition may be set by an administrator of the target live broadcast room according to actual requirements, and the content of the broadcast screening condition is not specifically limited in this specification. Based on this, the method described by the corresponding embodiment of fig. 2 may be further illustrated as fig. 9. Fig. 9 is a flowchart of an embodiment of a live broadcast-based information processing method.

Specifically, in step 2111, the execution subject may obtain, in real time, a comment statement that meets the broadcast filtering condition and is submitted in the target live broadcast room, as a target comment statement. For example, when the broadcast filtering condition is applied to filter a single comment statement, for example, the broadcast filtering condition includes that the comment statement is related to a live topic, or the comment statement includes a target keyword, or the like, it may be determined whether the comment statement satisfies the broadcast filtering condition in response to receiving the comment statement submitted by the viewer user in the target live broadcast room, and if so, the comment statement is determined as the target comment statement.

In practice, live subject matter is typically related to live content. For example, when live content is related to the putting on of a light girl, the live topic may be, for example, "little skill in the matching of light girls". For another example, when the live content is related to the putting on of a young girl, the live subject may be, for example, "the way of the attack of the short leg". It should be understood that the present specification is not intended to limit the live subject matter in any way.

Optionally, in step 2111, the execution subject may also periodically acquire a comment statement that meets the broadcast filtering condition and is submitted in the target live broadcast room, as a target comment statement. For example, a plurality of comment sentences submitted in a target live broadcast room in a previous cycle of a current cycle are acquired, and comment sentences meeting broadcast screening conditions are selected from the plurality of comment sentences as target comment sentences.

Assuming that the broadcast filtering condition includes a preset value before the occurrence frequency ranking related to the live broadcast topic of the target live broadcast room, the filtering process of the target comment statement may be as shown in fig. 3. The preset value may be, for example, 5, 10, or 15, and may be set according to actual requirements, and is not specifically limited herein.

Referring to fig. 3, a schematic diagram of a filtering process of a target comment statement is shown. The screening process comprises the following steps:

301, acquiring a plurality of comment sentences submitted in a target live broadcast room in the previous period of the current period;

step 302, obtaining the occurrence frequency of different comment sentences in a plurality of comment sentences and the correlation degree of the comment sentences and the live broadcast theme of a target live broadcast room;

and 303, selecting comment sentences meeting the broadcasting and screening conditions from different comment sentences as target comment sentences according to the acquired occurrence frequency and relevancy.

In the screening process, the duration of each period may be, for example, 3, 4, 5, or 6 minutes, and is not limited herein.

In step 302, for any one of the different comment sentences, the frequency of occurrence of the comment sentence in the comment sentences can be counted. In addition, a text similarity calculation method can be adopted to calculate the similarity between the comment statement and the live topic of the target live broadcast room, and the similarity is determined as the correlation between the comment statement and the live topic. The text similarity calculation method may be any algorithm for text similarity calculation, and may include, but is not limited to, cosine similarity calculation, euclidean distance, and/or pearson correlation coefficient, for example.

Alternatively, a relevance calculation model may be trained in advance, the input of the model may include, for example, a comment sentence and a live topic, and the output of the model may include, for example, the relevance of the comment sentence and the live topic. Based on this, the comment sentences in the comment sentences different from each other and the live subject of the target live broadcast room can be input into the model, so that the model outputs the correlation degree between the comment sentences and the live broadcast subject.

In step 303, comment sentences whose relevancy to the live broadcast topic in the target live broadcast room reaches the relevancy threshold may be selected from the different comment sentences, and then comment sentences whose occurrence frequency is a preset value are further selected from the selected comment sentences, and the comment sentences whose occurrence frequency is a preset value are determined as the target comment sentences. Here, the correlation in this specification may be within [0, 1 ]. The correlation threshold may be, for example, 0.45, 0.5, or 0.55, and may be set according to actual requirements, and is not specifically limited herein.

By executing the screening process, the content which is most concerned in a period of time can be screened out and given to the anchor feedback. The anchor can obtain user's hot feedback according to voice prompt very first time, in time makes live broadcast adjustment etc. can effectively promote live broadcast experience.

In step 212, various speech synthesis algorithms may be employed to convert the target comment sentence into comment speech. The various speech synthesis algorithms, including existing speech synthesis algorithms and speech synthesis algorithms developed in the future, are not specifically limited herein.

It should be noted that, whether the execution subject is located on the terminal side or on the server side, the execution subject may locally convert the target comment sentence into a comment voice. Optionally, when the execution main body is located at a terminal side, the execution main body may also send the target comment sentence to a server side, so that the server side converts the target comment sentence into comment voice, and then the execution main body may receive the comment voice from the server side.

In step 213, when the execution body is located on the terminal side, the execution body may directly play the comment voice to the anchor. When the execution main body is located at the server side, the execution main body can send the comment voice to the anchor version APP where the target live broadcast room is located, and the anchor version APP plays the comment voice to the anchor. It should be noted that the terminal device where the anchor APP is located includes a voice playing device, such as a speaker. The main broadcasting APP can control the voice playing device to play comment voice.

In practice, the information processing method based on the live broadcast room provided by the embodiment of the present specification can be applied to different live broadcast scenes.

For example, in an e-commerce live broadcast scenario, a flow of an information processing method based on an e-commerce live broadcast room may be as shown in fig. 4. Fig. 4 is a flowchart of an embodiment of an information processing method based on an e-commerce live room. The method comprises the following steps: step 411, under the condition that the live telecast room is currently in a first live telecast mode, acquiring target comment sentences submitted in the live telecast room; step 412, converting the target comment sentence into comment voice; and step 413, providing comment voice to the anchor of the live television broadcast room.

Wherein, the E-commerce live broadcast room can be a live broadcast room for the main broadcast to sell the commodities. The commodity may include a physical commodity, a virtual commodity, and the like, and is not particularly limited herein. Audience users may submit arbitrary comment statements within the e-commerce live room, such as comment statements related to items sold by the anchor or anchor, and so forth.

The method described in the embodiment corresponding to fig. 4 can enable the anchor in the live telecast of the e-commerce live broadcasting room to obtain the user comment through the played comment voice without paying attention to the subtitle information in real time in the live broadcasting process. Therefore, the work load of the anchor can be effectively reduced, and the anchor can acquire the user feedback information.

In the scene of the direct government affairs, the flow of the information processing method based on the direct government affair room can be as shown in fig. 5. Fig. 5 is a flowchart of an embodiment of an information processing method based on a government affair live broadcast room. The method comprises the following steps: step 511, under the condition that the government affair live broadcasting room is currently in the first direct broadcasting mode, acquiring target comment sentences submitted in the government affair live broadcasting room; step 512, converting the target comment sentences into comment voices; step 513, providing comment voice to the anchor of the government affair live broadcast room.

Wherein, the direct broadcasting room of the government affairs can be a direct broadcasting room for the direct broadcasting of the government affairs. Government affairs generally refer to the transactional work of the government. The government affair live broadcast may include a live broadcast related to a transactional work of the government. For example, the government affair live broadcast can include, but is not limited to, a live broadcast related to official statement, a live broadcast related to audition, a live broadcast related to government affair publishing and opinion feedback collection, a government affair meeting live broadcast suitable for meeting listening, and the like, and the embodiment does not limit the content of the live broadcast of the government affair. Audience users may submit arbitrary comment statements within the government live room, such as comment statements related to the anchor or live government content.

The method described in the embodiment corresponding to fig. 5 can enable the anchor of the government affair live broadcast room to obtain the user comment through the played comment voice without paying attention to the subtitle information in real time in the live broadcast process. Therefore, the work load of the anchor can be effectively reduced, and the anchor can acquire the user feedback information.

In the education live broadcast scene, the flow of the information processing method based on the education live broadcast room can be as shown in fig. 6. FIG. 6 is a flow diagram of one embodiment of a method for information processing based on an educational direct broadcast room. The method comprises the following steps: 611, under the condition that the education live broadcast room is currently in the first live broadcast mode, acquiring target comment sentences submitted in the education live broadcast room; step 612, converting the target comment sentence into comment voice; step 613, providing comment voice to the anchor of the education live broadcast room.

Wherein the education live broadcast room may be a live broadcast room for education live broadcast. In practice, the students in free teaching, schools, teachers in training institutions and the like can all use the direct broadcasting room for teaching on line. Audience users may submit arbitrary review phrases within an educational live room, such as review phrases related to an on-air or live course, and the like.

The method described in the embodiment corresponding to fig. 6 can enable the anchor in the education live broadcast room to obtain the user comments through the played comment voice without paying attention to the subtitle information in real time in the live broadcast process. Therefore, the work load of the anchor can be effectively reduced, and the anchor can acquire the user feedback information.

In a conference live scene, a flow of the information processing method based on the conference live room may be as shown in fig. 7. Fig. 7 is a flowchart of an embodiment of a conference live room-based information processing method. The method comprises the following steps: step 711, under the condition that the conference live broadcasting room is currently in the first live broadcasting mode, acquiring a target comment statement submitted in the conference live broadcasting room; step 712, converting the target comment sentence into comment voice; step 713, providing the comment voice to the anchor of the conference live room.

Wherein, the conference live room can be a live room for conference live. The conference live may include live broadcasts relating to various categories of conferences. The various categories may include, but are not limited to, business meetings, educational meetings at schools, meetings at state organizations, social organizational meetings, and the like. Audience users may submit arbitrary comment statements within the live conference room, such as comment statements related to the anchor, the conference content, or the conference flow, etc.

The method described in the embodiment corresponding to fig. 7 can enable the anchor in the live conference room to obtain the user comment through the played comment voice without paying attention to the subtitle information in real time in the live broadcasting process. Therefore, the work load of the anchor can be effectively reduced, and the anchor can acquire the user feedback information.

In some embodiments, for example, embodiments corresponding to fig. 2 and fig. 9 respectively, the terminal device where the anchor APP is located may further include a voice collecting device, such as a microphone. In order to avoid returning the speech played by the speech playing device to the viewer user, step 215 may be further executed to cancel the Echo of the played speech by using an Acoustic Echo Cancellation (AEC) algorithm in the process of playing the comment speech. Specifically, in step 215, if a voice signal collected by the voice collecting device is received, an acoustic echo cancellation algorithm may be used to cancel the comment voice from the voice signal. Thereafter, the voice signal after the comment voice is eliminated can be provided to the viewer user.

In some embodiments, for example, the embodiments corresponding to fig. 2 and fig. 9 respectively, in order to enrich the information processing manner and to actively broadcast the live atmosphere, the comment speech corresponding to the comment statement of the praise class may be directly played out without performing echo cancellation. The praise-like comment statements may include, but are not limited to, "hello stick," "beautiful anchor," "666," and so on, for example. Based on this, after step 211 or step 2111, and before canceling the echo of the comment speech by executing step 215, step 214 may be executed to determine whether the target comment sentence is a comment sentence of the praise class.

Specifically, in step 214, various methods may be adopted to determine whether the target comment statement is a comment statement of a praise class. For example, a word set may be preset, and each word in the word set is a word of the praise class. If the target comment statement includes a word in the preset word set, it may be determined that the target comment statement is a comment statement of a praise class. For another example, a neural network for identifying the comment sentences of the praise class may be trained in advance, and whether the target comment sentences are comment sentences of the praise class may be identified using the neural network.

Upon executing step 214, step 215 may further include, in response to the target comment sentence not being a comment sentence of the praise class, canceling an echo of the played comment speech using an echo cancellation algorithm. In addition, if it is determined that the target comment sentence is a comment sentence of the like of praise, the step 215 is not executed.

Optionally, if the target comment statement is screened out according to the broadcast screening condition, the target comment statement may also be provided to the anchor. Specifically, when the execution body is located on the terminal side, the execution body may directly present the target comment sentence to the anchor. When the execution main body is located at the server side, the execution main body can send the target comment statement to the anchor version APP where the target live broadcast room is located, so that the anchor version APP shows the target comment statement to the anchor.

The target comment sentences may be displayed in various display manners, for example, in the form of a list, a pop-up window, a pop-up screen, or the like, and the target comment sentences may be displayed at any position on a main-broadcast-version live interface of the target live broadcast room, which is not specifically limited herein.

As an example, assume that the layout of the main live interface of the target live room is as shown in fig. 8 a. Fig. 8a is a schematic diagram of a main broadcast interface. In fig. 8a, it is shown that the anchor live interface includes a comment display area and an anchor image display area. The comment display area is used for displaying comment sentences submitted by audience users. The anchor image display area is used for displaying, and the live broadcast equipment faces the images collected by the anchor.

Assuming that the obtained target comment sentences are respectively "how small children attack in the opposite direction", "how small short legs take in autumn", "how small legs take in summer without showing leg shortness", the display effect of the target comment sentences may be as shown in fig. 8b, fig. 8c, or fig. 8 d. Fig. 8b-8d are each a schematic diagram of the exhibition effect of the target comment sentence. In fig. 8b, the target comment sentences are presented in the comment display area in the form of pop-up windows. In fig. 8c, the respective target comment sentences are presented in the comment display area in the form of a list. In fig. 8d, the respective target comment sentences are presented in the form of a bullet screen in the anchor image display area.

Optionally, under the condition that the target live broadcast room is currently in the first live broadcast mode, an administrator of the target live broadcast room may set the broadcast screening condition at any time. Based on this, the execution main body can respond to the received broadcast screening condition set for the target live broadcast room, and correspondingly stores the broadcast screening condition and the identification information of the target live broadcast room.

Optionally, besides the comment statement can be broadcasted in voice, a voice prompt can be performed when the fact that the audience user enters the target live broadcasting room is detected. Specifically, in the method described in the embodiments corresponding to fig. 2 and fig. 9, the method may further include: step 210, under the condition that the target live broadcasting room is currently in the first direct broadcasting mode, in response to detecting that the audience user enters the target live broadcasting room, providing a prompt voice for the anchor of the target live broadcasting room, wherein the prompt voice indicates that the audience user enters the live broadcasting room.

In step 210, as an implementation manner, the prompt voice may be preset. As another implementation manner, the first prompt message may be generated according to the user identifier of the viewer user who is detected to enter the live broadcast room and the prompt message template, and the first prompt message may be converted into the prompt voice. The user identifier may be, for example, a user number or a user name of the viewer user in the viewer version APP, which is not specifically limited herein. As an example, assuming that the cue information template is ". star to live room", the user id may be used to replace ". star" in the template, and the replaced template is used as the first cue information.

It should be noted that when the anchor is in the waiting state, if the prompt voice is heard, the anchor can choose to call, and if no further interaction is performed, the anchor can continue to enter the waiting state without staring at the screen in real time, so that the workload of the anchor can be reduced, and the anchor can obtain the feedback of the audience user entering the live broadcast room in time.

Optionally, in order to avoid transmitting the played prompt voice back to the viewer user and reduce the live experience of the viewer user, during the playing of the prompt voice, the step 215 may be executed to cancel the echo of the played prompt voice.

Combining the above-described contents related to echo cancellation, the echo cancellation scheme in this specification can be as shown in fig. 10. Fig. 10 is a flow diagram of one embodiment of a live-air based information processing method relating to echo cancellation. The information processing method based on the live broadcast room can comprise the following steps:

step 1001, acquiring two paths of voice signals acquired by a voice acquisition device, wherein a terminal device where the voice acquisition device is located further comprises a voice playing device and a main broadcasting version APP is installed, the main broadcasting version APP is provided with a target live broadcasting room, the first path of voice signal in the two paths of voice signals is the main broadcasting voice of the target live broadcasting room, and the second path of voice signal is an output signal of the voice playing device;

in step 1002, the second path of voice signal is selectively eliminated or retained.

In step 1001, when the executing body is located at a terminal side, the executing body may directly obtain the two voice signals from the voice collecting device. When the execution body is located at the service end side, the execution body may receive the two voice signals from the main broadcasting version APP.

In step 1002, when the second path of voice signal is the prompt voice output by the voice playing apparatus, as described above, the executing entity may eliminate the second path of voice signal from the two paths of voice signals. When the second path of voice signal is the comment voice output by the voice playing device, and the target comment statement corresponding to the comment voice is not a praise comment statement, the execution main body may eliminate the second path of voice signal from the two paths of voice signals. When the second path of voice signal is the comment voice output by the voice playing device, and the target comment statement corresponding to the comment voice is a praise comment statement, the execution main body may retain the second path of voice signal in the two paths of voice signals.

In some embodiments, for example, the embodiments corresponding to fig. 2 and fig. 9 respectively, before the anchor starts live broadcast by using the target live broadcast room, the anchor can make a selection to enter the first live broadcast mode or the second live broadcast mode, so as to enrich the information processing manner and improve the live broadcast experience of the anchor.

As shown in fig. 11, it shows a schematic diagram of the start flow of the live mode of the target live broadcast room. The starting process comprises the following steps:

step 201, responding to a starting instruction of an anchor version APP where a target live broadcasting room is located, and providing second prompt information for an anchor, wherein the second prompt information is used for prompting whether a first direct broadcasting mode is started or not;

step 202, in response to receiving first feedback information indicating that the first direct broadcasting mode is started, setting the current direct broadcasting mode of the target direct broadcasting room as the first direct broadcasting mode;

and step 203, in response to receiving second feedback information indicating that the first live broadcast mode is not started, setting the current live broadcast mode of the target live broadcast room to be a second live broadcast mode.

It should be appreciated that the anchor may be made normally live after the current live mode of the target live room is set to the second live mode.

In step 201, when the execution main body is located at the terminal side, the execution main body may directly display the second prompt information to the anchor in response to the start instruction. When the execution main body is located at the server side, the execution main body can respond to the starting instruction and send the second prompt message to the main broadcast version APP where the target live broadcast room is located, so that the main broadcast version APP shows the second prompt message to the main broadcast.

It should be noted that the second prompt message may include any message content for prompting whether to start the first direct broadcast mode, and is not specifically limited herein. As an example, assuming that the first live mode is referred to as a light live mode, the information content may include, for example, "do the light live mode turn on? ".

In some embodiments, for example, the embodiments respectively corresponding to fig. 2 and fig. 9, when the target live broadcast room is currently in the first live broadcast mode, in the live broadcast process, the execution main body may further respond to a closing instruction for the first live broadcast mode, and set the current live broadcast mode of the target live broadcast room to the second live broadcast mode or quit the anchor version APP in which the target live broadcast room is located according to the closing instruction.

As an example, a specific shutdown procedure of the first direct broadcast mode may be as shown in fig. 12. Fig. 12 shows a schematic diagram of a shutdown procedure of the first direct play mode. Wherein, the closing process comprises the following steps:

step 215, responding to a closing instruction aiming at the first live broadcasting mode, and providing third prompt information for the anchor, wherein the third prompt information is used for prompting whether to quit live broadcasting;

step 216, in response to receiving third feedback information indicating that the live broadcast does not exit, setting the current live broadcast mode of the target live broadcast room to be a second live broadcast mode;

and step 217, in response to receiving the fourth feedback information indicating that the live broadcast is quitted, quitting the main broadcast APP.

In step 215, when the execution body is located at the terminal side, the execution body may directly display the third prompt message to the anchor in response to the close command. When the execution main body is located at the server side, the execution main body can respond to the closing instruction and send the third prompt message to the main broadcast version APP where the target live broadcast room is located, so that the main broadcast version APP shows the third prompt message to the main broadcast.

In step 217, when the execution body is located at the terminal side, the execution body may execute a preset command to exit the main-cast APP. When the execution main body is located at the server side, the execution main body can send an instruction for quitting the anchor version APP to the anchor version APP where the target live broadcast room is located, so that the anchor version APP quits the anchor version APP by executing a preset instruction for quitting the anchor version APP.

It should be noted that the third prompt message may include any message content for prompting whether to quit live broadcasting, and is not limited in this respect. As an example, the information content may include, for example, "do you quit live? "

Taking the first live mode as the light live mode, the second live mode as the common live mode, and the execution subject as the anchor APP, assume that the anchor live interface in the light live mode is as shown in fig. 13 a. Fig. 13a is a diagram of a main version live interface in a light live mode. In fig. 13a, a anchor image display area, a comment display area, and a light live mode button are shown. The symbol "√" shown in this button indicates that the current live mode is the live light mode. The anchor can send a close instruction for the live light mode to the anchor version APP by triggering (e.g., clicking) the button. The anchor version APP may present the third prompt in response to the close instruction.

The effect of displaying the third prompting message can be as shown by a reference number 1301 in fig. 13 b. Fig. 13b is a schematic diagram illustrating the effect of displaying the third prompting message. In fig. 13b, the prompt window indicated by reference numeral 1301 shows that the third prompt message "does the user exit from the live broadcast? And buttons yes and no. Wherein the anchor may submit the third feedback information by triggering the no button and the fourth feedback information by triggering the yes button.

After the anchor submits the third feedback information by triggering the 'no' button, the anchor APP can set the current live mode of the target live broadcast room to be the common live broadcast mode. Further, the anchor APP may change the light live mode button to a normal live mode button as shown in fig. 13 c. Fig. 13c is a schematic diagram of a main broadcast live interface in the normal live mode.

By executing the closing flow shown in fig. 12, the anchor can select whether to quit live broadcasting, which not only enriches the information processing mode, but also improves the live broadcasting experience of the anchor.

With further reference to fig. 14, the present specification provides an embodiment of a live broadcast room-based information processing apparatus, which may be applied to the server 103, the terminal device 104, or the main broadcast APP installed on the terminal device 104 shown in fig. 1.

As shown in fig. 14, the information processing apparatus 1400 based on the live broadcast room of the present embodiment includes: an acquisition unit 1401, a voice conversion unit 1402, and a voice providing unit 1403. Wherein the obtaining unit 1401 is configured to obtain a target comment sentence submitted in a target live broadcast room, in a case where the target live broadcast room is currently in a first live broadcast mode; the voice conversion unit 1402 is configured to convert the target comment sentence into a comment voice; the voice providing unit 1403 is configured to provide the comment voice to the anchor of the target live broadcast room.

Optionally, the target live broadcast room may be provided with broadcast screening conditions; and the obtaining unit 1401 may be further configured to: and obtaining comment sentences which are submitted in the target live broadcast room and meet the broadcast screening conditions, and using the comment sentences as target comment sentences.

With further reference to fig. 15, the present specification provides an embodiment of a live-air-based information processing apparatus, and the apparatus embodiment may be applied to a server 103, a terminal device 104, or a main broadcast APP installed on the terminal device 104 as shown in fig. 1.

As shown in fig. 15, the information processing apparatus 1500 based on a live broadcast room of the present embodiment includes: an acquisition unit 1501, a voice conversion unit 1502, and a voice providing unit 1503. The obtaining unit 1501 is configured to obtain, as a target comment statement, a comment statement submitted in a target live broadcast room and meeting a broadcast screening condition set for the target live broadcast room, when the target live broadcast room is currently in a first live broadcast mode; the voice conversion unit 1502 is configured to convert the target comment sentence into a comment voice; the voice providing unit 1503 is configured to provide comment voice to the anchor of the target live room.

Optionally, the obtaining unit 1401 and/or the obtaining unit 1501 as described above may be further configured to: acquiring a plurality of comment sentences submitted in a target live broadcast room in the previous period of the current period; and selecting the comment sentences meeting the broadcast screening condition from the plurality of comment sentences.

Optionally, the broadcast screening condition may include a preset value related to a live broadcast topic of the target live broadcast room and before the occurrence frequency ranking; and the acquisition unit 1401 and/or the acquisition unit 1501 as described before may be further configured to: acquiring the occurrence frequency of different comment sentences in the comment sentences and the correlation degree with the live topic; and selecting comment sentences meeting the broadcasting and screening conditions from the mutually different comment sentences according to the acquired occurrence frequency and the acquired relevancy.

Optionally, the apparatus 1400 and/or the apparatus 1500 may further include: and a presentation unit (not shown in the figure) configured to present the target comment sentence to the anchor after the acquisition unit acquires the comment sentence satisfying the broadcast filtering condition submitted in the target live broadcast as the target comment sentence.

Optionally, the apparatus 1400 and/or the apparatus 1500 may further include: and a storage unit (not shown in the figure) configured to store the broadcast filtering condition in correspondence with the identification information of the target live broadcast room in response to receiving the broadcast filtering condition set for the target live broadcast room.

Optionally, the voice providing unit 1403 and/or the voice providing unit 1503 as described before may be further configured to: and under the condition that the target live broadcast room is in the first live broadcast mode currently, providing prompt voice for the anchor broadcast in response to detecting that the audience user enters the target live broadcast room, wherein the prompt voice indicates that the audience user enters the live broadcast room.

Optionally, the speech conversion unit 1402 and/or the speech conversion unit 1502 as described before may also be configured to: before a voice providing unit provides a prompt voice, generating first prompt information according to the user identification of the audience user and a prompt information template; and converting the first prompt message into prompt voice.

Optionally, the apparatus 1400 and/or the apparatus 1500 may further include: an echo cancellation unit (not shown in the figure) configured to cancel an echo of the played speech using an acoustic echo cancellation algorithm during the playing of the speech to the anchor.

Optionally, the apparatus 1400 and/or the apparatus 1500 may further include: a determining unit (not shown in the figure) configured to determine whether the target comment sentence is a comment sentence of the praise class after the acquiring unit acquires the target comment sentence submitted in the target live broadcast; and the echo cancellation unit may be further configured to: and in response to the target comment statement not being the comment statement of the praise class, eliminating the echo of the comment voice by adopting an acoustic echo elimination algorithm.

Optionally, the apparatus 1400 and/or the apparatus 1500 may further include: and a live broadcast mode control unit (not shown in the figure) configured to provide second prompt information to the anchor in response to a start instruction for the anchor version APP where the target live broadcast room is located, wherein the second prompt information is used for prompting whether to start the first live broadcast mode.

Optionally, the live mode control unit may be further configured to: and in response to receiving first feedback information indicating that the first direct broadcasting mode is started, setting the current direct broadcasting mode of the target direct broadcasting room as the first direct broadcasting mode.

Optionally, the live mode control unit may be further configured to: and in response to receiving second feedback information which indicates that the first live broadcasting mode is not started, setting the current live broadcasting mode of the target live broadcasting room to be a second live broadcasting mode, wherein the second live broadcasting mode indicates common live broadcasting.

Optionally, the live mode control unit may be further configured to: and responding to a closing instruction aiming at the first live broadcasting mode, and setting the current live broadcasting mode of the target live broadcasting room as a second live broadcasting mode or quitting the anchor edition APP where the target live broadcasting room is located according to the closing instruction.

Optionally, the live mode control unit may be further configured to: responding to the closing instruction, and providing third prompt information for the anchor broadcast, wherein the third prompt information is used for prompting whether to quit the live broadcast; in response to receiving third feedback information indicating that the live broadcast does not exit, setting the current live broadcast mode of the target live broadcast room to be a second live broadcast mode; and exiting the main broadcasting version APP in response to receiving fourth feedback information indicating exiting the live broadcasting.

With further reference to fig. 16, the present specification provides an embodiment of a live broadcast room-based information processing apparatus, which may be applied to the server 103, the terminal device 104, or the main broadcast APP installed on the terminal device 104 shown in fig. 1.

As shown in fig. 16, the live-air-based information processing apparatus 1600 includes: an acquisition unit 1601 and an echo cancellation unit 1602. The acquiring unit 1601 is configured to acquire two paths of voice signals acquired by a voice acquiring device, wherein a terminal device where the voice acquiring device is located further includes a voice playing device and is provided with an anchor version APP, a target live broadcast room is opened in the anchor version APP, a first path of voice signal in the two paths of voice signals is the voice of the anchor of the target live broadcast room, and a second path of voice signal is an output signal of the voice playing device; the echo cancellation unit 1602 is configured to selectively cancel or retain the second path of speech signals.

With further reference to fig. 17, the present specification provides an embodiment of an information processing apparatus based on an e-commerce live broadcast room, which may be applied to a server, an anchor version APP or a terminal device where the anchor version APP is located in an e-commerce live broadcast scene.

As shown in fig. 17, the information processing apparatus 1700 based on the electricity merchant live broadcast of the present embodiment includes: an acquisition unit 1701, a voice conversion unit 1702, and a voice providing unit 1703. Wherein the obtaining unit 1701 is configured to obtain a target comment statement submitted within the live telecast room if the live telecast room is currently in the first live mode; the voice conversion unit 1702 is configured to convert the target comment sentence into a comment voice; the voice providing unit 1703 is configured to provide comment voice to a main cast of the live telecast.

With further reference to fig. 18, the present specification provides an embodiment of an information processing apparatus based on a government affairs live broadcast room, which may be applied to a terminal device where a server, a main broadcast version APP or a main broadcast version APP in a government affairs live broadcast scene is located.

As shown in fig. 18, the information processing apparatus 1800 based on the government affair live broadcast room according to the present embodiment includes: an acquisition unit 1801, a voice conversion unit 1802, and a voice providing unit 1803. The obtaining unit 1801 is configured to obtain a target comment statement submitted in a direct government affair broadcast room when the direct government affair broadcast room is currently in a first direct broadcast mode; the voice converting unit 1402 is configured to convert the target comment sentence into a comment voice; the voice providing unit 1803 is configured to provide a comment voice to a host of a government affair live room.

With further reference to fig. 19, the present specification provides an embodiment of an information processing apparatus based on an education live broadcast room, which can be applied to a server, an anchor version APP or a terminal device where the anchor version APP is located in an education live broadcast scene.

As shown in fig. 19, an information processing apparatus 1900 based on an education live room of the present embodiment includes: an acquisition unit 1901, a voice conversion unit 1902, and a voice providing unit 1903. Wherein the obtaining unit 1901 is configured to obtain a target comment sentence submitted in the education live broadcast room in a case where the education live broadcast room is currently in the first live broadcast mode; the voice conversion unit 1902 is configured to convert the target comment sentence into a comment voice; the voice providing unit 1903 is configured to provide commentary voice to a main broadcast of an education live room.

With further reference to fig. 20, the present specification provides an embodiment of an information processing apparatus based on a live conference room, where the apparatus may be applied to a server, an anchor APP, or a terminal device where the anchor APP is located in a live conference scene.

As shown in fig. 20, the information processing apparatus 2000 based on the live conference room of the present embodiment includes: an acquisition unit 2001, a voice conversion unit 2002, and a voice providing unit 2003. Wherein the acquiring unit 2001 is configured to acquire a target comment sentence submitted in the live conference room in a case where the live conference room is currently in the first live mode; the voice converting unit 2002 is configured to convert the target comment sentence into a comment voice; the voice providing unit 2003 is configured to provide comment voice to the anchor of the live conference room.

In the device embodiments corresponding to fig. 14 to 20, the specific processing of each unit and the technical effect thereof can refer to the related descriptions in the corresponding method embodiments, and are not repeated herein.

The present specification also provides a computer readable storage medium, on which a computer program is stored, wherein when the computer program is executed in a computer, the computer program causes the computer to execute the methods respectively described in the above method embodiments.

Embodiments of the present specification further provide a computing device, including a memory and a processor, where the memory stores executable codes, and the processor executes the executable codes to implement the methods respectively described in the foregoing method embodiments.

The present specification also provides a computer program product, which when executed on a data processing apparatus, causes the data processing apparatus to implement the methods respectively described in the above method embodiments.

Those skilled in the art will recognize that the functionality described in the various embodiments disclosed herein may be implemented in hardware, software, firmware, or any combination thereof, in one or more of the examples described above. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.

In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The above-mentioned embodiments, objects, technical solutions and advantages of the embodiments disclosed in the present specification are further described in detail, it should be understood that the above-mentioned embodiments are only specific embodiments of the embodiments disclosed in the present specification, and are not intended to limit the scope of the embodiments disclosed in the present specification, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the embodiments disclosed in the present specification should be included in the scope of the embodiments disclosed in the present specification.

Claims

1. An information processing method based on a live broadcast room comprises the following steps:

under the condition that a target live broadcast room is in a first live broadcast mode currently, obtaining comment sentences which are submitted in the target live broadcast room and meet broadcast screening conditions, and using the comment sentences as target comment sentences, wherein the broadcast screening conditions are set for the target live broadcast room;

converting the target comment sentence into comment voice;

and providing the comment voice to the anchor of the target live broadcast room.

2. The method according to claim 1, wherein an execution subject of the method comprises a main broadcast version APP where the target live broadcast room is located; and

the providing the comment voice to the anchor of the target live broadcast room includes:

and playing the comment voice to the anchor.

3. The method of claim 1, wherein an execution subject of the method comprises a server; and

and sending the comment voice to an anchor version APP where the target live broadcast room is located, so that the anchor version APP plays the comment voice to the anchor.

4. The method of claim 1, wherein the obtaining comment statements submitted in the target live broadcast room and meeting the report screening condition comprises:

acquiring a plurality of comment sentences submitted in the target live broadcast room in the previous period of the current period;

and selecting the comment sentences meeting the broadcast screening condition from the comment sentences.

5. The method according to claim 4, wherein the broadcast screening condition comprises a preset value which is related to a live broadcast theme of the target live broadcast room and appears before the ranking of the frequency; and

the selecting the comment sentences meeting the broadcast screening condition from the comment sentences comprises:

acquiring the occurrence frequency of different comment sentences in the comment sentences and the correlation degree of the comment sentences and the live topic;

and selecting the comment sentences meeting the broadcast screening conditions from the different comment sentences according to the acquired occurrence frequency and the acquired relevancy.

6. The method according to claim 1, wherein after the obtaining of comment sentences meeting a report filtering condition submitted in the target live broadcast room as target comment sentences, the method further comprises:

providing the target comment statement to the anchor.

7. The method of claim 1, wherein the method further comprises:

and responding to the received broadcast screening conditions set aiming at the target live broadcast room, and correspondingly storing the received broadcast screening conditions and the identification information of the target live broadcast room.

8. The method of claim 1, wherein the method further comprises:

and under the condition that the target live broadcast room is in a first live broadcast mode currently, providing prompt voice for the anchor broadcast in response to detecting that the audience user enters the target live broadcast room, wherein the prompt voice indicates that the audience user enters the live broadcast room.

9. The method of claim 8, wherein prior to said providing a prompt voice to said anchor, said method further comprises:

generating first prompt information according to the user identification of the audience user and a prompt information template;

and converting the first prompt message into the prompt voice.

10. The method of one of claims 1-9, wherein, during playing of speech to the anchor,

and eliminating the echo of the played voice by adopting an acoustic echo elimination algorithm.

11. The method according to claim 10, wherein after the obtaining of the comment sentences meeting the report filtering condition submitted in the target live broadcast room as the target comment sentences, the method further comprises:

determining whether the target comment statement is a comment statement of a praise class; and

the eliminating the echo of the played voice by adopting the acoustic echo eliminating algorithm comprises the following steps:

and in response to the target comment sentence not being a comment sentence of the praise class, eliminating the echo of the comment voice by adopting an acoustic echo elimination algorithm.

12. The method according to claim 1, wherein in a case that the target live broadcast room is currently in the first live broadcast mode, before obtaining comment sentences meeting the broadcast filtering condition submitted in the target live broadcast room as target comment sentences, the method further comprises:

responding to a starting instruction of an anchor version APP where the target live broadcast room is located, and providing second prompt information for the anchor, wherein the second prompt information is used for prompting whether the first live broadcast mode is started or not.

13. The method of claim 12, wherein the method further comprises:

and in response to receiving first feedback information indicating that the first direct broadcasting mode is started, setting the current direct broadcasting mode of the target direct broadcasting room to be the first direct broadcasting mode.

14. The method of claim 12, wherein the method further comprises:

and in response to receiving second feedback information indicating that the first live broadcasting mode is not started, setting the current live broadcasting mode of the target live broadcasting room to be a second live broadcasting mode, wherein the second live broadcasting mode represents common live broadcasting.

15. The method of claim 1, wherein the method further comprises:

responding to a closing instruction aiming at the first live broadcast mode, and setting the current live broadcast mode of the target live broadcast room to be a second live broadcast mode or quitting an anchor version APP where the target live broadcast room is located according to the closing instruction, wherein the second live broadcast mode represents common live broadcast.

16. The method of claim 15, wherein after the responding to the shutdown instruction for the first direct broadcast mode, the method further comprises:

providing third prompt information to the anchor, wherein the third prompt information is used for prompting whether to quit the live broadcast; and

the step of setting the current live broadcast mode of the target live broadcast room to be the second live broadcast mode or quitting the main broadcast version APP where the target live broadcast room is located according to the closing instruction comprises the following steps:

in response to receiving third feedback information indicating that the live broadcast does not exit, setting the current live broadcast mode of the target live broadcast room to be a second live broadcast mode;

and exiting the main broadcast APP in response to receiving fourth feedback information indicating exiting the live broadcast.

17. An information processing method based on a live broadcast room comprises the following steps:

under the condition that a target live broadcast room is in a first live broadcast mode currently, acquiring target comment sentences submitted in the target live broadcast room;

converting the target comment sentence into comment voice;

18. An information processing method based on a live broadcast room comprises the following steps:

acquiring two paths of voice signals acquired by a voice acquisition device, wherein the terminal equipment where the voice acquisition device is located further comprises a voice playing device and an anchor version APP, the anchor version APP opens a target live broadcast room, the first path of voice signal in the two paths of voice signals is the anchor voice of the target live broadcast room, and the second path of voice signal is the output signal of the voice playing device;

and selectively eliminating or reserving the second path of voice signals.

19. An information processing method based on an E-commerce live broadcast room comprises the following steps:

under the condition that a live telecast room is in a first live telecast mode at present, acquiring target comment sentences submitted in the live telecast room;

converting the target comment sentence into comment voice;

and providing the comment voice to a main broadcasting of the E-commerce live broadcast room.

20. An information processing method based on a government affair live broadcast room comprises the following steps:

under the condition that a government affair live broadcasting room is in a first direct broadcasting mode at present, acquiring target comment sentences submitted in the government affair live broadcasting room;

converting the target comment sentence into comment voice;

and providing the comment voice to a host of the government affair live broadcast room.

21. An information processing method based on an education live broadcast room comprises the following steps:

under the condition that an education live broadcasting room is in a first live broadcasting mode currently, target comment sentences submitted in the education live broadcasting room are obtained;

converting the target comment sentence into comment voice;

and providing the comment voice to a main broadcasting of the education live broadcasting room.

22. An information processing method based on a conference live room comprises the following steps:

under the condition that a conference live broadcast room is in a first live broadcast mode currently, acquiring target comment sentences submitted in the conference live broadcast room;

converting the target comment sentence into comment voice;

and providing the comment voice to the anchor of the conference live room.

23. An information processing apparatus based on a live broadcast room, comprising:

the device comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire comment sentences which are submitted in a target live broadcast room and meet broadcast screening conditions as target comment sentences under the condition that the target live broadcast room is currently in a first live broadcast mode, and the broadcast screening conditions are set for the target live broadcast room;

a voice conversion unit configured to convert the target comment sentence into a comment voice;

a voice providing unit configured to provide the comment voice to a host of the target live broadcast room.

24. An information processing apparatus based on a live broadcast room, comprising:

the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire a target comment statement submitted in a target live broadcast room under the condition that the target live broadcast room is currently in a first live broadcast mode;

25. An information processing apparatus based on a live broadcast room, comprising:

the device comprises an acquisition unit, a voice playing unit and a terminal device, wherein the acquisition unit is configured to acquire two paths of voice signals acquired by a voice acquisition device, the terminal device where the voice acquisition device is located further comprises the voice playing device and is provided with an anchor version APP, a target live broadcast room is opened in the anchor version APP, a first path of voice signal in the two paths of voice signals is the voice of an anchor of the target live broadcast room, and a second path of voice signal is an output signal of the voice playing device;

and the echo cancellation unit is configured to selectively cancel or reserve the second path of voice signals.

26. An information processing device based on an E-commerce live broadcast room comprises:

the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire a target comment statement submitted in a live telecast room under the condition that the live telecast room is currently in a first live broadcasting mode;

a voice providing unit configured to provide the comment voice to a host of the live telecast.

27. An information processing device based on a government affair live broadcast room comprises:

the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to respond to that a government affair live broadcasting room is currently in a first live broadcasting mode, and acquire target comment sentences submitted in the government affair live broadcasting room;

a voice providing unit configured to provide the comment voice to a host of the government affair live broadcasting room.

28. An information processing apparatus based on an education live room, comprising:

an acquisition unit configured to acquire a target comment sentence submitted in an education live broadcast room in a case where the education live broadcast room is currently in a first live broadcast mode;

a voice providing unit configured to provide the comment voice to a host of the education live broadcast room.

29. An information processing device based on a conference live room comprises:

the conference live broadcasting system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire a target comment statement submitted in a conference live broadcasting room under the condition that the conference live broadcasting room is currently in a first live broadcasting mode;

a voice providing unit configured to provide the comment voice to a host of the live conference room.

30. A computer-readable storage medium, on which a computer program is stored, wherein the computer program causes a computer to carry out the method of any one of claims 1-22 when the computer program is carried out in the computer.

31. A computing device comprising a memory and a processor, wherein the memory has stored therein executable code that when executed by the processor implements the method of any of claims 1-22.