CN114218376A

CN114218376A - Question-answer interaction method and system based on bullet screen

Info

Publication number: CN114218376A
Application number: CN202111591064.XA
Authority: CN
Inventors: 宁耀旭; 杨震泉; 于涛涛
Original assignee: Sichuan Qiruike Technology Co Ltd
Current assignee: Sichuan Qiruike Technology Co Ltd
Priority date: 2021-12-23
Filing date: 2021-12-23
Publication date: 2022-03-22

Abstract

The invention discloses a question-answer interaction method and system based on a bullet screen, wherein bullet screen question marks input by a user aiming at a video are obtained, the marks comprise one or more question sentences or vocabularies for describing the video, other users carry out targeted answers according to bullet screen questions of a first user, the first user can independently obtain an answer list, the corresponding relation between the questions and the answers is stored, and meanwhile, bullet screen mixing is carried out on subsequent common bullet screen questions, so that the user has better viewing experience.

Description

Question-answer interaction method and system based on bullet screen

Technical Field

The invention relates to the technical field of internet, in particular to a question-answer interaction method and system based on a bullet screen.

Background

The barrage video is a popular video form at present, which means that a user can display own comments in the video in a barrage sending form when watching the video, and is a watching mode capable of realizing instant interaction.

When a user watches a video, the continuously rolling barrage in the video can provide the user with a large amount of information, whether the information is supplementary to the video content, or is used for discussing and evaluating the video, or is various new barrages, which is one of the important characteristics of the barrage, namely the timeliness. However, for the audience who is really interested in a certain point of the video, for example, the audience puts forward a problem to a certain position of the video, the audience hopes to be solved quickly on a video page, but a plurality of flicking barrages cannot meet the requirements of the audience, jump out of the video page, and cannot determine the specific problem description, so that the audience is solved, more time and energy are wasted, and the experience of the audience is poor; although the user can also ask questions in the comment area, the comment lists seen by other users are often arranged based on the popularity, and newly published comments are difficult to see, so the user's comment on the text is often ignored.

Disclosure of Invention

The invention aims to provide a question-answer interaction method based on a bullet screen, which aims to solve the problem that a video user is difficult to obtain answers by adopting a bullet screen question-answer searching method.

The invention realizes the purpose through the following technical scheme:

a question-answer interaction method based on a bullet screen comprises the following steps:

step 1, obtaining question bullet screen marks of a user, and obtaining answer bullet screen marks of other users according to the question bullet screen marks of the user;

step 2, according to the problem bullet screen marks marked by a plurality of users, respectively corresponding to different moments of the video and storing the corresponding relation between the problem bullet screen marks and a plurality of video segments;

step 3, the questioning user adopts the answer barrage, and the server stores the relevant answer barrage data;

step 4, receiving question bullet screen marks input by other users; according to the question bullet screen mark, similarity judgment is carried out on the question set of the video at a specific moment, whether the question set is a similar question or not is judged, and excellent answer bullet screens are selected from the answer set and pushed for potential audiences;

and 5, after the question set reaches a certain value, judging that a certain number of audiences pay attention to the question, and pushing the excellent answer barrage to the video page in a mode different from the common barrage display mode by the server.

The method comprises the following steps that in the step 1, a problem bullet screen mark input by a user at a certain moment on a video interface is obtained, the server obtains the problem bullet screen mark, judges the problem bullet screen mark and displays the problem bullet screen mark in a bullet screen list in a rolling process of a video page in a special form;

other users click the bullet screen after seeing the question bullet screen, trigger the mark, pop up the bullet screen input box, the user inputs and releases the publication, the answer bullet screen input by the user is marked by the server at the moment and is associated with the corresponding question bullet screen;

the server pushes the answer barrage to the user who gives the question barrage, and the user checks and accepts the answer barrage and judges whether to adopt the answer barrage.

Further, in the step 3, a big data calculation excellent answer barrage is used for pushing a potentially needed barrage for the audience, the big data calculation excellent answer barrage is used for extracting the same keywords based on a large number of question barrage marks at the same time to generate a question set, and the answer barrage marks corresponding to the question barrage marks are gathered into answer sets with different adoption degrees.

The step 4 further includes selecting an answer barrage mark with high audience adoption degree based on an answer set calculated by big data, or selecting a superior barrage in a manual review mode, or judging based on a barrage environment, and the server actively pushes popular science barrages to the audiences.

In the step 2, a question bullet screen mark input by a single user for a moment of a specific video is obtained, a question is asked to other users, the other users can browse the special bullet screen mark and select to answer the special bullet screen mark, and the server stores the relation between the question bullet screen and the answer bullet screen and marks the relation to the specific moment of the video.

The invention also provides a system of the question-answer interaction method based on the bullet screen, which comprises a server, wherein the server is in communication connection with the terminal equipment through a network;

the terminal device is installed with a client and logs in to the server through the client, so that corresponding services are provided for the user through cooperation with the server 100.

The server is an independent server, or a server cluster or distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud computing, big data and artificial intelligence platforms;

the terminal equipment is a smart phone, a tablet personal computer, a notebook computer, a personal computer, a smart television and portable wearable equipment;

the client is any application program which has a video playing function and supports mark or bullet screen input, and comprises a video playing application, a live broadcast application, a page browsing platform with a video playing function, a social platform and an education platform.

The invention has the beneficial effects that:

after a user inputs bullet screen question marks aiming at a video, an answer list is collected, and needed knowledge confusion is obtained from the answer list; after the answer list exists, the ordinary user can see the science popularization barrage at the video mark position, and the basic experience of the user is enriched.

Can obtain the answer through other users 'answer barrage based on the question barrage of user input, supply the question and answer list about the video, when similar problem appears, no matter be the question barrage, still the form of ordinary barrage, the potential audience can obtain relevant video knowledge, promotes user's video and watches experience.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the embodiments or the drawings needed to be practical in the prior art description, and obviously, the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 shows a schematic diagram of an application environment suitable for the embodiment of the present application.

Fig. 2 shows a schematic flow chart of a bullet screen question-answer interaction method provided in an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.

In any embodiment, as shown in fig. 1, a system of a question-answer interaction method based on a barrage of the present invention includes:

the server 100 may be communicatively connected to the terminal device 200 through a network. The terminal device 200 is installed with a client 210, and can log in to the server 100 through the client 210, so as to provide corresponding services, such as a video playing service, a barrage question and answer service, for a user through cooperation with the server 100.

The server 100 may be an independent server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud computing, big data, an artificial intelligence platform, and the like. The terminal device 200 may be, but is not limited to, a smart phone, a tablet Computer, a notebook Computer, a Personal Computer (PC), a smart tv, a portable wearable device, and the like. The client 210 may be any application program having a video playing function and supporting markup or barrage input, for example, a video playing application, a live application, a page browsing platform (e.g., a browser client) having a video playing function, a social platform, an educational platform, and the like. The embodiment of the application can be applied to all scenes of video playing.

In any embodiment, as shown in fig. 2, a bullet screen question and answer searching method of the present application includes:

and acquiring a question bullet screen mark of the first user for the video input. When a user watches videos, the user asks about video pictures at a certain moment, hopes to timely obtain answers on video pages, and can input question bullet screen marks. The terminal device 200 may locally save the question mark in response to a user operation, while uploading the question mark to the server 100. In this embodiment, the user sends a question in the form of a bullet screen, and in general, the question is asked about a screen at a certain time. The terminal device and the server device need to save the problem bullet screen and the time marked by the problem.

The common bullet screen rolls from the right end to the left end in a video picture, and the problem bullet screen is different from the common bullet screen in expression form and different in issuing mode. After the user inputs a question in the bullet screen input box, the first component should be selected as a mark of the question bullet screen, and the server 100 obtains a question bullet screen different from a common bullet screen mark. The component can be issued by checking and marking the bullet screen through the problem box, can be distinguished from the input box of the common bullet screen, and can be issued in the special problem bullet screen box.

After the problem barrage is published, the problem barrage can appear in a barrage group of a video page, is distinguished from a common barrage through a special mark, and can continuously roll with the common barrage, so that the problem barrage can stay at a specific moment in a video to ensure that the barrage cannot be ignored. After other users notice the question bullet screen, the bullet screen can be clicked, specific interaction is carried out on the bullet screen, and answers are input. The answer barrage is tagged with the question and uploaded to the server 100, and the server 100 correlates the question with the answer. The questioning user can see the bullet screen marked as the answer on the video page, or can obtain the reply message on the background of the terminal equipment. The point-to-point barrage interaction can be used as a personalized barrage, and the video watching of the user which does not relate to question and answer interaction is not influenced.

Each terminal device 200 receives the question bullet screen mark of the user and uploads the mark to the server 100. After a plurality of users generate similar question bullet screen marks, similar keyword questions are generated in a certain time period, the picture can be marked, and the optimal answer bullet screen is mixed into a bullet screen list for output.

The acquisition of the similar question set is judged through keywords in the question bullet screen text and the time marked by the bullet screen, and the selection of the optimal answer bullet screen can be realized through praise or step on the answer bullet screen according to the adoption degree of the question user to the answer in the earlier stage. When the similarity degree of the question set is high enough, the answer barrage can be extracted from the similar answer set, when the adoption data of the answer barrage is not enough, the answer barrage can return to the relevant answer set of the user, when the adoption data is enough, the server obtains the optimal answer barrage and returns the optimal answer barrage to the user, and the optimal answer barrage is presented to the user at a specific moment in the video, so that potential audiences can obtain better impression.

In a specific embodiment, as shown in fig. 2, according to the question-answer interaction method based on the barrage, a barrage question mark input by a user for a video is obtained, the mark includes one or more question sentences or vocabularies describing the video, other users perform targeted answers according to the barrage question of the first user, and the first user can separately obtain an answer list and store the corresponding relationship between the question and the answer. Simultaneously, the bullet screen is doped for subsequent common bullet screen problems, so that the user has better viewing experience.

Regarding the realization of the user bullet screen problem mark, the server acquires the problem bullet screen issued by the user in the following way, displays a first component on the video playing interface, wherein the first component is used for inputting the problem generated on the video node picture by the user, and acquires the user problem bullet screen mark from a first interface corresponding to the first component. After a user inputs a problem in a bullet screen input frame, a first component is selected as a mark of a problem bullet screen, a server obtains a problem bullet screen different from a common bullet screen mark, the component can be a problem frame check box, the realization form is that a video playing interface only has one bullet screen input frame, the common bullet screen and the problem bullet screen are input from the frame, but one more check box or button is arranged, the check box or button is the mark form of the problem bullet screen, and when the check box or the button is used, the bullet screen is marked as the problem bullet screen and corresponds to data received by a first interface in the first component; the problem bullet screen frame can be a special problem bullet screen frame, two bullet screen frames are arranged at the left bottom and the right bottom of the video playing interface, a 'click me to send a bullet screen' and a 'click me to send a problem bullet screen', and a user can obviously select the problem bullet screen frame to correspond to the first interface of the first assembly. When the subassembly was selected to use, the bullet curtain that the server received should be than ordinary bullet curtain more a specific mark, promptly for the problem bullet curtain, compares and sneaks into the operation that ordinary bullet curtain discerned the screening with the problem, and a lot of calculations can be saved to the mark problem bullet curtain, and is more directly perceived simple and convenient like this.

Regarding the implementation of collecting the answer list, when the question bullet screen appears in the bullet screen list, other users watching the video notice the question bullet screen different from the common bullet screen and can click on the question bullet screen, an answer input box appears in the video, the answer input box is used as a third bullet screen frame different from the question bullet screen frame and the common bullet screen frame, the question bullet screen is clicked to trigger the appearance, "click me to send an answer", the user can input the answer in the input box, send the answer to the server, and the answer is associated with the question bullet screen mark. After other users finish the input of answers again, the video playing time possibly deviates from the time of a question questioning interface, so that the answer barrage and the question barrage are not synchronous enough, the effect of immediate confusion is difficult to achieve, and the answer barrage is displayed on the video mark node of the question barrage after the answer barrage is screened in the server through the corresponding relation between the answer barrage and the question barrage. When different users repeatedly ask a question of a certain node of the video, although sentences may be different, keywords are the same, by calculating the cosine similarity between the keywords and words and combining and judging the time nodes of the sentences, whether a question barrage is a question barrage can be judged, at the moment, a answer list obtained by the same question barrage mark can be pushed to a second user, in addition, other users can continue to push the question bullet screen marked by the question bullet screen, and the server needs to aggregate the answer bullet screens generated by the same question bullet screen, therefore, the answer list is enlarged, a follow-up questioning user can extract useful information from the answer barrage, the answer barrage can be more comprehensively known, the answer barrage has 'adoption degree' as a reference to judge whether the barrage can be automatically appeared on a video playing interface as an excellent answer barrage, and the answer barrage becomes an accurate popular science barrage.

Regarding the judgment of excellent reply, except that the user uses the mark data similar to 'useful' and 'adopted' and the like as one of the judgment criteria for the answer barrage, when the current click data volume is insufficient, the server can carry out semantic recognition on the answer barrage content, judge whether the keywords in the question barrage associated with the answer barrage have the contact degree, such as 'xx is who', 'xx is some … …', the content of different answer barrages can also carry out semantic recognition, the 'some' keywords appear for multiple times, the credibility of the answer barrage is proved, and based on the judgment, a part of the barrage which seems to be correct and useful can be screened out from a crowd answer barrage; the answer barrage is still a barrage and appears on a video page in a rolling mode, in the process of screening the answer barrage, the server needs to consider the impression effect given to a user by the barrage, the barrage cannot be a overlong text, and based on an answer list, a plurality of feature keywords with different dimensions, such as names, works, occupation, places and the like, are collected from a preset database according to semantic recognition and machine learning, so that the answer barrage is screened based on a keyword data set, and a part of the barrage with proper length and accuracy is screened out and returned to the video page. When the follow-up questioning user sees the answer barrage, the mark of "excellent reply" can be carried out to the answer barrage, and the mark that the quantity is more can push as the excellent answer barrage of potential, and after the excellent answer barrage is seen to the potential questioning user, also can carry out the continuation mark. When the "excellent responses" are converted into popular science bulletin screens, a background operator of the server or a search engine is required to judge, and text coverage is judged according to professional answers and a plurality of "excellent responses" of the search engine, so that the "excellent responses" with popular science standards are screened out.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims. It should be noted that the various technical features described in the above embodiments can be combined in any suitable manner without contradiction, and the invention is not described in any way for the possible combinations in order to avoid unnecessary repetition. In addition, any combination of the various embodiments of the present invention is also possible, and the same should be considered as the disclosure of the present invention as long as it does not depart from the spirit of the present invention.

Claims

1. A question-answer interaction method based on a bullet screen is characterized by comprising the following steps:

2. The question-answer interaction method based on the bullet screen as claimed in claim 1, wherein in step 1, the question bullet screen mark input by the user at a certain moment on the video interface is obtained, the server obtains the question bullet screen mark, judges the question bullet screen mark, and then displays the question bullet screen mark in a bullet screen list in a rolling process of the video page in a special form;

3. The method as claimed in claim 1, wherein in step 3, the step of calculating the top answer barrage based on the big data is performed to push the potentially required barrage to the audience, the top answer barrage based on the big data is generated by extracting the same keyword based on a plurality of question barrage marks at the same time, and the corresponding answer barrage marks are gathered into answer sets with different degrees of adoption.

4. The method as claimed in claim 1, wherein the step 4 includes selecting an answer set calculated based on big data, selecting an answer barrage mark with high audience adoption degree, or selecting an excellent barrage in a form of manual review, or performing a judgment based on a barrage environment, and the server actively pushes popular barrages to the audience.

5. The method according to claim 1, wherein in step 2, a question-answer interaction method based on a bullet screen is adopted, wherein a question bullet screen mark input by a single user for a moment of a specific video is obtained, and a question is asked to other users, the other users can browse the special bullet screen mark and select to answer the special bullet screen mark, and the server stores the relation between the question bullet screen and the answer bullet screen and marks the special moment of the video.

6. The system of the bullet screen based question-answer interaction method of claims 1-5, characterized by comprising a server, wherein the server is in communication connection with a terminal device through a network;

7. The system of claim 6, wherein the server is an independent server, a server cluster or distributed system composed of a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud computing, big data and artificial intelligence platforms;