CN109040297A

CN109040297A - User's portrait generation method and device

Info

Publication number: CN109040297A
Application number: CN201811005336.1A
Authority: CN
Inventors: 黄桂志
Original assignee: Guangzhou Kugou Computer Technology Co Ltd
Current assignee: Guangzhou Kugou Computer Technology Co Ltd
Priority date: 2018-08-30
Filing date: 2018-08-30
Publication date: 2018-12-18
Anticipated expiration: 2038-08-30
Also published as: CN109040297B

Abstract

The invention discloses a kind of user portrait generation method and devices, belong to network technique field.The described method includes: the video file to main broadcaster user is analyzed, obtain the finger print information of the main broadcaster user, the video file carries out the video data acquired when singing songs live streaming based on the main broadcaster user and audio data generates, and the finger print information is for describing the main broadcaster user；Description label of the spectators user according to the video file for main broadcaster user selection is obtained, and to the preference information of the main broadcaster user and the video file, the preference information includes liking and not liking；According to the description label and the preference information, the finger print information of the main broadcaster user is updated；According to updated finger print information, user's portrait of the main broadcaster user is generated.The information that the present invention is got is richer and comprehensive, so that the accuracy and reliability of the user's portrait generated is higher.

Description

User's portrait generation method and device

Technical field

The present invention relates to network technique field more particularly to a kind of user portrait generation method and devices.

Background technique

User's portrait is also known as user role, delineates having for target user, connection user's demand and design direction as a kind of Effect tool, user's portrait are widely used in each field, and user's portrait of main broadcaster user is obtained such as in network direct broadcasting.

Currently, for any main broadcaster user, generally by the essential attribute for obtaining the main broadcaster user, as gender, the age, Educational background etc. can also obtain some simple behavioural informations of the main broadcaster user, such as the live streaming duration of main broadcaster user.Further Ground generates user's portrait of the main broadcaster user according to the above-mentioned information got.

Above-mentioned technology generates user's portrait of main broadcaster user according only to the basic information of main broadcaster user, due to what is got Information is inadequate, and the accuracy and reliability for causing user to draw a portrait is poor.

Summary of the invention

The embodiment of the invention provides a kind of user portrait generation method and devices, can solve the relevant technologies user portrait Accuracy and reliability difference problem.The technical solution is as follows:

In a first aspect, providing a kind of user's portrait generation method, comprising:

The video file of main broadcaster user is analyzed, the finger print information of the main broadcaster user, the video file are obtained The video data acquired when singing songs live streaming is carried out based on the main broadcaster user and audio data generates, and the finger print information is used In the description main broadcaster user；

Description label of the spectators user according to the video file for main broadcaster user selection is obtained, and to the master The preference information of broadcasting user and the video file, the preference information include liking and not liking；

According to the description label and the preference information, the finger print information of the main broadcaster user is updated；

According to updated finger print information, user's portrait of the main broadcaster user is generated.

In a kind of possible implementation, the video file to main broadcaster user is analyzed, and is obtained the main broadcaster and is used The finger print information at family, comprising:

Phonetic analysis is carried out to the video file, the corresponding song information of the video file is analyzed, is obtained The audio-frequency fingerprint of the main broadcaster user, the song information include at least one of song title and song classification, the audio Fingerprint is used to describe the singing songs behavior of the main broadcaster user.

It is described that phonetic analysis is carried out to the video file in a kind of possible implementation, to the video file pair The song information answered is analyzed, and the audio-frequency fingerprint of the main broadcaster user is obtained, comprising:

Phonetic analysis is carried out to the video file, determines that the main broadcaster user and original singer sing the video file The similarity of corresponding song；

The corresponding song information of the video file is analyzed, the main broadcaster user is counted and sings each song and respectively The quantity of class song；

According to the similarity and the quantity, determine that the main broadcaster user is good at the song title and song classification of performance At least one of.

Phonetic analysis is carried out to the video file, the main broadcaster user is obtained and sings the corresponding song of the video file Performance score；

According to the performance score and the quantity, determine that the main broadcaster user is good at the song title and song class of performance At least one of not.

Personage's analysis and setting analysis are carried out to the video file, obtain the video finger print of the main broadcaster user, it is described Video finger print is used to describe the appearance and live video quality of the main broadcaster user.

It is described that personage's analysis and setting analysis are carried out to the video file in a kind of possible implementation, obtain institute State the video finger print of main broadcaster user, comprising:

Recognition of face, clothing and setting analysis are carried out to the video file, determine video pictures resolution ratio, the main broadcaster The gender and face value score of user.

It is described according to updated finger print information in a kind of possible implementation, generate the user of the main broadcaster user After portrait, the method also includes:

It is drawn a portrait according to the user of each main broadcaster user, is recommended between being broadcast live to spectators user.

It is described to be drawn a portrait according to the user of each main broadcaster user in a kind of possible implementation, spectators user is carried out straight Recommend between broadcasting, comprising:

When detecting any spectators' user login services device, according to the first historical behavior of the spectators user and described The user of each main broadcaster user draws a portrait, and recommends to the spectators user straight with the matched main broadcaster user of the first historical behavior Between broadcasting, first historical behavior includes the spectators user for the description label of main broadcasting user selection and to main broadcaster user's Preference information.

When detecting that any spectators user plays song, according to the second historical behavior of the spectators user and described each The user of a main broadcaster user draws a portrait, and recommends the live streaming with the matched main broadcaster user of the second historical behavior to the spectators user Between, second historical behavior, which includes the spectators user, plays out operation to song, likes operating and collect operation and go through History behavior.

Second aspect provides a kind of user's portrait generation method, comprising:

Show that main broadcaster's selection interface, main broadcaster's selection interface are selected for providing multiple main broadcaster users for spectators user；

When detecting the selection operation to any main broadcaster user, the video file of the main broadcaster user is shown；

When detecting the play operation to the video file, the video file is played；

During playing the video file or after playing, spectators user is obtained as main broadcaster user selection Preference information to the main broadcaster user and the video file of description label and the spectators user, the preference information Including liking and not liking；

The description label and the preference information are sent to server, the description label and the preference information are used User's portrait of the main broadcaster user is generated in the server.

In a kind of possible implementation, it is described obtain spectators user be the main broadcaster user selection description label and Preference information of the spectators user to the main broadcaster user and the video file, comprising:

Show preset multiple description labels and the first option and the second option, first option and second choosing The corresponding different preference information of item；

When detect the selection operation of label is described at least one in the multiple description label when, will described at least one A description label is as the description label that spectators user is that the main broadcaster user selects；

When detecting to the selection operation of any option in first option and second option, by the option Corresponding preference information is as the spectators user to the preference information of the main broadcaster user.

In a kind of possible implementation, the method also includes:

When showing the video file of the main broadcaster user, while showing that the main broadcaster user is good at the song title of performance At least one of with song classification.

The third aspect provides a kind of user's portrait generating means, comprising:

Module is obtained, is analyzed for the video file to main broadcaster user, obtains the finger print information of the main broadcaster user, The video file carries out the video data acquired when singing songs live streaming based on the main broadcaster user and audio data generates, institute Finger print information is stated for describing the main broadcaster user；

It is retouching for main broadcaster user selection that the acquisition module, which is also used to obtain spectators user according to the video file, Label is stated, and to the preference information of the main broadcaster user and the video file, the preference information includes liking and not liking Vigorously；

Update module, for updating the fingerprint letter of the main broadcaster user according to the description label and the preference information Breath；

Generation module, for generating user's portrait of the main broadcaster user according to updated finger print information.

In a kind of possible implementation, the acquisition module is used to carry out phonetic analysis to the video file, to institute It states the corresponding song information of video file to be analyzed, obtains the audio-frequency fingerprint of the main broadcaster user, the song information includes At least one of song title and song classification, the audio-frequency fingerprint are used to describe the singing songs behavior of the main broadcaster user.

In a kind of possible implementation, the acquisition module is used for:

In a kind of possible implementation, the acquisition module is used to carry out personage's analysis and setting to the video file Analysis, obtains the video finger print of the main broadcaster user, and the video finger print is used to describe the appearance and live streaming of the main broadcaster user Video quality.

In a kind of possible implementation, the acquisition module is used to carry out the video file recognition of face, clothing It is analyzed with setting, determines video pictures resolution ratio, the gender of the main broadcaster user and face value score.

In a kind of possible implementation, described device further include:

Recommending module is recommended between being broadcast live to spectators user for being drawn a portrait according to the user of each main broadcaster user.

In a kind of possible implementation, the recommending module, which is used to work as, detects any spectators' user login services device When, it is drawn a portrait according to the user of the first historical behavior of the spectators user and each main broadcaster user, to the spectators user Recommend the direct broadcasting room with the matched main broadcaster user of the first historical behavior, first historical behavior includes the spectators user For the description label of main broadcasting user selection and to the preference information of main broadcaster user.

In a kind of possible implementation, the recommending module is used for when detecting that any spectators user plays song, It is drawn a portrait according to the user of the second historical behavior of the spectators user and each main broadcaster user, is recommended to the spectators user With the direct broadcasting room of the matched main broadcaster user of the second historical behavior, second historical behavior includes that the spectators user sings in antiphonal style The historical behavior that song plays out operation, likes operating and collecting operation.

Fourth aspect provides a kind of user's portrait generating means, comprising:

Display module, for showing that main broadcaster's selection interface, main broadcaster's selection interface are supplied for providing multiple main broadcaster users Spectators user's selection；

The display module is also used to when detecting the selection operation to any main broadcaster user, shows that the main broadcaster uses The video file at family；

Playing module, for playing the video file when detecting the play operation to the video file；

Module is obtained, for during playing the video file or after playing, obtaining spectators user to be institute The description label and the spectators user for stating main broadcaster user's selection believe the hobby of the main broadcaster user and the video file Breath, the preference information include liking and not liking；

Sending module, for the description label and the preference information to be sent to server, the description label and The preference information generates user's portrait of the main broadcaster user for the server.

In a kind of possible implementation, the acquisition module is used for:

In a kind of possible implementation, the display module is also used in the video file for showing the main broadcaster user When, while showing that the main broadcaster user is good at least one of song title and song classification of performance.

5th aspect provides a kind of user's portrait generation system, and the system comprises first terminal, server and second Terminal,

The first terminal was used within the period that main broadcaster user carries out singing songs live streaming, was based on collected video Data and audio data generate the video file of the main broadcaster user, and the video file of the main broadcaster user is sent to service Device；

The server obtains the fingerprint letter of the main broadcaster user for analyzing the video file of main broadcaster user Breath；

The second terminal is used for when detecting the play operation to any video file of the main broadcaster user, is played The corresponding video file of the play operation obtains description label and the sight that spectators user is main broadcaster user selection The description label and the preference information are sent to the server to the preference information of the main broadcaster user by many users, The preference information includes liking and not liking；

The server is also used to update the fingerprint of the main broadcaster user according to the description label and the preference information Information generates user's portrait of the main broadcaster user according to updated finger print information.

6th aspect, provides a kind of server, including processor and memory；The memory is calculated for storing Machine program；The processor realizes any reality of first aspect for executing the computer program stored on the memory Method and step described in existing mode.

7th aspect, provides a kind of terminal, including processor and memory；The memory, for storing computer Program；The processor realizes any realization of second aspect for executing the computer program stored on the memory Method and step described in mode.

Eighth aspect provides a kind of computer readable storage medium, is stored in the computer readable storage medium Computer program realizes the step of method described in any implementation of either side when the computer program is executed by processor Suddenly.

Technical solution bring beneficial effect provided in an embodiment of the present invention includes at least:

It is analyzed by the video file to main broadcaster user, after getting the finger print information for describing main broadcaster user, The description label that spectators user is main broadcaster user selection is further obtained, and to the main broadcaster user and the video file Preference information after obtaining updated finger print information, generates user's portrait of main broadcaster user, since the information got is richer With it is comprehensive so that generate user portrait accuracy and reliability it is higher.

Detailed description of the invention

To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other Attached drawing.

Fig. 1 is a kind of schematic diagram of user's portrait generation system provided in an embodiment of the present invention；

Fig. 2 is a kind of flow chart of user's portrait generation method provided in an embodiment of the present invention；

Fig. 3 is a kind of flow chart of user's portrait generation method provided in an embodiment of the present invention；

Fig. 4 is a kind of flow chart of user's portrait generation method provided in an embodiment of the present invention；

Fig. 5 is a kind of schematic diagram of user interface provided in an embodiment of the present invention；

Fig. 6 is a kind of schematic diagram for recommending direct broadcasting room provided in an embodiment of the present invention；

Fig. 7 is a kind of schematic diagram for recommending direct broadcasting room provided in an embodiment of the present invention；

Fig. 8 is a kind of structural schematic diagram of user's portrait generating means provided in an embodiment of the present invention；

Fig. 9 is a kind of structural schematic diagram of user's portrait generating means provided in an embodiment of the present invention；

Figure 10 is a kind of structural schematic diagram of user's portrait generating means provided in an embodiment of the present invention；

Figure 11 is a kind of structural schematic diagram of terminal 1100 provided in an embodiment of the present invention；

Figure 12 is a kind of structural schematic diagram of server 1200 provided in an embodiment of the present invention.

Specific embodiment

To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention Formula is described in further detail.

Fig. 1 is a kind of schematic diagram of user's portrait generation system provided in an embodiment of the present invention.Referring to Fig. 1, which is drawn As generation system includes: first terminal 101, server 102 and second terminal 103.

First terminal 101 is the terminal that main broadcaster user is broadcast live.The time of singing songs live streaming is carried out in main broadcaster user In section, first terminal 101 can be based on collected video data and audio data, generate the video file of the main broadcaster user； After the main broadcaster user terminates live streaming, first terminal 101 can recorde the corresponding song information of the video file, by video text Part song information corresponding with the video file is sent to server 102.

Server 102 is used to analyze the video file of main broadcaster user song information corresponding with the video file, The finger print information of the main broadcaster user is obtained, the finger print information is for describing the main broadcaster user.

Second terminal 103 is used for when detecting the play operation to any video file of main broadcaster user, is played this and is broadcast Put the corresponding video file of operation；Second terminal 103 is also used to obtain during playing video file or after playing Spectators user is the preference information of the description label that the main broadcaster user selects and the spectators user to the main broadcaster user；Second eventually End 103 is also used to describe this label and the preference information is sent to server 102.

Wireless network can be passed through between first terminal 101 and server 102 and server 102 and second terminal 103 Or the mode of cable network is communicated.

Fig. 2 is a kind of flow chart of user's portrait generation method provided in an embodiment of the present invention.Referring to fig. 2, this method packet It includes:

201, the video file of main broadcaster user is analyzed, obtains the finger print information of the main broadcaster user, the video file The video data acquired when singing songs live streaming is carried out based on the main broadcaster user and audio data generates, and the finger print information is for retouching State the main broadcaster user.

202, description label of the spectators user according to the video file for main broadcaster user selection is obtained, and to the main broadcaster The preference information of user and the video file, the preference information include liking and not liking.

203, label and the preference information are described according to this, updates the finger print information of the main broadcaster user.

204, according to updated finger print information, user's portrait of the main broadcaster user is generated.

Method provided in an embodiment of the present invention is analyzed by the video file to main broadcaster user, is got for retouching After the finger print information for stating main broadcaster user, the description label and right that spectators user is main broadcaster user selection is further obtained The preference information of the main broadcaster user and the video file, after obtaining updated finger print information, the user for generating main broadcaster user is drawn Picture, since the information got is richer and comprehensive, so that the accuracy and reliability of the user's portrait generated is higher.

In a kind of possible implementation, which is analyzed, and obtains the main broadcaster user's Finger print information, comprising:

Phonetic analysis is carried out to the video file, the corresponding song information of the video file is analyzed, the master is obtained The audio-frequency fingerprint of broadcasting user, the song information include at least one of song title and song classification, and the audio-frequency fingerprint is for retouching State the singing songs behavior of the main broadcaster user.

In a kind of possible implementation, this carries out phonetic analysis, song corresponding to the video file to the video file Bent information is analyzed, and the audio-frequency fingerprint of the main broadcaster user is obtained, comprising:

Phonetic analysis is carried out to the video file, it is corresponding to determine that the main broadcaster user with original singer sings the video file The similarity of song；

The corresponding song information of the video file is analyzed, the main broadcaster user is counted and sings each song and all kinds of songs Bent quantity；

According to the similarity and the quantity, determine that the main broadcaster user is good in the song title and song classification of performance at least One.

Phonetic analysis is carried out to the video file, obtains the performance that the main broadcaster user sings the corresponding song of the video file Score；

According to the performance score and the quantity, determine that the main broadcaster user is good in the song title and song classification of performance extremely One item missing.

Personage's analysis and setting analysis are carried out to the video file, obtain the video finger print of the main broadcaster user, which refers to Line is used to describe the appearance and live video quality of the main broadcaster user.

In a kind of possible implementation, this carries out personage's analysis to the video file and setting is analyzed, and obtains the main broadcaster The video finger print of user, comprising:

Recognition of face, clothing and setting analysis are carried out to the video file, determine video pictures resolution ratio, the main broadcaster user Gender and face value score.

In a kind of possible implementation, this generates user's portrait of the main broadcaster user according to updated finger print information Later, this method further include:

In a kind of possible implementation, this according to each main broadcaster user user portrait, spectators user is broadcast live Between recommend, comprising:

It is each with this according to the first historical behavior of the spectators user when detecting any spectators' user login services device The user of main broadcaster user draws a portrait, and recommends the direct broadcasting room with the matched main broadcaster user of first historical behavior to the spectators user, should First historical behavior includes the description label and the preference information to main broadcaster user that the spectators user is the selection of main broadcasting user.

When detecting that any spectators user plays song, according to the second historical behavior of the spectators user and each master The user of broadcasting user draws a portrait, and recommends the direct broadcasting room with the matched main broadcaster user of second historical behavior to the spectators user, this Two historical behaviors include the historical behavior that the spectators user plays out operation to song, likes operating and collecting operation.

All the above alternatives can form alternative embodiment of the invention using any combination, herein no longer It repeats one by one.

Fig. 3 is a kind of flow chart of user's portrait generation method provided in an embodiment of the present invention.Referring to Fig. 3, this method packet It includes:

301, show that main broadcaster's selection interface, main broadcaster's selection interface are selected for providing multiple main broadcaster users for spectators user It selects.

302, when detecting the selection operation to any main broadcaster user, the video file of the main broadcaster user is shown.

303, when detecting the play operation to the video file, the video file is played.

304, during playing the video file or after playing, spectators user is obtained as main broadcaster user selection Description label and the spectators user to the preference information of the main broadcaster user and the video file, which includes liking With do not like.

305, this is described into label and the preference information is sent to server, this describes label and the preference information for being somebody's turn to do Server generates user's portrait of the main broadcaster user.

Method provided in an embodiment of the present invention obtains spectators user by the operation according to spectators user as main broadcaster use The description label of family selection, and to the preference information of the main broadcaster user and the video file, and the description label that will acquire It is sent to server with preference information, after allowing server to update finger print information according to these information, main broadcaster is generated and uses The user at family draws a portrait, since the information got is richer and comprehensive, so that the accuracy and reliability of the user's portrait generated It is higher.

In a kind of possible implementation, acquisition spectators user is description label and sight of main broadcaster user selection Preference information of many users to the main broadcaster user and the video file, comprising:

Show preset multiple description labels and the first option and the second option, first option and second option pair Answer different preference informations；

When detecting that at least one is retouched by this when describing the selection operation of label at least one in multiple description label State description label of the label as spectators user for main broadcaster user selection；

It is when detecting to the selection operation of any option in first option and second option, the option is corresponding Preference information is as the spectators user to the preference information of the main broadcaster user.

In a kind of possible implementation, this method further include:

When showing the video file of the main broadcaster user, while showing that the main broadcaster user is good at the song title and song of performance At least one of bent classification.

Fig. 4 is a kind of flow chart of user's portrait generation method provided in an embodiment of the present invention.Referring to fig. 4, this method packet It includes:

401, within the period that main broadcaster user carries out singing songs live streaming, first terminal is based on collected video data And audio data, generate the video file of the main broadcaster user.

In the embodiment of the present invention, specified application can be installed on first terminal, which can be live streaming tool, It is broadcast live for main broadcaster user.For example, the specified application can be a kind of accompaniment application, for playing the accompaniment of song.It is main For broadcasting user if it is intended to singing certain song during live streaming, then can select on the live streaming interface that first terminal is shown should Then song plays out operation to the song, when detecting the play operation, first terminal can play the companion of the song It plays.When first terminal starts to play the accompaniment of the song, main broadcaster user can start to sing the song, when first terminal stops When playing the accompaniment of the song, main broadcaster user can terminate to sing the song.

When main broadcaster user plays the accompaniment of song by operation triggering first terminal, and starts to sing the song, first Terminal can start to acquire the video data and audio data when main broadcaster's user live broadcast, when first terminal stops playing song Accompaniment, when main broadcaster user terminates to sing the song, first terminal can stop acquiring video data and audio data.First terminal Video file can be generated, and the video file is made based on collected video data and audio data in the live streaming period For the video file of the main broadcaster user.

402, after the main broadcaster user terminates singing songs live streaming, first terminal records the corresponding song letter of the video file Breath, which includes at least one of song title and song classification.

In the embodiment of the present invention, after main broadcaster user has sung the song, first terminal can recorde main broadcaster user's performance The song information of the song, including but not limited at least one of song title and song classification, certainly, in addition to song information with Outside, first terminal can also record other data that main broadcaster user sings the song, such as whether even wheat chorus etc..

It should be noted that the step 402 is optional step, the song information to be given song recitals by recording main broadcaster user, Help to analyze the song that main broadcaster user is good at performance.

403, video file song information corresponding with the video file is sent to server by first terminal.

The embodiment of the present invention is to generate video file with first terminal, and video file is sent to for server and is said It is bright, it is to be understood that collected video data and audio data only can also be sent to server by first terminal, by taking Device be engaged in based on the video data and audio data, generates video file.

It should be noted that the step 403 is to be believed video file song corresponding with the video file with first terminal Breath is illustrated for being sent to server, in fact, first terminal can also the case where being optional step for step 402 Video file is only sent to server, without sending the corresponding song information of the video file to server.

404, server analyzes the video file of main broadcaster user, obtains the finger print information of the main broadcaster user, the view Frequency file carries out the video data acquired when singing songs live streaming based on the main broadcaster user and audio data generates, the finger print information For describing the main broadcaster user.

In a kind of possible implementation, which includes audio-frequency fingerprint, the video file to main broadcaster user into Row analysis, the finger print information for obtaining the main broadcaster user includes: to carry out phonetic analysis to the video file, corresponding to the video file Song information analyzed, obtain the audio-frequency fingerprint of the main broadcaster user, which is used to describe the song of the main broadcaster user Bent performance behavior.

Wherein, the corresponding song information of the video file can be sent to server by first terminal, can also be by servicing Device obtains the corresponding song information of the video file by carrying out song recognition to video file.

In a kind of possible implementation, the audio-frequency fingerprint for obtaining the main broadcaster user includes but is not limited to following two side Formula:

First way carries out phonetic analysis to the video file, determines that the main broadcaster user and original singer sing the view The similarity of the corresponding song of frequency file；The corresponding song information of the video file is analyzed, the main broadcaster user is counted and drills Sing the quantity of each song and all kinds of songs；According to the similarity and the quantity, determine that the main broadcaster user is good at the song of performance At least one of title and song classification.

If the video file of main broadcaster user has multiple, for each video file, it is with the corresponding song of video file 1 For song A, server can carry out phonetic analysis to the video file 1, obtain the original singer of main broadcaster user Yu song A Similarity.In addition, server can analyze the corresponding song information of multiple video file, main broadcaster user is counted Sing the quantity of every song and every class song, wherein the quantity that main broadcaster user sings every class song broadcasting user can be drilled based on Sing the sum of the quantity for belonging to such all songs.Then, server can be sung in conjunction with main broadcaster user and the original singer of every song The similarity of hand show that main broadcaster user is good at the song of performance, to obtain the song title for being good at performance and song classification.Example Such as, when the quantity that main broadcaster user sings certain song reaches amount threshold, and main broadcaster user and the original singer's of the song is flat When equal similarity reaches similarity threshold, server can be good at the song of performance using the song as main broadcaster user, by the song Bent name is referred to as the song title that main broadcaster user is good at performance, wherein similar when average similarity can be multiple performance The average value of degree.Similarly, when the quantity that main broadcaster user sings certain class song reaches amount threshold, and main broadcaster user and such song In the average similarity of original singer of every song when reaching similarity threshold, server can make the classification of such song The song classification of performance is good at for main broadcasting user.

The second way carries out phonetic analysis to the video file, obtains the main broadcaster user and sings video file correspondence Song performance score；The corresponding song information of the video file is analyzed, the main broadcaster user is counted and sings each first song The quantity of bent and all kinds of songs；According to the performance score and the quantity, determine the main broadcaster user be good at performance song title and At least one of song classification.

Under which, for each video file of main broadcaster user, by carrying out phonetic analysis, service to the video file Device can obtain main broadcaster user and sing the performance score that the video file corresponds to song, in this way, service using default marking rule The available performance score that every song is sung to main broadcaster user of device.Further, server can be drilled in conjunction with main broadcaster user The quantity for singing every song and every class song show that main broadcaster user is good at the song and categorizing songs of performance.

For example, when the quantity that main broadcaster user sings certain song reaches amount threshold, and main broadcaster user sings the song When averagely performance score reaches score threshold, the name of the song can be referred to as the song that main broadcaster user is good at performance by server Title, wherein the average value of performance score when averagely performance score can be multiple performance.Similarly, when main broadcaster user sings The quantity of certain class song reaches amount threshold, and main broadcaster user sings the average performance score of every song in such song and reaches When score threshold, server can be good at the song classification of performance using the classification of such song as main broadcaster user.

Server, can be based on after acquisition main broadcaster user is good at least one of song title and song classification of performance Broadcasting user initializes audio-frequency fingerprint, that is to say, main broadcaster user is good at least one of song title and the song classification of performance The audio-frequency fingerprint initial as main broadcaster user.

In a kind of possible implementation, which includes video finger print, the video file to main broadcaster user into Row analysis, the finger print information for obtaining the main broadcaster user include: to carry out personage's analysis and setting analysis to the video file, and obtaining should The video finger print of main broadcaster user, the video finger print are used to describe the appearance and live video quality of the main broadcaster user.

In a kind of possible implementation, the acquisition process of the video finger print may include: to carry out people to the video file Face identification, clothing and setting analysis, determine video pictures resolution ratio, the gender of the main broadcaster user and face value score.

Wherein, face value score is a kind of marking attribute, and server can obtain master using the marking rule of the marking attribute The face value score of broadcasting user.Server is after obtaining video pictures resolution ratio, the gender of main broadcaster user and face value score, Ke Yiwei Main broadcaster user initializes video finger print, that is to say, using the video pictures resolution ratio, gender and face value score as at the beginning of main broadcaster user The video finger print of beginning.

It should be noted that the step 404 can only include the process of above-mentioned acquisition audio-frequency fingerprint, it can also only include upper The process for obtaining video finger print is stated, can also simultaneously include two processes of above-mentioned acquisition audio-frequency fingerprint and video finger print.

The step 404 is that server is the process that main broadcasting user initializes audio-frequency fingerprint and video finger print, further, clothes Business device can also supplement the initial audio-frequency fingerprint and video finger print, and detailed process is referring to subsequent step 405 to step 409。

405, second terminal shows main broadcaster's selection interface, when detecting the selection operation to any main broadcaster user, display The video file of the main broadcaster user, main broadcaster's selection interface are selected for providing multiple main broadcaster users for spectators user.

In the embodiment of the present invention, second terminal can provide main broadcaster's selection interface, and spectators user can be to the main broadcaster Any main broadcaster user in selection interface carries out selection operation, and triggering second terminal shows the video file of the main broadcaster user, with And the main broadcaster user is good at the song title and categorizing songs of performance.

It should be noted that second terminal can show all video files of the main broadcaster user, the master can also be shown The video file of the specified quantity of broadcasting user can also only show video file of the main broadcaster user at the appointed time in section, example Such as, the video file that main broadcaster user's the last time is broadcast live is shown.

Optionally, second terminal can also show the main broadcaster user when showing the video file of the main broadcaster user simultaneously It is good at least one of song title and the song classification of performance.By showing that main broadcaster user is good at the song title and song of performance At least one of bent classification allows spectators user to learn that the live content of the video file is biased to, determines whether to see See the video file.

406, when detecting the play operation to the video file, second terminal plays the video file.

In the embodiment of the present invention, spectators user if it is intended to viewing main broadcaster user any video file, then can be to this Video file plays out operation, such as clicks the video file, and triggering second terminal plays the video file.

407, during playing the video file or after playing, it is the main broadcaster that second terminal, which obtains spectators user, Preference information of the description label and the spectators user of user's selection to the main broadcaster user and the video file, the preference information Including liking and not liking.

In a kind of possible implementation, which may include following step a to step c:

Step a, second terminal shows preset multiple description labels and the first option and the second option, first option Different preference informations is corresponded to second option；

Wherein, multiple description label may include the label that the appearance of main broadcaster user is described, such as oval face, go back It may include the label that the sound of main broadcaster user is described, if sound is sweet, the embodiment of the present invention multiple is retouched to preset Label is stated to be not specifically limited.First option, which can be, likes option, and the second option, which can be, does not like option, likes pick list Show the video file for liking the main broadcaster user He the main broadcaster user, does not like option expression and do not like the main broadcaster user and the main broadcaster The video file of user.

It is a kind of schematic diagram of user interface provided in an embodiment of the present invention referring to Fig. 5, Fig. 5, as shown in figure 5, the user Interface can be face value identification interface, can show that Loli, oval face, sound be sweet in the interface and Quadratic Finite Element wind etc. is more A preset description label, and two options of " pronged shape " and " love shape ".

Second terminal can show preset multiple description labels and first choosing while playing video file Item and the second option can also show multiple description labels and first option and second after video file plays Option.Correspondingly, spectators user both can during second terminal playing video file, from multiple description labels based on Broadcasting user selection description label, an option is selected from the first option and the second option, can also be played in the video file After, carry out above-mentioned label option operations and option selection operation.

Step b, when detect the selection operation of label is described at least one in multiple description label when, second terminal Using this, at least one describes description label of the label as spectators user for main broadcaster user selection.

It, can be from if spectators user thinks that wherein one or more describe label and can be used for describing the spectators user Middle selection one or more describes label, so that second terminal gets the description mark that spectators user is the selection of main broadcasting user Label.

Step c, when detecting to the selection operation of any option in first option and second option, second eventually End is using the corresponding preference information of the option as the spectators user to the preference information of the main broadcaster user.

If detect the selection operation to the first option, second terminal can consider that spectators user likes main broadcaster use The video file at family and the main broadcaster user, that is to say, spectators user is to like to the preference information of the main broadcaster user.If detection When to selection operation to the second option, second terminal can consider that spectators user does not like the main broadcaster user and the main broadcaster user Video file, that is to say, spectators user is not like to the preference information of the main broadcaster user.

408, this is described label by second terminal and the preference information is sent to server.

In the embodiment of the present invention, spectators user can be the description label and right of main broadcasting user selection by second terminal The preference information of the main broadcaster user and the video file is sent to server.

409, when the description label for getting spectators user according to the video file and be main broadcaster user selection, and to this After the preference information of main broadcaster user and the video file, server describes label and the preference information according to this, updates the main broadcaster The finger print information of user.

In the embodiment of the present invention, server can by mass viewer audiences user be the main broadcaster user selection description label and To the preference information of the main broadcaster user, the finger print information of main broadcaster user is updated, that is to say, this is described into label and preference information adds It is added in initial finger print information, obtains the more complete finger print information of main broadcaster user.

First passing through step 404 is that main broadcasting user initializes finger print information, then is referred to by the step 409 for main broadcasting user supplement Line information, so that the finger print information of main broadcaster user is more comprehensively and abundant.

410, server generates user's portrait of the main broadcaster user according to updated finger print information.

In the embodiment of the present invention, updated finger print information includes the song title and song class that main broadcaster user is good at performance At least one of not, video pictures resolution ratio, the gender of main broadcaster user and face value score when main broadcaster's user live broadcast further include seeing Many users are the description label of main broadcaster user selection, and to the preference information etc. of the main broadcaster user and the video file, this A little information may be incorporated for describing the main broadcaster user.In a kind of possible implementation, server generates the process of user's portrait It include: that user's portrait of the main broadcaster user using information fusion algorithm, is generated according to updated finger print information.

411, it is drawn a portrait according to the user of each main broadcaster user, the direct broadcasting room that server carries out main broadcaster user to spectators user pushes away It recommends.

In the embodiment of the present invention, server is directed to each main broadcaster user, can execute above-mentioned steps 401 to step 410, User's portrait of each main broadcaster user is got, and then user's portrait is applied in the direct broadcasting room recommendation of main broadcaster user.One In the possible implementation of kind, which includes but is not limited to following two mode:

First way is gone through when detecting that any spectators user logs in the server according to the first of the spectators user The user of history behavior and each main broadcaster user draw a portrait, and recommend to use with the matched main broadcaster of first historical behavior to the spectators user The direct broadcasting room at family, first historical behavior include the spectators user for the description label of main broadcasting user selection and to main broadcaster user Preference information.

User's portrait of main broadcaster user can reflect the description label that spectators user is the selection of main broadcasting user and to main broadcaster The preference information of user, if user's portrait of some main broadcaster user and the first historical behavior include identical description label and happiness Good information, then server can consider that the main broadcaster user matches with the first historical behavior of the spectators user, and then to the spectators User recommends the direct broadcasting room of the main broadcaster user.By taking main broadcaster user A and spectators user B as an example, each spectators user is main broadcasting user A The description label selected includes label 1 and label 2, and selects the spectators user of the label 1 and label 2 to the main broadcaster user A Preference information be to like, spectators user B is that the label that selected of each main broadcaster user includes label 1, and spectators user B is to this The preference information of the corresponding main broadcaster user of label 1 is to like, then server can be to the straight of spectators user B recommendation main broadcaster user A Between broadcasting.

The application scenarios of which are the servers that platform is broadcast live by logging in spectators, into the homepage of live streaming platform When, which can show some recommendation direct broadcasting rooms.It is a kind of recommendation direct broadcasting room provided in an embodiment of the present invention referring to Fig. 6, Fig. 6 Schematic diagram, as shown in fig. 6, homepage can show main broadcaster user A, main broadcaster user B to multiple direct broadcasting rooms such as main broadcaster user F, this A little that direct broadcasting room is recommended to show user in the form of " guessing that you like " prefecture, these direct broadcasting rooms are servers according to spectators user For main broadcasting user selection description label and behavior is liked to main broadcaster user, for spectators user recommendation be consistent with its habit User draw a portrait belonging to main broadcaster user direct broadcasting room.

The second way, when detecting that any spectators user plays song, according to the second history row of the spectators user To draw a portrait with the user of each main broadcaster user, recommend to the spectators user with the matched main broadcaster user's of second historical behavior Direct broadcasting room, which, which includes the spectators user, plays out operation to song, likes operating and collect operation and go through History behavior.

User's portrait of main broadcaster user can reflect the song that main broadcaster user is good at performance, if the use of some main broadcaster user Family portrait and the second historical behavior include identical song, it may be considered that the second history of the main broadcaster user and the spectators user Behavior matching.By taking main broadcaster user A and spectators user B as an example, the song that main broadcaster user A is good at performance includes song 1 and song 2, Spectators user B carried out play operation to song 1, likes operating or collecting operating, then server can be recommended to spectators user B The direct broadcasting room of main broadcaster user A.

The application scenarios of which are spectators users when playing song in music application, and server can be used according to spectators Song and song that family was listened in the music application, liking and collected are single, recommend to be consistent with it for spectators user User draw a portrait belonging to main broadcaster user direct broadcasting room.It is a kind of recommendation direct broadcasting room provided in an embodiment of the present invention referring to Fig. 7, Fig. 7 Schematic diagram can show some master recommended to spectators user as shown in fig. 7, in the upper right side region at playback of songs interface The direct broadcasting room of broadcasting user.

It should be noted that the step 411 is optional step, by being drawn a portrait according to the user of main broadcaster user, used to spectators Its possible interested direct broadcasting room is recommended at family, and the accuracy of information recommendation can be improved.

Fig. 8 is a kind of structural schematic diagram of user's portrait generating means provided in an embodiment of the present invention.Referring to Fig. 8, the dress It sets and includes:

Module 801 is obtained, is analyzed for the video file to main broadcaster user, the fingerprint letter of the main broadcaster user is obtained Breath, which carries out the video data acquired when singing songs live streaming based on the main broadcaster user and audio data generates, should Finger print information is for describing the main broadcaster user；

The acquisition module 801 is also used to obtain description mark of the spectators user according to the video file for main broadcaster user selection Label, and to the preference information of the main broadcaster user and the video file, which includes liking and not liking；

Update module 802 updates the finger print information of the main broadcaster user for describing label and the preference information according to this；

Generation module 803, for generating user's portrait of the main broadcaster user according to updated finger print information.

In a kind of possible implementation, which is used for:

In a kind of possible implementation, which is used to carry out personage's analysis and setting to the video file Analysis, obtains the video finger print of the main broadcaster user, which is used to describe the appearance and live video matter of the main broadcaster user Amount.

In a kind of possible implementation, the acquisition module 801 be used for the video file carry out recognition of face, clothing and Setting analysis, determines video pictures resolution ratio, the gender of the main broadcaster user and face value score.

In a kind of possible implementation, referring to Fig. 9, the device further include:

Recommending module 804 is recommended between being broadcast live to spectators user for being drawn a portrait according to the user of each main broadcaster user.

In a kind of possible implementation, which, which is used to work as, detects any spectators' user login services device When, drawn a portrait according to the user of the first historical behavior of the spectators user and each main broadcaster user, to the spectators user recommend with The direct broadcasting room of the matched main broadcaster user of first historical behavior, first historical behavior include that the spectators user selects for main broadcasting user The description label selected and the preference information to main broadcaster user.

In a kind of possible implementation, which is used for when detecting that any spectators user plays song, Drawn a portrait according to the user of the second historical behavior of the spectators user and each main broadcaster user, to the spectators user recommend with this The direct broadcasting room of the matched main broadcaster user of two historical behaviors, second historical behavior include that the spectators user plays out behaviour to song Make, like operating and collecting the historical behavior operated.

It in the embodiment of the present invention, is analyzed by the video file to main broadcaster user, gets and used for describing main broadcaster After the finger print information at family, the description label that spectators user is main broadcaster user selection is further obtained, and use the main broadcaster The preference information at family and the video file after obtaining updated finger print information, generates user's portrait of main broadcaster user, due to obtaining The information got is richer and comprehensive, so that the accuracy and reliability of the user's portrait generated is higher.

Figure 10 is a kind of structural schematic diagram of user's portrait generating means provided in an embodiment of the present invention.Referring to Fig.1 0, it should Device includes:

Display module 1001, for showing main broadcaster's selection interface, main broadcaster's selection interface is for providing multiple main broadcaster users It is selected for spectators user；

The display module 1001 is also used to when detecting the selection operation to any main broadcaster user, shows that the main broadcaster uses The video file at family；

Playing module 1002, for playing the video file when detecting the play operation to the video file；

Module 1003 is obtained, is for during playing the video file or after playing, obtaining spectators user Preference information of the description label and the spectators user of main broadcaster user selection to the main broadcaster user and the video file, the happiness Good information includes liking and not liking；

Sending module 1004 is sent to server for this to be described label and the preference information, this describes label and should Preference information generates user's portrait of the main broadcaster user for the server.

In a kind of possible implementation, which is used for:

In a kind of possible implementation, which is also used in the video file for showing the main broadcaster user When, while showing that the main broadcaster user is good at least one of song title and song classification of performance.

In the embodiment of the present invention, by the operation according to spectators user, obtaining spectators user is main broadcaster user selection Label is described, and to the preference information of the main broadcaster user and the video file, and the description label that will acquire and hobby letter Breath is sent to server, after allowing server to update finger print information according to these information, generates the user of main broadcaster user Portrait, since the information got is richer and comprehensive, so that the accuracy and reliability of the user's portrait generated is higher.

It should be understood that user provided by the above embodiment draws a portrait, generating means are when user draws a portrait and generates, only more than The division progress of each functional module is stated for example, can according to need and in practical application by above-mentioned function distribution by difference Functional module complete, i.e., the internal structure of equipment is divided into different functional modules, with complete it is described above whole or Person's partial function.In addition, user provided by the above embodiment draws a portrait, generating means belong to user's portrait generation method embodiment Same design, specific implementation process are detailed in embodiment of the method, and which is not described herein again.

Figure 11 is a kind of structural schematic diagram of terminal 1100 provided in an embodiment of the present invention.The terminal 1100 may is that intelligence It can mobile phone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic shadow As expert's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic Image expert's compression standard audio level 4) player, laptop or desktop computer.Terminal 1100 is also possible to referred to as use Other titles such as family equipment, portable terminal, laptop terminal, terminal console.

In general, terminal 1100 includes: processor 1101 and memory 1102.

Processor 1101 may include one or more processing cores, such as 4 core processors, 8 core processors etc..Place Reason device 1101 can use DSP (Digital Signal Processing, Digital Signal Processing), FPGA (Field- Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array, may be programmed Logic array) at least one of example, in hardware realize.Processor 1101 also may include primary processor and coprocessor, master Processor is the processor for being handled data in the awake state, also referred to as CPU (Central Processing Unit, central processing unit)；Coprocessor is the low power processor for being handled data in the standby state.? In some embodiments, processor 1101 can be integrated with GPU (Graphics Processing Unit, image processor), GPU is used to be responsible for the rendering and drafting of content to be shown needed for display screen.In some embodiments, processor 1101 can also be wrapped AI (Artificial Intelligence, artificial intelligence) processor is included, the AI processor is for handling related machine learning Calculating operation.

Memory 1102 may include one or more computer readable storage mediums, which can To be non-transient.Memory 1102 may also include high-speed random access memory and nonvolatile memory, such as one Or multiple disk storage equipments, flash memory device.In some embodiments, the non-transient computer in memory 1102 can Storage medium is read for storing at least one instruction, at least one instruction performed by processor 1101 for realizing this Shen Please in embodiment of the method provide user draw a portrait generation method.

In some embodiments, terminal 1100 is also optional includes: peripheral device interface 1103 and at least one periphery are set It is standby.It can be connected by bus or signal wire between processor 1101, memory 1102 and peripheral device interface 1103.It is each outer Peripheral equipment can be connected by bus, signal wire or circuit board with peripheral device interface 1103.Specifically, peripheral equipment includes: In radio circuit 1104, display screen 1105, camera 1106, voicefrequency circuit 1107, positioning component 1108 and power supply 1109 extremely Few one kind.

Peripheral device interface 1103 can be used for I/O (Input/Output, input/output) is relevant outside at least one Peripheral equipment is connected to processor 1101 and memory 1102.In some embodiments, processor 1101, memory 1102 and periphery Equipment interface 1103 is integrated on same chip or circuit board；In some other embodiments, processor 1101, memory 1102 and peripheral device interface 1103 in any one or two can be realized on individual chip or circuit board, this implementation Example is not limited this.

Radio circuit 1104 is for receiving and emitting RF (Radio Frequency, radio frequency) signal, also referred to as electromagnetic signal. Radio circuit 1104 is communicated by electromagnetic signal with communication network and other communication equipments.Radio circuit 1104 is by telecommunications Number being converted to electromagnetic signal is sent, alternatively, the electromagnetic signal received is converted to electric signal.Optionally, radio circuit 1104 include: antenna system, RF transceiver, one or more amplifiers, tuner, oscillator, digital signal processor, volume solution Code chipset, user identity module card etc..Radio circuit 1104 can by least one wireless communication protocol come with it is other Terminal is communicated.The wireless communication protocol includes but is not limited to: Metropolitan Area Network (MAN), each third generation mobile communication network (2G, 3G, 4G and 5G), WLAN and/or WiFi (Wireless Fidelity, Wireless Fidelity) network.In some embodiments, radio frequency electrical Road 1104 can also include NFC (Near Field Communication, wireless near field communication) related circuit, the application This is not limited.

Display screen 1105 is for showing UI (UserInterface, user interface).The UI may include figure, text, figure Mark, video and its their any combination.When display screen 1105 is touch display screen, display screen 1105 also has acquisition aobvious The ability of the touch signal on the surface or surface of display screen 1105.The touch signal can be used as control signal and be input to processing Device 1101 is handled.At this point, display screen 1105 can be also used for providing virtual push button and/or dummy keyboard, also referred to as soft button And/or soft keyboard.In some embodiments, display screen 1105 can be one, and the front panel of terminal 1100 is arranged；At other In embodiment, display screen 1105 can be at least two, be separately positioned on the different surfaces of terminal 1100 or in foldover design；? In still other embodiments, display screen 1105 can be flexible display screen, be arranged on the curved surface of terminal 1100 or fold plane On.Even, display screen 1105 can also be arranged to non-rectangle irregular figure, namely abnormity screen.Display screen 1105 can be adopted With LCD (Liquid Crystal Display, liquid crystal display), (Organic Light-Emitting Diode, has OLED Machine light emitting diode) etc. materials preparation.

CCD camera assembly 1106 is for acquiring image or video.Optionally, CCD camera assembly 1106 includes front camera And rear camera.In general, the front panel of terminal is arranged in front camera, the back side of terminal is arranged in rear camera.? In some embodiments, rear camera at least two is that main camera, depth of field camera, wide-angle camera, focal length are taken the photograph respectively As any one in head, to realize that main camera and the fusion of depth of field camera realize background blurring function, main camera and wide Pan-shot and VR (Virtual Reality, virtual reality) shooting function or other fusions are realized in camera fusion in angle Shooting function.In some embodiments, CCD camera assembly 1106 can also include flash lamp.Flash lamp can be monochromatic temperature flash of light Lamp is also possible to double-colored temperature flash lamp.Double-colored temperature flash lamp refers to the combination of warm light flash lamp and cold light flash lamp, can be used for Light compensation under different-colour.

Voicefrequency circuit 1107 may include microphone and loudspeaker.Microphone is used to acquire the sound wave of user and environment, and It converts sound waves into electric signal and is input to processor 1101 and handled, or be input to radio circuit 1104 to realize that voice is logical Letter.For stereo acquisition or the purpose of noise reduction, microphone can be separately positioned on the different parts of terminal 1100 to be multiple. Microphone can also be array microphone or omnidirectional's acquisition type microphone.Loudspeaker is then used to that processor 1101 or radio frequency will to be come from The electric signal of circuit 1104 is converted to sound wave.Loudspeaker can be traditional wafer speaker, be also possible to piezoelectric ceramics loudspeaking Device.When loudspeaker is piezoelectric ceramic loudspeaker, the audible sound wave of the mankind can be not only converted electrical signals to, can also be incited somebody to action Electric signal is converted to the sound wave that the mankind do not hear to carry out the purposes such as ranging.In some embodiments, voicefrequency circuit 1107 may be used also To include earphone jack.

Positioning component 1108 is used for the current geographic position of positioning terminal 1100, to realize navigation or LBS (Location Based Service, location based service).Positioning component 1108 can be the GPS (Global based on the U.S. Positioning System, global positioning system), the dipper system of China, Russia Gray receive this system or European Union The positioning component of Galileo system.

Power supply 1109 is used to be powered for the various components in terminal 1100.Power supply 1109 can be alternating current, direct current Electricity, disposable battery or rechargeable battery.When power supply 1109 includes rechargeable battery, which can support wired Charging or wireless charging.The rechargeable battery can be also used for supporting fast charge technology.

In some embodiments, terminal 1100 further includes having one or more sensors 1110.One or more sensing Device 1110 includes but is not limited to: acceleration transducer 1111, gyro sensor 1112, pressure sensor 1113, fingerprint sensing Device 1114, optical sensor 1115 and proximity sensor 1116.

Acceleration transducer 1111 can detecte the acceleration in three reference axis of the coordinate system established with terminal 1100 Size.For example, acceleration transducer 1111 can be used for detecting component of the acceleration of gravity in three reference axis.Processor The 1101 acceleration of gravity signals that can be acquired according to acceleration transducer 1111, control touch display screen 1105 with transverse views Or longitudinal view carries out the display of user interface.Acceleration transducer 1111 can be also used for game or the exercise data of user Acquisition.

Gyro sensor 1112 can detecte body direction and the rotational angle of terminal 1100, gyro sensor 1112 Acquisition user can be cooperateed with to act the 3D of terminal 1100 with acceleration transducer 1111.Processor 1101 is according to gyro sensors The data that device 1112 acquires, following function may be implemented: action induction (for example changing UI according to the tilt operation of user) is clapped Image stabilization, game control and inertial navigation when taking the photograph.

The lower layer of side frame and/or touch display screen 1105 in terminal 1100 can be set in pressure sensor 1113.When When the side frame of terminal 1100 is arranged in pressure sensor 1113, user can detecte to the gripping signal of terminal 1100, by Reason device 1101 carries out right-hand man's identification or prompt operation according to the gripping signal that pressure sensor 1113 acquires.Work as pressure sensor 1113 when being arranged in the lower layer of touch display screen 1105, is grasped by processor 1101 according to pressure of the user to touch display screen 1105 Make, realization controls the operability control on the interface UI.Operability control include button control, scroll bar control, At least one of icon control, menu control.

Fingerprint sensor 1114 is used to acquire the fingerprint of user, is collected by processor 1101 according to fingerprint sensor 1114 Fingerprint recognition user identity, alternatively, by fingerprint sensor 1114 according to the identity of collected fingerprint recognition user.Knowing Not Chu the identity of user when being trusted identity, authorize the user to execute relevant sensitive operation by processor 1101, which grasps Make to include solving lock screen, checking encryption information, downloading software, payment and change setting etc..Fingerprint sensor 1114 can be set Set the front, the back side or side of terminal 1100.When being provided with physical button or manufacturer Logo in terminal 1100, fingerprint sensor 1114 can integrate with physical button or manufacturer Logo.

Optical sensor 1115 is for acquiring ambient light intensity.In one embodiment, processor 1101 can be according to light The ambient light intensity that sensor 1115 acquires is learned, the display brightness of touch display screen 1105 is controlled.Specifically, work as ambient light intensity When higher, the display brightness of touch display screen 1105 is turned up；When ambient light intensity is lower, the aobvious of touch display screen 1105 is turned down Show brightness.In another embodiment, the ambient light intensity that processor 1101 can also be acquired according to optical sensor 1115, is moved The acquisition parameters of state adjustment CCD camera assembly 1106.

Proximity sensor 1116, also referred to as range sensor are generally arranged at the front panel of terminal 1100.Proximity sensor 1116 for acquiring the distance between the front of user Yu terminal 1100.In one embodiment, when proximity sensor 1116 is examined When measuring the distance between the front of user and terminal 1100 and gradually becoming smaller, by processor 1101 control touch display screen 1105 from Bright screen state is switched to breath screen state；When proximity sensor 1116 detect the distance between front of user and terminal 1100 by When gradual change is big, touch display screen 1105 is controlled by processor 1101 and is switched to bright screen state from breath screen state.

It, can be with it will be understood by those skilled in the art that the restriction of the not structure paired terminal 1100 of structure shown in Figure 11 Including than illustrating more or fewer components, perhaps combining certain components or being arranged using different components.

Figure 12 is a kind of structural schematic diagram of server 1200 provided in an embodiment of the present invention, which can be because matching It sets or performance is different and generate bigger difference, may include one or more processors (central Processing units, CPU) 1201 and one or more memory 1202, wherein it is stored in the memory 1202 There is at least one instruction, which is loaded by the processor 1201 and executed to realize above-mentioned each embodiment of the method The method of offer.Certainly, which can also have the portions such as wired or wireless network interface, keyboard and input/output interface Part, to carry out input and output, which can also include other for realizing the component of functions of the equipments, not do herein superfluous It states.

In the exemplary embodiment, a kind of computer readable storage medium for being stored with computer program, example are additionally provided It is such as stored with the memory of computer program, above-mentioned computer program realizes the user in above-described embodiment when being executed by processor Portrait generation method.For example, the computer readable storage medium can be read-only memory (Read-Only Memory, ROM), with Machine accesses memory (Random Access Memory, RAM), CD-ROM (Compact Disc Read-Only Memory, CD-ROM), tape, floppy disk and optical data storage devices etc..

Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware It completes, relevant hardware can also be instructed to complete by program, the program being somebody's turn to do can store computer-readable deposits in a kind of In storage media, storage medium mentioned above can be read-only memory, disk or CD etc..

It should be only above presently preferred embodiments of the present invention, be not intended to limit the invention, it is all in spirit and original of the invention Within then, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.

Claims

The generation method 1. a kind of user draws a portrait, which is characterized in that the described method includes:

The video file of main broadcaster user is analyzed, the finger print information of the main broadcaster user is obtained, the video file is based on The main broadcaster user carries out the video data acquired when singing songs live streaming and audio data generates, and the finger print information is for retouching State the main broadcaster user；

Description label of the spectators user according to the video file for main broadcaster user selection is obtained, and the main broadcaster is used The preference information at family and the video file, the preference information include liking and not liking；

According to the description label and the preference information, the finger print information of the main broadcaster user is updated；

According to updated finger print information, user's portrait of the main broadcaster user is generated.
2. being obtained the method according to claim 1, wherein the video file to main broadcaster user is analyzed Take the finger print information of the main broadcaster user, comprising:

Phonetic analysis is carried out to the video file, the corresponding song information of the video file is analyzed, described in acquisition The audio-frequency fingerprint of main broadcaster user, the song information include at least one of song title and song classification, the audio-frequency fingerprint For describing the singing songs behavior of the main broadcaster user.
3. according to the method described in claim 2, it is characterized in that, described carry out phonetic analysis to the video file, to institute It states the corresponding song information of video file to be analyzed, obtains the audio-frequency fingerprint of the main broadcaster user, comprising:

Phonetic analysis is carried out to the video file, determines that the main broadcaster user is corresponding with original singer's performance video file Song similarity；

The corresponding song information of the video file is analyzed, the main broadcaster user is counted and sings each song and all kinds of songs Bent quantity；

According to the similarity and the quantity, determine that the main broadcaster user is good in the song title and song classification of performance extremely One item missing.
4. according to the method described in claim 2, it is characterized in that, described carry out phonetic analysis to the video file, to institute It states the corresponding song information of video file to be analyzed, obtains the audio-frequency fingerprint of the main broadcaster user, comprising:

Phonetic analysis is carried out to the video file, the main broadcaster user is obtained and sings drilling for the corresponding song of the video file Sing score；

The corresponding song information of the video file is analyzed, the main broadcaster user is counted and sings each song and all kinds of songs Bent quantity；

According to the performance score and the quantity, determine that the main broadcaster user is good in the song title and song classification of performance At least one of.
5. method according to claim 1 or 2, which is characterized in that the video file to main broadcaster user is analyzed, Obtain the finger print information of the main broadcaster user, comprising:

Personage's analysis and setting analysis are carried out to the video file, obtain the video finger print of the main broadcaster user, the video Fingerprint is used to describe the appearance and live video quality of the main broadcaster user.
6. according to the method described in claim 5, it is characterized in that, described carry out personage's analysis and setting to the video file Analysis, obtains the video finger print of the main broadcaster user, comprising:

Recognition of face, clothing and setting analysis are carried out to the video file, determine video pictures resolution ratio, the main broadcaster user Gender and face value score.
7. generating the master the method according to claim 1, wherein described according to updated finger print information After user's portrait of broadcasting user, the method also includes:

It is drawn a portrait according to the user of each main broadcaster user, is recommended between being broadcast live to spectators user.
8. the method according to the description of claim 7 is characterized in that described draw a portrait according to the user of each main broadcaster user, to sight Many users recommend between being broadcast live, comprising:

When detecting any spectators' user login services device, according to the first historical behavior of the spectators user and described each The user of main broadcaster user draws a portrait, and recommends the live streaming with the matched main broadcaster user of the first historical behavior to the spectators user Between, first historical behavior includes the description label and the happiness to main broadcaster user that the spectators user is the selection of main broadcasting user Good information.
9. the method according to the description of claim 7 is characterized in that described draw a portrait according to the user of each main broadcaster user, to sight Many users recommend between being broadcast live, comprising:

When detecting that any spectators user plays song, according to the second historical behavior of the spectators user and each master The user of broadcasting user draws a portrait, and recommends the direct broadcasting room with the matched main broadcaster user of the second historical behavior to the spectators user, Second historical behavior includes the history row that the spectators user plays out operation to song, likes operating and collecting operation For.
The generation method 10. a kind of user draws a portrait, which is characterized in that the described method includes:

Show that main broadcaster's selection interface, main broadcaster's selection interface are selected for providing multiple main broadcaster users for spectators user；

When detecting the selection operation to any main broadcaster user, the video file of the main broadcaster user is shown；

When detecting the play operation to the video file, the video file is played；

During playing the video file or after playing, obtaining spectators user is retouching for main broadcaster user selection Label and the spectators user are stated to the preference information of the main broadcaster user and the video file, the preference information includes Like and does not like；

The description label and the preference information are sent to server, the description label and the preference information are used for institute State user's portrait that server generates the main broadcaster user.
11. according to the method described in claim 10, it is characterized in that, the acquisition spectators user is main broadcaster user selection Description label and the spectators user to the preference information of the main broadcaster user and the video file, comprising:

Show preset multiple description labels and the first option and the second option, first option and second option pair Answer different preference informations；

When detect the selection operation of label is described at least one in the multiple description label when, by it is described at least one retouch State description label of the label as spectators user for main broadcaster user selection；

It is when detecting to the selection operation of any option in first option and second option, the option is corresponding Preference information as the spectators user to the preference information of the main broadcaster user.
12. according to the method described in claim 10, it is characterized in that, the method also includes:

When showing the video file of the main broadcaster user, while showing that the main broadcaster user is good at the song title and song of performance At least one of bent classification.
The generating means 13. a kind of user draws a portrait, which is characterized in that the described method includes:

Module is obtained, is analyzed for the video file to main broadcaster user, obtains the finger print information of the main broadcaster user, it is described Video file carries out the video data acquired when singing songs live streaming based on the main broadcaster user and audio data generates, the finger Line information is for describing the main broadcaster user；

The module that obtains is also used to obtain description mark of the spectators user according to the video file for main broadcaster user selection Label, and to the preference information of the main broadcaster user and the video file, the preference information includes liking and not liking；

Update module, for updating the finger print information of the main broadcaster user according to the description label and the preference information；

Generation module, for generating user's portrait of the main broadcaster user according to updated finger print information.
14. device according to claim 13, which is characterized in that the acquisition module is used for:

Phonetic analysis is carried out to the video file, the corresponding song information of the video file is analyzed, described in acquisition The audio-frequency fingerprint of main broadcaster user, the song information include at least one of song title and song classification, the audio-frequency fingerprint For describing the singing songs behavior of the main broadcaster user.
15. device according to claim 14, which is characterized in that the acquisition module is used for:

Phonetic analysis is carried out to the video file, determines that the main broadcaster user is corresponding with original singer's performance video file Song similarity；

The corresponding song information of the video file is analyzed, the main broadcaster user is counted and sings each song and all kinds of songs Bent quantity；

According to the similarity and the quantity, determine that the main broadcaster user is good in the song title and song classification of performance extremely One item missing.
16. device according to claim 14, which is characterized in that the acquisition module is used for:

Phonetic analysis is carried out to the video file, the main broadcaster user is obtained and sings drilling for the corresponding song of the video file Sing score；

The corresponding song information of the video file is analyzed, the main broadcaster user is counted and sings each song and all kinds of songs Bent quantity；

According to the performance score and the quantity, determine that the main broadcaster user is good in the song title and song classification of performance At least one of.
17. device described in 3 or 14 according to claim 1, which is characterized in that the acquisition module is used for:

Personage's analysis and setting analysis are carried out to the video file, obtain the video finger print of the main broadcaster user, the video Fingerprint is used to describe the appearance and live video quality of the main broadcaster user.
18. device according to claim 17, which is characterized in that the acquisition module is used to carry out the video file Recognition of face, clothing and setting analysis, determine video pictures resolution ratio, the gender of the main broadcaster user and face value score.
19. device according to claim 13, which is characterized in that described device further include:

Recommending module is recommended between being broadcast live to spectators user for being drawn a portrait according to the user of each main broadcaster user.
20. device according to claim 19, which is characterized in that the recommending module, which is used to work as, detects that any spectators use When the login service device of family, drawn a portrait according to the user of the first historical behavior of the spectators user and each main broadcaster user, to The spectators user recommends the direct broadcasting room with the matched main broadcaster user of the first historical behavior, and first historical behavior includes The description label and the preference information to main broadcaster user that the spectators user is the selection of main broadcasting user.
21. device according to claim 19, which is characterized in that the recommending module, which is used to work as, detects that any spectators use When family plays song, drawn a portrait according to the user of the second historical behavior of the spectators user and each main broadcaster user, to institute The direct broadcasting room of spectators user's recommendation and the matched main broadcaster user of the second historical behavior is stated, second historical behavior includes institute State the historical behavior that spectators user plays out operation to song, likes operating and collecting operation.
The generating means 22. a kind of user draws a portrait, which is characterized in that described device includes:

Display module, for showing main broadcaster's selection interface, main broadcaster's selection interface is for providing multiple main broadcaster users for spectators User's selection；

The display module is also used to show the main broadcaster user's when detecting the selection operation to any main broadcaster user Video file；

Playing module, for playing the video file when detecting the play operation to the video file；

Module is obtained, for during playing the video file or after playing, acquisition spectators user to be the master Preference information of the description label and the spectators user of broadcasting user selection to the main broadcaster user and the video file, institute Stating preference information includes liking and not liking；

Sending module, for the description label and the preference information to be sent to server, the description label and described Preference information generates user's portrait of the main broadcaster user for the server.
23. device according to claim 22, which is characterized in that the acquisition module is used for:

Show preset multiple description labels and the first option and the second option, first option and second option pair Answer different preference informations；

When detect the selection operation of label is described at least one in the multiple description label when, by it is described at least one retouch State description label of the label as spectators user for main broadcaster user selection；

It is when detecting to the selection operation of any option in first option and second option, the option is corresponding Preference information as the spectators user to the preference information of the main broadcaster user.
24. device according to claim 22, which is characterized in that the display module is also used to showing main broadcaster's use When the video file at family, while showing that the main broadcaster user is good at least one of song title and song classification of performance.
The generation system 25. a kind of user draws a portrait, which is characterized in that the system comprises first terminal, server and second terminal,

The first terminal was used within the period that main broadcaster user carries out singing songs live streaming, was based on collected video data And audio data, the video file of the main broadcaster user is generated, the video file of the main broadcaster user is sent to server；

The server obtains the finger print information of the main broadcaster user for analyzing the video file of main broadcaster user；

The second terminal is used for when detecting the play operation to any video file of the main broadcaster user, described in broadcasting The corresponding video file of play operation obtains description label and spectators use that spectators user is main broadcaster user selection The description label and the preference information are sent to the server to the preference information of the main broadcaster user by family, described Preference information includes liking and not liking；

The server is also used to update the fingerprint letter of the main broadcaster user according to the description label and the preference information Breath generates user's portrait of the main broadcaster user according to updated finger print information.
26. a kind of server, which is characterized in that including processor and memory；The memory, for storing computer journey Sequence；The processor realizes any one of claim 1-9 institute for executing the computer program stored on the memory The method and step stated.
27. a kind of terminal, which is characterized in that including processor and memory；The memory, for storing computer program； The processor is realized described in any one of claim 10-12 for executing the computer program stored on the memory Method and step.
28. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium Program realizes claim 1-12 described in any item method and steps when the computer program is executed by processor.