CN110475155A - Live video temperature state identification method, device, equipment and readable medium - Google Patents

Live video temperature state identification method, device, equipment and readable medium Download PDF

Info

Publication number
CN110475155A
CN110475155A CN201910765321.3A CN201910765321A CN110475155A CN 110475155 A CN110475155 A CN 110475155A CN 201910765321 A CN201910765321 A CN 201910765321A CN 110475155 A CN110475155 A CN 110475155A
Authority
CN
China
Prior art keywords
bean vermicelli
live video
parameter
live
temperature
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910765321.3A
Other languages
Chinese (zh)
Other versions
CN110475155B (en
Inventor
姜子阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing ByteDance Network Technology Co Ltd
Original Assignee
Beijing ByteDance Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing ByteDance Network Technology Co Ltd filed Critical Beijing ByteDance Network Technology Co Ltd
Priority to CN201910765321.3A priority Critical patent/CN110475155B/en
Publication of CN110475155A publication Critical patent/CN110475155A/en
Application granted granted Critical
Publication of CN110475155B publication Critical patent/CN110475155B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched

Abstract

The present disclosure discloses a kind of live video temperature state identification method, device, equipment and readable mediums.This method comprises: obtaining the temperature assessment parameter of the live video during main broadcaster's user live broadcast video；The temperature assessment parameter includes bean vermicelli parameter and/or income parameter；Parameter is assessed according to the temperature, generates the recognition result of the current temperature state of the live video.The scheme of the embodiment of the present disclosure can be realized the assessment parameter based on various dimensions, accurately identify the real-time temperature state of live video, provide guarantee for the main broadcaster user's reward of giving fair in real time of live streaming platform.

Description

Live video temperature state identification method, device, equipment and readable medium
Technical field
The embodiment of the present disclosure be related to Internet technical field more particularly to a kind of live video temperature state identification method, Device, equipment and readable medium.
Background technique
Currently, main broadcaster user can be straight to attract by opening net cast function in live video class application program Broadcast spectators user's viewing on platform.In order to enhance the viewing temperature of live streaming platform live video, live streaming platform can regard live streaming Frequency temperature state higher main broadcaster user give premiums.But since the factor for influencing live video temperature state is more, The quality of such as video content, the type of video subject subject matter and live streaming time, live streaming platform are difficult in real time accurately identification The temperature state of live video out, and then the fairness and real-time rewarded main broadcaster user are influenced, it needs to improve.
Summary of the invention
The embodiment of the present disclosure provides a kind of live video temperature state identification method, device, equipment and readable medium, with reality The now assessment parameter based on various dimensions accurately identifies the real-time temperature state of live video, gives for live streaming platform is fair in real time It gives main broadcaster user's reward and provides guarantee.
In a first aspect, the embodiment of the present disclosure provides a kind of live video temperature state identification method, this method comprises:
During main broadcaster's user live broadcast video, the temperature assessment parameter of the live video is obtained；The temperature is commented Estimating parameter includes bean vermicelli parameter and/or income parameter；
Parameter is assessed according to the temperature, generates the recognition result of the current temperature state of the live video.
Second aspect, the embodiment of the present disclosure additionally provide a kind of live video temperature status identification means, which includes:
Parameter acquisition module is assessed, for obtaining the heat of the live video during main broadcaster's user live broadcast video Degree assessment parameter；The temperature assessment parameter includes bean vermicelli parameter and/or income parameter；
Temperature state recognition module generates the current temperature shape of the live video for assessing parameter according to the temperature The recognition result of state.
The third aspect, the embodiment of the present disclosure additionally provide a kind of electronic equipment, which includes:
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing Device realizes the live video temperature state identification method as described in disclosure any embodiment.
Fourth aspect, the embodiment of the present disclosure provide a kind of readable medium, are stored thereon with computer program, the program quilt The live video temperature state identification method as described in disclosure any embodiment is realized when processor executes.
The embodiment of the present disclosure provides a kind of live video temperature state identification method, device, equipment and readable medium, leads to It crosses during main broadcaster's user live broadcast video, obtains comprising bean vermicelli parameter and/or take in the live video temperature assessment of parameter Parameter, and the recognition result based on the temperature assessment parameter generation current temperature state of live video.The side of the embodiment of the present disclosure Case can realize the assessment parameter based on various dimensions, accurately identify the real-time temperature state of live video, public in real time for live streaming platform Flat main broadcaster user's reward of giving provides guarantee.
Detailed description of the invention
In conjunction with attached drawing and refer to following specific embodiments, the above and other feature, advantage of each embodiment of the disclosure and Aspect will be apparent.In attached drawing, the same or similar appended drawing reference indicates the same or similar element.It should manage Solution attached drawing is schematically that original part and element are not necessarily drawn to scale.
Fig. 1 shows a kind of flow chart of live video temperature state identification method of embodiment of the present disclosure offer；
Fig. 2A -2B shows the process of another live video temperature state identification method of embodiment of the present disclosure offer Figure；
Fig. 3 shows the flow chart of another live video temperature state identification method of embodiment of the present disclosure offer；
Fig. 4 shows a kind of structural schematic diagram of live video temperature status identification means of embodiment of the present disclosure offer；
Fig. 5 shows the structural schematic diagram of a kind of electronic equipment of embodiment of the present disclosure offer.
Specific embodiment
Embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the certain of the disclosure in attached drawing Embodiment, it should be understood that, the disclosure can be realized by various forms, and should not be construed as being limited to this In the embodiment that illustrates, providing these embodiments on the contrary is in order to more thorough and be fully understood by the disclosure.It should be understood that It is that being given for example only property of the accompanying drawings and embodiments effect of the disclosure is not intended to limit the protection scope of the disclosure.
It should be appreciated that each step recorded in disclosed method embodiment can execute in a different order, And/or parallel execution.In addition, method implementation may include additional step and/or omit the step of execution is shown.This public affairs The range opened is not limited in this respect.
Terms used herein " comprising " and its deformation are that opening includes, i.e., " including but not limited to ".Term "based" It is " being based at least partially on ".Term " one embodiment " expression " at least one embodiment "；Term " another embodiment " indicates " at least one other embodiment "；Term " some embodiments " expression " at least some embodiments ".The correlation of other terms is fixed Justice provides in will be described below.
It is noted that the concepts such as " first " that refers in the disclosure, " second " are only used for different devices, module or list Member distinguishes, and is not intended to limit the sequence or relation of interdependence of function performed by these devices, module or unit.
It is noted that referred in the disclosure "one", the modification of " multiple " be schematically and not restrictive this field It will be appreciated by the skilled person that being otherwise construed as " one or more " unless clearly indicate otherwise in context.The disclosure is real The title for applying the message or information that are interacted between multi-party in mode is for illustrative purposes only, and is not used to pair The range of these message or information is limited.
Fig. 1 is a kind of flow chart for live video temperature state identification method that the embodiment of the present disclosure provides, the present embodiment The case where being applicable to during main broadcaster's user live broadcast, identifying to the temperature state of live video, this method can be with It is executed by live video temperature status identification means or electronic equipment, which can be by way of software and/or hardware It realizes, which can be only fitted in electronic equipment.Optionally, the rear end live streaming which can be application program is put down The corresponding equipment of platform, can also be the mobile terminal device for being equipped with application client.
Optionally, as shown in Figure 1, the method in the present embodiment may include steps of:
S101 obtains the temperature assessment parameter of live video during main broadcaster's user live broadcast video.
Wherein, temperature assessment parameter can refer to the judge ginseng of the burning hot degree of live video for predicting main broadcaster user Number can include but is not limited to bean vermicelli parameter and/or income parameter.
Optionally, the corresponding income of the income parameter includes: the basic income and/or bean vermicelli of main broadcaster's user live broadcast video Watch the additional income of live video.Wherein, basic income can be live streaming platform and main broadcaster user made an appointment, and give The fixed income of main broadcaster user.Additional income can be when the excellent temperature of main broadcaster's user live broadcast content is higher, and live streaming platform is given The reward income and/or bean vermicelli user of giving main broadcaster user give the present income of main broadcaster user.Optionally, income parameter can wrap It includes but is not limited to: the amount of money and type of income；When the reward income that income is present class, taking in parameter can also be further Title, unit price and quantity including present etc..
Optionally, the bean vermicelli parameter may further include bean vermicelli number parameter and/or bean vermicelli preference parameters.Wherein, Bean vermicelli number parameter can refer to the total quantity of a certain vermicelli.Bean vermicelli preference parameters can refer to happiness of the bean vermicelli to live video The parameter of joyous degree, for example, it may be liking some live video being broadcast live on platform；It can also be and like being broadcast live on platform Certain a kind of live video；It can also be some the main broadcaster user etc. for liking being broadcast live on platform.Optionally, the bean vermicelli ginseng Count the current of the currently viewing bean vermicelli, the high consumption bean vermicelli in live streaming platform, main broadcaster user that corresponding bean vermicelli includes: live streaming platform Watch at least one of bean vermicelli, the newly-increased bean vermicelli of main broadcaster user and pre- loss bean vermicelli of main broadcaster user.
Wherein, the currently viewing bean vermicelli that platform is broadcast live can refer to currently watches all of live video on live streaming platform Bean vermicelli user.For example, watching this 100 live streaming views if thering are 100 main broadcaster users being broadcast live on current time live streaming platform The bean vermicelli summation of frequency is the currently viewing bean vermicelli that platform is broadcast live.High consumption bean vermicelli in live streaming platform can refer to live streaming platform Upper often main broadcaster user gives gifts object, and the higher bean vermicelli of the amount of money for object of giving gifts.The currently viewing bean vermicelli of main broadcaster user can be Refer to the bean vermicelli user that its live video is being watched in all beans vermicelli of the main broadcaster user.For example, if 100 of certain main broadcaster user There are 30 live video is currently viewed in bean vermicelli, then this 30 bean vermicelli users are the currently viewing bean vermicelli of the main broadcaster user. The newly-increased bean vermicelli of main broadcaster user can refer to main broadcaster user in preset time period (during interior or primary live streaming in such as one week) What is newly increased pays close attention to the bean vermicelli user of the main broadcaster.The pre- loss bean vermicelli of main broadcaster user can refer to that the existing bean vermicelli of main broadcaster user is used In family, i.e., it will cancel the bean vermicelli user of concern.
Optionally, during main broadcaster's user live broadcast video, this step can real-time or timing (such as every 10 minutes) Parameter is assessed to obtain the temperature an of live video.Specifically, obtaining a kind of embodiment of income parameter may is that directly The income parameter that record in platform has each main broadcaster user is broadcast, electronic equipment can lead to during main broadcaster's user live broadcast video Cross the income parameter that live streaming platform obtains the current basic income of live streaming user and/or additional income.Obtain income parameter Another embodiment may is that, for basic income parameter, electronic equipment detects main broadcaster user's current live duration, in conjunction with The incidence relation between main broadcaster's user live broadcast duration and basic income made an appointment, the income parameter taken in substantially. Wherein, which can be the basic income (such as 50 yuan) of the corresponding amount of money of every live streaming unit time (such as one hour) of main broadcaster； It can also be that main broadcaster's user live broadcast reaches preset duration (such as 4 hours) and gives main broadcaster's basic income (such as 300 yuan) of this live streaming. For additional income parameter, during electronic equipment can be by detection live video, present that the bean vermicelli received is given Title, unit price and quantity, the corresponding additional income parameter of Lai Tongji gifts；User's current live temperature is broadcast live by detection Whether live streaming platform incentive standard is reached, to determine whether to obtain the additional income parameter that platform is broadcast live and gives.
Optionally, when obtaining bean vermicelli parameter, it can be electronic equipment and first determine that the bean vermicelli for needing to obtain bean vermicelli parameter is used Family, if being prerecorded with the bean vermicelli parameter for each main broadcaster user's bean vermicelli that it is managed in live streaming platform, electronic equipment can be in master During broadcasting user live video, the bean vermicelli number parameter and/or bean vermicelli of each bean vermicelli required for being obtained by live streaming platform Preference parameters.If being broadcast live in platform without record bean vermicelli parameter, electronic equipment, which can be, obtains each bean vermicelli from live streaming platform All bean vermicelli data of user obtain the bean vermicelli parameter of each bean vermicelli, example then by being analyzed and processed to the bean vermicelli data Such as, it can be and bean vermicelli quantity counted, obtain bean vermicelli number parameter, model is drawn a portrait to number of fans using trained user According to being analyzed and processed, the bean vermicelli portrait of bean vermicelli data is obtained, and then obtain bean vermicelli preference parameters from bean vermicelli portrait.
Optionally, electronic equipment can be in the corresponding bean vermicelli user of the determining bean vermicelli parameter for needing to obtain for straight The currently viewing bean vermicelli and high consumption bean vermicelli for broadcasting platform can be by interacting determination with live streaming platform；For main broadcaster user's Currently viewing bean vermicelli and newly-increased bean vermicelli can be by being monitored acquisition to the bean vermicelli data statistics process in current live video； It can be for being lost bean vermicelli in advance and the main broadcaster watched in current time period and upper a period of time according to the bean vermicelli of main broadcaster user The frequency and/or duration of user live broadcast video determine that the bean vermicelli watches in current time period the live streaming frequency and/or duration Down ratio；If the down ratio is greater than preset ratio threshold value, which is the pre- loss bean vermicelli of the main broadcaster user.
Specifically, this sub-step can preset the detection pre- time cycle (such as one week) for being lost bean vermicelli and preset ratio Threshold value (such as 70%).When determining the pre- loss bean vermicelli of a main broadcaster user, current time period can be first obtained respectively (such as this Week) and the interior main broadcaster user of upper a period of time (one week as above) each bean vermicelli watch its live video the frequency and/or when It is long.Optionally, which can be the times or frequency that each bean vermicelli in a time cycle watches its live video.The duration can To be the duration for each video that each bean vermicelli watches its live streaming in a time cycle, or watch all videos of its live streaming Total duration.Then in the frequency and/or duration according to acquisition, determine the bean vermicelli current according to formula W=(S1-S2)/S1 The down ratio of the viewing live streaming frequency and/or duration in time cycle.Wherein, W is down ratio；S1 is the sight of upper a period of time See the frequency and/or duration of main broadcaster's user live broadcast video；S2 is the frequency that current time period watches main broadcaster's user live broadcast video And/or duration.Judge whether the corresponding down ratio of each bean vermicelli of the main broadcaster user is greater than preset ratio threshold value, if so, Illustrate that the bean vermicelli watches the ratio decline of main broadcaster's user live broadcast video seriously, is likely to what the main broadcaster user will lose Bean vermicelli is lost bean vermicelli in advance.Otherwise illustrate that the bean vermicelli is the stabilization bean vermicelli of the main broadcaster user.
S102 assesses parameter according to temperature, generates the recognition result of the current temperature state of live video.
Wherein, the recognition result of the current temperature state of live video can be the temperature shape of main broadcaster user's current live video The corresponding temperature numerical value of state or temperature rank, optionally, wherein can also include that temperature assesses parameter and in live video heat Intermediate data obtained in status assessment process is spent, for example, intermediate data can include but is not limited to: bean vermicelli quantity, bean vermicelli happiness At least one of good distributed data, bean vermicelli hobby migrating data, income fluctuation numerical value, income fluctuation influence factor.
Optionally, parameter is assessed according to temperature in this step, generates the recognition result of the current temperature state of live video Process may is that when temperature assessment parameter be bean vermicelli parameter when, can be by as follows for the corresponding bean vermicelli parameter of different beans vermicelli Mode identifies the current temperature state of live video.Specifically, when bean vermicelli is the currently viewing bean vermicelli or live streaming platform that platform is broadcast live High consumption bean vermicelli when, can be the preference parameters according to these two types of beans vermicelli, if liking these two types of beans vermicelli of the type of theme Quantity or specific gravity are more, then the temperature of the live video of corresponding current temperature state to be identified is higher.When bean vermicelli is main broadcaster When the currently viewing bean vermicelli of user or the newly-increased bean vermicelli of main broadcaster user, can be according to the number parameters of these two types of beans vermicelli and/or Preference parameters, if the quantitative value of these two types of beans vermicelli is bigger, the temperature of the live video of corresponding current state to be identified is got over It is high；Type of theme belonging to live video for current temperature state to be identified, if liking these two types of powder of the type of theme Silk quantity or specific gravity are more, then the temperature of the live video of corresponding current temperature state to be identified is higher.Based on bean vermicelli When the pre- loss bean vermicelli of broadcasting user, it can be according to the pre- number parameter for being lost bean vermicelli, if the pre- loss bean vermicelli of main broadcaster user Quantitative value is fewer, then the temperature of the live video of corresponding current state to be identified is higher.Optionally, when temperature assesses parameter When to take in parameter, it can be and video is broadcast live according to the basic income parameter and/or additional income parameter taken in parameter The identification of current temperature.Specifically, the amount of money that can be basic income parameter and/or additional income parameter is higher, then to should The temperature of the live video of preceding state to be identified is higher；It can also be that the corresponding quantity of additional income parameter is more, for example, volume The outer quantity for taking in the corresponding present of parameter is more, then the temperature of the live video of corresponding current state to be identified is higher.
It should be noted that how this step is specifically according to the bean vermicelli number parameter and/or bean vermicelli hobby in bean vermicelli parameter Parameter, and how according to the basic income parameter and/or additional income parameter in income parameter, identification live video is currently warm The process of degree state will describe in detail in subsequent embodiment.
Optionally, when temperature assessment parameter is the parameter of at least two types, it can be the heat for each type Degree assessment parameter all identifies the corresponding temperature state of the parameter, then carries out General Office to the multiple temperature states identified again Reason (such as sum, processing of averaging, weighted sum, weighting average processing) obtains the current temperature state of the live video.
The embodiment of the present disclosure provides a kind of live video temperature state identification method, by main broadcaster's user live broadcast video During, the live video temperature assessment parameter of parameter is obtained comprising bean vermicelli parameter and/or takes in, and assess based on the temperature The recognition result of the parameter generation current temperature state of live video.The scheme of the embodiment of the present disclosure can realize commenting based on various dimensions Estimate parameter, accurately identify the real-time temperature state of live video, is mentioned for the main broadcaster user's reward of giving fair in real time of live streaming platform It has supplied to guarantee.
Optionally, it for main broadcaster user during live streaming, can only be estimated by the bean vermicelli quantity of viewing live streaming straight The temperature for broadcasting video is difficult accurately to grasp the lower grade reason of live video, and then also can not just accomplish in real time accurately to live streaming The content of video carries out effectively optimization to improve the temperature of live video, and especially for new hand main broadcaster, the phenomenon is even more serious. The enthusiasm of strong influence main broadcaster's live streaming, results in the loss of live streaming application client.In order to solve this problem, this implementation Example can generate the live streaming according to recognition result after the recognition result that electronic equipment generates the current temperature state of live video The diagnostic data of the current temperature of video, and the diagnostic data is sent to main broadcaster user.Wherein, diagnostic data can be according to straight Broadcast the current temperature state of video, provide raising live video temperature state suggestion data, the diagnostic data may include but Be not limited to: the recognition result of live video temperature state leads to the reason of current temperature state and the improvement for the reason It is recommended that etc..Optionally, it when generating the diagnostic data of the current temperature of live video according to recognition result, can be to recognition result In include temperature assessment parameter or between data carry out the temperature analysis of causes, for example, if the recognition result of current temperature state Show that the temperature state of live video is lower, then can analyze the preference parameters of various types bean vermicelli, the hobby number of discriminatory analysis According to whether be main broadcasting user current live type of theme, if it is not, then diagnostic result be broadcast live user live broadcast video subject Type is not that bean vermicelli is liked, and using the type of theme of bean vermicelli hobby as the type of theme for suggesting adjustment when subsequent live streaming, from And attract more beans vermicelli to watch live video.Wherein, various types bean vermicelli may include: the high consumption powder being broadcast live in platform The pre- loss bean vermicelli of silk, the currently viewing bean vermicelli of main broadcaster user, the newly-increased bean vermicelli of main broadcaster user and main broadcaster user.If the receipts of main broadcaster Enter that the amount of money is lower, then can analyze the preference parameters of high consumption bean vermicelli, the type of theme that high consumption bean vermicelli is liked is as subsequent Suggest the type of theme of adjustment when live streaming, so that high consumption bean vermicelli be attracted to watch live video.The present embodiment is arranged good in this way Be in, for main broadcaster user, can not only understand the temperature state of oneself live video in real time during live streaming, The diagnostic data for current live video can also be obtained, and then according to the diagnostic data in real time to the theme class of live content Type is adjusted, to attract a large amount of bean vermicelli, even new hand main broadcaster, can also improve live video temperature in quick grasp Method, greatly improve main broadcaster live streaming enthusiasm, enhancing live streaming platform live video viewing temperature.
Fig. 2A -2B shows the process of another live video temperature state identification method of embodiment of the present disclosure offer Figure；The present embodiment is optimized on the basis of each optinal plan provided by the above embodiment, shows in particular when temperature is commented Estimate parameter be bean vermicelli parameter and/or income parameter when, how to execute being discussed in detail for live video temperature state identification method.
Optionally, Fig. 2A is to execute live video temperature state identification method when it is bean vermicelli parameter that temperature, which assesses parameter, Flow chart.Specifically executing step includes:
S201 obtains bean vermicelli number parameter and bean vermicelli data during main broadcaster's user live broadcast video, and by number of fans According to input user's portrait model, the bean vermicelli portrait of bean vermicelli data is obtained.
Wherein, bean vermicelli data can be the essential information of bean vermicelli user and in the total of the operation data being broadcast live on platform With for example, can include but is not limited to: the user name of bean vermicelli, gender, the age, location, the viewing in application program, Collect operation data and the comment data etc. of live video.The bean vermicelli data can recorde on live streaming platform, electronic equipment Bean vermicelli data can be obtained by interacting with live streaming platform.Bean vermicelli portrait, which can be, delineates bean vermicelli attributive character, behavior spy The tool of the various dimensions feature such as sign or hobby feature, can be to the feature abstraction of each dimension into label, utilizes these labels Precisely to delineate bean vermicelli portrait.
Optionally, the present embodiment is delineated bean vermicelli portrait and be can be is delineated using trained user portrait model.The use Family portrait model can be using a large amount of sample of users data, and what training obtained can delineate the neural network mould of user's portrait Type.The present embodiment can be during main broadcaster's user live broadcast video, real-time or each bean vermicelli of timing acquisition bean vermicelli data.Then For each bean vermicelli, user is called to draw a portrait the related program code of model, using the bean vermicelli data of the bean vermicelli as input data, The related program code is run, user's portrait model will draw out the user of the bean vermicelli based on the bean vermicelli data of input at this time It draws a portrait (i.e. bean vermicelli portrait).For example, include: in bean vermicelli data name-Zhang San, gender-male, the age -20, location-Beijing, The live video of viewing in nearest one week has live video 1, live video 2 and a live video 3, and viewing time is all in the afternoon six O'clock to during 7 points, live video 1 is all the video of sports genre to live video 3.Model is drawn a portrait to this by user at this time The bean vermicelli portrait that bean vermicelli data are delineated may is that bean vermicelli attributive character label includes: Zhang San, male, youth, Beijing Area；Behavioural characteristic attribute includes: the viewing of supper time of having a rest；Liking characteristic attribute label includes: game themes type.
It should be noted that the present embodiment during main broadcaster's user live broadcast video, obtains the mistake of bean vermicelli number parameter Introduction has been carried out in above-described embodiment in journey, herein without repeating.
S202 obtains bean vermicelli preference parameters from bean vermicelli portrait.
Optionally, since bean vermicelli portrait is that the label being abstracted by each dimensional characteristics is constituted, record has again in each label The bean vermicelli is directed to the specific data parameters of the label characteristics.For example, including name, gender, age in bean vermicelli attributive character label With the data parameters such as area；It include: the data parameters such as operating time, operation behavior in behavior property feature tag；Like feature It include: the data parameters such as hobby type of theme in attribute tags.So this step can be for each bean vermicelli, all in its powder Hobby characteristic attribute label is searched in silk portrait, and obtains bean vermicelli preference parameters from hobby characteristic attribute label.For example, from Bean vermicelli preference parameters: game themes type are obtained in the hobby characteristic attribute label for the bean vermicelli portrait that S201 is delineated.
S203 determines at least one in quantity, hobby distributed data and the hobby migrating data of bean vermicelli according to bean vermicelli parameter It is a, and according at least one of the quantity of bean vermicelli, hobby distributed data and hobby migrating data, identification live video is currently warm Degree state.
Wherein, the bean vermicelli parameter in this step includes the bean vermicelli number parameter that S201 is obtained and the bean vermicelli hobby that S202 is obtained At least one of parameter.Optionally, in this step, according to the bean vermicelli number parameter in bean vermicelli parameter, the number of bean vermicelli is determined The process of amount may is that the bean vermicelli quantitative value obtained in bean vermicelli number parameter, the quantity as bean vermicelli.According in bean vermicelli parameter Bean vermicelli preference parameters determine that the process of current hobby distribution may is that the bean vermicelli preference parameters according to the bean vermicelli of acquisition, statistics are each Corresponding bean vermicelli quantity or specific gravity under hobby, and then the current hobby distribution of bean vermicelli can be obtained.For example, if the bean vermicelli to acquisition is liked Good parameter, which carries out statistics discovery, to be had the hobby cuisines type of theme of 10 beans vermicelli, has 30 like game themes type, have 60 Like song and dance type of theme, then can determine the current hobby distribution of bean vermicelli are as follows: song and dance topic type distribution accounting 60%；Game Topic type distribution accounting 30%；Cuisines topic type distribution accounting 10%.
Optionally, since the present embodiment is real-time or bean vermicelli portrait is delineated in timing, bean vermicelli preference parameters are obtained, so this step Suddenly when determining the hobby migrating data of bean vermicelli according to bean vermicelli preference parameters, can be to this determine hobby distributed data and The hobby distributed data that last time determines is analyzed, by the hobby migration and variation of each type of theme in the adjacent distribution of hobby twice Situation is as hobby migrating data.For example, if counting the current hobby distribution of this bean vermicelli are as follows: song and dance topic type distribution accounts for Than 60%, game themes type is distributed accounting 30%, cuisines topic type distribution accounting 10%；The hobby of last bean vermicelli is distributed Are as follows: song and dance topic type distribution accounting 10%, game themes type are distributed accounting 80%, cuisines topic type distribution accounting 10%.Then corresponding hobby migrating data at this time are as follows: song and dance type of theme the amount of migration increases by 50%, game themes type the amount of migration 50% is reduced, cuisines class type of theme the amount of migration is constant.
Optionally, this step is in the current temperature state of identification live video, if identifying live streaming view according to the quantity of bean vermicelli The current temperature state of frequency, then the quantity of bean vermicelli is directly proportional to the current temperature state of live video, i.e. the quantity of bean vermicelli is more, then right Should live video temperature it is higher.If currently hot according to hobby distributed data and/or hobby migrating data identification live video Degree state then needs first to determine the type of theme of current live video, specific to determine that method have very much, for example, can be with It is that theme is carried out to current live video by current live video content using subject categories identification model trained in advance Identification can also be that building one in advance records the incidence relation database of each type of theme and its corresponding candidate keywords, Live content, title to current live video etc. carry out keyword extraction, and will record in the keyword and database of extraction Candidate keywords matched, using the corresponding type of theme of matched candidate keywords as master belonging to current live video Inscribe type；It can also be the type of theme that the live video is recorded at a certain position at live video interface, it is directly straight from this It broadcasts video page corresponding position and extracts its type of theme.After the type of theme that current live video has been determined, if according to The current hobby of determining bean vermicelli is distributed, and when the current temperature state of identification live video, can be the theme of current live video Type corresponding distributed quantity or specific gravity in current hobby distribution is directly proportional to live video temperature state, i.e., distributed quantity or Specific gravity is higher, then corresponding live video temperature is higher.If identifying live video according to the hobby migrating data of determining bean vermicelli When current temperature state, the type of theme of current live video corresponding migration quantity or ratio in hobby migrating data can be Weight is directly proportional to live video temperature state, i.e., migration quantity or specific gravity are higher, then corresponding live video temperature is higher.
It should be noted that according in the quantity of the bean vermicelli, hobby distributed data and hobby migrating data at least One parameter, when identifying the current temperature state of the live video, if identifying that live video is current according to one of parameter Temperature state then can be and be identified according to above-mentioned corresponding method, be broadcast live if being identified according at least two parameter therein When the current temperature state of video, it can be and first identify a temperature state according to above-mentioned corresponding method for each parameter, Then the temperature state identified to each parameter carries out integrated treatment and (such as sums, processing of averaging, weighted sum, weighting ask equal Value processing etc.), obtain the current temperature state of live video.
Optionally, in this step according to bean vermicelli parameter, when identifying the current temperature state of live video, in addition to above-mentioned basis is pre- Except the proportionate relationship identification current temperature state of live video being first arranged, it can also be calling previously according to sample data training The related program code of the neural network model of the good temperature of live video for identification is joined the quantity of bean vermicelli as input Number, or the hobby migrating data of the current hobby distribution of type of theme belonging to live video and bean vermicelli and/or analysis is made For input data, runs the program code and obtain the current temperature state of live video.Wherein, which can be number of fans Amount and corresponding temperature state can also be the distribution of current hobby and/or analysis of type of theme belonging to live video, bean vermicelli Hobby migrating data and the corresponding temperature state of the live video.
Optionally, Fig. 2 B is to execute live video temperature state identification method when it is income parameter that temperature, which assesses parameter, Flow chart.Specifically executing step includes:
S204 obtains the income parameter of live video during main broadcaster's user live broadcast video.
Optionally, how this step obtains the mistake of the income parameter of live video during main broadcaster's user live broadcast video Journey has been carried out be discussed in detail in the above-described embodiments, herein without repeating.
S205 determines the fluctuation numerical value and/or influence of fluctuations factor of income according to income parameter, and according to fluctuation numerical value And/or influence of fluctuations factor, identify the current temperature state of live video.
Optionally, in this step, according to income parameter, determine that the process of the fluctuation numerical value of income can be, according to this The income parameter of secondary acquisition, determines this gross income；The gross income that this is determined and the income according to last time acquisition The last gross income that parameter determines carries out fluctuation operation, obtains fluctuation numerical value.Wherein, the gross income can be it is basic The amount of income and/or additional income volume.Fluctuation operation can be this gross income and last gross income are carried out it is slotting It is worth operation；It can also be and this gross income and last gross income are subjected to increase ratio or down ratio operation.
Optionally, the influence factor of income fluctuation can be the influence factor for influencing this gross income, may include But it is not limited to income type, the quantity of present, the distribution of present rank etc..This step determines above-mentioned according to income parameter When each influence of fluctuations factor, the basic income parameter according to main broadcaster's user live broadcast video can be, determine in this income type Including taking in type substantially；The additional income parameter that live video is watched according to bean vermicelli, determines that this additional income type belongs to The present income that platform reward income or bean vermicelli are given；If including the present income that bean vermicelli is given in income type, may be used also To determine the rank of present and the quantity of present.Wherein, the determination of present rank, which can be, carries out rank according to the value of present Division, for example, value belongs to first level present in 10 yuan of presents below, the present being worth between 11-100 member belongs to Second level present, the present being worth at 100 yuan or more belong to third level present.The quantity of present can be the sum of present Amount, can also be the quantity of each rank present.
Optionally, when this step identification current temperature state of live video, if being identified according to the fluctuation numerical value of income, The size that can be income fluctuation numerical value is directly proportional to live video temperature state, i.e., when income fluctuation numerical value is timing, fluctuation It is bigger, then it is higher to correspond to live video temperature.On the contrary when income fluctuation numerical value is negative, fluctuation is bigger, then corresponds to live video Temperature is lower.If influence of fluctuations according to income because usually identifying, can be present rank in influence of fluctuations factor and straight Broadcast that video temperature state is directly proportional, i.e. present rank is higher, corresponding live video temperature is higher；It can also be influence of fluctuations factor In present quantity it is directly proportional to live video temperature state, i.e. present quantity is more, and corresponding live video temperature is higher.It can also To be that the number of species that the income type in influence of fluctuations factor includes are directly proportional to live video temperature state, that is, take in type The number of species for including are more, and corresponding live video temperature is higher.For example, being said if live streaming type only includes basic income type The bright main broadcaster user does not have the additional income of bean vermicelli viewing live video, i.e. bean vermicelli is not high to the fancy grade of the live video, Therefore the temperature of corresponding live video is not just high.Optionally, if being based on the fluctuation numerical value and influence of fluctuations factor of income, Then specific identification process can be identified pair according to the fluctuation numerical value and influence of fluctuations factor of income respectively using the above method Then the two temperature state values answered carry out integrated treatment to the two temperature state values, obtain the current temperature of live video State.
Optionally, in this step according to income parameter, when the identification current temperature state of live video, in addition to above-mentioned basis is pre- Except the proportionate relationship identification current temperature state of live video being first arranged, it can also be calling in advance using sample data training The related program code of the neural network model of the good temperature of live video for identification, by the fluctuation numerical value and/or wave of income Influence factor is moved as input data, the program code is run and obtains the current temperature state of live video.Wherein, the sample data It can be fluctuation numerical value and/or influence of fluctuations factor and its corresponding temperature state.
It should be noted that the embodiment of the present disclosure can be in live video temperature state recognition through above-mentioned bean vermicelli One of parameter and income parameter temperature assess parameter to identify live video temperature state, in order to further increase live streaming view The accuracy of frequency temperature identification can also be according to bean vermicelli parameter and income parameter, in conjunction with the corresponding temperature of above two parameter Recognition methods identifies the corresponding live video temperature state of each parameter, then carries out to the multiple temperature states identified Integrated treatment obtains the final current temperature state of live video.
The live video temperature state identification method that the embodiment of the present disclosure provides, in the process of main broadcaster's user live broadcast video In, obtain different temperature assessment parameters, i.e. bean vermicelli number parameter, bean vermicelli preference parameters, basic income parameter and additional income At least one of parameter assesses parameter for each temperature, different temperature assessment rules is all correspondingly arranged on, according to each Temperature assesses the current temperature state of the live video of the corresponding temperature assessment rule identification main broadcaster user of parameter, with existing people Work assessment live video temperature is compared, and greatly reduces cost of labor, and the factor considered is comprehensive, so that live video Temperature identification is more accurate, provides guarantee for the main broadcaster user's reward of giving fair in real time of live streaming platform.
Fig. 3 shows the flow chart of another live video temperature state identification method of embodiment of the present disclosure offer, this Embodiment is optimized on the basis of each optinal plan provided by the above embodiment, shows in particular and is generating live video After the recognition result of current temperature state, it is situated between according to the details that recognition result generates the diagnostic data of the current temperature of live video It continues.
Optionally, as shown in figure 3, the method in the present embodiment may include steps of:
S301 obtains the temperature assessment parameter of live video during main broadcaster's user live broadcast video.
Wherein, the temperature assessment parameter includes bean vermicelli parameter and/or income parameter.
S302 assesses parameter according to temperature, generates the recognition result of the current temperature state of live video.
S303 then obtains live video when the current temperature state in recognition result that detects belongs to diagnostic state Bean vermicelli quantity is mutated the period.
Wherein, the temperature state for needing to carry out state cause diagnosis pre-set, example can be referred to diagnostic state It such as, can be temperature state value to diagnostic state lower than lower limit state threshold, or height if current temperature state is indicated by state value In upper limit threshold；If current temperature state is indicated by multiple Status Levels, low level and advanced can be to diagnostic state Other state.The reason of available low-heat of state of the present embodiment diagnosis low-heat degree is spent, ties convenient for live streaming user according to diagnosis Live content is adjusted when fruit, improves live streaming temperature.The reason of diagnosing the state available high temperature of high temperature, how to mention High live video temperature is offered reference.Bean vermicelli quantity catastrophic event is to watch the bean vermicelli of live streaming during main broadcaster's user live broadcast Quantity is mutated (including increase suddenly or reduce suddenly) corresponding event.
Optionally, this step can be after the recognition result that S302 generates the current temperature state of live video, and detection is known It is pre-set to diagnostic state whether the current temperature state in other result belongs to, if being not belonging to, illustrates current temperature shape The reason of state is general, can not diagnose the state.If belonging to, need to carry out cause diagnosis to current state.Due to main broadcaster user The duration of live video is longer, and current state is as caused by the sub-fraction video content in live video, so originally Step needs first to determine the period for analyzing current temperature state, and since viewing live video number of fans amount variation is live video Form is the most intuitively cashed in temperature variation.So the period that bean vermicelli quantity mutates in the available live video of this step As the period for analyzing current temperature state.Specifically, one kind can be real when the bean vermicelli quantity for obtaining live video is mutated the period The mode of applying, which can be, obtains S301 at the time of temperature assessment parameter correspond to as the first moment, by the first moment before and with the As the second moment at the time of one time at intervals preset duration, using the period between the first moment and the second moment as number of fans The amount mutation period, for example, being 8:10 if obtaining at the time of temperature assessment parameter corresponds to, and between default first moment and the second moment Every 3 minutes.Then the first moment was 8:10 at this time, and the second moment was 8:07, and the mutation period is 8:07-8:10.
In order to further increase the accuracy of determining mutation period, another embodiment of the present embodiment can be with It is: from intercepting for the first moment in live video to the reference live video content the second moment；Wherein, the second moment was to obtain Take temperature assessment parameter at the time of correspond to, the first moment before the second moment, and with the second time at intervals preset duration；Detection The high frequency period issued with reference to barrage content in live video content is mutated the period as the bean vermicelli quantity.Specifically, holding When the row embodiment, it can be the method using the first embodiment, first determine the first moment and the second moment, It then is not directly to be mutated the period for the period between the first moment and the second moment as bean vermicelli quantity, but regard from live streaming Intercepted for the first moment in frequency to the live video content between the second moment as live content is referred to, in reference live content The barrage frequency of occurrences analyzed, using barrage content publication frequency high period in reference live video content as number of fans The amount mutation period.Optionally, unit time (as per minute) corresponding barrage publication is can be in statistical-reference live video content The sustained periods of time that barrage publication quantity is greater than preset quantity threshold value is mutated the period as bean vermicelli quantity by quantity.Can also be will Unit time corresponds to barrage publication quantity at least one sustained periods of time in the top and is mutated the period as bean vermicelli quantity.
It should be noted that the bean vermicelli quantity mutation period that this step obtains can be a period, it is also possible to more A period.
S304, is mutated the period according to bean vermicelli quantity, and bean vermicelli quantity mutation period corresponding target is obtained from live video Live video content.
Optionally, after S303 determines the bean vermicelli quantity mutation period, in main broadcaster's user live broadcast video, when by the mutation Initial time of the initial time of section as interception video, at the end of finish time of period will be mutated as video is intercepted It carves, one section of live video content is intercepted from live video as the target live video for carrying out the current temperature state analysis of causes Content.
S305 is mutated the period according to bean vermicelli quantity and/or target live video content generates the current temperature of live video Diagnostic data.
Optionally, if this step is mutated the diagnostic data of the period generation current temperature of live video according to bean vermicelli quantity, It can be and judge whether the bean vermicelli quantity mutation period belongs to the pre-set possible mutation period.This, which may be mutated the period, can be Corresponding possible mutation period, example are reduced and increased based on user job period setting corresponding with rest, including bean vermicelli quantity Such as, 8 points 9 points of morning is the time started to work, so when this period can be used as the reduction corresponding mutation of bean vermicelli quantity Between section.Ten half past one to the half past one at noon is the lunch break, so this period can be used as the increase of bean vermicelli quantity and correspond to Mutation time section.If the bean vermicelli quantity mutation period, which belongs to, may be mutated the period, further judge that this may be mutated the period pair What is answered is that bean vermicelli quantity is reduced or bean vermicelli quantity increases, and is reduced if bean vermicelli quantity, then the current temperature of the live video generated Diagnostic data are as follows: it is as current time is caused by the working time that current temperature state is lower, it is proposed that the adjustment live streaming time, Or change live streaming theme, type of theme of the main broadcaster without person in middle and old age's bean vermicelli user preferences of work.Increase if bean vermicelli quantity, then The current temperature diagnostic data of the live video of generation are as follows: higher current temperature state is to be caused due to current time for the time of having a rest , it is proposed that it is broadcast live from now in the period, live video temperature can be improved.
If this step generates the diagnostic data of the current temperature of live video according to target live video content, one kind can be real The mode of applying is to carry out image recognition to the image data of target live content, identifies the picture material for causing bean vermicelli quantity to be mutated As diagnostic data；Speech recognition is carried out to the audio data of target live content, identifies the language for causing bean vermicelli quantity to be mutated Sound content is as diagnostic data.For example, the image data to target live content carries out image recognition, find occur in image The picture material of electronic game, then illustrate this cause bean vermicelli quantity be mutated be electronic game picture material, by the electronics Diagnostic data of the image of game as current temperature carries out speech recognition to the audio data of target live content, finds sound Occur the audio content sung in frequency, then illustrate this cause bean vermicelli quantity be mutated be sing audio content, by the singing Diagnostic data of the audio as current temperature.
Optionally, when generating the diagnostic data of the current temperature of live video according to target live video content, another kind can Embodiment is to identify the barrage content in target live video content by character recognition technology；It extracts in barrage content The reason of keyword inputs in reasons analysis model, obtains the mutation of bean vermicelli quantity and/or recommendation on improvement, it is current as live video The diagnostic data of temperature.
Specifically, Text region, the text bullet identified can be carried out to the barrage content in target live video content Curtain content is segmented, and is extracted high frequency vocabulary, entity vocabulary or vocabulary relevant to type of theme etc. and is used as key vocabularies, calls The related program code of preparatory trained reasons analysis model runs the program using the keyword of extraction as input data The reason of code, reasons analysis model can go out the mutation of bean vermicelli quantity according to the keyword resolution of input at this time and/or improvement are built Discuss the diagnostic data as current temperature.Optionally, this step, which can also be, presets diagnostic data base, the diagnostic data base In the reason of recording the corresponding bean vermicelli quantity mutation of different candidate keywords and/or recommendation on improvement, can be by that will extract The candidate keywords recorded in keyword and diagnostic data base are matched, by the corresponding bean vermicelli of the candidate keywords of successful match The diagnostic data of the reason of quantity is mutated and/or recommendation on improvement as current temperature.
Diagnostic data is sent to main broadcaster user by S306.
Optionally, this step can be after the diagnostic data that S305 generates the current temperature of live video, in order to allow main broadcaster User is better understood by the higher or lower concrete reason of temperature of current live video, and electronic equipment can examine this of generation Disconnected data are sent to main broadcaster user.Specifically, can be the application client hair installed in the affiliated terminal of main broadcaster user Give the diagnostic result, wherein diagnostic result can be to be sent in the form of notification message, the acknowledgement message of live video, pop-up etc. To main broadcaster user.After main broadcaster user receives the diagnostic result, oneself current live video can be understood by the diagnostic result The higher or lower reason of temperature, so according to the reason determine currently whether to continue to be broadcast live and it is subsequent to live content into The direction of row optimization, improves the quality of subsequent live video, attracts more beans vermicelli.
The embodiment of the present disclosure provides a kind of live video temperature state identification method, in the mistake of main broadcaster's user live broadcast video Cheng Zhong obtains comprising bean vermicelli parameter and/or takes in the live video temperature assessment parameter of parameter, generates the current temperature of live video The recognition result of state, if current temperature state belongs to diagnostic state, it is determined that bean vermicelli quantity is mutated the period, and to number of fans Amount mutation period and/or the period corresponding live video content are analyzed, and the diagnosis number of the current temperature of live video is generated According to being sent to main broadcaster user.The scheme of the embodiment of the present disclosure not only can carry out temperature by the live video to main broadcaster user in real time State recognition, can also be according to recognition result to the diagnostic data of the current temperature state of user feedback, to help main broadcaster user Type of theme real-time perfoming adjustment to live content, improves the temperature of live video.It, can also be fast even new hand main broadcaster Speed grasps the method for improving live video temperature, greatly improves the enthusiasm of main broadcaster's live streaming, enhancing live streaming platform live video Viewing temperature.
Fig. 4 shows a kind of structural schematic diagram of live video temperature status identification means of embodiment of the present disclosure offer, The embodiment of the present disclosure is applicable to during main broadcaster's user live broadcast, the feelings identified to the temperature state of live video Condition.The device can be realized by software and/or hardware, and be integrated in the electronic equipment for executing this method, such as Fig. 4 institute Show, the apparatus may include:
Parameter acquisition module 401 is assessed, for obtaining the live video during main broadcaster's user live broadcast video Temperature assesses parameter；The temperature assessment parameter includes bean vermicelli parameter and/or income parameter；
Temperature state recognition module 402 generates the current temperature of the live video for assessing parameter according to the temperature The recognition result of state.
The embodiment of the present disclosure provides a kind of live video temperature status identification means, by main broadcaster's user live broadcast video During, the live video temperature assessment parameter of parameter is obtained comprising bean vermicelli parameter and/or takes in, and assess based on the temperature The recognition result of the parameter generation current temperature state of live video.The scheme of the embodiment of the present disclosure can realize commenting based on various dimensions Estimate parameter, accurately identify the real-time temperature state of live video, is mentioned for the main broadcaster user's reward of giving fair in real time of live streaming platform It has supplied to guarantee.
Further, the bean vermicelli parameter includes bean vermicelli number parameter and/or bean vermicelli preference parameters；The bean vermicelli parameter pair The bean vermicelli answered includes: the currently viewing bean vermicelli that platform is broadcast live, the high consumption bean vermicelli in the live streaming platform, the main broadcaster user At least one of currently viewing bean vermicelli, the newly-increased bean vermicelli of the main broadcaster user and pre- loss bean vermicelli of the main broadcaster user.
Further, if temperature assessment parameter is bean vermicelli preference parameters, the assessment parameter acquisition module 401 has Body is used for:
By bean vermicelli data input user's portrait model, the bean vermicelli portrait of the bean vermicelli data is obtained；
Bean vermicelli preference parameters are obtained from bean vermicelli portrait.
Further, described device further include: be lost bean vermicelli determining module, which is used for:
Main broadcaster's user live broadcast view is watched in current time period and upper a period of time according to the bean vermicelli of main broadcaster user The frequency and/or duration of frequency determine that the bean vermicelli watches the suppression ratio of the live streaming frequency and/or duration in current time period Example；
If the down ratio is greater than preset ratio threshold value, the bean vermicelli is the pre- loss bean vermicelli of the main broadcaster user.
Further, the corresponding income of the income parameter includes: the basic income and/or powder of main broadcaster's user live broadcast video The additional income of silk viewing live video.
Further, the temperature state recognition module 402 is specifically used for:
According to bean vermicelli parameter, at least one of quantity, hobby distributed data and hobby migrating data of bean vermicelli are determined, and According at least one of the quantity of the bean vermicelli, hobby distributed data and hobby migrating data, identify that the live video is worked as Preceding temperature state；And/or
According to income parameter, the fluctuation numerical value and/or influence of fluctuations factor of income are determined, and according to the fluctuation numerical value And/or influence of fluctuations factor, identify the current temperature state of the live video.
Further, described device further include:
Data diagnosis module, for generating the diagnostic data of the current temperature of the live video according to recognition result；
Data transmission blocks, for the diagnostic data to be sent to main broadcaster user.
Further, the data diagnosis module includes:
It is mutated period acquiring unit, detects that the current temperature state in recognition result belongs to diagnostic state for working as, Then obtain the bean vermicelli quantity mutation period of the live video；
Video content acquiring unit obtains institute for being mutated the period according to the bean vermicelli quantity from the live video State bean vermicelli quantity mutation period corresponding target live video content；
Diagnostic data generation unit, for being mutated in period and/or the target live video according to the bean vermicelli quantity Hold the diagnostic data for generating the current temperature of live video.
Further, the mutation period acquiring unit is specifically used for:
From intercepting for the first moment in the live video to the reference live video content the second moment；Wherein, institute At the time of stating for the second moment and assess parameter to obtain the temperature and correspond to, first moment before second moment, and With the second time at intervals preset duration；
Detect it is described with reference in live video content barrage content issue the high frequency period be mutated as the bean vermicelli quantity Period.
Further, the diagnostic data generation unit is specifically used for:
By character recognition technology, the barrage content in the target live video content is identified；
The reason of extracting in the keyword input reasons analysis model in the barrage content, obtaining the mutation of bean vermicelli quantity And/or recommendation on improvement, the diagnostic data as the current temperature of the live video.
The live video temperature status identification means that the embodiment of the present disclosure provides are regarded with the live streaming that the various embodiments described above provide Frequency temperature state identification method belongs to same inventive concept, and the technical detail of detailed description not can be found in the embodiments of the present disclosure The various embodiments described above, and the embodiment of the present disclosure and the various embodiments described above beneficial effect having the same.
Below with reference to Fig. 5, it illustrates the structural representations for the electronic equipment 500 for being suitable for being used to realize the embodiment of the present disclosure Figure.Electronic equipment in the embodiment of the present disclosure can be the corresponding equipment of rear end live streaming platform of application program, can also be peace Mobile terminal device equipped with application client.Specifically, the electronic equipment can include but is not limited to such as move electricity Words, laptop, digit broadcasting receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia Player), the mobile terminal and such as number TV, desktop computer etc. of car-mounted terminal (such as vehicle mounted guidance terminal) etc. Fixed terminal.Electronic equipment 500 shown in Fig. 5 is only an example, should not function and use to the embodiment of the present disclosure Range band carrys out any restrictions.
As shown in figure 5, electronic equipment 500 may include processing unit (such as central processing unit, graphics processor etc.) 501, random access can be loaded into according to the program being stored in read-only memory (ROM) 502 or from storage device 508 Program in memory (RAM) 503 and execute various movements appropriate and processing.In RAM 503, it is also stored with electronic equipment Various programs and data needed for 500 operations.Processing unit 501, ROM 502 and RAM 503 pass through the phase each other of bus 504 Even.Input/output (I/O) interface 505 is also connected to bus 504.
In general, following device can connect to I/O interface 505: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph As the input unit 506 of head, microphone, accelerometer, gyroscope etc.；Including such as liquid crystal display (LCD), loudspeaker, vibration The output device 507 of dynamic device etc.；Storage device 508 including such as tape, hard disk etc.；And communication device 509.Communication device 509, which can permit electronic equipment 500, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 5 shows tool There is the electronic equipment 500 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with Alternatively implement or have more or fewer devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising being carried on non-transient computer can The computer program on medium is read, which includes the program code for method shown in execution flow chart.At this In the embodiment of sample, which can be downloaded and installed from network by communication device 509, or be filled from storage It sets 508 to be mounted, or is mounted from ROM 502.When the computer program is executed by processing unit 501, the disclosure is executed The above-mentioned function of being limited in the method for embodiment.
It should be noted that the above-mentioned computer-readable medium of the disclosure can be computer-readable signal media or meter Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device, Or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can be it is any include or storage journey The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this In open, computer-readable signal media may include in a base band or as the data-signal that carrier wave a part is propagated, In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable and deposit Any computer-readable medium other than storage media, the computer-readable signal media can send, propagate or transmit and be used for By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium Program code can transmit with any suitable medium, including but not limited to: electric wire, optical cable, RF (radio frequency) etc. are above-mentioned Any appropriate combination.
In some embodiments, electronic equipment can use such as HTTP (HyperText Transfer Protocol, hypertext transfer protocol) etc the network protocols of any currently known or following research and development communicated, and can To be interconnected with the digital data communications (for example, communication network) of arbitrary form or medium.The example of communication network includes local area network (" LAN "), wide area network (" WAN "), Internet (for example, internet) and ad-hoc network are (for example, the end-to-end net of ad hoc Network) and any currently known or following research and development network.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment；It is also possible to individualism, and not It is fitted into the electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by the electricity When sub- equipment executes, so that the electronic equipment internal process executes: during main broadcaster's user live broadcast video, obtaining described straight Broadcast the temperature assessment parameter of video；The temperature assessment parameter includes bean vermicelli parameter and/or income parameter；It is commented according to the temperature Estimate parameter, generates the recognition result of the current temperature state of the live video.
The calculating of the operation for executing the disclosure can be write with one or more programming languages or combinations thereof Machine program code, above procedure design language include but is not limited to object oriented program language-such as Java, Smalltalk, C++ further include conventional procedural programming language-such as " C " language or similar program design language Speech.Program code can be executed fully on the user computer, partly be executed on the user computer, as an independence Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit It is connected with ISP by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction Combination realize.
Being described in unit involved in the embodiment of the present disclosure can be realized by way of software, can also be by hard The mode of part is realized.Wherein, the title of unit does not constitute the restriction to the unit itself under certain conditions.
Function described herein can be executed at least partly by one or more hardware logic components.Example Such as, without limitation, the hardware logic component for the exemplary type that can be used include: field programmable gate array (FPGA), specially With integrated circuit (ASIC), Application Specific Standard Product (ASSP), system on chip (SOC), complex programmable logic equipment (CPLD) etc. Deng.
In the context of the disclosure, machine readable media can be tangible medium, may include or is stored for The program that instruction execution system, device or equipment are used or is used in combination with instruction execution system, device or equipment.Machine can Reading medium can be machine-readable signal medium or machine-readable storage medium.Machine readable media can include but is not limited to electricity Son, magnetic, optical, electromagnetism, infrared or semiconductor system, device or equipment or above content any conjunction Suitable combination.The more specific example of machine readable storage medium will include the electrical connection of line based on one or more, portable meter Calculation machine disk, hard disk, random access memory (RAM), read-only memory (ROM), Erasable Programmable Read Only Memory EPROM (EPROM Or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage facilities or Any appropriate combination of above content.
According to a kind of live video temperature state identification method that one or more other embodiments of the present disclosure provide, this method Include:
During main broadcaster's user live broadcast video, the temperature assessment parameter of the live video is obtained；The temperature is commented Estimating parameter includes bean vermicelli parameter and/or income parameter；
Parameter is assessed according to the temperature, generates the recognition result of the current temperature state of the live video.
According to one or more other embodiments of the present disclosure, in the above method, the bean vermicelli parameter includes bean vermicelli number parameter And/or bean vermicelli preference parameters；The corresponding bean vermicelli of the bean vermicelli parameter includes: the currently viewing bean vermicelli that platform is broadcast live, the live streaming The currently viewing bean vermicelli of high consumption bean vermicelli, the main broadcaster user, the newly-increased bean vermicelli of the main broadcaster user and the master in platform At least one of pre- loss bean vermicelli of broadcasting user.
According to one or more other embodiments of the present disclosure, in the above method, if temperature assessment parameter is that bean vermicelli is liked Parameter then obtains the temperature assessment parameter of the live video, comprising:
By bean vermicelli data input user's portrait model, the bean vermicelli portrait of the bean vermicelli data is obtained；
Bean vermicelli preference parameters are obtained from bean vermicelli portrait.
According to one or more other embodiments of the present disclosure, in the above method, during main broadcaster's user live broadcast video, obtain Before taking the temperature of live video to assess parameter, further includes:
Main broadcaster's user live broadcast view is watched in current time period and upper a period of time according to the bean vermicelli of main broadcaster user The frequency and/or duration of frequency determine that the bean vermicelli watches the suppression ratio of the live streaming frequency and/or duration in current time period Example；
If the down ratio is greater than preset ratio threshold value, the bean vermicelli is the pre- loss bean vermicelli of the main broadcaster user.
According to one or more other embodiments of the present disclosure, in the above method, the corresponding income of the income parameter includes: master The basic income of broadcasting user live video and/or the additional income of bean vermicelli viewing live video.
According to one or more other embodiments of the present disclosure, in the above method, parameter is assessed according to the temperature, described in generation The recognition result of the current temperature state of live video, comprising:
According to bean vermicelli parameter, at least one of quantity, hobby distributed data and hobby migrating data of bean vermicelli are determined, and According at least one of the quantity of the bean vermicelli, hobby distributed data and hobby migrating data, identify that the live video is worked as Preceding temperature state；And/or
According to income parameter, the fluctuation numerical value and/or influence of fluctuations factor of income are determined, and according to the fluctuation numerical value And/or influence of fluctuations factor, identify the current temperature state of the live video.
According to one or more other embodiments of the present disclosure, in the above method, the current temperature state of the live video is generated Recognition result after, further includes:
The diagnostic data of the current temperature of the live video is generated according to recognition result, and the diagnostic data is sent to Main broadcaster user.
According to one or more other embodiments of the present disclosure, in the above method, the live video is generated according to recognition result The diagnostic data of current temperature, comprising:
When the current temperature state in recognition result that detects belongs to diagnostic state, then the powder of the live video is obtained Silk quantity is mutated the period；
It is mutated the period according to the bean vermicelli quantity, it is corresponding that the bean vermicelli quantity mutation period is obtained from the live video Target live video content；
The period is mutated according to the bean vermicelli quantity and/or the target live video content generation live video is current The diagnostic data of temperature.
According to one or more other embodiments of the present disclosure, in the above method, the bean vermicelli quantity for obtaining the live video is prominent Become the period, comprising:
From intercepting for the first moment in the live video to the reference live video content the second moment；Wherein, institute At the time of stating for the second moment and assess parameter to obtain the temperature and correspond to, first moment before second moment, and With the second time at intervals preset duration；
Detect it is described with reference in live video content barrage content issue the high frequency period be mutated as the bean vermicelli quantity Period.
According to one or more other embodiments of the present disclosure, in the above method, generated according to the target live video content The diagnostic data of the current temperature of live video, comprising:
By character recognition technology, the barrage content in the target live video content is identified；
The reason of extracting in the keyword input reasons analysis model in the barrage content, obtaining the mutation of bean vermicelli quantity And/or recommendation on improvement, the diagnostic data as the current temperature of the live video.
According to a kind of live video temperature status identification means that one or more other embodiments of the present disclosure provide, the device Include:
Parameter acquisition module is assessed, for obtaining the heat of the live video during main broadcaster's user live broadcast video Degree assessment parameter；The temperature assessment parameter includes bean vermicelli parameter and/or income parameter；
Temperature state recognition module generates the current temperature shape of the live video for assessing parameter according to the temperature The recognition result of state.
According to one or more other embodiments of the present disclosure, the bean vermicelli parameter in above-mentioned apparatus includes bean vermicelli number parameter And/or bean vermicelli preference parameters；The corresponding bean vermicelli of the bean vermicelli parameter includes: the currently viewing bean vermicelli that platform is broadcast live, the live streaming The currently viewing bean vermicelli of high consumption bean vermicelli, the main broadcaster user, the newly-increased bean vermicelli of the main broadcaster user and the master in platform At least one of pre- loss bean vermicelli of broadcasting user.
It is above-mentioned if temperature assessment parameter is bean vermicelli preference parameters according to one or more other embodiments of the present disclosure The assessment parameter acquisition module 401 in device is specifically used for:
By bean vermicelli data input user's portrait model, the bean vermicelli portrait of the bean vermicelli data is obtained；
Bean vermicelli preference parameters are obtained from bean vermicelli portrait.
According to one or more other embodiments of the present disclosure, above-mentioned apparatus further include: be lost bean vermicelli determining module, which uses In:
Main broadcaster's user live broadcast view is watched in current time period and upper a period of time according to the bean vermicelli of main broadcaster user The frequency and/or duration of frequency determine that the bean vermicelli watches the suppression ratio of the live streaming frequency and/or duration in current time period Example；
If the down ratio is greater than preset ratio threshold value, the bean vermicelli is the pre- loss bean vermicelli of the main broadcaster user.
According to one or more other embodiments of the present disclosure, the corresponding income of the income parameter in above-mentioned apparatus includes: The basic income of main broadcaster's user live broadcast video and/or the additional income of bean vermicelli viewing live video.
According to one or more other embodiments of the present disclosure, the temperature state recognition module 402 in above-mentioned apparatus is specific For:
According to bean vermicelli parameter, at least one of quantity, hobby distributed data and hobby migrating data of bean vermicelli are determined, and According at least one of the quantity of the bean vermicelli, hobby distributed data and hobby migrating data, identify that the live video is worked as Preceding temperature state；And/or
According to income parameter, the fluctuation numerical value and/or influence of fluctuations factor of income are determined, and according to the fluctuation numerical value And/or influence of fluctuations factor, identify the current temperature state of the live video.
According to one or more other embodiments of the present disclosure, above-mentioned apparatus further include:
Data diagnosis module, for generating the diagnostic data of the current temperature of the live video according to recognition result；
Data transmission blocks, for the diagnostic data to be sent to main broadcaster user.
According to one or more other embodiments of the present disclosure, the data diagnosis module in above-mentioned apparatus includes:
It is mutated period acquiring unit, detects that the current temperature state in recognition result belongs to diagnostic state for working as, Then obtain the bean vermicelli quantity mutation period of the live video；
Video content acquiring unit obtains institute for being mutated the period according to the bean vermicelli quantity from the live video State bean vermicelli quantity mutation period corresponding target live video content；
Diagnostic data generation unit, for being mutated in period and/or the target live video according to the bean vermicelli quantity Hold the diagnostic data for generating the current temperature of live video.
According to one or more other embodiments of the present disclosure, the mutation period acquiring unit in above-mentioned apparatus is specifically used In:
From intercepting for the first moment in the live video to the reference live video content the second moment；Wherein, institute At the time of stating for the second moment and assess parameter to obtain the temperature and correspond to, first moment before second moment, and With the second time at intervals preset duration；
Detect it is described with reference in live video content barrage content issue the high frequency period be mutated as the bean vermicelli quantity Period.
According to one or more other embodiments of the present disclosure, the diagnostic data generation unit in above-mentioned apparatus is specifically used In:
By character recognition technology, the barrage content in the target live video content is identified；
The reason of extracting in the keyword input reasons analysis model in the barrage content, obtaining the mutation of bean vermicelli quantity And/or recommendation on improvement, the diagnostic data as the current temperature of the live video.
According to a kind of electronic equipment that one or more other embodiments of the present disclosure provide, which includes:
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing Device realizes the live video temperature state identification method as described in disclosure any embodiment.
According to a kind of readable medium that one or more other embodiments of the present disclosure provide, it is stored thereon with computer program, The live video temperature state identification method as described in disclosure any embodiment is realized when the program is executed by processor.
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art Member is it should be appreciated that the open scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic Scheme, while should also cover in the case where not departing from design disclosed above, it is carried out by above-mentioned technical characteristic or its equivalent feature Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed in the disclosure Can technical characteristic replaced mutually and the technical solution that is formed.
Although this is not construed as requiring these operations with institute in addition, depicting each operation using certain order The certain order that shows executes in sequential order to execute.Under certain environment, multitask and parallel processing may be advantageous 's.Similarly, although containing several specific implementation details in being discussed above, these are not construed as to this public affairs The limitation for the range opened.Certain features described in the context of individual embodiment can also be realized in combination single real It applies in example.On the contrary, the various features described in the context of single embodiment can also be individually or with any suitable The mode of sub-portfolio is realized in various embodiments.
Although having used specific to this theme of the language description of structure feature and/or method logical action, answer When understanding that theme defined in the appended claims is not necessarily limited to special characteristic described above or movement.On on the contrary, Special characteristic described in face and movement are only to realize the exemplary forms of claims.

Claims (13)

1. a kind of live video temperature state identification method characterized by comprising
During main broadcaster's user live broadcast video, the temperature assessment parameter of the live video is obtained；The temperature assessment ginseng Number includes bean vermicelli parameter and/or income parameter；
Parameter is assessed according to the temperature, generates the recognition result of the current temperature state of the live video.
2. the method according to claim 1, wherein the bean vermicelli parameter includes bean vermicelli number parameter and/or powder Silk preference parameters；The corresponding bean vermicelli of the bean vermicelli parameter includes: the currently viewing bean vermicelli that platform is broadcast live, in the live streaming platform High consumption bean vermicelli, the currently viewing bean vermicelli of the main broadcaster user, the newly-increased bean vermicelli of the main broadcaster user and the main broadcaster user It is pre- to be lost at least one of bean vermicelli.
3. according to the method described in claim 2, it is characterized in that, if the temperature assessment parameter be bean vermicelli preference parameters, Obtain the temperature assessment parameter of the live video, comprising:
By bean vermicelli data input user's portrait model, the bean vermicelli portrait of the bean vermicelli data is obtained；
Bean vermicelli preference parameters are obtained from bean vermicelli portrait.
4. according to the method described in claim 2, it is characterized in that, obtaining live streaming during main broadcaster's user live broadcast video Before the temperature assessment parameter of video, further includes:
Main broadcaster's user live broadcast video is watched in current time period and upper a period of time according to the bean vermicelli of main broadcaster user The frequency and/or duration determine that the bean vermicelli watches the down ratio of the live streaming frequency and/or duration in current time period；
If the down ratio is greater than preset ratio threshold value, the bean vermicelli is the pre- loss bean vermicelli of the main broadcaster user.
5. the method according to claim 1, wherein the corresponding income of the income parameter includes: main broadcaster user The basic income of live video and/or the additional income of bean vermicelli viewing live video.
6. generating the live streaming view the method according to claim 1, wherein assessing parameter according to the temperature The recognition result of the current temperature state of frequency, comprising:
According to bean vermicelli parameter, determines the quantity of bean vermicelli, likes at least one of distributed data and hobby migrating data, and according to At least one of quantity, hobby distributed data and hobby migrating data of the bean vermicelli, identify that the live video is currently warm Degree state；And/or
According to income parameter, determine the fluctuation numerical value and/or influence of fluctuations factor of income, and according to the fluctuation numerical value and/or Influence of fluctuations factor identifies the current temperature state of the live video.
7. the method according to claim 1, wherein generating the identification knot of the current temperature state of the live video After fruit, further includes:
The diagnostic data of the current temperature of the live video is generated according to recognition result, and the diagnostic data is sent to main broadcaster User.
8. the method according to the description of claim 7 is characterized in that generating the current temperature of live video according to recognition result Diagnostic data, comprising:
When the current temperature state in recognition result that detects belongs to diagnostic state, then the number of fans of the live video is obtained The amount mutation period；
It is mutated the period according to the bean vermicelli quantity, the bean vermicelli quantity mutation period corresponding mesh is obtained from the live video Mark live video content；
The period is mutated according to the bean vermicelli quantity and/or the target live video content generates the current temperature of live video Diagnostic data.
9. according to the method described in claim 8, it is characterized in that, obtain the live video bean vermicelli quantity mutation the period, Include:
From intercepting for the first moment in the live video to the reference live video content the second moment；Wherein, described Two moment were at the time of obtaining the temperature to assess parameter and correspond to, first moment before second moment, and with institute State the second time at intervals preset duration；
The high frequency period issued with reference to barrage content in live video content is detected as the bean vermicelli quantity and is mutated the period.
10. according to the method described in claim 8, it is characterized in that, being generated according to the target live video content described straight Broadcast the diagnostic data of the current temperature of video, comprising:
By character recognition technology, the barrage content in the target live video content is identified；
Extract in the barrage content keyword input reasons analysis model in, obtain bean vermicelli quantity mutation the reason of and/or Recommendation on improvement, the diagnostic data as the current temperature of the live video.
11. a kind of live video temperature status identification means characterized by comprising
Parameter acquisition module is assessed, for during main broadcaster's user live broadcast video, the temperature for obtaining the live video to be commented Estimate parameter；The temperature assessment parameter includes bean vermicelli parameter and/or income parameter；
Temperature state recognition module generates the current temperature state of the live video for assessing parameter according to the temperature Recognition result.
12. a kind of electronic equipment characterized by comprising
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real The now live video temperature state identification method as described in any in claim 1-10.
13. a kind of readable medium, is stored thereon with computer program, which is characterized in that the realization when program is executed by processor Live video temperature state identification method as described in any in claim 1-10.
CN201910765321.3A 2019-08-19 2019-08-19 Live video hot state identification method, device, equipment and readable medium Active CN110475155B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910765321.3A CN110475155B (en) 2019-08-19 2019-08-19 Live video hot state identification method, device, equipment and readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910765321.3A CN110475155B (en) 2019-08-19 2019-08-19 Live video hot state identification method, device, equipment and readable medium

Publications (2)

Publication Number Publication Date
CN110475155A true CN110475155A (en) 2019-11-19
CN110475155B CN110475155B (en) 2022-02-18

Family

ID=68511238

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910765321.3A Active CN110475155B (en) 2019-08-19 2019-08-19 Live video hot state identification method, device, equipment and readable medium

Country Status (1)

Country Link
CN (1) CN110475155B (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111107342A (en) * 2019-12-30 2020-05-05 广州市百果园网络科技有限公司 Audio and video evaluation method, device, equipment and storage medium
CN112040254A (en) * 2020-08-13 2020-12-04 广州虎牙信息科技有限公司 Risk control method and device, storage medium and computer equipment
CN112084369A (en) * 2020-08-03 2020-12-15 广州数说故事信息科技有限公司 Highlight moment mining method and model based on video live broadcast
CN112235596A (en) * 2020-12-10 2021-01-15 杭州次元岛科技有限公司 Live webcast-based food recommendation method and device
CN112434053A (en) * 2020-12-02 2021-03-02 百果园技术(新加坡)有限公司 Method, device, equipment and storage medium for calculating live broadcast heat
CN113038168A (en) * 2021-04-09 2021-06-25 上海哔哩哔哩科技有限公司 Data processing method and device
CN113449593A (en) * 2021-05-25 2021-09-28 北京达佳互联信息技术有限公司 Early warning method and device for anchor loss situation
CN114302242A (en) * 2022-01-25 2022-04-08 聚好看科技股份有限公司 Media asset recommendation method, display device and server
CN115150664A (en) * 2022-09-01 2022-10-04 北京达佳互联信息技术有限公司 Data processing method and device, electronic equipment and storage medium
CN115396682A (en) * 2022-08-15 2022-11-25 北京奇虎科技有限公司 Abnormal point positioning method, device, equipment and storage medium

Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106331779A (en) * 2016-08-22 2017-01-11 暴风集团股份有限公司 Method and system for pushing anchor based on user preferences during video playing process
CN106604050A (en) * 2016-12-19 2017-04-26 天脉聚源(北京)传媒科技有限公司 Direct broadcast video assessment method and device
CN106658038A (en) * 2016-12-19 2017-05-10 广州虎牙信息科技有限公司 Live broadcast interaction method based on video stream and corresponding device thereof
WO2017092259A1 (en) * 2015-12-04 2017-06-08 腾讯科技（深圳）有限公司 Transmission control method and apparatus for game live video
CN106851349A (en) * 2017-03-21 2017-06-13 上海星红桉数据科技有限公司 Based on magnanimity across the live recommendation method for shielding viewing behavior data
CN106937177A (en) * 2017-03-06 2017-07-07 北京潘达互娱科技有限公司 Direct broadcasting room popularity display methods and device
CN107172498A (en) * 2017-04-25 2017-09-15 北京潘达互娱科技有限公司 Live room methods of exhibiting and device
EP3300305A1 (en) * 2016-09-26 2018-03-28 Yokogawa Electric Corporation Processing device, control method of processing device, and recording medium
CN108012158A (en) * 2017-11-22 2018-05-08 广州虎牙信息科技有限公司 Direct broadcasting room main broadcaster bean vermicelli ranks method, apparatus and corresponding terminal
CN108040285A (en) * 2017-11-15 2018-05-15 上海掌门科技有限公司 Net cast picture adjusting method, computer equipment and storage medium
CN108322829A (en) * 2018-03-02 2018-07-24 北京奇艺世纪科技有限公司 Personalized main broadcaster recommends method, apparatus and electronic equipment
CN108401162A (en) * 2018-01-11 2018-08-14 北京潘达互娱科技有限公司 Applied to the message treatment method and device in network direct broadcasting
CN108419126A (en) * 2018-01-23 2018-08-17 广州虎牙信息科技有限公司 Abnormal main broadcaster's recognition methods, storage medium and the terminal of platform is broadcast live
CN109218776A (en) * 2017-06-30 2019-01-15 武汉斗鱼网络科技有限公司 A kind of method, apparatus and computer equipment improving main broadcaster's popularity
CN109246441A (en) * 2018-09-30 2019-01-18 武汉斗鱼网络科技有限公司 Wonderful time video automatic generation method, storage medium, equipment and system
CN109348237A (en) * 2018-09-20 2019-02-15 武汉斗鱼网络科技有限公司 A kind of direct broadcasting room management method, device, server and storage medium
CN109361932A (en) * 2018-11-23 2019-02-19 武汉斗鱼网络科技有限公司 The method that temperature prediction is broadcast live, device, equipment and medium
CN109451326A (en) * 2018-11-13 2019-03-08 广州虎牙科技有限公司 A kind of methods of exhibiting, device, server and the storage medium of main broadcaster's information
CN109858971A (en) * 2019-02-03 2019-06-07 北京字节跳动网络技术有限公司 Processing method, device, storage medium and the electronic equipment of user's portrait

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017092259A1 (en) * 2015-12-04 2017-06-08 腾讯科技（深圳）有限公司 Transmission control method and apparatus for game live video
CN106331779A (en) * 2016-08-22 2017-01-11 暴风集团股份有限公司 Method and system for pushing anchor based on user preferences during video playing process
EP3300305A1 (en) * 2016-09-26 2018-03-28 Yokogawa Electric Corporation Processing device, control method of processing device, and recording medium
CN106604050A (en) * 2016-12-19 2017-04-26 天脉聚源(北京)传媒科技有限公司 Direct broadcast video assessment method and device
CN106658038A (en) * 2016-12-19 2017-05-10 广州虎牙信息科技有限公司 Live broadcast interaction method based on video stream and corresponding device thereof
CN106937177A (en) * 2017-03-06 2017-07-07 北京潘达互娱科技有限公司 Direct broadcasting room popularity display methods and device
CN106851349A (en) * 2017-03-21 2017-06-13 上海星红桉数据科技有限公司 Based on magnanimity across the live recommendation method for shielding viewing behavior data
CN107172498A (en) * 2017-04-25 2017-09-15 北京潘达互娱科技有限公司 Live room methods of exhibiting and device
CN109218776A (en) * 2017-06-30 2019-01-15 武汉斗鱼网络科技有限公司 A kind of method, apparatus and computer equipment improving main broadcaster's popularity
CN108040285A (en) * 2017-11-15 2018-05-15 上海掌门科技有限公司 Net cast picture adjusting method, computer equipment and storage medium
CN108012158A (en) * 2017-11-22 2018-05-08 广州虎牙信息科技有限公司 Direct broadcasting room main broadcaster bean vermicelli ranks method, apparatus and corresponding terminal
CN108401162A (en) * 2018-01-11 2018-08-14 北京潘达互娱科技有限公司 Applied to the message treatment method and device in network direct broadcasting
CN108419126A (en) * 2018-01-23 2018-08-17 广州虎牙信息科技有限公司 Abnormal main broadcaster's recognition methods, storage medium and the terminal of platform is broadcast live
CN108322829A (en) * 2018-03-02 2018-07-24 北京奇艺世纪科技有限公司 Personalized main broadcaster recommends method, apparatus and electronic equipment
CN109348237A (en) * 2018-09-20 2019-02-15 武汉斗鱼网络科技有限公司 A kind of direct broadcasting room management method, device, server and storage medium
CN109246441A (en) * 2018-09-30 2019-01-18 武汉斗鱼网络科技有限公司 Wonderful time video automatic generation method, storage medium, equipment and system
CN109451326A (en) * 2018-11-13 2019-03-08 广州虎牙科技有限公司 A kind of methods of exhibiting, device, server and the storage medium of main broadcaster's information
CN109361932A (en) * 2018-11-23 2019-02-19 武汉斗鱼网络科技有限公司 The method that temperature prediction is broadcast live, device, equipment and medium
CN109858971A (en) * 2019-02-03 2019-06-07 北京字节跳动网络技术有限公司 Processing method, device, storage medium and the electronic equipment of user's portrait

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
仲丽君等: "社交网络异常用户识别技术综述", 《计算机工程与应用》 *

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111107342A (en) * 2019-12-30 2020-05-05 广州市百果园网络科技有限公司 Audio and video evaluation method, device, equipment and storage medium
CN111107342B (en) * 2019-12-30 2022-04-05 广州市百果园网络科技有限公司 Audio and video evaluation method, device, equipment and storage medium
CN112084369A (en) * 2020-08-03 2020-12-15 广州数说故事信息科技有限公司 Highlight moment mining method and model based on video live broadcast
CN112040254A (en) * 2020-08-13 2020-12-04 广州虎牙信息科技有限公司 Risk control method and device, storage medium and computer equipment
CN112434053A (en) * 2020-12-02 2021-03-02 百果园技术(新加坡)有限公司 Method, device, equipment and storage medium for calculating live broadcast heat
CN112434053B (en) * 2020-12-02 2024-03-26 百果园技术(新加坡)有限公司 Method, device, equipment and storage medium for calculating live broadcast heat
CN112235596B (en) * 2020-12-10 2021-03-19 杭州次元岛科技有限公司 Live webcast-based food recommendation method and device
CN112235596A (en) * 2020-12-10 2021-01-15 杭州次元岛科技有限公司 Live webcast-based food recommendation method and device
CN113038168A (en) * 2021-04-09 2021-06-25 上海哔哩哔哩科技有限公司 Data processing method and device
CN113449593A (en) * 2021-05-25 2021-09-28 北京达佳互联信息技术有限公司 Early warning method and device for anchor loss situation
CN114302242A (en) * 2022-01-25 2022-04-08 聚好看科技股份有限公司 Media asset recommendation method, display device and server
CN114302242B (en) * 2022-01-25 2023-10-31 聚好看科技股份有限公司 Media asset recommendation method, display equipment and server
CN115396682A (en) * 2022-08-15 2022-11-25 北京奇虎科技有限公司 Abnormal point positioning method, device, equipment and storage medium
CN115396682B (en) * 2022-08-15 2024-04-16 北京奇虎科技有限公司 Abnormal point positioning method, device, equipment and storage medium
CN115150664A (en) * 2022-09-01 2022-10-04 北京达佳互联信息技术有限公司 Data processing method and device, electronic equipment and storage medium
CN115150664B (en) * 2022-09-01 2023-01-20 北京达佳互联信息技术有限公司 Data processing method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN110475155B (en) 2022-02-18

Similar Documents

Publication Publication Date Title
CN110475155A (en) Live video temperature state identification method, device, equipment and readable medium
CN110446057A (en) Providing method, device, equipment and the readable medium of auxiliary data is broadcast live
Srinivasan et al. Biases in AI systems
CN108304379B (en) Article identification method and device and storage medium
CN108351870A (en) According to the Computer Distance Education and semantic understanding of activity pattern
CN108351992A (en) It is experienced according to the enhanced computer of active prediction
JP6807389B2 (en) Methods and equipment for immediate prediction of media content performance
CN110378732A (en) Information display method, information correlation method, device, equipment and storage medium
CN110401844A (en) Generation method, device, equipment and the readable medium of net cast strategy
CN110880127B (en) Consumption level prediction method and device, electronic equipment and storage medium
US9344507B2 (en) Method of processing web access information and server implementing same
CN109409949A (en) Determination method, apparatus, electronic equipment and the storage medium of user group's classification
Yu et al. Inferring user profile attributes from multidimensional mobile phone sensory data
CN110458360A (en) Prediction technique, device, equipment and the storage medium of hot resource
CN110366043A (en) Method for processing video frequency, device, electronic equipment and readable medium
CN107943583A (en) Processing method, device, storage medium and the electronic equipment of application program
CN109509010A (en) A kind of method for processing multimedia information, terminal and storage medium
CN111931073B (en) Content pushing method and device, electronic equipment and computer readable medium
Yang et al. Quantitative study of music listening behavior in a smartphone context
CN110223124A (en) Data processing method, device, electronic equipment and computer-readable medium
CN110198460A (en) Choosing method and device, storage medium, the electronic device of media information
CN110475158B (en) Video learning material providing method and device, electronic equipment and readable medium
US20150227970A1 (en) System and method for providing movie file embedded with advertisement movie
CN109542297A (en) The method, apparatus and electronic equipment of operation guiding information are provided
CN105243133B (en) A kind of search record display methods and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant