CN113301360A

CN113301360A - Information prompting method, computing device and storage medium

Info

Publication number: CN113301360A
Application number: CN202010898365.6A
Authority: CN
Inventors: 卢孩
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2020-08-31
Filing date: 2020-08-31
Publication date: 2021-08-24
Anticipated expiration: 2040-08-31
Also published as: CN113301360B

Abstract

The embodiment of the application provides an information prompting method, a computing device and a storage medium. In the embodiment of the application, a plurality of information is received, wherein the information is information provided by a user in a video live broadcast process; classifying the plurality of information; and determining information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the live video replies based on the prompted information. The information is classified to generate various types of information, and then the information to be prompted is determined according to the information in the categories. For example, a larger amount of information may be considered to determine the information to be prompted, and thus, the anchor may reply based on the prompted information. The method and the device can improve the interaction efficiency in live video and reduce the omission problem caused by excessive interaction information. Meanwhile, the experience of a user watching live video is improved.

Description

Information prompting method, computing device and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method for prompting information, a computing device, and a storage medium.

Background

With the rapid development of the internet, the internet can provide various services for users, such as online games, online ticket booking, online shopping, online live broadcasting and the like. In some services, interaction between users is required. Such as live online services, there is an interaction between the anchor and the viewing user. However, in the interaction, if the number of users is large, the number of the interaction information is also large, and some interaction information is inevitably missed by the anchor, so that the interaction effect is reduced.

Disclosure of Invention

Aspects of the present disclosure provide an information prompting method, a computing device, and a storage medium, which are used to effectively prompt information to improve interaction efficiency.

The embodiment of the application provides an information prompting method, which comprises the following steps: receiving a plurality of information, wherein the information is provided by a user in a video live broadcast process; classifying the plurality of information; and determining information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the live video replies based on the prompted information.

The embodiment of the present application further provides a method for prompting information, including: receiving a plurality of information, wherein the information is provided by a user in a video live broadcast process; classifying the plurality of information; and determining information needing to be prompted according to the classified information in the category so as to send the information to the corresponding terminal and display the information, so that the anchor of the live video replies based on the prompted information.

The embodiment of the present application further provides a method for prompting information, including: receiving a plurality of information, wherein the information is provided by a user in the voice live broadcast process; classifying the plurality of information; and determining the information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the voice live broadcast replies based on the prompted information.

An embodiment of the present application further provides a computing device, including: a memory, a processor, and a communication component; the memory for storing a computer program; the communication component is used for receiving a plurality of information, and the information is information provided by a user in a video live broadcast process; the processor to execute the computer program to: classifying the plurality of information; and determining information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the live video replies based on the prompted information.

An embodiment of the present application further provides a computing device, including: a memory, a processor, and a communication component; the memory for storing a computer program; the communication component is used for receiving a plurality of information, and the information is information provided by a user in a voice live broadcast process; the processor to execute the computer program to: classifying the plurality of information; and determining the information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the voice live broadcast replies based on the prompted information.

An embodiment of the present application further provides a computing device, including: a memory, a processor, and a communication component; the memory for storing a computer program; the communication component is used for receiving a plurality of information, and the information is information provided by a user in a voice live broadcast process; the processor to execute the computer program to: classifying the plurality of information; and determining information needing to be prompted according to the classified information in the category so as to send the information to the corresponding terminal and display the information, so that the anchor of the live video replies based on the prompted information.

Embodiments of the present application also provide a computer-readable storage medium storing a computer program, which when executed by one or more processors causes the one or more processors to implement the steps of the above-mentioned method.

In the embodiment of the application, a plurality of information is received, wherein the information is information provided by a user in a video live broadcast process; classifying the plurality of information; and determining information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the live video replies based on the prompted information. The information is classified to generate various types of information, and then the information to be prompted is determined according to the information in the categories. For example, a larger amount of information may be considered to determine the information to be prompted, and thus, the anchor may reply based on the prompted information. The method and the device can improve the interaction efficiency in live video and reduce the omission problem caused by excessive interaction information. Meanwhile, the experience of a user watching live video is improved.

Similarly, except live video, also can be used to live voice for improve this kind of interactive efficiency in live voice, promote user's experience.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

FIG. 1 is a schematic structural diagram of an information prompting system according to an exemplary embodiment of the present application;

fig. 2 is a flowchart illustrating a method for prompting information according to an exemplary embodiment of the present application;

FIG. 3 is a schematic interface diagram of interaction information in an exemplary implementation of the present application;

FIG. 4 is a schematic interface diagram of a prompted message according to an exemplary embodiment of the present application;

FIG. 5 is a schematic interface diagram of interaction information for improving conversion according to an exemplary embodiment of the present application;

FIG. 6 is a schematic interface diagram of interaction information of a target user according to an exemplary embodiment of the present application;

FIG. 7 is a flowchart illustrating a method for presenting information according to another exemplary embodiment of the present application;

FIG. 8 is a flowchart illustrating a method for presenting information according to another exemplary embodiment of the present application;

FIG. 9 is a schematic structural diagram of a message prompt apparatus according to an exemplary embodiment of the present application;

FIG. 10 is a schematic structural diagram of a message prompt device according to yet another exemplary embodiment of the present application;

FIG. 11 is a schematic structural diagram of a message prompt device according to another exemplary embodiment of the present application;

FIG. 12 is a schematic block diagram of a computing device provided in an exemplary embodiment of the present application;

FIG. 13 is a schematic block diagram of a computing device provided in an exemplary embodiment of the present application;

fig. 14 is a schematic structural diagram of a computing device according to an exemplary embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Based on the background technology, the video anchor can interact with the anchor in the live broadcast process, such as sending a problem according to the commodity condition in the video live broadcast, and the video anchor needs to reply the problem of the user to interact with the anchor, so that the user watching the live broadcast can be retained. However, in the process of broadcasting by the anchor, the following problems occur when a question in the user comment is replied: when the anchor answers the questions one by one, the flow of talking and broadcasting the commodities is influenced. But the gap reply to the current question may not be comprehensive enough, resulting in inefficient reply to the user question. If the anchor pays attention to the questions in the user comments and memorizes the questions at all times, and answers the questions after the commodity is spoken, the memory cost is high.

Fig. 1 is a schematic structural diagram of an information prompt system according to an exemplary embodiment of the present application. As shown in fig. 1, the system 100 may include: a first device 101, a second device 102 and a third device 103.

The first device 101 may be a device with certain computing capability, and may implement a function of sending data to the third device 103 and acquiring data from the third device 103. The basic structure of the first device 101 may include: at least one processor. The number of processors may depend on the configuration and type of device with a certain computing power. A device with certain computing capabilities may also include Memory, which may be volatile, such as RAM, non-volatile, such as Read-Only Memory (ROM), flash Memory, etc., or both. The memory typically stores an Operating System (OS), one or more application programs, and may also store program data and the like. In addition to the processing unit and the memory, the device with certain computing capabilities also includes some basic configurations, such as a network card chip, an IO bus, a display component, and some peripheral devices. Alternatively, some peripheral devices may include, for example, a keyboard, a stylus, and the like. Other peripheral devices are well known in the art and will not be described in detail herein. Alternatively, the first device 101 may be a smart terminal, such as a mobile phone, a desktop computer, a notebook, a tablet computer, and the like.

The number of the first devices 101 may be plural.

The third device 103 refers to a device that can provide a computing processing service in a network virtual environment, and may refer to a device that performs live broadcast (e.g., video live broadcast) using a network. In physical implementation, the third device 103 may be any device capable of providing a computing service, responding to a service request, and performing live video, and may be, for example, a cloud server, a cloud host, a virtual center, a conventional server, and the like. The third device 103 mainly includes a processor, a hard disk, a memory, a system bus, and the like, and is similar to a general computer architecture.

The second device 102 may be a device with certain computing capability, and may implement a function of sending data to the third device 103 and acquiring data from the third device 103. The specific implementation form is similar to that of the first device 101, and is not described here again.

In this embodiment of the application, the second device 102 may send a video live broadcast request to the third device 103, and the third device 103 may respond to the request and start receiving live video sent by a main broadcast corresponding to the second device 102. The first device 101 may send a video live broadcast watching request to the third device 103, and the third device 103 sends the live broadcast video to the first device 101 in response to the request, so that a user of the first device 101, that is, a user watching a video live broadcast, watches the video live broadcast. Therefore, the user can watch the live video.

Based on this, the user of the first device 101 may send information, i.e. interactive information, through the respective device. The first device 101 acquires information in response to an input operation by a user, and transmits the information to the third device 103 in response to a transmission operation. The third device 103 then sends the information to the second device 102. The second device 102 receives a plurality of information, wherein the information is information provided by a user in a video live broadcast process; classifying the plurality of information; and determining information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the live video replies based on the prompted information.

Specifically, the second device 102 classifies a plurality of information according to the semantics of the information.

Specifically, the second device 102 sorts the classified categories according to the number corresponding to the information in the classified categories; selecting a preset number of categories from the side with the largest number based on the sorting result; and determining information needing prompting based on the selected category so as to display the information.

In addition, the system 100 may also realize presentation of information in the following execution manner in addition to the above execution manner.

Based on the fact that the user has watched the live device through the respective device, the first device 101 can still send information to the third device 103, which will not be repeated here. The third device 103 receives a plurality of information, wherein the information is information provided by the user in the video live broadcast process; directly classifying a plurality of information; and determining the information needing to be prompted according to the classified information in the categories. Then, the third device 103 sends the prompted information to the second device 102 and displays the prompted information, so that the anchor of the live video replies based on the prompted information.

It should be noted that the third device 103 may send normal information to the second device 102 for displaying as usual.

In the video live broadcast application scenario of the embodiment of the application, a second device 102, such as a host computer, and a third device 103, such as a video live broadcast server (hereinafter, may be referred to as a server for short), perform network connection, and send a video live broadcast request, where the server responds to the request and receives a live broadcast video sent by the host computer. The server may also receive a live video viewing request sent by a first device 101 of a user, such as a mobile phone, where the live video viewing request may carry an ID of a main broadcast, the server responds to the viewing request, sends a live video of the main broadcast to the mobile phone of the user, and the mobile phone receives the live video and plays the live video.

Based on the method, a plurality of users can watch the live video through respective mobile phones. The user can interact with the anchor by sending information. The user can watch live video through the APP (application) installed on the mobile phone and watching live video, and inputs interactive information on a live video interface provided by the APP, for example, the current clothes are still replenished. And the user carries out sending operation on the interface, and the APP can respond to the operation through the mobile phone and send the interaction information to the server. And after receiving the interaction information, the server forwards the interaction information to the computer of the anchor.

The computer of the anchor can receive a large amount of interactive information sent by a plurality of users through the installed live video client. And the client classifies the interactive information according to the voice of the interactive information. Various types of interaction information can be obtained. Each type of interaction information may represent a type of semantics. As is the current clothes being restocked. Then, the client can sort the information from large to small according to the amount of the interactive information in each class. A preset number of categories, such as the first two categories, may be selected based on the preset number, starting from the side with the largest number according to the sorting result. The client can randomly select one interactive message from the two categories respectively to be displayed as a message needing prompting, so that the anchor can watch the message through a computer, and voice response or character response is carried out based on the displayed interactive message. And then the server returns to the mobile phone of the user so that the user can watch the mobile phone.

In addition, the client can still normally display the common (or normal) interaction information, that is, the interaction information that is not processed is forwarded to the anchor computer by the server, and the specific forwarding process has already been described above, and will not be described herein again.

In addition, the above processing procedure of the interactive information may also be executed by the server. The processing procedure of the server is similar to that of the client of the anchor, and thus, the processing procedure is not repeated excessively. Only the description is as follows: and after determining the prompted information, the server sends the information to the client of the anchor and the client shows the information through the computer of the anchor. Similarly, the server can still forward the common interaction information to the client for display. The server can also receive the reply information of the anchor sent by the client to the mobile phone of the user.

It should be noted that the system 100 can also be applied to live voice broadcast, and the implementation process is similar, and will not be described here again.

In the present embodiment described above, the first device 101, the second device 102, and the third device 103 make network connections, which may be wireless connections. If the first device 101, the second device 102, and the third device 103 are communicatively connected, the network format of the mobile network may be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G + (LTE +), WiMax, and 5G.

The following describes the information prompting process in detail with reference to the method embodiment.

Fig. 2 is a flowchart illustrating a method for prompting information according to an exemplary embodiment of the present application. The method 200 provided by the embodiment of the present application is executed by a computing device, such as an intelligent terminal, for example, a computer or a mobile phone. The method 200 comprises the steps of:

201: and receiving a plurality of information, wherein the information is information provided by a user in the video live broadcast process.

202: a plurality of information is classified.

203: and determining information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the live video replies based on the prompted information.

The following is detailed for the above steps:

The information can be interactive information in live video, and a user, namely a user watching the live video, sends the interactive information to a main broadcast of the live video in the process of watching the live video. The interactive information may be questions, suggestions, introduction of articles, and the like related to the live video, such as user a sending "whether the current clothing is still restocked".

For example, as described above, a live video anchor for online shopping is connected to a live video server, which may be referred to as a server hereinafter, through a live video client installed on a computer of the live video anchor and the live video server. Namely, the anchor logs on the client and sends a video live broadcast request to the server, and the server responds to the request to start live broadcast and receives live broadcast video sent by the anchor. The live video may be composed of video images.

The user watching the live video can be in network connection with the server through the APP installed on the mobile phone and used for watching the live video. The user can log in the APP and send a request for watching live broadcast to the server through the APP, where the request can carry the ID of the anchor or the number of the live broadcast room where the anchor is located. And the server responds to the watching request and sends the live video corresponding to the anchor to the APP of the mobile phone of the user so as to watch the live video through the respective mobile phone of the user. It should be understood that there may be multiple users watching a live video, and that each user's manner of watching the live video is similar.

After the APP of the user mobile phone receives the live broadcast video of the anchor, the live broadcast can be watched, and the anchor can be live broadcast along with the live broadcast flow of the anchor, such as selling of clothes. At this time, the APP may provide a viewing interface for live video to enable a user to view on the viewing interface. In addition, the interface provides an interaction area for interacting with the anchor. The user can enter interactive information in the interactive region, such as "whether the current clothing is still restocked". The APP responds to the input operation, acquires the interactive information, responds to the sending operation of the user, and sends the interactive information to the server. The server can send the interaction information to the client side of the anchor for display. Meanwhile, the server also sends the received interactive information to the APP of the mobile phone of the user, so that the user can see the interactive information in the interface.

Correspondingly, the client of the anchor can also display the received interactive information through an interface. FIG. 3 illustrates a presentation interface 300 for interactive information. In the interface 300, an introduction area 301 of the number of users is shown, and the number of people who have watched the live broadcast currently, i.e., the number of site viewers 233444, is shown in the introduction area 301. The number of people currently watching the live broadcast, i.e., the number of people online, 29341 people. The new number of people who paid attention to the anchor, i.e., new meal, 3999 people.

In addition, the interface 300 also shows an information area 302 for the item currently being introduced live. In the product information area 302, a product image 3022, a product name "Xx sweater" 3026, a product price: live price "899.98" 3027. A point of sale icon 3025 of the point of sale of the item, as well as a point of sale "face-lift, skin-friendly icon" 3023 and "no lower with double 11, 618" 3024 of the item 12 may also be displayed in the information area 302 of the item.

In addition, the interface 300 also shows an interactive information area 303, and the interactive information 3031 sent by the user can be shown in the interactive information area 303 in a scrolling manner, for example, "user a: what the quality of the baby # 1 is "enables the anchor to view, and performs voice response or text response according to the interactive information 3031 provided by the user. The client can respond to the reply operation, such as voice reply, directly acquire the live video and send the live video to the user for watching. It should be understood that the anchor can accompany the video when performing voice reply, so that the user's voice does not need to be specially captured when performing voice reply, and only the live video broadcast needs to be performed normally.

It should be noted that, in addition to the display areas, an area 3041 where the merchandise needs to be introduced additionally may be displayed in the interface 300, and a merchandise picture 3041 which needs to be presented again by an anchor may be displayed in the area 3041. The anchor may supplement the introduction of the merchandise again based on the merchandise images 3041.

202: a plurality of information is classified.

The classification of information means that information belonging to a category, the same information, or similar information is classified into a category.

In the process of live video, a large number of users watching live video may have a lot of interactive information. However, the anchor may not be able to view every piece of information when viewing the interactive information, or even if every piece of information is viewable, it takes a lot of time to reply, which may cause problems to be missed. The interactive information reply effect is improved, the time cost of the anchor is reduced, the user experience is improved, the interactive information can be classified, multiple types of problems are generated, and reply can be performed on each type of problems.

When the interactive information is classified, the interactive information can be specifically divided according to the semantics of the interactive information.

Specifically, classifying a plurality of pieces of information includes: and classifying the plurality of information according to the semantics of the information.

For example, the client of the anchor receives a large amount of interaction information, and can classify the interaction information within a preset time. Such as interactive information received within 20 seconds. And performing semantic recognition on the interactive information, and then dividing the interactive information with the same or similar semantics into a class. Thereby generating a plurality of types of interactive information.

More specifically, classifying a plurality of information according to the semantics of the information includes: determining the similarity of any two pieces of information in the plurality of pieces of information according to the semantics of the information; and when the similarity meets the similarity threshold, dividing the corresponding information into one class, thereby generating at least one class.

The semantic determination mode may be: and performing word segmentation processing on each piece of information to obtain at least one word segmentation, and determining a word vector of each word segmentation in each piece of information according to a preset word vector model. And combining the word vectors according to the sequence of combining the word segments into the information to obtain the vector representing the information.

The dividing mode may be that, according to a clustering algorithm, vectors of the obtained information are clustered, and information corresponding to vectors with the same vectors or within a similar threshold value is divided together. Wherein, the clustering algorithm may include: k-means, K-means Clustering algorithm and DBSCAN (sensitivity-Based Spatial Clustering of Applications with Noise, Density-Based Clustering method with Noise).

For example, as can be seen from the foregoing, the client may perform word segmentation and clustering on the interaction information acquired within 20 seconds according to the above manner, and may compare vectors of two pairs of interaction information in the clustering process. Therefore, various types of interaction information are obtained for prompt display.

It should be noted that after obtaining multiple types of interactive information, the interactive information meanings represented by the various types of interactive information can be directly displayed, so that the anchor can watch and reply.

However, since the interactive information of each category is directly displayed, the interactive information is too much, so that the anchor is difficult to reply, and the interactive information of each category can be selected to select meaningful interactive information from the interactive information so as to reply the anchor.

Based on the foregoing, since the interactive information is filtered under the condition that there is a lot of interactive information in each category, for example, the filtering can be performed according to the number of the interactive information in each category. Such as to screen out a greater number of categories. To be presented in a presentation interface of the client of the anchor.

Specifically, according to the classified information in the category, the information needing to be prompted is determined, and the method includes the following steps: sorting the classified classes according to the number corresponding to the information in the classified classes; selecting a preset number of categories from the side with the largest number based on the sorting result; and determining information needing prompting based on the selected category so as to display the information.

Based on the selected category, the manner of determining the information to be prompted may be: and randomly selecting one piece of interaction information from the corresponding category to display. Or selecting the interactive information with the least word number from the corresponding categories for displaying.

For example, as described above, the client of the anchor counts the amount of interaction information in each category. And the categories can be sorted according to the sequence of the number from large to small or the sequence of small to large. A preset number of categories, such as the top 3 categories with the largest number, are selected from the end with the largest number. Alternatively, a number of categories greater than 5 are selected. Thereby determining the corresponding interactive information and displaying the interactive information to the anchor.

It should be noted that, in addition to determining the information to be presented according to the number, the information to be presented may also be determined according to the conversion rate of the information corresponding to each category. For example, by determining which category or categories (satisfying a preset number), the information conversion rate can be increased, so that the corresponding category is selected and the information of the corresponding category is displayed. The selection may be in the form of a sort.

Or, the category with the specific gravity larger than the threshold value or the maximum specific gravity or the categories with the preset number of specific gravities larger may be selected by the specific gravity of the information provided by the VIP user in each category in the category information, and the information of the corresponding category is displayed. The selection may be in the form of a sort.

Specifically, according to the classified information in the category, the information needing to be prompted is determined, and the method includes the following steps: selecting corresponding categories which are larger than a quantity threshold value according to the quantity corresponding to the information in the classified categories; and determining the information needing to be prompted according to the selected category so as to display the information.

For example, according to the foregoing, the client of the anchor can count the number of the interactive information in each category respectively. The categories with the number larger than 5 are directly selected for showing.

As can be seen from the foregoing, the information may be determined by the above-described conversion rate and VIP ratio. Similarly, the corresponding category larger than the threshold, such as larger than the conversion rate threshold, or larger than the VIP ratio threshold, may be selected, and will not be described herein again.

The display mode can be as follows: the method 200 further comprises: and displaying information needing prompting on a preset area in a video live interface of the main broadcast.

Wherein fig. 4 shows a presentation interface 400 for prompted information. Outside the various regions of the interface 300 of fig. 3, the interface 400 may display a prompt message, i.e., the aforementioned screened interactive message 401, in the interactive message region 303. If the number 15 baby is returned with the goods, the number 18 baby is returned with the goods, and the number 20 baby is returned with the goods.

In order to enable the anchor to reply the interactive information in a better targeted manner, the interactive information can be shown and proposed by several users after the screened interactive information is shown.

Specifically, the method 200 further includes: and displaying the number of the prompted information in the corresponding category as the number of the users.

For example, as described above, the client of the anchor determines the amount of interactive information in each category. And after the information needing to be prompted is determined, displaying the information, and simultaneously displaying the number corresponding to the information.

As shown in fig. 4, in addition to the screened interactive information 401, the interactive information area 303 in the interface 400 also shows the number of users corresponding to the information, i.e. the number of interactive information 402 in the category to which the information belongs, such as "6" audience.

After information needing prompting is displayed, the main intention of the information can be quickly understood by a main broadcaster. Keywords in the information may also be labeled.

Specifically, the method 200 further includes: after determining the information needing to be prompted, determining key information in the information; in the case of the presentation of information, the key information is highlighted.

The highlighting is a display mode in which the key information can be distinguished from other information, and the key information is displayed, such as highlight display, bold display, underline display, colored display, and the like.

The key information refers to a keyword in the information. The key information may be determined in such a manner that the key information is recognized by presetting a recognition model. The model creation mode may be that the model is created by a server or a client. If the model is created by the server, the client can acquire the created model from the server to identify, or send information to the server to identify the model deployed in the server, and then return the identified key information to the client. The specific creation process may be: training data is obtained, which may be historical data, such as a large amount of interactive information of the user. Or a large number of words and sentences in a preset word and sentence library. And then marking out key information in each word or sentence or interactive information. And as training data of a Neural Network model, the Neural Network model may be CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks), and the like. And determining weight parameters in the neural network through training to obtain a trained model. Therefore, the information for prompting can be sent to the trained model, and key information in the information can be obtained. Such as keywords, restocking.

And when the information needing to be prompted is displayed, highlighting or bolding and underlining the key information. As shown in fig. 4, the interactive information 401 screened out in the interface 400 is, for example, "baby 15 has returned to replenishment", wherein the keywords "baby" and "replenishment" are shown in bold and underlined.

In addition, the method 200 further comprises: displaying information needing to be prompted, responding to the reply operation of the anchor and receiving reply information of the anchor; the reply information is provided to the user.

Since the foregoing has been set forth, further description is omitted herein.

Except that the interactive information is clustered and selected in a screening mode, the interactive information can be displayed in the following mode in order to improve the experience of the user and improve the live broadcast delivery efficiency of the live broadcast.

Specifically, the method 200 further includes: inputting a plurality of information into a preset model to obtain corresponding information, wherein the corresponding information can be used for improving the conversion rate of the information; and using the obtained corresponding information as information needing to be prompted.

Wherein, the conversion rate of the information refers to the rate of the interactive information converted into the purchasing power or profit.

The pre-set model refers to interactive information for enabling a determination of an increase in the conversion rate. The specific training model and deployment method are similar to those described above, and are not described here again. Only the description is as follows: the interactive information in the historical video live broadcast can be used as training data. The interactive information which plays a role in conversion can be used as forward data of training data. That is, after the user proposes the interactive information, the anchor replies the question, and the user makes a purchase. Thus, as the training data of the Neural Network model, the Neural Network model may be CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks), or the like. And determining weight parameters in the neural network through training to obtain a trained model.

For example, according to the foregoing, after the client acquires the interaction information, the client inputs the interaction information into the preset model, so as to obtain the interaction information for improving the conversion rate. The client displays the interactive information.

FIG. 5 shows a presentation interface 500 of interactive information for improved conversion. In addition to the screened interactive information 401, the interactive information area 303 of the interface 500 also displays interactive information 501 for improving the conversion rate, such as "user D: how this color is collocated ". Wherein, the 'collocation' keyword can be displayed by highlighting.

In addition, the interactive information can be displayed according to the characteristics or the characteristics of the user.

Specifically, the method 200 further includes: determining a user grade according to account information of a user; and selecting a target user according to the user grade, and taking the information corresponding to the target user as the information needing to be prompted.

For example, according to the foregoing, after receiving the interaction information, the client may acquire and identify an account of the user corresponding to the interaction information, so as to determine the level of the account of the user. For example, user a belongs to a VIP (guest) user, a super user, and so on. The interactive information of the user A is displayed as the information needing prompting.

Fig. 6 illustrates a presentation interface 600 of the interaction information of the target user. In addition to the screened interactive information 401 and the interactive information 501 for improving the conversion rate, the interactive information area 303 in the interface 600 also shows the interactive information 601 "user E: is this baby unavailable? ". The "user E" and the "purchase" may be keywords, and are displayed by highlighting.

Specifically, the method 200 further includes: determining the consumption condition of the live video broadcast of a user within preset historical time; and selecting a target user according to the consumption condition, and taking the information corresponding to the target user as information needing prompting.

For example, according to the foregoing, the client may perform statistics on the purchase condition of the commodity according to the consumption condition of the user in the historical live video data. For example, the purchase amount of the user in the video live broadcast in the last month is counted, and the user with the purchase amount exceeding the threshold value is taken as the target user. Therefore, after the interactive information of the target user is received, the interactive information is directly displayed.

It should be noted that, when performing statistics on target users, in order to further refine the users, statistics may be performed according to different types of commodities, such as furniture, snacks, skin care products, and the like, and the user purchase conditions are respectively determined, so as to select target users corresponding to different commodity types. Therefore, when the video is live broadcast, the target user is selected according to different commodities.

In order to display the interactive information more comprehensively, the received interactive information can be continuously displayed.

Specifically, the method 200 further includes: and displaying the received interactive information.

For example, according to the foregoing, after receiving the interactive information sent by the server, the client may continue to directly display the received interactive information on the basis of displaying the information that needs to be prompted. Enabling selective viewing by the anchor. And meanwhile, the experience of the user and the anchor is improved.

It should be noted that any kind of interactive information can be displayed in the corresponding display area, such as the aforementioned interactive information area 303. In the interactive information area 303, a plurality of display positions may be set, and most of the information provided for the prompt is provided, and a small part of the information is provided for the normal interactive information. If the display positions can be 5, the prompted information can occupy 3 display positions, and the normal interaction information can occupy 2 display positions.

In order to highlight the prompted information, the prompted information and the normally displayed interactive information can be better distinguished in the display time.

Specifically, the method 200 further includes: the display time of the received interactive information is less than the display time of the prompted information.

For example, according to the foregoing, after receiving the interactive information, the client may directly display the interactive information on the corresponding display position in a scrolling manner. In addition, the client can display the information needing prompting on the corresponding display position in a rolling mode. The scrolling time of the prompted information is slower than the scrolling time of the interactive information directly presented. So as to improve the display time of the prompted information.

In order to facilitate the response of the anchor to the interactive information and the prompted information, a function can be provided, so that the anchor can mark the corresponding interactive information and the prompted information after the anchor finishes responding to the interactive information and the prompted information.

Specifically, the method 200 further includes: in response to the operation of marking information, marking information is completed; and repeatedly displaying the unmarked information based on a preset time interval.

For example, interactive information and/or prompted information may be presented on the interface in accordance with the foregoing. After the anchor replies the information, the anchor can mark the problem by a mouse, such as colluding. And the client responds to the operation of the identification information and displays the marked information on the interface, such as checking the information. The client can filter out the marked information, and the unmarked information can be repeatedly displayed at regular time. For example, repeated display is carried out every 2 minutes to remind the anchor to reply, and the experience of the user is improved.

In addition, it should be noted that the embodiment of the present application may be applied to live video and live voice. And for live video broadcast, the system can be used for live video broadcast of online education, live singing video broadcast, live chat video broadcast and the like in addition to live video broadcast of online shopping. The interactive information can be different for different live videos, but the clustering and displaying manner is similar. The information can also be displayed according to the grade of the user. And conversion rate for information presentation. It should be understood that the conversion rate may be different for different live scenes. For example, for live singing video and live chatting video, the conversion rate is the rate of converting interactive information into live video for sharing. For online education live broadcasting, evaluation can be performed according to the quality of the interactive information. Interaction information of high quality, i.e. quality greater than a threshold value, can also be determined by means of a preset model. The training of the model is similar to that described above and will not be described further here.

Based on the similar inventive concept, fig. 7 is a flowchart illustrating a method for prompting information according to another exemplary embodiment of the present application. The method 700 provided by the embodiment of the present application is executed by a server, such as a cloud server, and the method 700 includes the following steps:

701: and receiving a plurality of information, wherein the information is information provided by a user in the video live broadcast process.

702: a plurality of information is classified.

703: and determining information needing to be prompted according to the classified information in the category so as to send the information to the corresponding terminal and display the information, so that the anchor of the live video replies based on the prompted information.

Since the detailed description of the steps 701-703 has already been provided above, it is not repeated here. For illustration only, since the method 700 is executed by the server, the execution process is completed in the server, and the prompted information is sent to the client. In addition, the server can also continue to send the normal interaction information to the client side so as to carry out normal display.

Specifically, classifying a plurality of information according to the semantics of the information includes: determining the similarity of any two pieces of information in the plurality of pieces of information according to the semantics of the information; and when the similarity meets the similarity threshold, dividing the corresponding information into one class, thereby generating at least one class.

In addition, the method 700 further includes: after determining the information needing to be prompted, determining key information in the information; and sending the key information and prompt information representing the key information to be highlighted to the corresponding terminal so that the terminal highlights the key information under the condition of displaying the information.

In addition, the method 700 further comprises: receiving reply information of the anchor sent by a corresponding terminal; the reply information is provided to the user. Wherein the corresponding terminal refers to a terminal of the anchor.

Since the foregoing has described specific embodiments, further description is omitted.

In addition, reference may also be made to various steps in the method 200 described above, where the method 700 is not described in detail.

Based on the similar inventive concept, fig. 8 is a flowchart illustrating a method for prompting information according to another exemplary embodiment of the present application. The method 800 provided by the embodiment of the present application is executed by an intelligent terminal, such as a computer, and the method 800 includes the following steps:

801: and receiving a plurality of information, wherein the information is provided by the user in the voice live broadcast process.

802: a plurality of information is classified.

803: and determining the information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the voice live broadcast replies based on the prompted information.

Since the detailed description of the steps 801-803 has been given above, it is not repeated here. Only, when the live broadcast is a voice live broadcast, the user receives the audio of the main broadcast, and plays and displays the corresponding interactive information on the corresponding interface. And meanwhile, the client side of the anchor can also display interactive information and/or information needing prompting and the like.

In addition, the method 800 may refer to the steps of the method 200, which are not described in detail.

For voice live broadcast, a prompt mode of information can also be realized through the server, and a specific implementation mode is similar to the video live broadcast mode described above, and is not described here again.

Fig. 9 is a schematic structural framework diagram of an information prompt apparatus according to an exemplary embodiment of the present application. The apparatus 900 may be applied to an intelligent terminal, such as a computer. The apparatus 900 includes: a receiving module 901, a classifying module 902 and a determining module 903; the following detailed description is directed to the functions of the various modules:

the receiving module 901 is configured to receive a plurality of pieces of information, where the information is information provided by a user in a live video broadcast process.

A classification module 902 is configured to classify a plurality of information.

A determining module 903, configured to determine, according to the classified information in the category, information that needs to be prompted, so as to display the information, so that a main broadcast of live video replies based on the prompted information.

In addition, the apparatus 900 further comprises: and the display module is used for displaying the information needing prompting in a preset area in a video live broadcast interface of the anchor.

Specifically, the classification module 902 is configured to: and classifying the plurality of information according to the semantics of the information.

Specifically, the classification module 902 includes: the first determining unit is used for determining the similarity of any two pieces of information in the plurality of pieces of information according to the semantics of the information; and the dividing unit is used for dividing the corresponding information into one class under the condition that the similarity meets the similarity threshold value, so as to generate at least one class.

Specifically, the determining module 903 includes: the sorting unit is used for sorting the classified categories according to the number corresponding to the information in the classified categories; the selecting unit is used for selecting a preset number of categories from the side with the largest number based on the sorting result; and the second determining unit is used for determining the information needing to be prompted based on the selected category so as to display the information.

Specifically, the determining module 903 includes: the selecting unit is used for selecting the corresponding category larger than the threshold value according to the number corresponding to the information in the classified categories; and the second determining unit is also used for determining the information needing to be prompted according to the selected category so as to display the information.

Further, the determining module 903 is further configured to: after determining the information needing to be prompted, determining key information in the information; the display module is further configured to: in the case of the presentation of information, the key information is highlighted.

In addition, the display module is further configured to: displaying information needing to be prompted, responding to the reply operation of the anchor and receiving reply information of the anchor; the reply information is provided to the user.

Further, the determining module 903 is further configured to: determining a user grade according to account information of a user; in addition, the apparatus 900 further comprises: and the selection module is used for selecting the target user according to the user grade and taking the information corresponding to the target user as the information needing prompting.

Further, the determining module 903 is further configured to: determining the consumption condition of the live video broadcast of a user within preset historical time; and the selection module is also used for selecting a target user according to the consumption condition and taking the information corresponding to the target user as the information needing prompting.

In addition, the apparatus 900 further comprises: the input module is used for inputting a plurality of information into the preset model to obtain corresponding information, and the corresponding information can be used for improving the conversion rate of the information; and using the obtained corresponding information as information needing to be prompted.

In addition, the apparatus 900 further comprises: a marking module for responding to the operation of marking information, the marking information being completed; and the display module is also used for repeatedly displaying the unmarked information based on the preset time interval.

In addition, the display module is further configured to display the number of the prompted information in the corresponding category as the number of the users.

In addition, the display module is also used for displaying the received interactive information.

And the display time of the received interactive information is shorter than that of the prompted information.

Fig. 10 is a schematic structural framework diagram illustrating a message prompt device according to yet another exemplary embodiment of the present application. The apparatus 1000 may be applied to a server, such as a cloud server. The apparatus 1000 comprises: the receiving module 1001, the classifying module 1002, and the determining module 1003, the following describes the functions of the respective modules in detail:

the receiving module 1001 is configured to receive a plurality of pieces of information, where the information is information provided by a user in a live video broadcast process.

The classification module 1002 is configured to classify a plurality of information.

The determining module 1003 is configured to determine, according to the classified information in the category, information that needs to be prompted, to send the information to a corresponding terminal and display the information, so that a main broadcasting of live video replies based on the prompted information.

Specifically, the classification module 1002 is configured to: and classifying the plurality of information according to the semantics of the information.

Specifically, the classification module 1002 includes: the determining unit is used for determining the similarity of any two pieces of information in the plurality of pieces of information according to the semantics of the information; and the dividing unit is used for dividing the corresponding information into one class under the condition that the similarity meets the similarity threshold value, so as to generate at least one class.

In addition, the determining module 1003 is further configured to determine key information in the information after determining the information that needs to be prompted; the apparatus 1000 further comprises: and the sending module is used for sending the key information and prompt information representing the key information to be highlighted to the corresponding terminal so that the terminal can highlight the key information under the condition of displaying the information.

In addition, the receiving module 1001 is configured to receive reply information of the anchor sent by the corresponding terminal; the apparatus 1000 further comprises: and the providing module is used for providing the reply information to the user.

For parts of the content that cannot be mentioned by the apparatus 1000, reference may be made to the content of the apparatus 900 described above.

Fig. 11 is a schematic structural framework diagram illustrating a message prompt device according to another exemplary embodiment of the present application. The apparatus 1100 may be applied to an intelligent terminal, such as a computer. The apparatus 1100 comprises: the receiving module 1101, the classifying module 1102 and the determining module 1103 are described in detail below with respect to the functions of the respective modules:

the receiving module 1101 is configured to receive a plurality of pieces of information, where the information is information provided by a user in a live voice broadcast process.

A classification module 1102 configured to classify a plurality of information.

A determining module 1103, configured to determine, according to the classified information in the category, information that needs to be prompted, so as to display the information, so that a main broadcast of live voice replies based on the prompted information.

For parts of the content that cannot be mentioned by the apparatus 1100, reference may be made to the content of the apparatus 900 described above.

While the internal functions and structures of the apparatus 900 shown in FIG. 9 have been described above, in one possible design, the structures of the apparatus 900 shown in FIG. 9 may be implemented as a computing device, such as a computer. As shown in fig. 12, the apparatus 1200 may include: memory 1201, processor 1202, and communications component 1203;

a memory 1201 for storing a computer program.

A communication component 1203 is configured to receive a plurality of information, where the information is information provided by a user during a live video.

A processor 1202 for executing the computer program for: classifying the plurality of information; and determining information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the live video replies based on the prompted information.

Further, the processor 1202 is further configured to: and displaying information needing prompting on a preset area in a video live interface of the main broadcast.

Specifically, the processor 1202 is specifically configured to: and classifying the plurality of information according to the semantics of the information.

Specifically, the processor 1202 is specifically configured to: determining the similarity of any two pieces of information in the plurality of pieces of information according to the semantics of the information; and when the similarity meets the similarity threshold, dividing the corresponding information into one class, thereby generating at least one class.

Specifically, the processor 1202 is specifically configured to: sorting the classified classes according to the number corresponding to the information in the classified classes; selecting a preset number of categories from the side with the largest number based on the sorting result; and determining information needing prompting based on the selected category so as to display the information.

Specifically, the processor 1202 is specifically configured to: selecting corresponding categories which are larger than a quantity threshold value according to the quantity corresponding to the information in the classified categories; and determining the information needing to be prompted according to the selected category so as to display the information.

Further, the processor 1202 is further configured to: after determining the information needing to be prompted, determining key information in the information; in the case of the presentation of information, the key information is highlighted.

Further, the processor 1202 is further configured to: displaying information needing to be prompted, responding to the reply operation of the anchor and receiving reply information of the anchor; the reply information is provided to the user.

Further, the processor 1202 is further configured to: determining a user grade according to account information of a user; and selecting a target user according to the user grade, and taking the information corresponding to the target user as the information needing to be prompted.

Further, the processor 1202 is further configured to: determining the consumption condition of the live video broadcast of a user within preset historical time; and selecting a target user according to the consumption condition, and taking the information corresponding to the target user as information needing prompting.

Further, the processor 1202 is further configured to: inputting a plurality of information into a preset model to obtain corresponding information, wherein the corresponding information can be used for improving the conversion rate of the information; and using the obtained corresponding information as information needing to be prompted.

Further, the processor 1202 is further configured to: in response to the operation of marking information, marking information is completed; and repeatedly displaying the unmarked information based on a preset time interval.

Further, the processor 1202 is further configured to: and displaying the number of the prompted information in the corresponding category as the number of the users.

Further, the processor 1202 is further configured to: and displaying the received interactive information.

In addition, embodiments of the present invention provide a computer storage medium, and when executed by one or more processors, cause the one or more processors to implement the steps of a method for prompting information in the method embodiment of fig. 2.

Having described the internal functionality and structure of the apparatus 1000 shown in FIG. 10, in one possible design, the structure of the apparatus 1000 shown in FIG. 10 may be implemented as a computing device, such as a server. As shown in fig. 13, the apparatus 1300 may include: memory 1301, processor 1302, and communications component 1303;

a memory 1301 for storing a computer program.

And the communication component 1303 is used for receiving a plurality of information, wherein the information is information proposed by a user in the voice live broadcast process.

A processor 1302 for executing the computer program for: classifying the plurality of information; and determining the information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the voice live broadcast replies based on the prompted information.

Specifically, the processor 1302 is specifically configured to: and classifying the plurality of information according to the semantics of the information.

Specifically, the processor 1302 is specifically configured to: determining the similarity of any two pieces of information in the plurality of pieces of information according to the semantics of the information; and when the similarity meets the similarity threshold, dividing the corresponding information into one class, thereby generating at least one class.

Further, processor 1302 is further configured to: after determining the information needing to be prompted, determining key information in the information; and sending the key information and prompt information representing the key information to be highlighted to the corresponding terminal so that the terminal highlights the key information under the condition of displaying the information.

Further, the communication component 1303 is further configured to: receiving reply information of the anchor sent by a corresponding terminal; the reply information is provided to the user.

It should be noted that, for some contents that cannot be mentioned by the apparatus 1300, the contents of the apparatus 1200 described above may be referred to.

In addition, embodiments of the present invention provide a computer storage medium, and the computer program, when executed by one or more processors, causes the one or more processors to implement the steps of a method for prompting information in the method embodiment of fig. 7.

While the internal functions and structures of the apparatus 1100 shown in FIG. 11 have been described above, in one possible design, the structures of the apparatus 1100 shown in FIG. 11 may be implemented as a computing device, such as a computer. As shown in fig. 14, the apparatus 1400 may include: memory 1401, processor 1402, and communications component 1403;

a memory 1401 for storing the computer program.

A communication component 1403 is used for receiving a plurality of information, which is information proposed by the user in the process of live voice broadcast.

A processor 1402 for executing the computer program for: classifying the plurality of information; and determining information needing to be prompted according to the classified information in the category so as to send the information to the corresponding terminal and display the information, so that the anchor of the live video replies based on the prompted information.

It should be noted that, for some contents that the device 1400 fails to mention, reference may be made to the contents of the device 1200 described above.

In addition, embodiments of the present invention provide a computer storage medium, and when executed by one or more processors, cause the one or more processors to implement the steps of a method for prompting information in the method embodiment of fig. 8.

In addition, in some of the flows described in the above embodiments and the drawings, a plurality of operations are included in a specific order, but it should be clearly understood that the operations may be executed out of the order presented herein or in parallel, and the sequence numbers of the operations, such as 201, 202, 203, etc., are merely used for distinguishing different operations, and the sequence numbers themselves do not represent any execution order. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course, can also be implemented by a combination of hardware and software. With this understanding in mind, the above-described aspects and portions of the present technology which contribute substantially or in part to the prior art may be embodied in the form of a computer program product, which may be embodied on one or more computer-usable storage media having computer-usable program code embodied therein, including without limitation disk storage, CD-ROM, optical storage, and the like.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable multimedia data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable multimedia data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable multimedia data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable multimedia data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A method for prompting information is characterized by comprising the following steps:

receiving a plurality of information, wherein the information is provided by a user in a video live broadcast process;

classifying the plurality of information;

and determining information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the live video replies based on the prompted information.

2. The method of claim 1, further comprising:

and displaying the information needing prompting on a preset area in a video live broadcast interface of the anchor.

3. The method of claim 1, wherein the classifying the plurality of information comprises:

and classifying the plurality of information according to the semantics of the information.

4. The method of claim 3, wherein the classifying the plurality of information according to semantics of the information comprises:

determining the similarity of any two pieces of information in the plurality of pieces of information according to the semantics of the information;

and when the similarity meets the similarity threshold, dividing the corresponding information into one class so as to generate at least one class.

5. The method of claim 1, wherein determining information that needs to be prompted based on the classified information in the category comprises:

sorting the classified classes according to the number corresponding to the information in the classified classes;

selecting a preset number of categories from the side with the largest number based on the sorting result;

and determining information needing prompting based on the selected category so as to display the information.

6. The method of claim 1, wherein determining information that needs to be prompted based on the classified information in the category comprises:

selecting corresponding categories larger than a quantity threshold value according to the quantity corresponding to the information in the classified categories;

and determining the information needing to be prompted according to the selected category so as to display the information.

7. The method of claim 1, further comprising:

after determining the information needing to be prompted, determining key information in the information;

and under the condition of displaying the information, highlighting the key information.

8. The method of claim 1, further comprising:

displaying information needing to be prompted, responding to the reply operation of the anchor and receiving reply information of the anchor;

and providing the reply information to the user.

9. The method of claim 1, further comprising:

determining a user grade according to account information of a user;

and selecting a target user according to the user grade, and taking the information corresponding to the target user as information needing prompting.

10. The method of claim 1, further comprising:

determining the consumption condition of the live video broadcast of a user within preset historical time;

and selecting a target user according to the consumption condition, and taking the information corresponding to the target user as information needing prompting.

11. The method of claim 1, further comprising:

inputting the plurality of information into a preset model to obtain corresponding information, wherein the corresponding information can be used for improving the conversion rate of the information;

and using the obtained corresponding information as information needing to be prompted.

12. The method of claim 8, further comprising:

in response to the operation of marking information, marking information is completed;

and repeatedly displaying the unmarked information based on a preset time interval.

13. The method of claim 2, further comprising:

and displaying the number of the prompted information in the corresponding category as the number of the users.

14. The method of claim 1, further comprising:

and displaying the received interactive information.

15. The method of claim 14, further comprising:

and the display time of the received interactive information is shorter than the display time of the prompted information.

16. A method for prompting information is characterized by comprising the following steps:

classifying the plurality of information;

and determining information needing to be prompted according to the classified information in the category so as to send the information to the corresponding terminal and display the information, so that the anchor of the live video replies based on the prompted information.

17. The method of claim 16, wherein the classifying the plurality of information comprises:

18. The method of claim 17, wherein the classifying the plurality of information according to semantics of the information comprises:

19. The method of claim 16, further comprising:

and sending the key information and prompt information representing the key information to be highlighted to a corresponding terminal so that the key information is highlighted when the terminal displays the information.

20. The method of claim 16, further comprising:

receiving reply information of the anchor sent by a corresponding terminal;

and providing the reply information to the user.

21. A method for prompting information is characterized by comprising the following steps:

receiving a plurality of information, wherein the information is provided by a user in the voice live broadcast process;

classifying the plurality of information;

and determining the information needing to be prompted according to the classified information in the category so as to display the information, so that the anchor of the voice live broadcast replies based on the prompted information.

22. A computing device, comprising: a memory, a processor, and a communication component;

the memory for storing a computer program;

the communication component is used for receiving a plurality of information, and the information is information provided by a user in a video live broadcast process;

the processor to execute the computer program to:

classifying the plurality of information;

23. A computing device, comprising: a memory, a processor, and a communication component;

the memory for storing a computer program;

the communication component is used for receiving a plurality of information, and the information is information provided by a user in a voice live broadcast process;

the processor to execute the computer program to:

classifying the plurality of information;

24. A computing device, comprising: a memory, a processor, and a communication component;

the memory for storing a computer program;

the processor to execute the computer program to:

classifying the plurality of information;

25. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by one or more processors, causes the one or more processors to perform the steps of the method of any one of claims 1-21.