CN110337008B

CN110337008B - Video interaction adjusting method, device, equipment and storage medium

Info

Publication number: CN110337008B
Application number: CN201910541821.9A
Authority: CN
Inventors: 罗胜; 洪楷; 钟炳武; 杨平; 李津
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-06-21
Filing date: 2019-06-21
Publication date: 2020-10-13
Anticipated expiration: 2039-06-21
Also published as: CN110337008A

Abstract

The embodiment of the invention discloses a video interaction adjusting method, a device, equipment and a storage medium, wherein the embodiment of the invention acquires the interaction content aiming at a video; extracting keywords from the interactive content to obtain interactive content keywords; when the occurrence frequency of the interactive content keywords is greater than a preset threshold value, acquiring a video interaction adjustment strategy corresponding to the interactive content keywords, wherein the occurrence frequency is the occurrence frequency of the interactive content keywords in an interactive content database; and adjusting the video interaction based on the video interaction adjusting strategy. The scheme can solve the problem of abnormal video playing and improve the video interaction adjustment efficiency.

Description

Video interaction adjusting method, device, equipment and storage medium

Technical Field

The invention relates to the technical field of communication, in particular to a video interaction adjusting method, device, equipment and storage medium.

Background

With the development of internet technology and the popularization of mobile terminals, some emerging spreading and social ways are gradually emerging, and network video playing is one of them.

The conventional data indexes such as online user quantity, playing bandwidth and playing pause are greatly fluctuated due to the reasons of popularization resources, popularity, anchor influence, network video playing time interval, program wonderful degree, randomness of audience entering and leaving a room, and the like in different network video playing activities, and the abnormality of network video playing services cannot be monitored in real time by depending on the conventional data indexes such as online user quantity, playing bandwidth and playing pause: the user side is blank, stuck, silent, asynchronous voice and picture, small in sound and the like, so that the user watching experience problem cannot be found in real time, the optimization adjustment cannot be made in real time, and manual watching and manual adjustment are needed.

Disclosure of Invention

The embodiment of the invention provides a video interaction adjusting method, a video interaction adjusting device, video interaction adjusting equipment and a storage medium, which can improve the accuracy and efficiency of video interaction adjustment.

In order to solve the above technical problems, embodiments of the present invention provide the following technical solutions:

acquiring interactive content aiming at a video;

extracting keywords from the interactive content to obtain interactive content keywords;

when the occurrence frequency of the interactive content keywords is greater than a preset threshold value, acquiring a video interaction adjustment strategy corresponding to the interactive content keywords, wherein the occurrence frequency is the occurrence frequency of the interactive content keywords in an interactive content database;

and adjusting the video interaction based on the video interaction adjusting strategy.

Correspondingly, an embodiment of the present invention further provides a video interaction adjusting apparatus, including:

the first acquisition unit is used for acquiring interactive contents aiming at the video;

the extraction unit is used for extracting keywords from the interactive content to obtain interactive content keywords;

the second obtaining unit is used for obtaining a video interaction adjustment strategy corresponding to the interactive content keywords when the occurrence frequency of the interactive content keywords is greater than a preset threshold value, wherein the occurrence frequency is the occurrence frequency of the interactive content keywords in an interactive content database;

and the adjusting unit is used for adjusting the video interaction based on the video interaction adjusting strategy.

Optionally, in some embodiments, the video interaction adjusting apparatus further includes:

and the third obtaining unit is used for obtaining the appearance positions corresponding to the interactive content keywords based on a mapping relation set, wherein the mapping relation set comprises the interactive content keywords and the mapping relations among the appearance positions and the appearance frequencies.

Optionally, in some embodiments, the adjusting unit includes:

and the first adjusting subunit is used for adjusting the video interaction corresponding to the appearance position based on the video interaction adjusting strategy.

the first establishing unit is used for establishing an interactive content database according to the acquired interactive content;

the computing unit is used for computing the occurrence frequency of the interactive content keywords according to the interactive content database;

a fourth obtaining unit, configured to obtain a client identifier for displaying the interactive content and a position of the interactive content keyword in the interactive content database;

and the second establishing unit is used for establishing a mapping relation set of the interactive content key words, the client identification, the positions in the interactive content database and the occurrence frequency.

Optionally, in some embodiments, the fourth obtaining unit includes:

the sequencing subunit is used for sequencing each character included in each interactive content according to the total word number of each interactive content to obtain each character number; sequencing the interactive contents in the interactive content database according to the acquisition sequence to obtain the serial numbers of the interactive contents;

and the first acquisition subunit is used for acquiring the position of the interactive content key word in the interactive content database according to the character number and the interactive content number.

the compression unit is used for compressing the interactive content keywords, the client identification, the position in the interactive content database and the occurrence frequency included in the mapping relation set to obtain a compressed mapping relation set;

and the storage unit is used for storing the compressed mapping relation set.

Optionally, in some embodiments, the adjusting unit further includes:

the second obtaining subunit is used for obtaining the interactive content number and the character number of the interactive content key word in the interactive content database according to the interactive content key word; acquiring a client identifier of the interactive content keyword according to the interactive content number;

and the second adjusting subunit is used for adjusting the video parameters corresponding to the client identifier through the video interaction adjusting strategy.

Optionally, in some embodiments, the extracting unit includes:

the third acquisition subunit is used for acquiring the associated interactive content keyword library;

and the searching subunit is used for searching in the associated interactive content keyword library to match out the keywords in the interactive content.

a fifth obtaining unit, configured to obtain historical interactive content; acquiring an unambiguous word according to the historical interactive content;

the construction unit is used for constructing the database of the meaningless words;

and the filtering unit is used for filtering the interactive content according to the meaningless word database to obtain the filtered interactive content.

In addition, an embodiment of the present invention further provides a video interaction adjusting device, including: a processor and a memory; the memory stores a plurality of instructions, and the processor loads the instructions stored in the memory to execute any one of the video interaction adjusting methods provided by the embodiments of the present invention.

In addition, an embodiment of the present invention further provides a storage medium, where multiple instructions are stored in the storage medium, and the instructions are suitable for being loaded by a processor to execute any video interaction adjustment method provided in the embodiment of the present invention.

The embodiment of the invention acquires the interactive content aiming at the video; extracting keywords from the interactive content to obtain interactive content keywords; when the occurrence frequency of the interactive content keywords is greater than a preset threshold value, acquiring a video interaction adjustment strategy corresponding to the interactive content keywords, wherein the occurrence frequency is the occurrence frequency of the interactive content keywords in an interactive content database; and adjusting the video interaction based on the video interaction adjusting strategy. According to the scheme, the corresponding video interaction adjustment strategy is directly obtained according to the interactive content keywords, the video interaction is directly adjusted according to the video interaction adjustment strategy, manual watching and adjustment are not needed, and therefore the video interaction adjustment efficiency is improved.

Drawings

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

Fig. 1 is a schematic structural diagram of a video interaction adjustment system according to an embodiment of the present invention;

fig. 2 is a flowchart of a video interaction adjustment method according to an embodiment of the present invention;

fig. 3 is a schematic public opinion trend diagram of interactive content keywords of the video interaction adjustment method according to the embodiment of the invention;

fig. 4 is a schematic diagram illustrating keyword derivation of interactive content in a video interaction adjustment method according to an embodiment of the present invention;

fig. 5 is a schematic view illustrating video interaction adjustment of a video interaction adjustment method according to an embodiment of the present invention;

FIG. 6a is a schematic diagram of a service cluster provided by an embodiment of the present invention;

fig. 6b is an architecture diagram of a video interaction adjustment method according to an embodiment of the present invention;

fig. 7a is a schematic structural diagram of a video interaction adjusting apparatus according to an embodiment of the present invention;

fig. 7b is a schematic structural diagram of a video interaction adjusting device according to an embodiment of the present invention

Fig. 7c is a schematic structural diagram of a video interaction adjusting device according to an embodiment of the present invention;

fig. 7d is a schematic view of another structure of the video interaction adjustment apparatus according to the embodiment of the present invention;

fig. 8 is a schematic structural diagram of a server according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention.

The embodiment of the invention provides a video interaction adjusting method, a video interaction adjusting device, video interaction adjusting equipment and a storage medium. The following are detailed below.

The embodiment of the invention provides a video interaction adjusting system, which comprises the video interaction adjusting device provided by the embodiment of the invention, wherein the video interaction adjusting device can be integrated in a terminal, and the terminal can be a mobile phone, a tablet computer, a notebook computer and other equipment. In addition, the video interactive adjustment system may further include other devices, such as a server and the like.

For example, referring to fig. 1, a video interaction adjustment system provided by the embodiment of the present invention includes a terminal and a server, and a video interaction adjustment apparatus provided by the embodiment of the present invention may be integrated in the terminal or integrated in the server, where the terminal and the server are connected through a network.

In a specific implementation process, when the video interaction adjusting device is integrated in the server, the terminal can receive the interaction content sent by the user for the video, for example, the user sends the interaction content to the video data through the live broadcast user side, and the live broadcast user side receives the interaction content sent by the user and sends the received interaction content to the server.

The method comprises the steps that a server acquires interactive content sent by a terminal aiming at a video, extracts the keywords of the interactive content to obtain keywords of the interactive content, specifically, a related interactive content keyword library is acquired, the acquired interactive content aiming at the video is matched in the interactive content keyword library, and when the content which is consistent with the interactive content aiming at the video is matched in the interactive content keyword library, the interactive content aiming at the video is determined to contain the keywords of the interactive content, so that the extraction of the keywords is realized, and the keywords of the interactive content are obtained; and then acquiring the occurrence frequency of the interactive content keywords, acquiring a video interaction adjustment strategy corresponding to the interactive content keywords when the occurrence frequency of the interactive content keywords is greater than a preset threshold value, and adjusting the video interaction based on the video interaction adjustment strategy.

The following are detailed below. The order of the following examples is not intended to limit the preferred order of the examples.

In this embodiment, a description will be given from the perspective of a video interaction adjustment apparatus, which may be specifically integrated in a network device, such as a terminal or a server.

A video interaction adjustment method comprises the following steps: acquiring interactive content aiming at a video; extracting keywords from the interactive content to obtain interactive content keywords; when the occurrence frequency of the interactive content keywords is greater than a preset threshold value, acquiring a video interaction adjustment strategy corresponding to the interactive content keywords, wherein the occurrence frequency is the occurrence frequency of the interactive content keywords in an interactive content database; and adjusting the video interaction based on the video interaction adjusting strategy.

As shown in fig. 2, the specific process of the video interaction adjusting apparatus may be as follows:

and 201, acquiring interactive content aiming at the video.

In a specific implementation process, the interactive content for the video is obtained, specifically, the interactive content may be input by a user through a video client, where the video client may specifically be a mobile phone, a tablet computer, a PDA, or the like. The video can be live webcast, which refers to a playing mode that video data can be watched on different communication platforms through a network system at the same time. It can be understood that various types of messages are generated during the process of watching video data in a live webcast manner, such as interactive content published by a live user end to the video data, where the interactive content may include a bullet screen, a message, a gift, and the like.

202, extracting keywords from the interactive content to obtain interactive content keywords.

In an embodiment, the keyword extraction is performed on the acquired interactive content for the video, the associated interactive content keyword library is acquired, the acquired interactive content for the video is matched in the interactive content keyword library, and when the content consistent with the interactive content for the video is matched in the interactive content keyword library, the interactive content for the video is determined to contain the interactive content keyword, so that the keyword extraction is realized, and the interactive content keyword is acquired.

Further, in order to reduce the number of times of comparing keyword extraction on the interactive content, before extracting the keyword of the interactive content, the interactive content may be processed, for example, first obtaining the historical interactive content, and obtaining the meaningless words according to the historical interactive content, such as "having" and "having" a greater number of occurrences in the interactive content, which have no practical meaning. And then constructing a semantic word database according to the obtained semantic words, and finally filtering the interactive content according to the semantic word database so as to obtain the filtered interactive content. Namely, the non-meaning words in the interactive content are filtered and deleted, so that the non-meaning words do not need to be matched and extracted when the keywords are extracted, the matching times are reduced, and the matching efficiency is improved.

In a specific implementation process, the step 202 further includes: and acquiring an associated interactive content keyword library, searching in the associated interactive content keyword library, and matching keywords in the interactive content.

In the step of obtaining the associated interactive content keyword library, the interactive content keyword library is obtained by analyzing and establishing the historical live broadcast interactive content. More specifically, historical live broadcast interactive content is obtained, text analysis is carried out on the obtained historical live broadcast interactive content, word segmentation processing can be carried out on the historical live broadcast interactive content through a full segmentation algorithm to obtain word segmentation of the historical live broadcast interactive content, then quantization processing is carried out on the word segmentation of the historical live broadcast interactive content through a neural network language model to obtain word vectors of the word segmentation of the historical live broadcast interactive content; inputting the word vector of the participle of the historical live broadcast interactive content into a preset database model, and obtaining the Euclidean distance between the word vector of the participle of the historical live broadcast interactive content and the word vector in a preset database; analyzing the semantics of the historical live broadcast interactive content according to the Euclidean distance between the word vectors of the participles of the historical live broadcast interactive content and the word vectors in the preset database, carrying out word classification on the historical live broadcast interactive content according to the semantics of the historical live broadcast interactive content, calculating the occurrence frequency of various words according to the historical live broadcast interactive content after the word classification, setting the words with the occurrence frequency larger than the preset value as keywords, and establishing a content keyword library according to the set keywords. Further, keywords corresponding to abnormal types which are less in occurrence but also need to be solved in the live broadcast process can be further added in the content keyword library.

203, determining whether the occurrence frequency of the interactive content keyword is greater than a preset threshold, and if so, performing step 204.

Comparing the occurrence frequency of the interactive content keywords with a preset threshold, and when the occurrence frequency of the interactive content keywords is greater than the preset threshold, the preset threshold is the preset frequency, and the specific threshold can be set according to actual conditions to obtain a video interactive adjustment strategy corresponding to the interactive content keywords. When the occurrence frequency of the interactive content keywords is less than or equal to the preset threshold, it is indicated that no abnormality occurs, or the number of cases of abnormality occurrence is small, no processing is required, and the process is ended.

And 204, acquiring a video interaction adjustment strategy corresponding to the interactive content keyword. And the occurrence frequency is the occurrence frequency of the interactive content keywords in an interactive content database.

Further, after the interactive content keywords are obtained, whether live video parameters need to be adjusted or not can be judged according to the occurrence frequency of the interactive content keywords. Specifically, the occurrence frequency of the interactive content keywords is compared with a preset frequency, if the occurrence frequency of the interactive content keywords is greater than the preset frequency, that is, greater than a preset threshold, it is determined that the live video parameters need to be adjusted, otherwise, it is determined that the live video parameters do not need to be adjusted. And when the occurrence frequency of the interactive content keywords is determined to be greater than a preset threshold value, acquiring a video interaction adjustment strategy corresponding to the interactive content keywords. Therefore, before step 204, the method may further include:

and associating each interactive content keyword with the corresponding video interactive adjustment strategy.

Namely, each interactive content keyword is associated with a corresponding video interactive adjustment strategy, wherein the video interactive adjustment strategy can be set by professional live video exception handling personnel in combination with the exception handling process. For example, if the interactive content keyword is a card, the definition of the terminal is adjusted by a live video exception handler in the processing process, so that the problem of the card is solved, and the interactive content keyword "card" can be associated with the definition of the video interactive adjustment policy "adjustment terminal". It can be understood that the same interactive content keyword can correspond to a plurality of video interactive adjustment strategies, and the specific solution strategy can be adjusted according to the actual situation.

In order to facilitate the calculation of the frequency of occurrence of the interactive content keyword, after obtaining the interactive content keyword, the method may further include:

establishing an interactive content database according to the acquired interactive content;

and acquiring the occurrence frequency of the interactive content keywords according to the interactive content database.

The occurrence frequency may include a frequency of the interactive content keyword corresponding to the occurring interactive content and a frequency in the interactive content database. Specifically, an interactive content database is established according to the acquired interactive content, the occurrence frequency of the interactive content keywords is calculated according to the interactive content database, the interactive content in the interactive content database can be subjected to word segmentation to obtain word segmentation of the interactive content, then the occurrence frequency of the interactive content keywords in the interactive content which correspondingly appears is obtained, then the ratio of the occurrence frequency of the interactive content keywords in the interactive content which correspondingly appears to the word which is obtained by word segmentation of the interactive content which correspondingly appears is obtained, and the occurrence frequency of the interactive content keywords in the interactive content which correspondingly appears is obtained. And then obtaining the total occurrence frequency of the interactive content keywords in the interactive content database, and comparing the total occurrence frequency of the interactive content keywords in the interactive content database with the total word number of the interactive content database to obtain the occurrence frequency of the interactive content keywords in the interactive content database.

After obtaining the frequency of the interactive content keyword appearing in the interactive content database, the public opinion trend of the interactive content keyword may be further displayed on a public opinion trend display page of the interactive content keyword, as shown in fig. 3, so that the user can intuitively know the public opinion trend of the interactive content keyword. Specifically, the number of the interactive content keyword items with the public opinion tendency can be selected by the user, such as selecting and displaying the top ten items, or the top three items.

Further, interactive content keywords can be exported, as shown in fig. 4, which facilitates subsequent analysis of the reason for live broadcast abnormality and perfection of a scheme for solving the abnormality.

205, adjusting the video interaction based on the video interaction adjustment policy.

Adjusting the video interaction based on the video interaction adjustment policy, for example, when the interactive content keyword is a card, performing definition adjustment on the client that the card is stuck, specifically, as shown in fig. 5, adjusting the definition to a default definition, and turning off the client hard flick. Therefore, live broadcast bandwidth, on-line and blocking rate can be guaranteed within a reasonable range, excessive bandwidth consumption and serious blocking caused by the excessive bandwidth consumption are avoided, and service cost and experience are balanced.

Further, before step 205, the method may further include:

and acquiring the appearance position corresponding to the interactive content keyword based on a mapping relation set, wherein the mapping relation set comprises the mapping relation between the interactive content keyword and the appearance position and appearance frequency.

When video interactive adjustment is performed, adjustment can be performed on part of the clients, for example, part of the clients with the stuck state, and video interactive adjustment can be performed only on the clients with the stuck state, for example, resolution adjustment is performed on the clients with the stuck state. Or to all clients joining the video. For example, when there are many clients with the same abnormal problem, in order to reduce and acquire the identifier of the client with the abnormal problem, the positions of the interactive content keywords do not need to be located, and all the clients added to the video can be adjusted, so that the efficiency of video interactive adjustment is improved.

Specifically, when video interaction adjustment is performed on part of the clients, the appearance positions corresponding to the interactive content keywords are obtained based on the mapping relation set.

When video interaction adjustment is performed on part of the clients, the specific adjustment process is to adjust the video interaction corresponding to the occurring position based on the video interaction adjustment strategy. For example, a client that obtains the interactive content corresponding to the interactive keyword appears, and for the obtained client, video interactive adjustment is performed based on a video interactive adjustment strategy corresponding to the interactive keyword.

Further, after the step of "obtaining the occurrence frequency of the interactive content keyword according to the interactive content database", the method further includes:

acquiring a client identifier for displaying the interactive content and the position of the interactive content key words in the interactive content database;

and establishing a mapping relation set of the interactive content key words, the client identification, the positions in the interactive content database and the occurrence frequency.

The appearance position includes an interactive content position and a client position of the interactive content keyword, after the interactive content keyword is obtained, a client identifier corresponding to the client displaying each piece of interactive content and a position of the interactive content keyword in the interactive content database can be further obtained, for example, if the interactive content in the interactive content database is the first piece of interactive content, the interactive content is "Haka", the interactive content keyword is "card", and the position of the interactive content keyword in the interactive content database can be represented as (1, 2). Establishing a mapping relationship set of the interactive content keywords, the client identifier, the position in the interactive content database, and the occurrence frequency, wherein the established mapping relationship set can be obtained by establishing based on an inverted index, for example, the interactive content keywords are cards, the client identifier is XX, the position of the interactive content keywords in the interactive content database is (1, 2), and the occurrence frequency is 50%, and then the mapping relationship set established based on the inverted index can be:

the positions of the client identifier and the interactive content keyword in the interactive content database can be unified as the appearance positions for displaying, which is not limited herein. In the subsequent searching process, for example, assuming that the interactive content keyword "card" is searched, the searching process is to perform binary search on the mapping relationship set to search for the keyword, read out all the interactive content numbers through the pointer pointing to the mapping relationship set, and then return the result. The mapping relation set is usually very small, so that the time required by the whole query process is very short, the query efficiency is improved, and the efficiency of processing abnormal conditions occurring in the video playing process is further improved.

Further, in order to clearly express the position of the standard interactive content keyword in the interactive content database, the numbering process may be performed on the interactive content in the interactive content database, and specifically, the obtaining the position of the interactive content keyword in the interactive content database may include:

sequencing all characters included in the interactive contents according to the total word number of each piece of interactive contents to obtain the serial numbers of all the characters;

sequencing the interactive contents in the interactive content database according to the acquisition sequence to obtain the serial numbers of the interactive contents;

and acquiring the position of the interactive content key word in the interactive content database according to the character number and the interactive content number.

Specifically, the characters included in each interactive content can be sequenced according to the total word number of each interactive content, and the serial number of each character is obtained; for example, the interactive content is "good card", that is, the character number in the interactive content is 1, the character number in the interactive content is 2, and the character number in the interactive content is 3. And sequencing the interactive contents in the interactive content database according to the acquisition sequence to obtain the serial numbers of the interactive contents, wherein the sequencing mode is similar to the mode of sequencing the characters included in the interactive contents, and the description is omitted here. And obtaining the position of the interactive content key words in the interactive content database according to the character number and the interactive content number.

Further, after the mapping relationship set of the interactive content keyword, the client identifier, the position in the interactive content database, and the occurrence frequency is established, in order to reduce the storage space, the storage may be performed after compression processing, specifically:

compressing the interactive content key words, the client identification, the positions in the interactive content database and the occurrence frequency included in the mapping relation set to obtain a compressed mapping relation set;

and storing the compressed mapping relation set.

Specifically, the interactive content keywords are compressed into the expression form of < prefix length, suffix >, and if the interactive content keywords are "card-in" and the last word is "card", then "card-in" is compressed into <1, so that the saved bytes are reduced. Compressing the numbers in sequence to obtain a compressed mapping relation set; and the compressed mapping relation set is stored, so that the storage space is reduced.

In the video interaction adjustment method provided by the embodiment, interaction content for a video is acquired; extracting keywords from the interactive content to obtain interactive content keywords; when the occurrence frequency of the interactive content keywords is greater than a preset threshold value, acquiring a video interaction adjustment strategy corresponding to the interactive content keywords, wherein the occurrence frequency is the occurrence frequency of the interactive content keywords in an interactive content database; and adjusting the video interaction based on the video interaction adjusting strategy. According to the scheme, the corresponding video interaction adjustment strategy is directly obtained according to the interactive content keywords, the video interaction is directly adjusted according to the video interaction adjustment strategy, manual watching and adjustment are not needed, and therefore the video interaction adjustment efficiency is improved.

The method according to the preceding embodiment is illustrated in further detail below by way of example.

In this embodiment, the video interaction adjusting apparatus is specifically integrated in a server as an example for explanation. The server may include multiple types of servers, the number of each type of server may be determined according to a specific application scenario, and the servers may be deployed in different regions or rooms, or use different network providers. The server comprises a user input layer and a video interaction adjusting layer. Different hierarchies may be implemented using different types of servers. For example, as shown in fig. 6a, it is exemplified to include at least one input server, at least one video interaction adjustment server, wherein the functions of various types of servers can be as follows:

(1) inputting a server;

the import server essentially assumes "access stratum" functionality for communicating communications between the client and the server cluster, such as with reference to fig. 6 a.

For example, as shown in fig. 6a, the input server (i.e., the access layer) may specifically receive various types of interactive contents, such as cards, black screens, and small sounds, sent by the client, and transmit the received various types of interactive contents to the interactive content processing server.

(2) An interactive content processing server;

for example, referring to fig. 6a, the interactive content processing server may receive the interactive content input by the input server, extract keywords from the interactive content to obtain interactive content keywords, calculate the occurrence probability of the interactive content keywords, extract a video interaction adjustment policy corresponding to the interactive content keywords when the occurrence probability is greater than a preset value, and then send the extracted video interaction adjustment policy to the parameter adjustment server.

(3) A parameter adjustment server;

the parameter adjusting server is mainly used for adjusting video parameters. Such as shown in fig. 6 a. The parameter adjusting server is used for adjusting abnormal conditions occurring in the playing process of various videos. Such as stuck, black screen, loud, etc.

As shown in fig. 6b, a specific process of a video interaction adjustment method may be as follows:

601, an input server acquires interactive content aiming at a video and sends the acquired interactive content to an interactive content processing server;

the method comprises the steps of obtaining interactive content aiming at a video, and inputting the interactive content by a user through a video client, wherein the client can be a terminal such as a mobile phone, a tablet personal computer, a palm computer PDA and the like. The video can be live webcast, which refers to a playing mode that video data can be watched through a network system on different communication platforms at the same time, and it can be understood that various types of messages can be generated in the process of watching the video data in the live webcast mode, such as interactive contents published to the video data by a live user end. The interactive content mainly comprises a bullet screen, a message and the like.

602, an interactive content processing server acquires historical interactive content;

603, the interactive content processing server obtains the nonsense word according to the historical interactive content;

604, the interactive content processing server constructs a database of meaningless words;

605, the interactive content processing server filters the interactive content according to the semantic word free database to obtain the filtered interactive content.

Firstly, historical interactive content is obtained, and nonsense words, such as ' having ' and the like ' which have more occurrences in the interactive content and have no practical meaning, are obtained according to the historical interactive content, and then a nonsense word database is constructed according to the nonsense words; and filtering the interactive content according to the nonsense word database to obtain the filtered interactive content. Namely, the non-meaning words in the interactive content are filtered and deleted, so that the non-meaning words do not need to be matched and extracted when the keywords are extracted, the matching times are reduced, and the matching efficiency is improved.

606, the interactive content processing server obtains the associated interactive content keyword library;

607, the interactive content processing server searches in the associated interactive content keyword library to match the keywords in the interactive content.

And acquiring a related interactive content keyword library, wherein the interactive content keyword library is obtained by analyzing and establishing the historical live interactive content. Specifically, historical live broadcast interactive content is obtained, text analysis is carried out on the obtained historical live broadcast interactive content, and word segmentation processing can be carried out on the historical live broadcast interactive content through a full segmentation algorithm to obtain word segmentation of the historical live broadcast interactive content; quantizing the participles of the historical live broadcast interactive content through a neural network language model to obtain word vectors of the participles of the historical live broadcast interactive content; inputting the word vector of the participle of the historical live broadcast interactive content into a preset database model, and obtaining the Euclidean distance between the word vector of the participle of the historical live broadcast interactive content and the word vector in a preset database; analyzing the semantics of the historical live broadcast interactive content according to the Euclidean distance between the word vectors of the participles of the historical live broadcast interactive content and the word vectors in the preset database, carrying out word classification on the historical live broadcast interactive content according to the semantics of the historical live broadcast interactive content, calculating the occurrence frequency of various words according to the historical live broadcast interactive content after the word classification, setting the words with the occurrence frequency larger than the preset value as keywords, and establishing a content keyword library according to the set keywords. Furthermore, keywords corresponding to abnormal types which are less in appearance but also need to be solved in the live broadcast adding process can be further added in the content keyword library.

608, the interactive content processing server associates each interactive content keyword with a corresponding video interaction adjustment policy.

609, the interactive content processing server establishes an interactive content database according to the acquired interactive content;

and 610, the interactive content processing server calculates the occurrence frequency of the interactive content keywords according to the interactive content database.

The occurrence frequency may include a frequency of the interactive content keyword corresponding to the occurring interactive content and a frequency in the interactive content database. Specifically, an interactive content database is established according to the acquired interactive content, the occurrence frequency of the interactive content keywords is calculated according to the interactive content database, specifically, the interactive content in the interactive content database can be subjected to word segmentation to obtain word segmentation of the interactive content, then the occurrence frequency of the interactive content keywords in the interactive content which correspondingly appears is calculated, then the ratio of the occurrence frequency of the interactive content keywords in the interactive content which correspondingly appears to the word which is obtained by word segmentation of the interactive content which correspondingly appears is calculated, and the occurrence frequency of the interactive content keywords in the interactive content which correspondingly appears is obtained. And then obtaining the total occurrence frequency of the interactive content keywords in the interactive content database, and comparing the total occurrence frequency of the interactive content keywords in the interactive content database with the total word number of the interactive content database to obtain the occurrence frequency of the interactive content keywords in the interactive content database.

611, when the occurrence frequency of the interactive content keyword is greater than a preset threshold, the interactive content processing server obtains a video interaction adjustment strategy corresponding to the interactive content keyword.

Further, after the interactive content keywords are obtained, whether live video parameters need to be adjusted or not can be judged according to the occurrence frequency of the interactive content keywords. Specifically, the occurrence frequency of the interactive content keywords is compared with a preset frequency, if the occurrence frequency of the interactive content keywords is greater than the preset frequency, that is, greater than a preset threshold, it is determined that the live video parameters need to be adjusted, otherwise, it is determined that the live video parameters do not need to be adjusted. And when the occurrence frequency of the interactive content keywords is determined to be greater than a preset threshold value, acquiring a video interaction adjustment strategy corresponding to the interactive content keywords.

612, the interactive content processing server obtains a client identifier for displaying the interactive content and a position of the interactive content keyword in the interactive content database;

613, the interactive content processing server constructs a mapping relation set of the interactive content keywords, the client identifiers, the positions in the interactive content database and the occurrence frequencies.

the positions of the client identifier and the interactive content keyword in the interactive content database can be unified as the appearance positions for displaying, which is not limited herein. In the subsequent searching process, for example, assuming that the interactive content keyword "card" is searched, the searching process is to perform binary search on the mapping relationship set to search for the keyword, read out all the interactive content numbers through the pointer pointing to the mapping relationship set, and then return the result. The mapping relation set is usually very small, so that the time required by the whole query process is very short, the query efficiency is improved, and the efficiency of processing video playing abnormal conditions is further improved.

and storing the compressed mapping relation set.

614, the interactive content processing server obtains the appearance position corresponding to the interactive content keyword based on a mapping relation set, wherein the mapping relation set comprises the mapping relation between the interactive content keyword and the appearance position and appearance frequency;

after the video interaction adjustment strategy corresponding to the interactive content keywords is obtained, the appearance positions corresponding to the interactive content keywords can be obtained based on the pre-established mapping relation set, and therefore the appearance positions of the interactive content can be accurately positioned.

615, sending the video interaction adjustment strategy to the appearance position to a parameter adjustment server.

And 616, adjusting the video parameters corresponding to the appearance positions by the parameter adjusting server based on the video interaction adjusting strategy.

Adjusting video parameters corresponding to the appearance position based on a video interaction adjustment strategy, wherein when video interaction adjustment is performed on the appearance position, the video interaction adjustment is generally performed on part of the clients, for example, when the interactive content keyword is a card, resolution adjustment is performed on the client with the card, specifically, as shown in fig. 5, default resolution is adjusted, and client hard flicking is turned off. Therefore, live broadcast bandwidth, on-line and blocking rate can be guaranteed within a reasonable range, excessive bandwidth consumption and serious blocking caused by the excessive bandwidth consumption are avoided, and service cost and experience are balanced.

Further, when the number of the abnormal conditions is too large, all adjustments can be performed, for example, when the number of the clients with cards reaches 80%, that is, the occurrence frequency of the interactive content keywords is high, the definition of all the clients playing the video can be adjusted, and the positions where the interactive content keywords appear are not needed to be located. With further reference to fig. 5, the specific video interaction adjustment may further include current limit adjustment, frame rate adjustment, and the like.

As can be seen from the above, the present embodiment obtains the interactive content for the video; extracting keywords from the interactive content to obtain interactive content keywords; when the occurrence frequency of the interactive content keywords is greater than a preset threshold value, acquiring a video interactive adjustment strategy corresponding to the interactive content keywords; acquiring the appearance position corresponding to the interactive content keyword based on a mapping relation set, wherein the mapping relation set comprises the mapping relation between the interactive content keyword and the appearance position and the appearance frequency, and the appearance position comprises the interactive content position and the client position of the interactive content keyword; and adjusting the video parameters corresponding to the appearance positions based on the video interaction adjustment strategy. According to the scheme, the corresponding video interaction adjustment strategy is directly obtained according to the interactive content keywords, the video parameters are directly adjusted according to the positions where the interactive content keywords appear, manual watching and adjustment are not needed, and therefore the video parameter adjustment efficiency is improved.

In order to better implement the above method, an embodiment of the present invention may further provide a video interaction adjusting apparatus, where the video interaction adjusting apparatus may be specifically integrated in a network device, and the network device may be a terminal or a server.

For example, as shown in fig. 7a, the video interaction adjusting apparatus may include a first obtaining unit 701, an extracting unit 702, a second obtaining unit 703 and an adjusting unit 704, as follows:

(1) a first acquisition unit 701;

a first obtaining unit 701, configured to obtain interactive content for a video.

(2) An extraction unit 702;

an extracting unit 702, configured to perform keyword extraction on the interactive content to obtain an interactive content keyword.

And acquiring an associated interactive content keyword library, searching in the associated interactive content keyword library, and matching keywords in the interactive content.

(3) A second acquisition unit 703;

a second obtaining unit 703 is configured to obtain a video interaction adjustment policy corresponding to the interactive content keyword when the occurrence frequency of the interactive content keyword is greater than a preset threshold, where the occurrence frequency is the occurrence frequency of the interactive content keyword in an interactive content database.

Furthermore, after the interactive content keywords are obtained, whether live video interaction needs to be adjusted or not can be judged according to the occurrence frequency of the interactive content keywords. Specifically, the occurrence frequency of the interactive content keywords is compared with a preset frequency, if the occurrence frequency of the interactive content keywords is greater than the preset frequency, that is, greater than a preset threshold, it is determined that the live video interaction needs to be adjusted, otherwise, it is determined that the live video interaction does not need to be adjusted. And when the occurrence frequency of the interactive content keywords is determined to be greater than a preset threshold value, acquiring a video interaction adjustment strategy corresponding to the interactive content keywords.

(4) An adjustment unit 704;

an adjusting unit 704, configured to adjust the video interaction based on the video interaction adjusting policy.

Specifically, as shown in fig. 7b, the video interaction adjusting apparatus may further include a third obtaining unit 705;

a third obtaining unit 705, configured to obtain the occurrence position corresponding to the interactive content keyword based on a mapping relationship set, where the mapping relationship set includes mapping relationships between the interactive content keyword and the occurrence position and the occurrence frequency.

Specifically, as shown in fig. 7c, the video interaction adjusting apparatus may further include a first establishing unit 706, a calculating unit 707, a fourth obtaining unit 708, and a second establishing unit 709:

a first establishing unit 706, configured to establish an interactive content database according to the acquired interactive content;

a calculating unit 707 configured to calculate an occurrence frequency of the interactive content keyword according to the interactive content database;

a fourth obtaining unit 708, configured to obtain a client identifier for displaying the interactive content and a position of the interactive content keyword in the interactive content database;

the second establishing unit 709 is configured to establish a mapping relationship set of the interactive content keyword, the client identifier, the position in the interactive content database, and the occurrence frequency.

the positions of the client identifier and the interactive content keyword in the interactive content database can be unified as the appearance positions for displaying, which is not limited herein. In the subsequent searching process, for example, assuming that the interactive content keyword "card" is searched, the searching process is to perform binary search on the mapping relationship set to search for the keyword, read out all the interactive content numbers through the pointer pointing to the mapping relationship set, and then return the result. The mapping relation set is usually very small, so that the time required by the whole query process is very short, the query efficiency is improved, and the efficiency of video playing abnormity is further improved.

Specifically, as shown in fig. 7d, the fourth obtaining unit may include an ordering subunit 710 and a obtaining subunit 711:

a sorting subunit 710, configured to sort, according to the total word number of each piece of interactive content, each character included in the piece of interactive content, to obtain a serial number of each character; sequencing the interactive contents in the interactive content database according to the acquisition sequence to obtain the serial numbers of the interactive contents;

the obtaining subunit 711 is configured to obtain, according to the text number and the interactive content number, a position of the interactive content keyword in the interactive content database.

As can be seen from the above, the first obtaining unit 701 of the video interaction adjusting apparatus of the present embodiment obtains the interaction content for the video; the extraction unit 702 performs keyword extraction on the interactive content to obtain interactive content keywords; when the occurrence frequency of the interactive content keyword is greater than a preset threshold, the second obtaining unit 703 obtains a video interaction adjustment policy corresponding to the interactive content keyword; the adjusting unit 704 adjusts the video interaction based on the video interaction adjusting policy. According to the scheme, the corresponding video interaction adjustment strategy is directly obtained according to the interactive content keywords, and manual watching and adjustment are not needed, so that the video interaction adjustment efficiency is improved.

An embodiment of the present invention further provides a server, as shown in fig. 8, which shows a schematic structural diagram of the server according to the embodiment of the present invention, specifically:

the server may include components such as a processor 701 of one or more processing cores, memory 702 of one or more computer-readable storage media, a power supply 703, and an input unit 704. Those skilled in the art will appreciate that the server architecture shown in FIG. 8 is not meant to be limiting, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:

the processor 701 is a control center of the server, connects various parts of the entire server using various interfaces and lines, and performs various functions of the server and processes data by running or executing software programs and/or modules stored in the memory 702 and calling data stored in the memory 702, thereby performing overall monitoring of the server. Optionally, processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 701.

The memory 702 may be used to store software programs and modules, and the processor 701 executes various functional applications and data processing by operating the software programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to the use of the server, and the like. Further, the memory 702 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 702 may also include a memory controller to provide the processor 701 with access to the memory 702.

The server further includes a power source 703 for supplying power to each component, and preferably, the power source 703 may be logically connected to the processor 701 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system. The power supply 703 may also include any component including one or more of a dc or ac power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

The server may also include an input unit 704, and the input unit 704 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

Although not shown, the server may further include a display unit and the like, which will not be described in detail herein. Specifically, in this embodiment, the processor 701 in the server loads the executable file corresponding to the process of one or more application programs into the memory 702 according to the following instructions, and the processor 701 runs the application program stored in the memory 702, thereby implementing various functions as follows:

acquiring interactive content aiming at a video;

The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.

To this end, the present invention provides a storage medium, in which a plurality of instructions are stored, where the instructions can be loaded by a processor to execute the steps in any one of the video interaction adjusting methods provided by the embodiments of the present invention. For example, the instructions may perform the steps of:

acquiring interactive content aiming at a video;

Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.

Since the instructions stored in the storage medium can execute the steps in any video interaction adjustment method provided in the embodiments of the present invention, beneficial effects that can be achieved by any video interaction adjustment method provided in the embodiments of the present invention can be achieved, which are detailed in the foregoing embodiments and will not be described herein again.

The video interaction adjustment method, apparatus, device and storage medium provided by the embodiments of the present invention are described in detail above, and a specific example is applied in the present disclosure to explain the principle and the implementation of the present invention, and the description of the above embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A video interaction adjustment method is characterized by comprising the following steps:

acquiring interactive content aiming at a video;

acquiring the occurrence frequency of the interactive content keywords according to the interactive content database;

establishing a mapping relation set of the interactive content key words, the client identification, the positions in the interactive content database and the occurrence frequency;

acquiring the appearance positions corresponding to the interactive content keywords based on the mapping relation set, wherein the mapping relation set comprises the mapping relation among the interactive content keywords, the appearance positions and the appearance frequency, and the appearance positions comprise the positions of the interactive content keywords in the interactive content database and a client for displaying the interactive content;

and adjusting the video interaction corresponding to the appearance position based on the video interaction adjustment strategy.

2. The video interaction adjustment method of claim 1, wherein the obtaining the position of the interactive content keyword in the interactive content database comprises:

3. The video interaction adjustment method of claim 1, wherein after establishing the set of mapping relationships among the interactive content keywords, the client identifiers, the positions in the interactive content database, and the occurrence frequencies, the method further comprises:

and storing the compressed mapping relation set.

4. The video interaction adjustment method of claim 2, wherein the adjusting the video interaction based on the video interaction adjustment policy comprises:

acquiring an interactive content number and a character number of the interactive content key word in the interactive content database according to the interactive content key word;

acquiring a client identifier of the interactive content keyword according to the interactive content number;

and adjusting the video parameters corresponding to the client identification through the video interaction adjustment strategy.

5. The video interaction adjustment method of claim 1, wherein the extracting keywords from the interaction content to obtain interaction content keywords comprises:

acquiring a related interactive content keyword library;

and searching in the associated interactive content keyword library to match out keywords in the interactive content.

6. The video interaction adjustment method of claim 1, wherein before the extracting keywords from the interactive content to obtain interactive content keywords, the method further comprises:

acquiring historical interactive content;

acquiring an unambiguous word according to the historical interactive content;

constructing a database of the meaningless words;

and filtering the interactive content according to the nonsense word database to obtain the filtered interactive content.

7. A video interaction adjustment device, comprising:

the second establishing unit is used for establishing a mapping relation set of the interactive content key words, the client identification, the positions in the interactive content database and the occurrence frequency;

a third obtaining unit, configured to obtain an occurrence position corresponding to the interactive content keyword based on the mapping relationship set, where the mapping relationship set includes mapping relationships between the interactive content keyword and the occurrence position and the occurrence frequency, and the occurrence position includes a position of the interactive content keyword in the interactive content database and a client that displays the interactive content;

and the adjusting unit is used for adjusting the video interaction corresponding to the appearance position based on the video interaction adjusting strategy.

8. A video interaction adjustment device, comprising: a processor and a memory; the memory stores a plurality of instructions, and the processor loads the instructions stored in the memory to execute the video interaction adjusting method according to any one of claims 1 to 6.

9. A storage medium storing instructions adapted to be loaded by a processor to perform the video interactive adjustment method of any one of claims 1 to 6.