CN110475155B

CN110475155B - Live video hot state identification method, device, equipment and readable medium

Info

Publication number: CN110475155B
Application number: CN201910765321.3A
Authority: CN
Inventors: 姜子阳
Original assignee: Beijing ByteDance Network Technology Co Ltd
Current assignee: Beijing ByteDance Network Technology Co Ltd
Priority date: 2019-08-19
Filing date: 2019-08-19
Publication date: 2022-02-18
Anticipated expiration: 2039-08-19
Also published as: CN110475155A

Abstract

The disclosure discloses a live video hot state identification method, a live video hot state identification device, live video hot state identification equipment and a readable medium. The method comprises the following steps: in the process of live broadcasting of a main broadcasting user, acquiring a heat evaluation parameter of the live broadcasting video; the heat evaluation parameters comprise fan parameters and/or income parameters; and generating an identification result of the current popularity state of the live video according to the popularity evaluation parameter. The scheme of the embodiment of the disclosure can realize multi-dimensional evaluation parameters, accurately identify the real-time heat state of the live video, and provide guarantee for real-time and fair awarding of the main broadcast user to the live platform.

Description

Live video hot state identification method, device, equipment and readable medium

Technical Field

The embodiment of the disclosure relates to the technical field of internet, in particular to a live video hot state identification method, a live video hot state identification device, live video hot state identification equipment and a readable medium.

Background

Currently, in a live video application, a main broadcast user can attract audience users on a live broadcast platform to watch the live broadcast by starting a video live broadcast function. In order to enhance the watching popularity of the live video of the live platform, the live platform can give an additional reward to the anchor user with a high popularity state of the live video. However, because there are many factors that affect the hot status of the live video, such as the quality of the video content, the type of the video subject matter, and the live time, it is difficult for the live platform to accurately identify the hot status of the live video in real time, which further affects the fairness and real-time property of the rewards to the anchor user, and improvement is urgently needed.

Disclosure of Invention

The embodiment of the disclosure provides a live video heat state identification method, a live video heat state identification device and a readable medium, so that a real-time heat state of a live video is accurately identified based on multidimensional evaluation parameters, and a guarantee is provided for a live platform to give rewards to anchor users in real time and fairly.

In a first aspect, an embodiment of the present disclosure provides a live video hotness status identification method, where the method includes:

in the process of live broadcasting of a main broadcasting user, acquiring a heat evaluation parameter of the live broadcasting video; the heat evaluation parameters comprise fan parameters and/or income parameters;

and generating an identification result of the current popularity state of the live video according to the popularity evaluation parameter.

In a second aspect, an embodiment of the present disclosure further provides a live video hotness status recognition apparatus, where the apparatus includes:

the evaluation parameter acquisition module is used for acquiring popularity evaluation parameters of a live video in the process of live video broadcast of a main broadcast user; the heat evaluation parameters comprise fan parameters and/or income parameters;

and the popularity state identification module is used for generating an identification result of the current popularity state of the live video according to the popularity evaluation parameter.

In a third aspect, an embodiment of the present disclosure further provides an electronic device, where the electronic device includes:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement a live video hotness status identification method as described in any embodiment of the present disclosure.

In a fourth aspect, the embodiments of the present disclosure provide a readable medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a live video hot status identification method according to any embodiment of the present disclosure.

The embodiment of the disclosure provides a live video popularity state identification method, a live video popularity state identification device, a live video popularity evaluation parameter containing a fan parameter and/or an income parameter is obtained in a live video broadcasting process of a main broadcasting user, and an identification result of a current popularity state of a live video is generated based on the popularity evaluation parameter. The scheme of the embodiment of the disclosure can realize multi-dimensional evaluation parameters, accurately identify the real-time heat state of the live video, and provide guarantee for real-time and fair awarding of the main broadcast user to the live platform.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.

Fig. 1 shows a flowchart of a live video hot status identification method provided by an embodiment of the present disclosure;

2A-2B illustrate a flow chart of another live video hot status identification method provided by the embodiments of the present disclosure;

fig. 3 shows a flowchart of another live video hot status identification method provided by the embodiment of the present disclosure;

fig. 4 is a schematic structural diagram illustrating a live video hot status recognition apparatus provided by an embodiment of the present disclosure;

fig. 5 shows a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise. The names of messages or information exchanged between multiple parties in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

Fig. 1 is a flowchart of a live video hot status identification method provided in an embodiment of the present disclosure, where this embodiment is applicable to a case where a live video hot status is identified in a live process of a anchor user, and the method may be executed by a live video hot status identification device or an electronic device, where the live video hot status identification device may be implemented in a software and/or hardware manner, and the live video hot status identification device may be configured in the electronic device. Optionally, the electronic device may be a device corresponding to a backend live broadcast platform of the application program, and may also be a mobile terminal device installed with an application program client.

Optionally, as shown in fig. 1, the method in this embodiment may include the following steps:

s101, in the process of live broadcasting of a main broadcasting user, obtaining a popularity evaluation parameter of the live broadcasting video.

The popularity assessment parameter may refer to a judgment parameter for predicting the fire popularity of the live video of the anchor user, which may include, but is not limited to, a fan parameter and/or a revenue parameter.

Optionally, the revenue corresponding to the revenue parameter includes: the primary revenue of the anchor user live video and/or the additional revenue of the fans watching the live video. The basic income can be fixed income given to the anchor user by the pre-appointed by the live broadcast platform and the anchor user. The additional revenue may be bonus revenue that the live platform gives to the anchor user and/or gift revenue that the fan user gives to the anchor user when the anchor user is highly exciting in live content. Alternatively, the revenue parameters may include, but are not limited to: amount and type of income; when the income is reward income of the gift class, the income parameter may further include a name, a unit price, a quantity, and the like of the gift.

Optionally, the fan parameters may further include a fan quantity parameter and/or a fan preference parameter. The number parameter of the fans can refer to the total number of fans of a certain category. The fan preference parameter may be a parameter of a degree of likeness of fans to live videos, for example, a certain live video on a live broadcast favorite platform; or a certain type of live video on a live broadcast platform is liked; but also a certain anchor user who likes on the live platform, etc. Optionally, the fans corresponding to the fan parameters include: at least one of a current watching fan of the live broadcast platform, a high-consumption fan of the live broadcast platform, a current watching fan of the anchor user, a new fan of the anchor user, and a pre-lost fan of the anchor user.

The current watching fan of the live broadcast platform can refer to all fan users who watch live broadcast videos on the live broadcast platform at present. For example, if 100 anchor users are live on the live broadcast platform at the current moment, the sum of the fans watching the 100 live videos is the current watching fan of the live broadcast platform. The high-consumption fans in the live broadcast platform can be fans which are used for frequently sending gifts to the anchor user on the live broadcast platform and have higher money for sending the gifts. A current viewing fan of a anchor user may refer to a fan user of all fans of the anchor user who is viewing their live video. For example, if 30 fans of 100 fans of a certain anchor user are currently watching a live video, the 30 fan users are the current watching fans of the anchor user. The new fan of the anchor user may refer to a fan user who newly increases in a preset time period (for example, within a week or during a live broadcast) and pays attention to the anchor. The pre-lost fan of the anchor user may refer to a fan user who is about to cancel attention among the existing fan users of the anchor user.

Optionally, in the process of live broadcasting the video by the anchor user, the step may obtain the heat evaluation parameter of the live video in real time or at regular time (e.g., every 10 minutes). Specifically, one possible implementation of the revenue acquisition parameter may be: the live broadcast platform records income parameters of each anchor user, and the electronic equipment can acquire the current basic income and/or income parameters of the live broadcast user through the live broadcast platform in the process of live broadcasting videos of the anchor users. Another possible implementation of the revenue capture parameter may be: and aiming at the basic income parameters, the electronic equipment detects the current live broadcast duration of the anchor user and obtains the income parameters of the basic income by combining the preset incidence relation between the live broadcast duration of the anchor user and the basic income. Wherein, the association relationship may be a basic income (e.g. 50 yuan) of the amount corresponding to each unit time length (e.g. one hour) of the live broadcast of the anchor; or the main broadcast user live broadcasts the live broadcast for a preset time (such as 4 hours) to give the main broadcast basic income (such as 300 yuan). For the extra income parameters, the electronic equipment can count the extra income parameters corresponding to the gifts given by the fans by detecting the names, unit prices and number of the gifts given by the fans in the live video process; whether an additional income parameter given by a live broadcast platform is acquired or not is determined by detecting whether the current live broadcast heat of a live broadcast user reaches a live broadcast platform reward standard or not.

Optionally, when obtaining the fan parameters, the electronic device may determine a fan user who needs to obtain the fan parameters, and if the fan parameters of the fan of each anchor user managed by the electronic device are recorded in the live broadcast platform in advance, the electronic device may obtain the required fan quantity parameters and/or fan preference parameters of each fan through the live broadcast platform in the process of live broadcasting the video by the anchor user. If the fan parameters are not recorded in the live broadcast platform, the electronic device may acquire all fan data of each fan user from the live broadcast platform, and then analyze and process the fan data to obtain the fan parameters of each fan, for example, the electronic device may count the number of fans to obtain the fan quantity parameters, analyze and process the fan data by using a trained user portrait model to obtain a fan portrait of the fan data, and further acquire fan preference parameters from the fan portrait.

Optionally, when determining a fan user corresponding to a fan parameter to be acquired, the electronic device may determine a current watching fan and a high-consumption fan of the live broadcast platform through interaction with the live broadcast platform; the current watched fans and the newly added fans of the anchor user can be obtained by monitoring the fan data statistical process in the current live broadcast video; for the pre-lost fans, the reduction proportion of the watching frequency and/or duration of the live broadcast by the fan in the current time period can be determined according to the frequency and/or duration of the live broadcast by the main broadcast user in the current time period and the last time period; and if the reduction proportion is larger than a preset proportion threshold value, the fan is a pre-lost fan of the anchor user.

Specifically, the sub-step may preset a time period (e.g., one week) for detecting the pre-lost fans and a preset ratio threshold (e.g., 70%). When determining the pre-lost fans of a anchor user, the frequency and/or duration of each fan of the anchor user watching the live video in the current time period (e.g., the current week) and the last time period (e.g., the last week) may be obtained separately. Optionally, the frequency may be the number of times or frequency that each fan watches its live video within a time period. The duration may be the duration of time for each of the fans to watch each of their live videos or the total duration of time for watching all of their live videos within a time period. And then determining the decreasing proportion of the fan watching the live broadcast frequency and/or duration in the current time period according to the obtained frequency and/or duration and the formula W ═ S1-S2)/S1. Wherein, W is a decreasing proportion; s1 is the frequency and/or duration of watching the live video of the anchor user in the last time period; s2 is the frequency and/or duration of viewing of the live video by the anchor user for the current time period. And judging whether the reduction proportion corresponding to each fan of the anchor user is larger than a preset proportion threshold value or not, if so, indicating that the proportion of the fan watching the live video of the anchor user is reduced seriously, and the fan is probably the fan which is about to be lost by the anchor user, namely the pre-lost fan. Otherwise, the fan is the stable fan of the anchor user.

And S102, generating an identification result of the current popularity state of the live video according to the popularity evaluation parameters.

The identification result of the current hot state of the live video may be a hot numerical value or a hot level corresponding to the hot state of the live video of the anchor user, optionally, the identification result may further include a hot evaluation parameter and intermediate data obtained in the process of evaluating the hot state of the live video, for example, the intermediate data may include but is not limited to: at least one of fan quantity, fan preference distribution data, fan preference migration data, income fluctuation numerical value, income fluctuation influence factor.

Optionally, in this step, according to the popularity assessment parameter, the process of generating the recognition result of the current popularity state of the live video may be: when the hotness evaluation parameter is a fan parameter, the current hotness state of the live video can be identified by the following method aiming at fan parameters corresponding to different fans. Specifically, when the fans are currently watched fans of the live broadcast platform or high-consumption fans of the live broadcast platform, the popularity of the corresponding live broadcast video in the current popularity state to be recognized is higher if the number or the proportion of the two types of fans which favor the theme type is higher according to the preference parameters of the two types of fans. When the fans are current watching fans of the anchor user or newly added fans of the anchor user, the number parameters and/or the preference parameters of the two types of fans can be determined, and if the number values of the two types of fans are larger, the heat of the corresponding live video in the current state to be identified is higher; aiming at the topic type to which the live video in the current hot state to be identified belongs, if the number or proportion of the two types of fans which favor the topic type is more, the hot degree of the corresponding live video in the current hot state to be identified is higher. When the fans are pre-lost fans of the anchor user, the number of the pre-lost fans can be according to the number parameter of the pre-lost fans, and if the number value of the pre-lost fans of the anchor user is less, the heat of the corresponding live video in the current state to be identified is higher. Optionally, when the popularity assessment parameter is a revenue parameter, the current popularity of the live video may be identified according to a basic revenue parameter and/or an additional revenue parameter in the revenue parameter. Specifically, the higher the amount of the basic income parameter and/or the extra income parameter is, the higher the popularity of the live broadcast video corresponding to the current state to be identified is; it may also be that the greater the number of the additional income parameters, for example, the greater the number of gifts corresponding to the additional income parameters, the higher the popularity of the live video corresponding to the current to-be-recognized status.

It should be noted that, how to identify the current hotness status of the live video according to the fan number parameter and/or fan preference parameter in the fan parameters and according to the basic income parameter and/or the extra income parameter in the income parameters in the step will be described in detail in the following embodiments.

Optionally, when the heat evaluation parameter is at least two types of parameters, the heat state corresponding to the parameter may be identified for each type of heat evaluation parameter, and then the identified multiple heat states are subjected to comprehensive processing (such as summation, averaging, weighted summation, weighted averaging, and the like) to obtain the current heat state of the live video.

The embodiment of the disclosure provides a live video popularity state identification method, which includes the steps of acquiring a live video popularity evaluation parameter containing a fan parameter and/or a income parameter in a live video broadcasting process of a main broadcasting user, and generating an identification result of the current popularity state of a live video based on the popularity evaluation parameter. The scheme of the embodiment of the disclosure can realize multi-dimensional evaluation parameters, accurately identify the real-time heat state of the live video, and provide guarantee for real-time and fair awarding of the main broadcast user to the live platform.

Optionally, in the live broadcast process, the anchor user can only estimate the heat of the live broadcast video by watching the number of live broadcast fans, so that the reason that the heat of the live broadcast video is low is difficult to accurately master, the content of the live broadcast video cannot be accurately optimized in real time to improve the heat of the live broadcast video, and the phenomenon is more serious especially for novice anchor. The enthusiasm of the anchor live broadcast is greatly influenced, and the loss of the live broadcast application program client is caused. In order to solve the problem, in this embodiment, after the electronic device generates the recognition result of the current popularity state of the live video, diagnostic data of the current popularity of the live video is generated according to the recognition result, and the diagnostic data is sent to the anchor user. The diagnosis data can be suggestion data for improving the hot status of the live video according to the current hot status of the live video, and the diagnosis data can include but is not limited to: the identification result of the hot state of the live video, the reason causing the current hot state, an improvement suggestion for the reason and the like. Optionally, when generating the diagnostic data of the current popularity of the live video according to the recognition result, popularity reason analysis may be performed on popularity evaluation parameters or data between the popularity evaluation parameters or data included in the recognition result, for example, if the recognition result of the current popularity state indicates that the popularity state of the live video is low, preference parameters of various fans may be analyzed, whether the analyzed preference data is the current live topic type of the anchor user is judged, if not, the diagnostic result indicates that the live video topic type of the live user is not preferred by the fans, and the favorite topic type of the fans is used as the topic type suggested to be adjusted during subsequent live broadcast, so that more fans are attracted to watch the live video. Wherein, the various vermicelli types can include: high-consumption fans in the live broadcast platform, current watching fans of the anchor user, newly-added fans of the anchor user, and pre-lost fans of the anchor user. If the income amount of the anchor is low, the favorite parameters of the high-consumption fans can be analyzed, and the favorite theme types of the high-consumption fans are used as theme types recommended to be adjusted in the subsequent live broadcasting process, so that the high-consumption fans are attracted to watch live videos. The advantage that this embodiment set up like this lies in, for the anchor user, it not only can know the hotness state of own live video in real time at live broadcasting in-process, can also acquire the diagnostic data to current live video, and then adjust the theme type of live content in real time according to this diagnostic data, thereby attract a large amount of fans, even if the beginner anchor, also can master the method that improves live video hotness fast, very big improvement the enthusiasm of live broadcast, strengthen the live video of live platform and watch the hotness.

2A-2B illustrate a flow chart of another live video hot status identification method provided by the embodiments of the present disclosure; the embodiment is optimized on the basis of the alternatives provided by the above embodiment, and specifically gives a detailed description of how to execute the live video hot status identification method when the hot evaluation parameter is a fan parameter and/or a revenue parameter.

Optionally, fig. 2A is a flowchart of a method for executing live video hot status recognition when the hot evaluation parameter is a fan parameter. The specific execution steps comprise:

s201, in the process of live broadcasting of videos by a main broadcasting user, acquiring vermicelli quantity parameters and vermicelli data, and inputting the vermicelli data into a user portrait model to obtain a vermicelli portrait of the vermicelli data.

The fan data may be the sum of the basic information of the fan user and the operation data on the live platform, and may include, but is not limited to: the user name, gender, age, region of the fan, viewing on an application program, operational data and comment data for collecting live video, and the like. The vermicelli data can be recorded on the live broadcast platform, and the electronic equipment can acquire the vermicelli data through interaction with the live broadcast platform. The vermicelli portrait can be a tool for sketching multi-dimensional characteristics such as attribute characteristics, behavior characteristics or preference characteristics of vermicelli, and can be obtained by abstracting the characteristics of each dimension into labels and accurately sketching the vermicelli portrait by using the labels.

Optionally, the drawing of the fan portrait in this embodiment may be performed by using a trained user portrait model. The user portrait model may be a neural network model that may be trained to delineate a user portrait using a large amount of sample user data. The embodiment can acquire the fan data of each fan in real time or at regular time in the process of live broadcasting of the video by the anchor user. Then, the relevant program code of the user portrait model is called for each fan, fan data of the fan is used as input data, and the relevant program code is operated, so that the user portrait model can draw the user portrait of the fan (namely the fan portrait) based on the input fan data. For example, fan data includes: the name of the live video is Zhang III, the gender of the live video is Male, the age of the live video is 20, the region of the live video is Beijing, the live video 1, the live video 2 and the live video 3 are watched in the last week, the watching time is in the period from six to seven pm, and the live video 1 to the live video 3 are sports type videos. At this time, the fan portrait obtained by sketching the fan data through the user portrait model may be: the vermicelli attribute feature label comprises: zhang III, male, youth, Beijing area; the behavior feature attributes include: the dinner is watched at the rest time; the preference feature attribute tags include: a game theme type.

It should be noted that, in the process of live broadcasting a video by a host user, the process of acquiring the fan number parameter in the embodiment is already described in the foregoing embodiment, and is not described herein again.

S202, fan preference parameters are obtained from the fan portrait.

Optionally, the fan portrait is formed by a label abstracted from each dimension feature, and a specific data parameter of the fan for the label feature is recorded in each label. For example, the fan attribute feature tag includes data parameters such as name, gender, age, and region; the behavior attribute feature tag comprises: data parameters such as operation time and operation behavior; the preference feature attribute tag comprises: preference theme type and the like. Therefore, in the step, the fan image is searched for the favorite feature attribute label aiming at each fan, and fan favorite parameters are obtained from the favorite feature attribute label. For example, fan preference parameters are obtained from the preference feature attribute label of the fan portrait sketched in S201: a game theme type.

S203, determining at least one of the number of fans, the favorite distribution data and the favorite migration data according to the fan parameters, and identifying the current hot state of the live video according to at least one of the number of fans, the favorite distribution data and the favorite migration data.

The fan-like parameter in this step includes at least one of the fan-like number parameter acquired in S201 and the fan-like preference parameter acquired in S202. Optionally, in this step, according to the number of fans in the fan parameters, the process of determining the number of fans may be: and acquiring the vermicelli quantity value in the vermicelli quantity parameter as the quantity of the vermicelli. According to the fan preference parameter in the fan parameters, the process of determining the current preference distribution can be as follows: and counting the number or the proportion of the corresponding fans under each preference according to the fan preference parameters of the obtained fans, so as to obtain the current preference distribution of the fans. For example, if statistics is performed on the obtained fan preference parameters to find that there are 10 fan preference gourmet theme types, 30 game preference theme types, and 60 song and dance preference theme types, it can be determined that the current preference distribution of fans is: the distribution of the types of the singing and dancing themes accounts for 60 percent; the game theme type distribution accounts for 30%; the cate subject type distribution accounts for 10%.

Optionally, in this embodiment, the fan portrait is sketched in real time or at regular time to obtain the fan preference parameter, so when determining the favorite migration data of the fan according to the fan preference parameter in this step, the favorite distribution data determined this time and the favorite distribution data determined last time may be analyzed, and the favorite migration change condition of each topic type in two adjacent favorite distributions is used as the favorite migration data. For example, if the current favorite distribution of the current fans is counted as: the distribution of the types of the singing and dancing themes accounts for 60 percent, the distribution of the types of the game themes accounts for 30 percent, and the distribution of the types of the food themes accounts for 10 percent; the favorite distribution of the vermicelli at the last time is as follows: the distribution of the types of the singing and dancing themes accounts for 10%, the distribution of the types of the game themes accounts for 80%, and the distribution of the types of the food themes accounts for 10%. Then the corresponding favorite migration data at this time is: the migration amount of the types of the singing and dancing themes is increased by 50%, the migration amount of the types of the game themes is reduced by 50%, and the migration amount of the types of the gourmet themes is unchanged.

Optionally, in the step, when the current hotness state of the live video is identified, if the current hotness state of the live video is identified according to the number of the fans, the number of the fans is in direct proportion to the current hotness state of the live video, that is, the number of the fans is more, and the hotness corresponding to the live video is higher. If the current popularity state of the live video is identified according to the preference distribution data and/or the preference migration data, the topic type of the current live video needs to be determined first, and the specific determination method can be various, for example, a pre-trained topic category identification model can be adopted to perform topic identification on the current live video through the current live video content, an association relation database for recording each topic type and corresponding candidate keywords can be constructed in advance, keyword extraction is performed on the live content, the title and the like of the current live video, the extracted keywords are matched with the candidate keywords recorded in the database, and the topic type corresponding to the matched candidate keywords is taken as the topic type to which the current live video belongs; or the theme type of the live video is recorded at a certain position of a live video interface, and the theme type of the live video can be directly extracted from the corresponding position of the live video page. After the theme type of the current live video is determined, if the current heat state of the live video is identified according to the determined current preference distribution of the fans, the corresponding distribution quantity or proportion of the theme type of the current live video in the current preference distribution can be in direct proportion to the heat state of the live video, namely, the higher the distribution quantity or proportion is, the higher the corresponding heat of the live video is. If the current popularity state of the live video is identified according to the determined favorite migration data of the fans, the corresponding migration number or proportion of the theme type of the current live video in the favorite migration data can be in direct proportion to the popularity state of the live video, namely, the higher the migration number or proportion is, the higher the popularity of the corresponding live video is.

It should be noted that, when the current heat state of the live video is identified according to at least one parameter of the number of the fans, the preference distribution data, and the preference migration data, if the current heat state of the live video is identified according to one of the parameters, the live video may be identified according to the corresponding method, and if the current heat state of the live video is identified according to at least two of the parameters, a heat state may be identified according to the corresponding method for each parameter, and then the heat states identified by the parameters are subjected to comprehensive processing (such as summation, averaging, weighted summation, weighted averaging, and the like) to obtain the current heat state of the live video.

Optionally, when the current heat state of the live video is identified according to the fan parameters in this step, in addition to identifying the current heat state of the live video according to the preset proportional relationship, a related program code of a neural network model trained in advance according to sample data and used for identifying the heat of the live video may be called, the number of fans is used as an input parameter, or the type of the topic to which the live video belongs and the current favorite distribution and/or analyzed favorite migration data of the fans are used as input data, and the program code is operated to obtain the current heat state of the live video. The sample data can be the number of fans and corresponding heat states, and can also be the theme type of the live video, the current favorite distribution of fans and/or the favorite migration data analyzed, and the heat state corresponding to the live video.

Optionally, fig. 2B is a flowchart of a method for performing live video hot status identification when the hot evaluation parameter is a revenue parameter. The specific execution steps comprise:

s204, in the process of live broadcasting of the video by the anchor user, income parameters of the live broadcasting video are obtained.

Optionally, in this step, a process of how to obtain the revenue parameter of the live video in the live video playing process of the anchor user is described in detail in the above embodiment, and is not described herein again.

S205, determining a fluctuation numerical value and/or fluctuation influence factor of the income according to the income parameters, and identifying the current popularity state of the live video according to the fluctuation numerical value and/or fluctuation influence factor.

Optionally, in this step, the process of determining the fluctuation value of the income according to the income parameter may be to determine the total income amount of this time according to the income parameter acquired this time; and performing fluctuation calculation on the determined income total amount and the income total amount of the last time determined according to the income parameters acquired last time to obtain a fluctuation numerical value. Wherein the total amount of revenue may be a base amount of revenue and/or an additional amount of revenue. The fluctuation operation can be interpolation operation of the total income amount of the current time and the previous total income amount; or the current income sum and the last income sum can be subjected to proportion increasing or proportion decreasing operation.

Alternatively, the influence of revenue fluctuation may be an influence that influences the total amount of revenue of this time, which may include, but is not limited to, a type of revenue, a number of gifts, a distribution of gift levels, and the like. In the step, when determining the fluctuation influence factors according to income parameters, the income types of the current time can be determined to include basic income types according to basic income parameters of live videos of anchor users; determining whether the type of the extra income belongs to platform reward income or gift income given by the fans according to the extra income parameter of the fans watching the live video; if the income type includes the gift income given by the fan, the grade of the gift and the number of the gift can also be determined. The gift level may be determined by dividing the gift into levels according to the value of the gift, for example, the gift with value below 10 yuan belongs to the first-level gift, the gift with value between 11-100 yuan belongs to the second-level gift, and the gift with value above 100 yuan belongs to the third-level gift. The number of gifts may be the total number of gifts or may be the number of gifts at each level.

Optionally, when the current popularity state of the live video is identified in this step, if the current popularity state of the live video is identified according to the fluctuation numerical value of the income, the size of the income fluctuation numerical value may be in direct proportion to the popularity state of the live video, that is, when the income fluctuation numerical value is positive, the larger the fluctuation is, the higher the popularity of the corresponding live video is. Conversely, when the income fluctuation value is negative, the larger the fluctuation is, the lower the corresponding live video heat is. If the identification is carried out according to the fluctuation influence factor of the income, the gift level in the fluctuation influence factor is in direct proportion to the hot degree state of the live video, namely the higher the gift level is, the higher the corresponding hot degree of the live video is; the number of gifts in the fluctuation influence factors can be in direct proportion to the hot degree state of the live video, namely, the larger the number of gifts, the higher the corresponding hot degree of the live video. It may also be that the number of categories included in the income type in the fluctuation influence factor is directly proportional to the hot status of the live video, that is, the larger the number of categories included in the income type, the higher the corresponding hot status of the live video. For example, if the live broadcast type only includes the basic income type, it indicates that the anchor user does not have additional income for vermicelli to watch the live broadcast video, that is, the preference degree of vermicelli to the live broadcast video is not high, and therefore the popularity of the corresponding live broadcast video is not high. Optionally, if the fluctuation value and the fluctuation influence factor of the revenue are determined, the specific identification process may identify two corresponding hotness status values according to the fluctuation value and the fluctuation influence factor of the revenue respectively by using the above method, and then perform comprehensive processing on the two hotness status values to obtain the current hotness status of the live video.

Optionally, when the current heat state of the live video is identified according to the income parameter in this step, in addition to identifying the current heat state of the live video according to the preset proportional relationship, a relevant program code of a neural network model trained by adopting sample data in advance and used for identifying the heat of the live video may be called, a fluctuation numerical value and/or fluctuation influence factor of income is used as input data, and the program code is operated to obtain the current heat state of the live video. The sample data may be a fluctuation value and/or a fluctuation influence factor, and a corresponding heat status.

It should be noted that, in the live video heat state identification of the embodiment of the present disclosure, the live video heat state may be identified through one of the fan parameters and the revenue parameters, and in order to further improve the accuracy of live video heat identification, the live video heat state corresponding to each parameter may be identified according to the fan parameters and the revenue parameters and by combining the heat identification methods corresponding to the two parameters, and then the identified multiple heat states are comprehensively processed to obtain the final current heat state of the live video.

The live video heat state identification method provided by the embodiment of the disclosure obtains different heat evaluation parameters, namely at least one of a fan number parameter, a fan preference parameter, a basic income parameter and an extra income parameter, in the process of live broadcasting of a main broadcasting user, correspondingly sets different heat evaluation rules for each heat evaluation parameter, identifies the current heat state of the live video of the main broadcasting user according to the heat evaluation rules corresponding to the heat evaluation parameters, greatly reduces the labor cost compared with the existing manual live video heat evaluation, and considers comprehensive factors, so that the heat identification of the live video is more accurate, and the real-time and fair promotion of the main broadcasting user is guaranteed for a live platform.

Fig. 3 shows a flowchart of another live video hot status identification method provided in the embodiment of the present disclosure, which is optimized based on the alternatives provided in the foregoing embodiments, and specifically gives a detailed description of generating diagnosis data of the current hot status of a live video according to a recognition result after generating the recognition result of the current hot status of the live video.

Optionally, as shown in fig. 3, the method in this embodiment may include the following steps:

s301, in the process of live broadcasting of the video by the anchor user, obtaining heat evaluation parameters of the live broadcasting video.

Wherein the heat evaluation parameters comprise fan parameters and/or income parameters.

And S302, generating an identification result of the current popularity state of the live video according to the popularity evaluation parameters.

And S303, when the current heat state in the identification result is detected to belong to the state to be diagnosed, acquiring the fan quantity mutation time period of the live video.

The state to be diagnosed may refer to a preset heat state in which a state reason diagnosis needs to be performed, for example, if the current heat state is represented by a state value, the state to be diagnosed may be a state in which the heat state value is lower than a lower limit state threshold value or higher than an upper limit threshold value; if the current hot state is represented by multiple state levels, the state to be diagnosed may be a low level and a high level state. The method and the device for diagnosing the low-heat state can obtain the reason of the low-heat, so that the live broadcast user can adjust live broadcast content in real time according to the diagnosis result, and the live broadcast heat is improved. The reason for the high heat can be obtained by diagnosing the high heat state, and a reference is provided for how to improve the heat of the live video. The event of the sudden change of the number of fans is an event corresponding to the sudden change (including sudden increase or sudden decrease) of the number of fans watching the live broadcast in the live broadcast process of the anchor user.

Optionally, in this step, after the identification result of the current hotness state of the live video is generated in S302, it may be detected whether the current hotness state in the identification result belongs to a preset state to be diagnosed, and if not, the current hotness state is general, and the reason for the state may not be diagnosed. If the current state is the current state, the reason needs to be diagnosed. Because the live video of the anchor user has long time and the current state is only caused by a small part of video content in the live video, the step needs to determine the time period for analyzing the current heat state, and the change of the number of fans watching the live video is the most intuitive change form of the heat change of the live video. Therefore, the time period when the number of the vermicelli in the live broadcast video changes suddenly can be obtained in the step and is used as the time period for analyzing the current heat state. Specifically, when acquiring the fan quantity mutation period of the live video, an implementation manner may be that a time corresponding to the acquisition of the heat evaluation parameter in S301 is taken as a first time, a time before the first time and separated from the first time by a preset time is taken as a second time, and a period between the first time and the second time is taken as the fan quantity mutation period, for example, if the time corresponding to the acquisition of the heat evaluation parameter is 8:10, and the first time and the second time are separated by 3 minutes. Then the first time is 8:10, the second time is 8:07 and the mutation period is 8:07-8: 10.

To further improve the accuracy of the determined mutation period, another possible implementation of this embodiment may be: intercepting reference live video content between a first moment and a second moment from a live video; the second moment is the moment corresponding to the acquired heat evaluation parameter, and the first moment is before the second moment and is separated from the second moment by a preset time length; and detecting a high-frequency time period of the release of the pop-up content in the reference live video content as the break-away time period of the fan quantity. Specifically, when the implementable mode is executed, the first implementable mode may be adopted, the first time and the second time are determined, then, instead of directly taking the time interval between the first time and the second time as the fan number mutation time interval, live video content between the first time and the second time is intercepted from the live video as reference live content, the occurrence frequency of the barrage in the reference live video content is analyzed, and the time interval with high barrage content publishing frequency in the reference live video content is taken as the fan number mutation time interval. Optionally, the corresponding bullet screen release number in unit time (e.g., per minute) in the reference live video content may be counted, and the duration period in which the bullet screen release number is greater than the preset number threshold is used as the fan number mutation period. Or at least one continuous time interval with the top ranking corresponding to the bullet screen release number per unit time can be used as the fan quantity mutation time interval.

It should be noted that the fan number mutation period obtained in this step may be one time period or a plurality of time periods.

S304, according to the time interval of the sudden change of the number of the fans, the target live broadcast video content corresponding to the time interval of the sudden change of the number of the fans is obtained from the live broadcast video.

Optionally, after the fan number mutation period is determined in S303, in the live video of the anchor user, the start time of the mutation period is used as the start time of the captured video, the end time of the mutation period is used as the end time of the captured video, and a section of live video content is captured from the live video and used as the target live video content for performing the reason analysis of the current hotness state.

S305, generating diagnosis data of the current popularity of the live video according to the time interval of the sudden change of the number of the fans and/or the content of the target live video.

Optionally, when the diagnostic data of the current popularity of the live video is generated according to the fan quantity mutation period in the step, whether the fan quantity mutation period belongs to a preset possible mutation period may be judged. The possible mutation period may be set based on the corresponding period of work and rest of the user, including a reduction and an increase in the number of fans, for example, eight and nine am is the time to start work, so this period may be used as the number of fans to reduce the corresponding mutation period. Half an hour and half a noon is the lunch break time, so the period can be used as a break time period corresponding to the increase of the number of fans. If the fans are decreased in number, the generated live video current heat diagnosis data is as follows: the current hot state is low because the current time is the working time, the live broadcast time is recommended to be adjusted, or the live broadcast theme is changed, and the anchor does not need the favorite theme types of the middle-aged and old fan users who work. If the number of the fans is increased, the generated live broadcast video current heat diagnosis data is as follows: the current heat state is higher because the current moment is the rest time, and the live broadcast is recommended to be carried out in the time period in future, so that the heat of the live broadcast video can be improved.

If the step generates the diagnosis data of the current popularity of the live broadcast video according to the target live broadcast video content, one possible implementation mode is to perform image recognition on the image data of the target live broadcast content, and recognize the image content causing the mutation of the number of the fans as the diagnosis data; and carrying out voice recognition on the audio data of the target live broadcast content, and recognizing the voice content causing the mutation of the number of the fans as diagnosis data. For example, image recognition is performed on image data of target live content, if image content of an electronic game appears in the image, it is indicated that the image content of the electronic game causes abrupt change of the number of fans this time, the image of the electronic game is used as diagnostic data of current popularity, voice recognition is performed on audio data of the target live content, if audio content of singing is found to appear in the audio, it is indicated that the audio content of singing causes abrupt change of the number of fans this time, and the singing audio is used as diagnostic data of current popularity.

Optionally, when generating the diagnostic data of the current popularity of the live video according to the target live video content, another implementable manner is to identify the bullet screen content in the target live video content by a character recognition technology; and extracting keywords in the bullet screen content, inputting the keywords into the reason analysis model, and obtaining the reason of the sudden change of the number of the fans and/or the improvement suggestion as the diagnosis data of the current heat of the live video.

Specifically, the method can perform character recognition on the bullet screen content in the target live broadcast video content, perform word segmentation on the recognized character bullet screen content, extract high-frequency words, entity words or words related to the theme type as key words, call the relevant program codes of the pre-trained reason analysis model, use the extracted keywords as input data, and operate the program codes, wherein at the moment, the reason analysis model can analyze the reason of the mutation of the number of the fans and/or improve suggestions as the diagnosis data of the current heat according to the input keywords. Optionally, the step may also be to preset a diagnosis database, where the diagnosis database records the reason and/or the improvement suggestion of the number of fans corresponding to different candidate keywords, and the reason and/or the improvement suggestion of the number of fans corresponding to the candidate keywords that are successfully matched may be used as the current hot diagnosis data by matching the extracted keywords with the candidate keywords recorded in the diagnosis database.

S306, the diagnosis data is sent to the anchor user.

Optionally, in this step, after the diagnostic data of the current popularity of the live video is generated in S305, in order to enable the anchor user to better know the specific reason why the popularity of the current live video is higher or lower, the electronic device may send the generated diagnostic data to the anchor user. Specifically, the diagnosis result may be sent to an application client installed on a terminal to which the anchor user belongs, where the diagnosis result may be sent to the anchor user in the form of a notification message, a receipt message of a live video, a popup window, and the like. After the anchor user receives the diagnosis result, the anchor user can know the reason that the heat of the current live video is higher or lower through the diagnosis result, and then decide whether to continue live broadcasting currently according to the reason and the direction for optimizing the live broadcasting content subsequently, so that the quality of the subsequent live video is improved, and more fans are attracted.

The embodiment of the disclosure provides a live video heat state identification method, in the process of live video broadcast by a main broadcast user, acquiring live video heat evaluation parameters including vermicelli parameters and/or income parameters, generating an identification result of the current heat state of the live video, if the current heat state belongs to a state to be diagnosed, determining a vermicelli quantity mutation time period, analyzing the vermicelli quantity mutation time period and/or live video content corresponding to the time period, generating diagnosis data of the current heat of the live video, and sending the diagnosis data to the main broadcast user. According to the scheme of the embodiment of the disclosure, the popularity state of the live video of the anchor user can be identified in real time, and the diagnosis data of the current popularity state can be fed back to the user according to the identification result, so that the anchor user is helped to adjust the theme type of the live content in real time, and the popularity of the live video is improved. Even if the live broadcast is a novice live broadcast, the method for improving the popularity of the live broadcast video can be rapidly mastered, the popularity of the live broadcast is greatly improved, and the watching popularity of the live broadcast video of the live broadcast platform is enhanced.

Fig. 4 is a schematic structural diagram illustrating a live video hot status recognition apparatus provided by an embodiment of the present disclosure, which is applicable to a situation where a live video hot status is recognized in a live broadcast process of a anchor user. The apparatus may be implemented by software and/or hardware and integrated in an electronic device executing the method, as shown in fig. 4, the apparatus may include:

an evaluation parameter obtaining module 401, configured to obtain a popularity evaluation parameter of a live video during a live video broadcast process of a anchor user; the heat evaluation parameters comprise fan parameters and/or income parameters;

and a popularity state identification module 402, configured to generate an identification result of the current popularity state of the live video according to the popularity evaluation parameter.

The embodiment of the disclosure provides a live video hotness state recognition device, which is used for acquiring a live video hotness evaluation parameter containing a fan parameter and/or a income parameter in the process of live video broadcast by a main broadcast user and generating a recognition result of the current hotness state of the live video based on the hotness evaluation parameter. The scheme of the embodiment of the disclosure can realize multi-dimensional evaluation parameters, accurately identify the real-time heat state of the live video, and provide guarantee for real-time and fair awarding of the main broadcast user to the live platform.

Further, the fan parameters comprise fan quantity parameters and/or fan preference parameters; the vermicelli corresponding to the vermicelli parameters comprises: at least one of a current watching fan of a live broadcast platform, a high-consumption fan in the live broadcast platform, a current watching fan of the anchor user, a newly added fan of the anchor user, and a pre-lost fan of the anchor user.

Further, if the popularity assessment parameter is a fan preference parameter, the assessment parameter obtaining module 401 is specifically configured to:

inputting vermicelli data into a user portrait model to obtain a vermicelli portrait of the vermicelli data;

and acquiring fan preference parameters from the fan portrait.

Further, the apparatus further comprises: a lost vermicelli determination module configured to:

determining the reduction ratio of the live broadcast frequency and/or time length watched by the fans in the current time period according to the frequency and/or time length of the live broadcast video watched by the fans in the current time period and the last time period by the fans of the anchor users;

and if the reduction proportion is larger than a preset proportion threshold value, the fan is a pre-lost fan of the anchor user.

Further, the income corresponding to the income parameter comprises: the primary revenue of the anchor user live video and/or the additional revenue of the fans watching the live video.

Further, the heat status identification module 402 is specifically configured to:

determining at least one of the number of fans, favorite distribution data and favorite migration data according to fan parameters, and identifying the current heat state of the live video according to at least one of the number of fans, favorite distribution data and favorite migration data; and/or the presence of a gas in the gas,

and determining a fluctuation value and/or fluctuation influence factor of the income according to the income parameters, and identifying the current popularity state of the live video according to the fluctuation value and/or fluctuation influence factor.

Further, the apparatus further comprises:

the data diagnosis module is used for generating diagnosis data of the current popularity of the live video according to the identification result;

and the data sending module is used for sending the diagnosis data to a main broadcasting user.

Further, the data diagnosis module includes:

a mutation time interval obtaining unit, configured to obtain a bean vermicelli number mutation time interval of the live video when it is detected that the current hotness state in the identification result belongs to a state to be diagnosed;

the video content acquisition unit is used for acquiring target live broadcast video content corresponding to the fan quantity mutation time period from the live broadcast video according to the fan quantity mutation time period;

and the diagnostic data generating unit is used for generating diagnostic data of the current popularity of the live video according to the fan quantity mutation time period and/or the target live video content.

Further, the mutation period acquiring unit is specifically configured to:

intercepting reference live video content between a first moment and a second moment from the live video; the second moment is a moment corresponding to the acquired heat evaluation parameter, and the first moment is before the second moment and is separated from the second moment by a preset time length;

and detecting a high-frequency time period of the release of the popup content in the reference live video content as the break-away time period of the fan quantity.

Further, the diagnostic data generating unit is specifically configured to:

identifying bullet screen content in the target live video content through a character identification technology;

and extracting keywords in the bullet screen content, inputting the keywords into a reason analysis model, and obtaining the reason of the sudden change of the number of the fans and/or improvement suggestions as diagnosis data of the current popularity of the live broadcast video.

The live video hot status recognition device provided by the embodiment of the present disclosure and the live video hot status recognition method provided by the embodiments belong to the same inventive concept, and technical details that are not described in detail in the embodiment of the present disclosure may be referred to in the embodiments, and the embodiment of the present disclosure and the embodiments have the same beneficial effects.

Referring now to FIG. 5, a block diagram of an electronic device 500 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device in the embodiment of the present disclosure may be a device corresponding to a back-end live broadcast platform of an application program, and may also be a mobile terminal device installed with an application program client. In particular, the electronic device may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle-mounted terminal (e.g., a car navigation terminal), etc., and a stationary terminal such as a digital TV, a desktop computer, etc. The electronic device 500 shown in fig. 5 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing device 501.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some implementations, the electronic devices may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the internal processes of the electronic device to perform: in the process of live broadcasting of a main broadcasting user, acquiring a heat evaluation parameter of the live broadcasting video; the heat evaluation parameters comprise fan parameters and/or income parameters; and generating an identification result of the current popularity state of the live video according to the popularity evaluation parameter.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, a live video hot status identification method is provided, and the method includes:

According to one or more embodiments of the disclosure, in the above method, the fan parameters include a fan number parameter and/or a fan preference parameter; the vermicelli corresponding to the vermicelli parameters comprises: at least one of a current watching fan of a live broadcast platform, a high-consumption fan in the live broadcast platform, a current watching fan of the anchor user, a newly added fan of the anchor user, and a pre-lost fan of the anchor user.

According to one or more embodiments of the present disclosure, in the above method, if the heat evaluation parameter is a fan preference parameter, acquiring the heat evaluation parameter of the live video includes:

and acquiring fan preference parameters from the fan portrait.

According to one or more embodiments of the present disclosure, in the method, before acquiring the heat evaluation parameter of the live video in the process of live video of the anchor user, the method further includes:

According to one or more embodiments of the present disclosure, in the above method, the revenue corresponding to the revenue parameter includes: the primary revenue of the anchor user live video and/or the additional revenue of the fans watching the live video.

According to one or more embodiments of the present disclosure, in the above method, generating an identification result of the current popularity state of the live video according to the popularity assessment parameter includes:

According to one or more embodiments of the present disclosure, in the above method, after generating the recognition result of the current hotness status of the live video, the method further includes:

and generating diagnosis data of the current popularity of the live video according to the identification result, and sending the diagnosis data to a main broadcasting user.

According to one or more embodiments of the present disclosure, the above method, generating diagnostic data of the current popularity of the live video according to the recognition result, includes:

when the current hotness state in the identification result is detected to belong to a state to be diagnosed, acquiring a fan quantity mutation period of the live video;

acquiring target live broadcast video content corresponding to the bean vermicelli quantity mutation time period from the live broadcast video according to the bean vermicelli quantity mutation time period;

and generating the diagnosis data of the current popularity of the live video according to the time interval of the sudden change of the number of the fans and/or the content of the target live video.

According to one or more embodiments of the present disclosure, in the above method, acquiring a fan number abrupt change period of the live video includes:

According to one or more embodiments of the present disclosure, in the above method, generating the diagnosis data of the current popularity of the live video according to the target live video content includes:

According to one or more embodiments of the present disclosure, an apparatus for identifying a hot status of a live video is provided, the apparatus including:

According to one or more embodiments of the present disclosure, the fan parameters in the device include a fan number parameter and/or a fan preference parameter; the vermicelli corresponding to the vermicelli parameters comprises: at least one of a current watching fan of a live broadcast platform, a high-consumption fan in the live broadcast platform, a current watching fan of the anchor user, a newly added fan of the anchor user, and a pre-lost fan of the anchor user.

According to one or more embodiments of the present disclosure, if the heat evaluation parameter is a fan preference parameter, the evaluation parameter obtaining module 401 in the foregoing apparatus is specifically configured to:

and acquiring fan preference parameters from the fan portrait.

According to one or more embodiments of the present disclosure, the apparatus further includes: a lost vermicelli determination module configured to:

According to one or more embodiments of the present disclosure, the revenue corresponding to the revenue parameter in the above apparatus includes: the primary revenue of the anchor user live video and/or the additional revenue of the fans watching the live video.

According to one or more embodiments of the present disclosure, the thermal status identification module 402 in the foregoing apparatus is specifically configured to:

According to one or more embodiments of the present disclosure, the apparatus further includes:

According to one or more embodiments of the present disclosure, the data diagnosis module in the above apparatus includes:

According to one or more embodiments of the present disclosure, the abrupt period obtaining unit in the above apparatus is specifically configured to:

According to one or more embodiments of the present disclosure, the diagnostic data generating unit in the above apparatus is specifically configured to:

According to one or more embodiments of the present disclosure, there is provided an electronic device including:

one or more processors;

a memory for storing one or more programs;

According to one or more embodiments of the present disclosure, a readable medium is provided, on which a computer program is stored, which when executed by a processor, implements a live video hot status identification method according to any embodiment of the present disclosure.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A live video hot state identification method is characterized by comprising the following steps:

generating an identification result of the current popularity state of the live video according to the popularity evaluation parameter;

after the generating of the identification result of the current hot status of the live video, the method further includes:

generating diagnosis data of the current popularity of the live video according to the identification result, and sending the diagnosis data to a main broadcasting user;

the generating of the diagnosis data of the current popularity of the live video according to the identification result comprises:

when the current hotness state in the identification result is detected to belong to a state to be diagnosed, acquiring a time interval of the sudden change of the fan quantity of the live video, wherein the state to be diagnosed refers to a preset hotness state needing state reason diagnosis;

2. The method of claim 1, wherein the fan parameters include a fan quantity parameter and/or a fan preference parameter; the vermicelli corresponding to the vermicelli parameters comprises: at least one of a current watching fan of a live broadcast platform, a high-consumption fan in the live broadcast platform, a current watching fan of the anchor user, a newly added fan of the anchor user, and a pre-lost fan of the anchor user.

3. The method of claim 2, wherein obtaining the hotness evaluation parameter of the live video if the hotness evaluation parameter is a fan preference parameter comprises:

and acquiring fan preference parameters from the fan portrait.

4. The method of claim 2, wherein before obtaining the hotness assessment parameter of the live video during the live video of the anchor user, further comprising:

5. The method of claim 1, wherein the revenue corresponding to the revenue parameter comprises: the primary revenue of the anchor user live video and/or the additional revenue of the fans watching the live video.

6. The method of claim 1, wherein generating the recognition result of the current hot status of the live video according to the hot evaluation parameter comprises:

7. The method as claimed in claim 1, wherein obtaining the fan number mutation period of the live video comprises:

8. The method of claim 1, wherein generating diagnostic data of the current popularity of the live video based on the target live video content comprises:

9. A live video hot state recognition device, comprising:

the popularity state identification module is used for generating an identification result of the current popularity state of the live video according to the popularity evaluation parameter;

the data sending module is used for sending the diagnosis data to a main broadcasting user;

the data diagnosis module includes:

a mutation time interval obtaining unit, configured to obtain a bean vermicelli quantity mutation time interval of the live video when it is detected that a current heat state in the identification result belongs to a state to be diagnosed, where the state to be diagnosed is a preset heat state in which a state reason diagnosis needs to be performed;

10. An electronic device, comprising:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement a live video hotness status identification method as recited in any of claims 1-8.

11. A readable medium having stored thereon a computer program, characterized in that the program, when being executed by a processor, implements the live video hot status recognition method according to any one of claims 1-8.