WO2019206090A1 - Media file remarking method, apparatus, mobile terminal and storage medium - Google Patents

Media file remarking method, apparatus, mobile terminal and storage medium Download PDF

Info

Publication number
WO2019206090A1
WO2019206090A1 PCT/CN2019/083714 CN2019083714W WO2019206090A1 WO 2019206090 A1 WO2019206090 A1 WO 2019206090A1 CN 2019083714 W CN2019083714 W CN 2019083714W WO 2019206090 A1 WO2019206090 A1 WO 2019206090A1
Authority
WO
WIPO (PCT)
Prior art keywords
character
media file
feature
behavior record
information
Prior art date
Application number
PCT/CN2019/083714
Other languages
French (fr)
Chinese (zh)
Inventor
黄勤波
杜霁轩
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2019206090A1 publication Critical patent/WO2019206090A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43—Querying
    • G06F16/435—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H04N5/91—Television signal processing therefor
    • H04N5/92—Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback

Definitions

  • the present invention relates to the field of communications technologies, and in particular, to a media file remarking method, apparatus, mobile terminal, and storage medium.
  • the photo records historical moments in two-dimensional data, and the video records historical segments in three-dimensional data (two-dimensional plane + time dimension). These historical moments and fragments do not exist in isolation.
  • the main object of the present invention is to provide a media file remarking method, device, mobile terminal and storage medium, which are intended to prompt the user with relevant information of the media file.
  • the present invention provides a media file remarking method, including: acquiring features of at least one character in a media file; and generating remark information of the media file according to characteristics of the at least one character.
  • the present invention further provides a media file remarking apparatus, comprising: a feature acquisition module, acquiring features of at least one character in the media file; and a remark generation module, generating the media file according to characteristics of the at least one character Remarks.
  • the present invention also provides a mobile terminal, the mobile terminal comprising a processor, a memory and a communication bus; the communication bus is for implementing connection communication between the processor and the memory; the processor is configured to execute A media file remarking program stored in the memory to implement the steps of the aforementioned media file remarking method.
  • the present invention also provides a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors, The steps of implementing the aforementioned media file remarking method.
  • FIG. 1 is a flow chart of a media file remarking method in accordance with one embodiment of the present invention
  • FIG. 2 is a flow chart of a media file remarking method in accordance with one embodiment of the present invention.
  • FIG. 3 is a block diagram of a media file remarking apparatus in accordance with one embodiment of the present invention.
  • FIG. 4 is a block diagram of a media file remarking apparatus in accordance with one embodiment of the present invention.
  • FIG. 5 is a block diagram of a mobile terminal in accordance with one embodiment of the present invention.
  • an embodiment of the present invention provides a media file remarking method, including:
  • Step S110 acquiring features of at least one character in the media file.
  • the type of the media file is not limited.
  • the media file may be various types of files such as a recording, a photo, a video, or the like, or may be a mixed media file or the like.
  • the manner in which the person is recorded includes, but is not limited to, recording a character, taking a photo, or recording a video.
  • the characteristics of the person include, but are not limited to, the user's name, phone number, voice print, face part map data, and the like.
  • Step S120 Generate remark information of the media file according to the feature of the at least one character.
  • the note information when a plurality of features of the person are acquired, the note information may be generated using all or part of the features.
  • the manner of generating the remark information is not limited. For example, when the user's name is obtained, the user name may be directly added to the background of the photo to form background information, and the image identification technology is used to identify the restaurant logo. When the user is in a restaurant, the generated remark information can be eaten at a restaurant.
  • the remark information can be displayed when the media file is opened, including playing the recording and video as a subtitle display, and displaying the remark information directly when the photo is opened, and can also display the remark information link, and click the link. You can view the contents of the note information later.
  • the character is the core element of the media file, and the character of the character reflects the information related to the character when the media file is formed, and generates the remark information according to the characteristics of the character, and can prompt the remark information by
  • the activity of the character when the media file is formed helps the user to recall the scene when the media file is formed.
  • an embodiment of the present invention provides a media file remarking method, including:
  • Step S210 identifying a first feature of at least one character in the media file.
  • the first feature is a feature that can be directly recognized from the media file, such as a voiceprint of a character in a recording, a face map data of a character in the photo, and a face of the character in at least one frame of the video. Bitmap data.
  • Step S220 searching for a second feature of the at least one character from the preset feature database according to the first feature of the at least one character, the feature of the at least one character comprising the first feature and the second feature.
  • the second feature is a feature that is not embodied in the media file.
  • the second feature is not limited in this embodiment, including but not limited to features that are difficult to be embodied in the media file.
  • the preset feature library stores the feature of the character, for example, storing the name, the phone, and the like of the character, and when the face part feature and the voiceprint feature of the character are recognized from the media file, Other features of the character, such as name, phone number, etc., are found from the feature library, and the media library can be matched with features identified from the media file to provide data support for further retrieval of other features.
  • Step S230 acquiring a behavior record of the at least one character according to the first feature and the second feature.
  • the behavior record can often reflect the relevant story of the media file, and can form a prompt for the user.
  • the time range is determined according to the recording time of the media file, and the behavior record of the character in the time range is searched for.
  • the related information of the media file may be searched for, and the related information of the media file includes but is not limited to the recording time and location information provided in the media file.
  • the behavior record of the person before and after the media file generation time can be matched, and is extracted as the basis for generating the remark information, because the behavior record of the character in the time range is consistent with the information related to the media file, for example, If a photo records that the character is located in the movie theater, the person can query the behavior record of the character on the day of photographing, and find that the movie ticket is ordered on the same day, and the remark information of the character can be generated based on the order record.
  • the characteristics of the character are not limited to the contact information including the person, the account number used to log in the application, and the active area of the character, and the above features may be recorded in the preset feature library.
  • the manner in which the behavior record is searched is not limited, including but not limited to the following methods:
  • the contact information of the character includes, but is not limited to, a phone number, an email address, and a social tool account, and the phone number can be used to find a corresponding call record, a short message, and the corresponding email content is searched according to the email address, and the social account number is searched.
  • Corresponding social records, call records, text messages, email content, and social records all belong to the person's behavior record.
  • the type of the application is restricted. If the application is a social tool, the social record corresponding to the character may be searched from the social tool, and if the application is a financial financial application, the financial management application may be searched.
  • the investment financial management record corresponding to the character if the application is a consumer application, the consumer application may be searched for consumption records such as shopping, eating, and watching movies, and the social record, the investment financial record, and the consumption record belong to the character. Behavior record.
  • the active area of the character may be identified from a media file such as a photo or a video, or the active area of the character may be queried based on the geographic location corresponding to the media file.
  • the active area is a work unit
  • the behavior record is Work, overtime, etc.
  • the activity area is a movie theater, the behavior is recorded as watching a movie.
  • Step S240 Generate remark information of the media file according to the behavior record of the at least one character.
  • the related photos are searched in the application commonly used by the user.
  • Information, and matching and subsequent processing, the scanned results provide users with richer photo background information through subtitles, watermarks, links, etc., which solves the problem of single information when viewing pictures, videos, etc., so that our image files fully utilize.
  • Extracting the identity of the person from the photo including but not limited to the face part map, ear pattern, etc.; matching the feature library by the extracted character feature to find further features of the character, including but not limited to mobile phone number, social account number, application login The account number, especially the account of the social and financial consumer application of the character; according to all or part of the acquired features, the social activity record of the relevant person for a period of time before and after the photo generation is retrieved, and if the photo is taken immediately, a subsequent period may be set.
  • the extraction task after the task is over, integrates the relevant information into the remark information of the photo; provides the photo remark information to the user through subtitles, watermarks, links, etc., and solves the current information of the picture, video, etc. The problem is to make the image file more effective.
  • an embodiment of the present invention provides a media file remarking apparatus, including:
  • the feature acquisition module 310 acquires features of at least one character in the media file.
  • the type of the media file is not limited.
  • the media file may be various types of files such as a recording, a photo, a video, or the like, or may be a mixed media file or the like.
  • the manner in which the person is recorded includes, but is not limited to, recording a character, taking a photo, or recording a video.
  • the characteristics of the person include, but are not limited to, the user's name, phone number, voice print, face part map data, and the like.
  • the remark generation module 320 generates remark information of the media file according to the characteristics of the at least one character.
  • the note information when a plurality of features of the person are acquired, the note information may be generated using all or part of the features.
  • the manner of generating the remark information is not limited. For example, when the user's name is obtained, the user name may be directly added to the background of the photo to form background information, and the image identification technology is used to identify the restaurant logo. When the user is in a restaurant, the generated remark information can be eaten at a restaurant.
  • the remark information can be displayed when the media file is opened, including playing the recording and video as a subtitle display, and displaying the remark information directly when the photo is opened, and can also display the remark information link, and click the link. You can view the contents of the note information later.
  • the character is the core element of the media file, and the character of the character reflects the information related to the character when the media file is formed, and generates the remark information according to the characteristics of the character, and can prompt the remark information by
  • the activity of the character when the media file is formed helps the user to recall the scene when the media file is formed.
  • an embodiment of the present invention provides a media file remarking apparatus, including:
  • the feature acquisition module 410 identifies a first feature of at least one character in the media file.
  • the first feature is a feature that can be directly recognized from the media file, such as a voiceprint of a character in a recording, a face map data of a character in the photo, and a face of the character in at least one frame of the video. Bitmap data.
  • the feature acquiring module 410 searches for a second feature of the at least one character from the preset feature database according to the first feature of the at least one character, the feature of the at least one character includes the first feature and the second feature.
  • the second feature is a feature that is not embodied in the media file.
  • the second feature is not limited in this embodiment, including but not limited to features that are difficult to be embodied in the media file.
  • the preset feature library stores the feature of the character, for example, storing the name, the phone, and the like of the character, and when the face part feature and the voiceprint feature of the character are recognized from the media file, Other features of the character, such as name, phone number, etc., are found from the feature library, and the media library can be matched with features identified from the media file to provide data support for further retrieval of other features.
  • the behavior obtaining module 420 acquires a behavior record of the at least one character according to the first feature and the second feature.
  • the behavior record can often reflect the relevant story of the media file, and can form a prompt for the user.
  • the time range is determined according to the recording time of the media file, and the behavior record of the character in the time range is searched for.
  • the related information of the media file may be searched for, and the related information of the media file includes but is not limited to the recording time and location information provided in the media file.
  • the behavior record of the person before and after the media file generation time can be matched, and is extracted as the basis for generating the remark information, because the behavior record of the character in the time range is consistent with the information related to the media file, for example, If a photo records that the character is located in the movie theater, the person can query the behavior record of the character on the day of photographing, and find that the movie ticket is ordered on the same day, and the remark information of the character can be generated based on the order record.
  • the characteristics of the character are not limited to the contact information including the person, the account number used to log in the application, and the active area of the character, and the above features may be recorded in the preset feature library.
  • the manner in which the behavior record is searched is not limited, including but not limited to the following methods:
  • the contact information of the character includes, but is not limited to, a phone number, an email address, and a social tool account, and the phone number can be used to find a corresponding call record, a short message, and the corresponding email content is searched according to the email address, and the social account number is searched.
  • Corresponding social records, call records, text messages, email content, and social records all belong to the person's behavior record.
  • the type of the application is restricted. If the application is a social tool, the social record corresponding to the character may be searched from the social tool, and if the application is a financial financial application, the financial management application may be searched.
  • the investment financial management record corresponding to the character if the application is a consumer application, the consumer application may be searched for consumption records such as shopping, eating, and watching movies, and the social record, the investment financial record, and the consumption record belong to the character. Behavior record.
  • the active area of the character may be identified from a media file such as a photo or a video, or the active area of the character may be queried based on the geographic location corresponding to the media file.
  • the active area is a work unit
  • the behavior record is Work, overtime, etc.
  • the activity area is a movie theater, the behavior is recorded as watching a movie.
  • the remark generation module 430 generates remark information of the media file based on the behavior record of the at least one character.
  • the generated comment information may be a voice note, a text note, or the like.
  • the association module 440 is further configured to associate the generated remark information with the media file, so as to combine the corresponding remark information when the media file is displayed. Show it to the user.
  • the remark information may be displayed in a manner of watermark, link, subtitle, voice, and the like.
  • the association module 440 can associate the remark information of the media file with a corresponding media file.
  • the related photos are searched in the application commonly used by the user.
  • Information, and matching and subsequent processing, the scanned results provide users with richer photo background information through subtitles, watermarks, links, etc., which solves the problem of single information when viewing pictures, videos, etc., so that our image files fully utilize.
  • the user can collect the contact voiceprint, the facial part map feature, etc. through the specific software and hardware on the mobile terminal when the user inputs the contact on the mobile terminal, and can also add these identity features when editing the existing contact. Save to a specific area in the mobile terminal and associate with the corresponding field mapping of each contact in the address book.
  • the steps for generating media file remark information based on the feature library are as follows:
  • the first step the user enters the identity feature of the contact in advance through the mobile terminal, and completes the feature storage to form a contact feature database, including but not limited to the voiceprint, face part map, eye pattern, ear of each contact. Patterns, fingerprints, contact numbers, company, location of the event, and other features.
  • Step 2 The user performs recording/recording/photographing on the mobile phone. During the recording process, these files are matched and identified through the aforementioned contact feature library, and the face part map (video, photo) included therein is recognized. Features such as lines (video, recording).
  • recording, photographing, and recording have the current location of the recording, photographing, and recording.
  • the recording can match the voiceprint of the contact, or it can be the contact note of the voice matching in the recording or the keyword in some information. If the photos and videos match the bitmap of some contacts, it is also a feature record of the media file, which is stored in the form of a database. These stored records are the background information for the recordings, photos and videos.
  • Step 3 Find certain behavior records related to them through certain features. Specifically, some features are searched for social records of related people through the application that the user has recently used, including but not limited to calls, text messages, social information, Dinner, watching movies, taking a taxi, etc.
  • the fourth step the above behavior record is displayed through the intelligent terminal for the user's reference.
  • the problem of difficulty in human memory can be effectively solved, and the remarks of media files such as photos and videos can be generated through features such as the face of a natural person, thereby enhancing the reference value of the media file and improving the user experience.
  • the technical solution of the embodiment replaces the manual data collection and retrieval, and greatly improves the efficiency of finding related information through machine retrieval.
  • an embodiment of the present invention provides a mobile terminal, where the mobile terminal includes a processor 510, a memory 520, and a communication bus 530;
  • Communication bus 530 is used to implement connection communication between processor 510 and memory 520;
  • the processor 510 is configured to execute the media file remarking program stored in the memory 520 to implement the following steps:
  • the type of the media file is not limited.
  • the media file may be various types of files such as a recording, a photo, a video, or the like, or may be a mixed media file or the like.
  • the manner in which the person is recorded includes, but is not limited to, recording a character, taking a photo, or recording a video.
  • the characteristics of the person include, but are not limited to, the user's name, phone number, voice print, face part map data, and the like.
  • Remark information of the media file is generated according to the characteristics of the at least one character.
  • the note information when a plurality of features of the person are acquired, the note information may be generated using all or part of the features.
  • the manner of generating the remark information is not limited. For example, when the user's name is obtained, the user name may be directly added to the background of the photo to form background information, and the image identification technology is used to identify the restaurant logo. When the user is in a restaurant, the generated remark information can be eaten at a restaurant.
  • the remark information can be displayed when the media file is opened, including playing the recording and video as a subtitle display, and displaying the remark information directly when the photo is opened, and can also display the remark information link, and click the link. You can view the contents of the note information later.
  • the character is the core element of the media file, and the character of the character reflects the information related to the character when the media file is formed, and generates the remark information according to the characteristics of the character, and can prompt the remark information by
  • the activity of the character when the media file is formed helps the user to recall the scene when the media file is formed.
  • an embodiment of the present invention provides a mobile terminal, where the mobile terminal includes a processor 510, a memory 520, and a communication bus 530;
  • Communication bus 530 is used to implement connection communication between processor 510 and memory 520;
  • the processor 510 is configured to execute the media file remarking program stored in the memory 520 to implement the following steps:
  • the first feature is a feature that can be directly recognized from the media file, such as a voiceprint of a character in a recording, a face map data of a character in the photo, and a face of the character in at least one frame of the video. Bitmap data.
  • the second feature is a feature that is not embodied in the media file.
  • the second feature is not limited in this embodiment, including but not limited to features that are difficult to be embodied in the media file.
  • the preset feature library stores the feature of the character, for example, storing the name, the phone, and the like of the character, and when the face part feature and the voiceprint feature of the character are recognized from the media file, Other features of the character, such as name, phone number, etc., are found from the feature library, and the media library can be matched with features identified from the media file to provide data support for further retrieval of other features.
  • a behavior record of the at least one character is acquired.
  • the behavior record can often reflect the relevant story of the media file, and can form a prompt for the user.
  • the time range is determined according to the recording time of the media file, and the behavior record of the character in the time range is searched for.
  • the related information of the media file may be searched for, and the related information of the media file includes but is not limited to the recording time and location information provided in the media file.
  • the behavior record of the person before and after the media file generation time can be matched, and is extracted as the basis for generating the remark information, because the behavior record of the character in the time range is consistent with the information related to the media file, for example, If a photo records that the character is located in the movie theater, the person can query the behavior record of the character on the day of photographing, and find that the movie ticket is ordered on the same day, and the remark information of the character can be generated based on the order record.
  • the characteristics of the character are not limited to the contact information including the person, the account number used to log in the application, and the active area of the character, and the above features may be recorded in the preset feature library.
  • the manner in which the behavior record is searched is not limited, including but not limited to the following methods:
  • the contact information of the character includes, but is not limited to, a phone number, an email address, and a social tool account, and the phone number can be used to find a corresponding call record, a short message, and the corresponding email content is searched according to the email address, and the social account number is searched.
  • Corresponding social records, call records, text messages, email content, and social records all belong to the person's behavior record.
  • the type of the application is restricted. If the application is a social tool, the social record corresponding to the character may be searched from the social tool, and if the application is a financial financial application, the financial management application may be searched.
  • the investment financial management record corresponding to the character if the application is a consumer application, the consumer application may be searched for consumption records such as shopping, eating, and watching movies, and the social record, the investment financial record, and the consumption record belong to the character. Behavior record.
  • the active area of the character may be identified from a media file such as a photo or a video, or the active area of the character may be queried based on the geographic location corresponding to the media file.
  • the active area is a work unit
  • the behavior record is Work, overtime, etc.
  • the activity area is a movie theater, the behavior is recorded as watching a movie.
  • the related photos are searched in the application commonly used by the user.
  • Information, and matching and subsequent processing, the scanned results provide users with richer photo background information through subtitles, watermarks, links, etc., which solves the problem of single information when viewing pictures, videos, etc., so that our image files fully utilize.
  • the preset feature library stores the multimedia features of the contact, the face part map, the voiceprint, the geographical location, the call record, the short message record, etc., and then associates the contact with each feature; when the media file is generated, the media file is identified
  • the features photo face, identity feature, photo location, etc.
  • the remark information is generated based on the acquired features, and the remark information of the media file is associated with the media file for display.
  • the remarks can be displayed in the form of watermarks, links, subtitles, etc.
  • the smart terminal can present the remark information to the user, and the user can know the background of the photo and the video generation according to the remark information.
  • Also provided in an embodiment of the present invention is a computer readable storage medium storing one or more programs, one or more programs executable by one or more processors to implement the following steps :
  • the type of the media file is not limited.
  • the media file may be various types of files such as a recording, a photo, a video, or the like, or may be a mixed media file or the like.
  • the manner in which the person is recorded includes, but is not limited to, recording a character, taking a photo, or recording a video.
  • the characteristics of the person include, but are not limited to, the user's name, phone number, voice print, face part map data, and the like.
  • Remark information of the media file is generated according to the characteristics of the at least one character.
  • the note information when a plurality of features of the person are acquired, the note information may be generated using all or part of the features.
  • the manner of generating the remark information is not limited. For example, when the user's name is obtained, the user name may be directly added to the background of the photo to form background information, and the image identification technology is used to identify the restaurant logo. When the user is in a restaurant, the generated remark information can be eaten at a restaurant.
  • the remark information can be displayed when the media file is opened, including playing the recording and video as a subtitle display, and displaying the remark information directly when the photo is opened, and can also display the remark information link, and click the link. You can view the contents of the note information later.
  • the character is the core element of the media file, and the character of the character reflects the information related to the character when the media file is formed, and generates the remark information according to the characteristics of the character, and can prompt the remark information by
  • the activity of the character when the media file is formed helps the user to recall the scene when the media file is formed.
  • the media file remarking method, apparatus, mobile terminal and storage medium of the present invention have at least the following advantages:
  • the character is a core element of the media file, and the character of the character reflects information related to the character when the media file is formed, and generates remark information according to the feature of the character, and can prompt by the remark information.
  • the character's activity when the media file is formed helps the user recall the scene when the media file is formed.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better.
  • Implementation Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal (which may be a cell phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Library & Information Science (AREA)
  • Telephone Function (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

Disclosed in the present invention are a media file remarking method, an apparatus, a mobile terminal and a storage medium. Said method comprises: acquiring features of at least one person in a media file; and generating remark information of the media file according to the features of the at least one person. According to the technical solutions of the present invention, for a media file recording a person, the person is the core element of the media file, and the features of the person reflect person-related information during the formation of the media file; the present invention generates remark information according to the features of the person, thereby being able to prompt, by means of the remark information, the person's activities during the formation of the media file, and helping a user to recall the scene during the formation of the media file.

Description

媒体文件备注方法、装置、移动终端和存储介质Media file remark method, device, mobile terminal and storage medium
交叉引用cross reference
本发明要求在2018年4月27日提交中国专利局、申请号为201810393790.2、发明名称为“媒体文件备注方法、装置、移动终端和存储介质”的中国专利申请的优先权，该申请的全部内容通过引用结合在本发明中。The present invention claims priority to Chinese Patent Application No. 201810393790.2, entitled "Media File Remarks, Apparatus, Mobile Terminals, and Storage Media", filed on April 27, 2018, the entire contents of which is hereby incorporated by reference. The invention is incorporated by reference.
技术领域Technical field
本发明涉及通信技术领域，尤其涉及一种媒体文件备注方法、装置、移动终端和存储介质。The present invention relates to the field of communications technologies, and in particular, to a media file remarking method, apparatus, mobile terminal, and storage medium.
背景技术Background technique
在当前高节奏的工作和社交生活中，人脑的处理能力、记忆能力明显不足，面对日益增长的信息，如何在工作和生活中有效利用，是一个很大的课题，也是未来长期的趋势，需要深入挖掘。In the current high-tempo work and social life, the human brain's processing ability and memory ability are obviously insufficient. In the face of increasing information, how to effectively use it in work and life is a big issue and a long-term trend in the future. Need to dig deeper.
信息社会的最主要特征是信息大***，用户经常会发现平时积累录制的海量的录音、照片和录像等联系人相关的影像录音资料，在经过很长一段时间后再去回顾时，很多当时的场景很难回想起来，这不能不说是一个非常大的遗憾，不符合当前人工智能和大数据时代的背景。The most important feature of the information society is the big explosion of information. Users often find a large number of recordings, photos and videos that are recorded by the contact-related video recordings. After a long period of time, they go back to review many of the time. It's hard to recall the scene. It's a big regret, not in line with the current background of artificial intelligence and big data.
照片是以二维资料记录历史瞬间，视频是以连续的三维资料(二维平面+时间维度)记录历史片段。这些历史瞬间和片段并不是孤立存在的，一张照片里面所蕴含的复杂关系，以及当前瞬间的背景及可能演化的方向，都是人们感兴趣的内容。The photo records historical moments in two-dimensional data, and the video records historical segments in three-dimensional data (two-dimensional plane + time dimension). These historical moments and fragments do not exist in isolation. The complex relationship contained in a photograph, as well as the background of the current moment and the direction in which it may evolve, are all interesting content.
而现有技术存在的问题就是，无法疏理出照片中的复杂关系，比如用户 在时隔多年后查看某张照片，已经忘记合影照片上人叫什么名字、照片在哪里照的、背后有什么故事。可见，现有技术无法为用户快速重现当时的场景及相关信息，相当于记录的影相资料没有发挥充分的作用。The problem with the prior art is that it is impossible to unravel the complex relationship in the photo, for example, the user views a certain photo after a lapse of time, has forgotten the name of the person on the photo, where the photo is taken, what is behind it. story. It can be seen that the prior art cannot quickly reproduce the scene and related information for the user, which is equivalent to the recorded image data does not play a sufficient role.
如果用户能从以往的影相文件中找到相关信息，则可以迅速解决这种困惑，相当于充分发挥这些照片和录像作用，极大的提升用户体验。If users can find relevant information from past image files, they can quickly solve this confusion, which is equivalent to making full use of these photos and videos, greatly improving the user experience.
发明内容Summary of the invention
本发明的主要目的在于提出一种媒体文件备注方法、装置、移动终端和存储介质，旨在为用户提示媒体文件的相关信息。The main object of the present invention is to provide a media file remarking method, device, mobile terminal and storage medium, which are intended to prompt the user with relevant information of the media file.
为实现上述目的，本发明提供了一种媒体文件备注方法，包括：获取媒体文件中至少一个人物的特征；根据该至少一个人物的特征，生成所述媒体文件的备注信息。To achieve the above object, the present invention provides a media file remarking method, including: acquiring features of at least one character in a media file; and generating remark information of the media file according to characteristics of the at least one character.
为实现上述目标，本发明还提供一种媒体文件备注装置，包括：特征获取模块，获取媒体文件中至少一个人物的特征；备注生成模块，根据该至少一个人物的特征，生成所述媒体文件的备注信息。In order to achieve the above object, the present invention further provides a media file remarking apparatus, comprising: a feature acquisition module, acquiring features of at least one character in the media file; and a remark generation module, generating the media file according to characteristics of the at least one character Remarks.
为实现上述目标，本发明还提供一种移动终端，所述移动终端包括处理器、存储器和通信总线；所述通信总线用于实现处理器和存储器之间的连接通信；所述处理器用于执行存储器中存储的媒体文件备注程序，以实现前述的媒体文件备注方法的步骤。To achieve the above object, the present invention also provides a mobile terminal, the mobile terminal comprising a processor, a memory and a communication bus; the communication bus is for implementing connection communication between the processor and the memory; the processor is configured to execute A media file remarking program stored in the memory to implement the steps of the aforementioned media file remarking method.
为实现上述目标，本发明还提供一种计算机可读存储介质，所述计算机可读存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现前述的媒体文件备注方法的步骤。To achieve the above object, the present invention also provides a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors, The steps of implementing the aforementioned media file remarking method.
附图说明DRAWINGS
图1是根据本发明的一个实施例的媒体文件备注方法的流程图；1 is a flow chart of a media file remarking method in accordance with one embodiment of the present invention;
图2是根据本发明的一个实施例的媒体文件备注方法的流程图；2 is a flow chart of a media file remarking method in accordance with one embodiment of the present invention;
图3是根据本发明的一个实施例的媒体文件备注装置的框图；3 is a block diagram of a media file remarking apparatus in accordance with one embodiment of the present invention;
图4是根据本发明的一个实施例的媒体文件备注装置的框图；4 is a block diagram of a media file remarking apparatus in accordance with one embodiment of the present invention;
图5是根据本发明的一个实施例的移动终端的框图。Figure 5 is a block diagram of a mobile terminal in accordance with one embodiment of the present invention.
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。The implementation, functional features, and advantages of the present invention will be further described in conjunction with the embodiments.
具体实施方式detailed description
应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
在后续的描述中，使用用于表示元件的诸如“模块”、“部件”或“单元”的后缀仅为了有利于本发明的说明，其本身没有特有的意义。因此，“模块”、“部件”或“单元”可以混合地使用。In the following description, the use of suffixes such as "module", "component" or "unit" for indicating an element is merely an explanation for facilitating the present invention, and has no specific meaning per se. Therefore, "module", "component" or "unit" can be used in combination.
如图1所示，本发明的一个实施例中提供了一种媒体文件备注方法，包括：As shown in FIG. 1 , an embodiment of the present invention provides a media file remarking method, including:
步骤S110，获取媒体文件中至少一个人物的特征。Step S110, acquiring features of at least one character in the media file.
在本实施例中，对媒体文件的类型不进行限制，媒体文件可以是录音、照片、视频等各种类型的文件，也可以是混合媒体文件等。在本实施例中，对人物进行记录的方式包括但不限于对人物进行录音、拍摄照片或录制视频。在本实施例中，人物的特征包括但不限于用户的姓名、电话、声纹、脸部位图数据等。In this embodiment, the type of the media file is not limited. The media file may be various types of files such as a recording, a photo, a video, or the like, or may be a mixed media file or the like. In the present embodiment, the manner in which the person is recorded includes, but is not limited to, recording a character, taking a photo, or recording a video. In this embodiment, the characteristics of the person include, but are not limited to, the user's name, phone number, voice print, face part map data, and the like.
步骤S120，根据该至少一个人物的特征，生成媒体文件的备注信息。Step S120: Generate remark information of the media file according to the feature of the at least one character.
在本实施例中，在获取到人物的多个特征时，可以使用全部或部分特征生成备注信息。在本实施例中，对于生成备注信息的方式不进行限制，例如，获取到用户的姓名时，可以直接将用户姓名添加到照片的背景中形成背景信息，通过图像识别技术识别出餐馆标志时判断用户位于餐馆，则生成的备注信息可以是在餐馆吃饭。在本实施例中，备注信息可以在媒体文件打开时展 示，包括播放录音、视频时作为字幕展示，打开照片时作为水印展示，可直接展示备注信息内容，也可展示备注信息的链接，点击链接后可查看备注信息内容。In this embodiment, when a plurality of features of the person are acquired, the note information may be generated using all or part of the features. In this embodiment, the manner of generating the remark information is not limited. For example, when the user's name is obtained, the user name may be directly added to the background of the photo to form background information, and the image identification technology is used to identify the restaurant logo. When the user is in a restaurant, the generated remark information can be eaten at a restaurant. In this embodiment, the remark information can be displayed when the media file is opened, including playing the recording and video as a subtitle display, and displaying the remark information directly when the photo is opened, and can also display the remark information link, and click the link. You can view the contents of the note information later.
在本实施例中，对于记录人物的媒体文件，人物是媒体文件的核心要素，人物的特征反应了媒体文件形成时与人物有关的信息，根据人物的特征生成备注信息，能够通过备注信息提示在媒体文件形成时该人物的活动，帮助用户回忆媒体文件形成时的场景。In the embodiment, for the media file of the recorded person, the character is the core element of the media file, and the character of the character reflects the information related to the character when the media file is formed, and generates the remark information according to the characteristics of the character, and can prompt the remark information by The activity of the character when the media file is formed helps the user to recall the scene when the media file is formed.
如图2所示，本发明的一个实施例中提供了一种媒体文件备注方法，包括：As shown in FIG. 2, an embodiment of the present invention provides a media file remarking method, including:
步骤S210，识别媒体文件中至少一个人物的第一特征。Step S210, identifying a first feature of at least one character in the media file.
在本实施例中，第一特征是从媒体文件中能够直接识别出的特征，如录音中人物的声纹，照片中人物的脸部位图数据，视频中至少一帧画面中人物的脸部位图数据。In this embodiment, the first feature is a feature that can be directly recognized from the media file, such as a voiceprint of a character in a recording, a face map data of a character in the photo, and a face of the character in at least one frame of the video. Bitmap data.
步骤S220，根据该至少一个人物的第一特征，从预设的特征库中查找该至少一个人物的第二特征，该至少一个人物的特征包括第一特征和第二特征。Step S220, searching for a second feature of the at least one character from the preset feature database according to the first feature of the at least one character, the feature of the at least one character comprising the first feature and the second feature.
在本实施例中，第二特征是未在媒体文件中体现的特征，本实施例中对第二特征不进行限制，包括但不限于难以在媒体文件中体现的特征。在本实施例中，预设特征库对人物的特征进行存储，例如，对人物的姓名、电话等进行存储，则从媒体文件中识别出人物的脸部位图特征及声纹特征时，可以从特征库中找到该人物的其他特征，例如姓名、电话等，媒体库能够与根据从媒体文件中识别的特征进行匹配，为进一步检索其他特征提供了数据支持。In this embodiment, the second feature is a feature that is not embodied in the media file. The second feature is not limited in this embodiment, including but not limited to features that are difficult to be embodied in the media file. In this embodiment, the preset feature library stores the feature of the character, for example, storing the name, the phone, and the like of the character, and when the face part feature and the voiceprint feature of the character are recognized from the media file, Other features of the character, such as name, phone number, etc., are found from the feature library, and the media library can be matched with features identified from the media file to provide data support for further retrieval of other features.
步骤S230，根据上述第一特征和第二特征，获取该至少一个人物的行为记录。Step S230, acquiring a behavior record of the at least one character according to the first feature and the second feature.
在本实施例中，行为记录往往能够反映媒体文件的相关故事，能够形成对用户的提示。In this embodiment, the behavior record can often reflect the relevant story of the media file, and can form a prompt for the user.
在本实施例中，进一步地，根据媒体文件的录制时间确定时间范围，查找人物在时间范围内的行为记录。在本实施例中，除将人物特征作为查找行为记录外，还可以结合媒体文件的相关信息进行查找，媒体文件的相关信息包括但不限于媒体文件中自带的录制时间和位置信息等。在本实施例中，可以匹配媒体文件生成时间前后人物的行为记录，提取后作为生成备注信息的依据，这是因为该时间范围内人物的行为记录与媒体文件相关的信息一致性较高，例如，某张照片记录了人物位于电影院，则可查询拍照当日该人物的行为记录，发现当日其订购了电影票，则可以基于该订购记录生成该人物的备注信息。In this embodiment, further, the time range is determined according to the recording time of the media file, and the behavior record of the character in the time range is searched for. In this embodiment, in addition to the character feature as the search behavior record, the related information of the media file may be searched for, and the related information of the media file includes but is not limited to the recording time and location information provided in the media file. In this embodiment, the behavior record of the person before and after the media file generation time can be matched, and is extracted as the basis for generating the remark information, because the behavior record of the character in the time range is consistent with the information related to the media file, for example, If a photo records that the character is located in the movie theater, the person can query the behavior record of the character on the day of photographing, and find that the movie ticket is ordered on the same day, and the remark information of the character can be generated based on the order record.
在本实施例中，人物的特征但不限于包括人物的联系方式、用于登录应用的账号、人物的活动区域，上述特征可记录在预设特征库中。在本实施例中，对查找行为记录的方式不进行限制，包括但不限于以下几种方式：In this embodiment, the characteristics of the character are not limited to the contact information including the person, the account number used to log in the application, and the active area of the character, and the above features may be recorded in the preset feature library. In this embodiment, the manner in which the behavior record is searched is not limited, including but not limited to the following methods:
(1)根据该至少一个人物的联系方式，查找该至少一个人物的联系记录作为人物的行为记录。(1) Find a contact record of the at least one character as a behavior record of the character according to the contact manner of the at least one character.
在本实施例中，人物的联系方式包括但不限于电话号码、邮箱地址、社交工具账号，则可以按电话号码查找对应的通话记录、短信，按邮箱地址查找对应的邮件内容，按社交账号查找对应的社交记录，通话记录、短信、邮件内容、社交记录均属于该人物的行为记录。In this embodiment, the contact information of the character includes, but is not limited to, a phone number, an email address, and a social tool account, and the phone number can be used to find a corresponding call record, a short message, and the corresponding email content is searched according to the email address, and the social account number is searched. Corresponding social records, call records, text messages, email content, and social records all belong to the person's behavior record.
(2)使用账号登录应用，从应用中查找该至少一个人物的行为记录。(2) Log in to the application using an account, and search for the behavior record of the at least one character from the application.
在本实施例中，对应用的类型进行限制，如果该应用是社交工具，则可以从社交工具中查找该人物对应的社交记录，如果该应用是金融理财应用，则可以从金融理财应用中查找该人物对应的投资理财记录，如果该应用是消费类应用，则可以从消费类应用中查找该人物购物、吃饭、看电影等消费记录，社交记录、投资理财记录、消费记录均属于该人物的行为记录。In this embodiment, the type of the application is restricted. If the application is a social tool, the social record corresponding to the character may be searched from the social tool, and if the application is a financial financial application, the financial management application may be searched. The investment financial management record corresponding to the character, if the application is a consumer application, the consumer application may be searched for consumption records such as shopping, eating, and watching movies, and the social record, the investment financial record, and the consumption record belong to the character. Behavior record.
(3)根据人物所在的活动区域，确定该至少一个人物的行为记录。(3) Determining the behavior record of the at least one character according to the activity area in which the character is located.
在本实施例中，人物的活动区域可以从照片、视频等媒体文件中识别出 来，或基于媒体文件对应的地理位置来查询该人物的活动区域，当活动区域为工作单位时，则行为记录为工作、加班等，当活动区域为电影院时，则行为记录为看电影等。In this embodiment, the active area of the character may be identified from a media file such as a photo or a video, or the active area of the character may be queried based on the geographic location corresponding to the media file. When the active area is a work unit, the behavior record is Work, overtime, etc. When the activity area is a movie theater, the behavior is recorded as watching a movie.
步骤S240，根据该至少一个人物的行为记录，生成媒体文件的备注信息。Step S240: Generate remark information of the media file according to the behavior record of the at least one character.
根据本实施例的技术方案，通过对照片、录像中可识别的一些人物特征，如人物脸部图像位图特征、拍摄时所处位置等要素，在用户常用的应用中去查找相关照片生成前后信息，并进行匹配和后续处理，扫描出的结果通过字幕、水印、链接等方式提供用户更丰富的照片背景信息，解决了目前的图片、视频等查看时信息单一的问题，使我们的影像文件充分发挥作用。According to the technical solution of the embodiment, by searching for some character features in the photo and the video, such as the character image of the face image of the person, the location of the image, and the like, the related photos are searched in the application commonly used by the user. Information, and matching and subsequent processing, the scanned results provide users with richer photo background information through subtitles, watermarks, links, etc., which solves the problem of single information when viewing pictures, videos, etc., so that our image files fully utilize.
根据本实施例的技术方案的一个具体示例如下：A specific example of the technical solution according to the present embodiment is as follows:
从照片中提取人物身份特征，包括但不限于脸部位图、耳纹等；通过提取的人物特征去匹配特征库，找到该人物进一步的特征，包括但不限于手机号码、社交账号、应用登录账号，尤其是该人物的社交及金融消费类应用的账号；根据获取的全部或部分特征去检索照片生成前后一段时间的相关人物的社交活动记录，如果是即时拍照，可设定一个后续一段时间的提取任务，待任务结束后再将相关信息整合到一起成为照片的备注信息；将照片备注信息通过字幕、水印、链接等方式提供给用户，解决了目前的图片、视频等查看时信息单一的问题，使影像文件更能够充分发挥作用。Extracting the identity of the person from the photo, including but not limited to the face part map, ear pattern, etc.; matching the feature library by the extracted character feature to find further features of the character, including but not limited to mobile phone number, social account number, application login The account number, especially the account of the social and financial consumer application of the character; according to all or part of the acquired features, the social activity record of the relevant person for a period of time before and after the photo generation is retrieved, and if the photo is taken immediately, a subsequent period may be set. The extraction task, after the task is over, integrates the relevant information into the remark information of the photo; provides the photo remark information to the user through subtitles, watermarks, links, etc., and solves the current information of the picture, video, etc. The problem is to make the image file more effective.
如图3所示，本发明的一个实施例中提供了一种媒体文件备注装置，包括：As shown in FIG. 3, an embodiment of the present invention provides a media file remarking apparatus, including:
特征获取模块310，获取媒体文件中至少一个人物的特征。The feature acquisition module 310 acquires features of at least one character in the media file.
在本实施例中，对媒体文件的类型不进行限制，媒体文件可以是录音、照片、视频等各种类型的文件，也可以是混合媒体文件等。在本实施例中，对人物进行记录的方式包括但不限于对人物进行录音、拍摄照片或录制视频。在本实施例中，人物的特征包括但不限于用户的姓名、电话、声纹、脸部位 图数据等。In this embodiment, the type of the media file is not limited. The media file may be various types of files such as a recording, a photo, a video, or the like, or may be a mixed media file or the like. In the present embodiment, the manner in which the person is recorded includes, but is not limited to, recording a character, taking a photo, or recording a video. In the present embodiment, the characteristics of the person include, but are not limited to, the user's name, phone number, voice print, face part map data, and the like.
备注生成模块320，根据该至少一个人物的特征，生成媒体文件的备注信息。The remark generation module 320 generates remark information of the media file according to the characteristics of the at least one character.
在本实施例中，在获取到人物的多个特征时，可以使用全部或部分特征生成备注信息。在本实施例中，对于生成备注信息的方式不进行限制，例如，获取到用户的姓名时，可以直接将用户姓名添加到照片的背景中形成背景信息，通过图像识别技术识别出餐馆标志时判断用户位于餐馆，则生成的备注信息可以是在餐馆吃饭。在本实施例中，备注信息可以在媒体文件打开时展示，包括播放录音、视频时作为字幕展示，打开照片时作为水印展示，可直接展示备注信息内容，也可展示备注信息的链接，点击链接后可查看备注信息内容。In this embodiment, when a plurality of features of the person are acquired, the note information may be generated using all or part of the features. In this embodiment, the manner of generating the remark information is not limited. For example, when the user's name is obtained, the user name may be directly added to the background of the photo to form background information, and the image identification technology is used to identify the restaurant logo. When the user is in a restaurant, the generated remark information can be eaten at a restaurant. In this embodiment, the remark information can be displayed when the media file is opened, including playing the recording and video as a subtitle display, and displaying the remark information directly when the photo is opened, and can also display the remark information link, and click the link. You can view the contents of the note information later.
在本实施例中，对于记录人物的媒体文件，人物是媒体文件的核心要素，人物的特征反应了媒体文件形成时与人物有关的信息，根据人物的特征生成备注信息，能够通过备注信息提示在媒体文件形成时该人物的活动，帮助用户回忆媒体文件形成时的场景。In the embodiment, for the media file of the recorded person, the character is the core element of the media file, and the character of the character reflects the information related to the character when the media file is formed, and generates the remark information according to the characteristics of the character, and can prompt the remark information by The activity of the character when the media file is formed helps the user to recall the scene when the media file is formed.
如图4所示，本发明的一个实施例中提供了一种媒体文件备注装置，包括：As shown in FIG. 4, an embodiment of the present invention provides a media file remarking apparatus, including:
特征获取模块410，识别媒体文件中至少一个人物的第一特征。The feature acquisition module 410 identifies a first feature of at least one character in the media file.
在本实施例中，第一特征是从媒体文件中能够直接识别出的特征，如录音中人物的声纹，照片中人物的脸部位图数据，视频中至少一帧画面中人物的脸部位图数据。In this embodiment, the first feature is a feature that can be directly recognized from the media file, such as a voiceprint of a character in a recording, a face map data of a character in the photo, and a face of the character in at least one frame of the video. Bitmap data.
特征获取模块410，根据该至少一个人物的第一特征，从预设的特征库中查找该至少一个人物的第二特征，该至少一个人物的特征包括第一特征和第二特征。The feature acquiring module 410 searches for a second feature of the at least one character from the preset feature database according to the first feature of the at least one character, the feature of the at least one character includes the first feature and the second feature.
在本实施例中，第二特征是未在媒体文件中体现的特征，本实施例中对 第二特征不进行限制，包括但不限于难以在媒体文件中体现的特征。在本实施例中，预设特征库对人物的特征进行存储，例如，对人物的姓名、电话等进行存储，则从媒体文件中识别出人物的脸部位图特征及声纹特征时，可以从特征库中找到该人物的其他特征，例如姓名、电话等，媒体库能够与根据从媒体文件中识别的特征进行匹配，为进一步检索其他特征提供了数据支持。In this embodiment, the second feature is a feature that is not embodied in the media file. The second feature is not limited in this embodiment, including but not limited to features that are difficult to be embodied in the media file. In this embodiment, the preset feature library stores the feature of the character, for example, storing the name, the phone, and the like of the character, and when the face part feature and the voiceprint feature of the character are recognized from the media file, Other features of the character, such as name, phone number, etc., are found from the feature library, and the media library can be matched with features identified from the media file to provide data support for further retrieval of other features.
行为获取模块420，根据上述第一特征和第二特征，获取该至少一个人物的行为记录。The behavior obtaining module 420 acquires a behavior record of the at least one character according to the first feature and the second feature.
在本实施例中，行为记录往往能够反映媒体文件的相关故事，能够形成对用户的提示。In this embodiment, the behavior record can often reflect the relevant story of the media file, and can form a prompt for the user.
在本实施例中，进一步地，根据媒体文件的录制时间确定时间范围，查找人物在时间范围内的行为记录。在本实施例中，除将人物特征作为查找行为记录外，还可以结合媒体文件的相关信息进行查找，媒体文件的相关信息包括但不限于媒体文件中自带的录制时间和位置信息等。在本实施例中，可以匹配媒体文件生成时间前后人物的行为记录，提取后作为生成备注信息的依据，这是因为该时间范围内人物的行为记录与媒体文件相关的信息一致性较高，例如，某张照片记录了人物位于电影院，则可查询拍照当日该人物的行为记录，发现当日其订购了电影票，则可以基于该订购记录生成该人物的备注信息。In this embodiment, further, the time range is determined according to the recording time of the media file, and the behavior record of the character in the time range is searched for. In this embodiment, in addition to the character feature as the search behavior record, the related information of the media file may be searched for, and the related information of the media file includes but is not limited to the recording time and location information provided in the media file. In this embodiment, the behavior record of the person before and after the media file generation time can be matched, and is extracted as the basis for generating the remark information, because the behavior record of the character in the time range is consistent with the information related to the media file, for example, If a photo records that the character is located in the movie theater, the person can query the behavior record of the character on the day of photographing, and find that the movie ticket is ordered on the same day, and the remark information of the character can be generated based on the order record.
在本实施例中，人物的特征但不限于包括人物的联系方式、用于登录应用的账号、人物的活动区域，上述特征可记录在预设特征库中。在本实施例中，对查找行为记录的方式不进行限制，包括但不限于以下几种方式：In this embodiment, the characteristics of the character are not limited to the contact information including the person, the account number used to log in the application, and the active area of the character, and the above features may be recorded in the preset feature library. In this embodiment, the manner in which the behavior record is searched is not limited, including but not limited to the following methods:
(1)根据该至少一个人物的联系方式，查找该至少一个的联系记录作为人物的行为记录。(1) Finding the at least one contact record as a behavior record of the character according to the contact manner of the at least one character.
在本实施例中，人物的联系方式包括但不限于电话号码、邮箱地址、社交工具账号，则可以按电话号码查找对应的通话记录、短信，按邮箱地址查找对应的邮件内容，按社交账号查找对应的社交记录，通话记录、短信、邮 件内容、社交记录均属于该人物的行为记录。In this embodiment, the contact information of the character includes, but is not limited to, a phone number, an email address, and a social tool account, and the phone number can be used to find a corresponding call record, a short message, and the corresponding email content is searched according to the email address, and the social account number is searched. Corresponding social records, call records, text messages, email content, and social records all belong to the person's behavior record.
(2)使用账号登录应用，从应用中查找该至少一个人物的行为记录。(2) Log in to the application using an account, and search for the behavior record of the at least one character from the application.
在本实施例中，对应用的类型进行限制，如果该应用是社交工具，则可以从社交工具中查找该人物对应的社交记录，如果该应用是金融理财应用，则可以从金融理财应用中查找该人物对应的投资理财记录，如果该应用是消费类应用，则可以从消费类应用中查找该人物购物、吃饭、看电影等消费记录，社交记录、投资理财记录、消费记录均属于该人物的行为记录。In this embodiment, the type of the application is restricted. If the application is a social tool, the social record corresponding to the character may be searched from the social tool, and if the application is a financial financial application, the financial management application may be searched. The investment financial management record corresponding to the character, if the application is a consumer application, the consumer application may be searched for consumption records such as shopping, eating, and watching movies, and the social record, the investment financial record, and the consumption record belong to the character. Behavior record.
(3)根据人物所在的活动区域，确定该至少一个人物的行为记录。(3) Determining the behavior record of the at least one character according to the activity area in which the character is located.
在本实施例中，人物的活动区域可以从照片、视频等媒体文件中识别出来，或基于媒体文件对应的地理位置来查询该人物的活动区域，当活动区域为工作单位时，则行为记录为工作、加班等，当活动区域为电影院时，则行为记录为看电影等。In this embodiment, the active area of the character may be identified from a media file such as a photo or a video, or the active area of the character may be queried based on the geographic location corresponding to the media file. When the active area is a work unit, the behavior record is Work, overtime, etc. When the activity area is a movie theater, the behavior is recorded as watching a movie.
备注生成模块430，根据该至少一个人物的行为记录，生成媒体文件的备注信息。所述生成的备注信息可以是语音备注、文字备注等。The remark generation module 430 generates remark information of the media file based on the behavior record of the at least one character. The generated comment information may be a voice note, a text note, or the like.
进一步的，在一实施例中，还可以包括关联模块440，所述关联模块440用于将生成的备注信息与所述媒体文件进行关联，以便在该媒体文件展示时将对应的备注信息一并展示给用户。所述备注信息可以以水印，链接，字幕、语音等方式进行展示。在一实施方式中，所述关联模块440可以在存储所述媒体文件的备注信息时将其与对应的媒体文件进行关联。Further, in an embodiment, the association module 440 is further configured to associate the generated remark information with the media file, so as to combine the corresponding remark information when the media file is displayed. Show it to the user. The remark information may be displayed in a manner of watermark, link, subtitle, voice, and the like. In an embodiment, the association module 440 can associate the remark information of the media file with a corresponding media file.
根据本实施例的技术方案，通过对照片、录像中可识别的一些人物特征，如人物脸部图像位图特征、拍摄时所处位置等要素，在用户常用的应用中去查找相关照片生成前后信息，并进行匹配和后续处理，扫描出的结果通过字幕、水印、链接等方式提供用户更丰富的照片背景信息，解决了目前的图片、视频等查看时信息单一的问题，使我们的影像文件充分发挥作用。According to the technical solution of the embodiment, by searching for some character features in the photo and the video, such as the character image of the face image of the person, the location of the image, and the like, the related photos are searched in the application commonly used by the user. Information, and matching and subsequent processing, the scanned results provide users with richer photo background information through subtitles, watermarks, links, etc., which solves the problem of single information when viewing pictures, videos, etc., so that our image files fully utilize.
根据本实施例的技术方案的一个具体示例如下：A specific example of the technical solution according to the present embodiment is as follows:
在该示例中需配置联系人特征数据库作为基础数据。用户可以在移动终 端上录入联系人时，通过移动终端上特定的软硬件采集该联系人声纹、脸部位图特征等，也可以在编辑已有联系人时加入这些身份特征，这些特征信息保存到移动终端中特定的区域，并与通讯录中的各联系人的相应字段映射关联，基于该特征库的生成媒体文件备注信息的步骤如下：In this example, you need to configure the contact signature database as the base data. The user can collect the contact voiceprint, the facial part map feature, etc. through the specific software and hardware on the mobile terminal when the user inputs the contact on the mobile terminal, and can also add these identity features when editing the existing contact. Save to a specific area in the mobile terminal and associate with the corresponding field mapping of each contact in the address book. The steps for generating media file remark information based on the feature library are as follows:
第一步：用户在预先通过移动终端录入联系人的身份特征，并完成特征存储，形成联系人特征库,这些特征包括但不限于各联系人的声纹、脸部位图、眼纹、耳纹、指纹、联系电话、所在公司、平时活动位置区域及其他特征。The first step: the user enters the identity feature of the contact in advance through the mobile terminal, and completes the feature storage to form a contact feature database, including but not limited to the voiceprint, face part map, eye pattern, ear of each contact. Patterns, fingerprints, contact numbers, company, location of the event, and other features.
第二步：用户在手机上进行录音/录相/拍照，这些文件在录制过程中，通过前述的联系人特征库进行匹配识别，识别出其中包含的脸部位图(录像，照片)，声纹(录像，录音)后等特征。Step 2: The user performs recording/recording/photographing on the mobile phone. During the recording process, these files are matched and identified through the aforementioned contact feature library, and the face part map (video, photo) included therein is recognized. Features such as lines (video, recording).
举例来说，录音、拍照和录像时有当前录音、拍照和录像的地理位置，录音可以匹配到联系人的声纹，也可以是录音中语音匹配的联系人备注或某些信息中的关键字，照片和录像如果匹配到某些联系人的位图，也是该媒体文件的一个特征记录，通过数据库的形式存储起来。这些存储起来的记录就是该录音、照片和录像的背景资料。For example, recording, photographing, and recording have the current location of the recording, photographing, and recording. The recording can match the voiceprint of the contact, or it can be the contact note of the voice matching in the recording or the keyword in some information. If the photos and videos match the bitmap of some contacts, it is also a feature record of the media file, which is stored in the form of a database. These stored records are the background information for the recordings, photos and videos.
考虑到以上两步的完成需要巨大的计算匹配工作，也可以考虑将视频、录音、录像上传至云端存储，相关匹配识别工作放在云端通过运算能力更强大的服务器计算机进行。Considering that the completion of the above two steps requires a huge computational matching work, it is also possible to upload video, audio, and video to the cloud storage, and the related matching identification work is performed in the cloud through a more powerful server computer.
第三步：通过某些特征查找与之相关的行为记录，具体地，将某些特征通过用户最近使用过的应用查找相关人物的社交记录，社交记录包括但不限于通话、短信、社交信息、聚餐、看电影、打车等；Step 3: Find certain behavior records related to them through certain features. Specifically, some features are searched for social records of related people through the application that the user has recently used, including but not limited to calls, text messages, social information, Dinner, watching movies, taking a taxi, etc.
第四步：将上述行为记录通过智能终端进行展示，供用户参考。The fourth step: the above behavior record is displayed through the intelligent terminal for the user's reference.
通过以上技术方案，能够有效解决人类记忆困难的问题，通过自然人的面部等特征，生成照片、录像等媒体文件的备注信息，提升媒体文件的参考价值，提升用户体验。本实施例的技术方案，代替人工的资料收集检索，通过机器检索，大大提高查找相关信息的效率。Through the above technical solutions, the problem of difficulty in human memory can be effectively solved, and the remarks of media files such as photos and videos can be generated through features such as the face of a natural person, thereby enhancing the reference value of the media file and improving the user experience. The technical solution of the embodiment replaces the manual data collection and retrieval, and greatly improves the efficiency of finding related information through machine retrieval.
如图5所示，本发明的一个实施例中提供了一种移动终端，移动终端包括处理器510、存储器520和通信总线530；As shown in FIG. 5, an embodiment of the present invention provides a mobile terminal, where the mobile terminal includes a processor 510, a memory 520, and a communication bus 530;
通信总线530用于实现处理器510和存储器520之间的连接通信； Communication bus 530 is used to implement connection communication between processor 510 and memory 520;
处理器510用于执行存储器520中存储的媒体文件备注程序，以实现以下步骤：The processor 510 is configured to execute the media file remarking program stored in the memory 520 to implement the following steps:
获取媒体文件中至少一个人物的特征。Get the characteristics of at least one character in the media file.
在本实施例中，对媒体文件的类型不进行限制，媒体文件可以是录音、照片、视频等各种类型的文件，也可以是混合媒体文件等。在本实施例中，对人物进行记录的方式包括但不限于对人物进行录音、拍摄照片或录制视频。在本实施例中，人物的特征包括但不限于用户的姓名、电话、声纹、脸部位图数据等。In this embodiment, the type of the media file is not limited. The media file may be various types of files such as a recording, a photo, a video, or the like, or may be a mixed media file or the like. In the present embodiment, the manner in which the person is recorded includes, but is not limited to, recording a character, taking a photo, or recording a video. In this embodiment, the characteristics of the person include, but are not limited to, the user's name, phone number, voice print, face part map data, and the like.
根据该至少一个人物的特征，生成媒体文件的备注信息。Remark information of the media file is generated according to the characteristics of the at least one character.
在本实施例中，在获取到人物的多个特征时，可以使用全部或部分特征生成备注信息。在本实施例中，对于生成备注信息的方式不进行限制，例如，获取到用户的姓名时，可以直接将用户姓名添加到照片的背景中形成背景信息，通过图像识别技术识别出餐馆标志时判断用户位于餐馆，则生成的备注信息可以是在餐馆吃饭。在本实施例中，备注信息可以在媒体文件打开时展示，包括播放录音、视频时作为字幕展示，打开照片时作为水印展示，可直接展示备注信息内容，也可展示备注信息的链接，点击链接后可查看备注信息内容。In this embodiment, when a plurality of features of the person are acquired, the note information may be generated using all or part of the features. In this embodiment, the manner of generating the remark information is not limited. For example, when the user's name is obtained, the user name may be directly added to the background of the photo to form background information, and the image identification technology is used to identify the restaurant logo. When the user is in a restaurant, the generated remark information can be eaten at a restaurant. In this embodiment, the remark information can be displayed when the media file is opened, including playing the recording and video as a subtitle display, and displaying the remark information directly when the photo is opened, and can also display the remark information link, and click the link. You can view the contents of the note information later.
在本实施例中，对于记录人物的媒体文件，人物是媒体文件的核心要素，人物的特征反应了媒体文件形成时与人物有关的信息，根据人物的特征生成备注信息，能够通过备注信息提示在媒体文件形成时该人物的活动，帮助用户回忆媒体文件形成时的场景。In the embodiment, for the media file of the recorded person, the character is the core element of the media file, and the character of the character reflects the information related to the character when the media file is formed, and generates the remark information according to the characteristics of the character, and can prompt the remark information by The activity of the character when the media file is formed helps the user to recall the scene when the media file is formed.
如图5所示，本发明的一个实施例中提供了一种移动终端，移动终端包括处理器510、存储器520和通信总线530；As shown in FIG. 5, an embodiment of the present invention provides a mobile terminal, where the mobile terminal includes a processor 510, a memory 520, and a communication bus 530;
通信总线530用于实现处理器510和存储器520之间的连接通信； Communication bus 530 is used to implement connection communication between processor 510 and memory 520;
处理器510用于执行存储器520中存储的媒体文件备注程序，以实现以下步骤：The processor 510 is configured to execute the media file remarking program stored in the memory 520 to implement the following steps:
识别媒体文件中至少一个人物的第一特征。Identifying a first feature of at least one character in the media file.
在本实施例中，第一特征是从媒体文件中能够直接识别出的特征，如录音中人物的声纹，照片中人物的脸部位图数据，视频中至少一帧画面中人物的脸部位图数据。In this embodiment, the first feature is a feature that can be directly recognized from the media file, such as a voiceprint of a character in a recording, a face map data of a character in the photo, and a face of the character in at least one frame of the video. Bitmap data.
根据该至少一个人物的第一特征，从预设的特征库中查找该至少一个人物的第二特征，该至少一个人物的特征包括第一特征和第二特征。And searching for a second feature of the at least one character from the preset feature library according to the first feature of the at least one character, the feature of the at least one character comprising the first feature and the second feature.
在本实施例中，第二特征是未在媒体文件中体现的特征，本实施例中对第二特征不进行限制，包括但不限于难以在媒体文件中体现的特征。在本实施例中，预设特征库对人物的特征进行存储，例如，对人物的姓名、电话等进行存储，则从媒体文件中识别出人物的脸部位图特征及声纹特征时，可以从特征库中找到该人物的其他特征，例如姓名、电话等，媒体库能够与根据从媒体文件中识别的特征进行匹配，为进一步检索其他特征提供了数据支持。In this embodiment, the second feature is a feature that is not embodied in the media file. The second feature is not limited in this embodiment, including but not limited to features that are difficult to be embodied in the media file. In this embodiment, the preset feature library stores the feature of the character, for example, storing the name, the phone, and the like of the character, and when the face part feature and the voiceprint feature of the character are recognized from the media file, Other features of the character, such as name, phone number, etc., are found from the feature library, and the media library can be matched with features identified from the media file to provide data support for further retrieval of other features.
根据上述第一特征和第二特征，获取该至少一个人物的行为记录。According to the first feature and the second feature described above, a behavior record of the at least one character is acquired.
在本实施例中，行为记录往往能够反映媒体文件的相关故事，能够形成对用户的提示。In this embodiment, the behavior record can often reflect the relevant story of the media file, and can form a prompt for the user.
在本实施例中，进一步地，根据媒体文件的录制时间确定时间范围，查找人物在时间范围内的行为记录。在本实施例中，除将人物特征作为查找行为记录外，还可以结合媒体文件的相关信息进行查找，媒体文件的相关信息包括但不限于媒体文件中自带的录制时间和位置信息等。在本实施例中，可以匹配媒体文件生成时间前后人物的行为记录，提取后作为生成备注信息的依据，这是因为该时间范围内人物的行为记录与媒体文件相关的信息一致性 较高，例如，某张照片记录了人物位于电影院，则可查询拍照当日该人物的行为记录，发现当日其订购了电影票，则可以基于该订购记录生成该人物的备注信息。In this embodiment, further, the time range is determined according to the recording time of the media file, and the behavior record of the character in the time range is searched for. In this embodiment, in addition to the character feature as the search behavior record, the related information of the media file may be searched for, and the related information of the media file includes but is not limited to the recording time and location information provided in the media file. In this embodiment, the behavior record of the person before and after the media file generation time can be matched, and is extracted as the basis for generating the remark information, because the behavior record of the character in the time range is consistent with the information related to the media file, for example, If a photo records that the character is located in the movie theater, the person can query the behavior record of the character on the day of photographing, and find that the movie ticket is ordered on the same day, and the remark information of the character can be generated based on the order record.
在本实施例中，人物的特征但不限于包括人物的联系方式、用于登录应用的账号、人物的活动区域，上述特征可记录在预设特征库中。在本实施例中，对查找行为记录的方式不进行限制，包括但不限于以下几种方式：In this embodiment, the characteristics of the character are not limited to the contact information including the person, the account number used to log in the application, and the active area of the character, and the above features may be recorded in the preset feature library. In this embodiment, the manner in which the behavior record is searched is not limited, including but not limited to the following methods:
(1)根据该至少一个人物的联系方式，查找该至少一个人物的联系记录作为人物的行为记录。(1) Find a contact record of the at least one character as a behavior record of the character according to the contact manner of the at least one character.
在本实施例中，人物的联系方式包括但不限于电话号码、邮箱地址、社交工具账号，则可以按电话号码查找对应的通话记录、短信，按邮箱地址查找对应的邮件内容，按社交账号查找对应的社交记录，通话记录、短信、邮件内容、社交记录均属于该人物的行为记录。In this embodiment, the contact information of the character includes, but is not limited to, a phone number, an email address, and a social tool account, and the phone number can be used to find a corresponding call record, a short message, and the corresponding email content is searched according to the email address, and the social account number is searched. Corresponding social records, call records, text messages, email content, and social records all belong to the person's behavior record.
(2)使用账号登录应用，从应用中查找该至少一个人物的行为记录。(2) Log in to the application using an account, and search for the behavior record of the at least one character from the application.
在本实施例中，对应用的类型进行限制，如果该应用是社交工具，则可以从社交工具中查找该人物对应的社交记录，如果该应用是金融理财应用，则可以从金融理财应用中查找该人物对应的投资理财记录，如果该应用是消费类应用，则可以从消费类应用中查找该人物购物、吃饭、看电影等消费记录，社交记录、投资理财记录、消费记录均属于该人物的行为记录。In this embodiment, the type of the application is restricted. If the application is a social tool, the social record corresponding to the character may be searched from the social tool, and if the application is a financial financial application, the financial management application may be searched. The investment financial management record corresponding to the character, if the application is a consumer application, the consumer application may be searched for consumption records such as shopping, eating, and watching movies, and the social record, the investment financial record, and the consumption record belong to the character. Behavior record.
(3)根据该至少一个人物所在的活动区域，确定该至少一个人物的行为记录。(3) determining a behavior record of the at least one character based on the activity area in which the at least one character is located.
在本实施例中，人物的活动区域可以从照片、视频等媒体文件中识别出来，或基于媒体文件对应的地理位置来查询该人物的活动区域，当活动区域为工作单位时，则行为记录为工作、加班等，当活动区域为电影院时，则行为记录为看电影等。In this embodiment, the active area of the character may be identified from a media file such as a photo or a video, or the active area of the character may be queried based on the geographic location corresponding to the media file. When the active area is a work unit, the behavior record is Work, overtime, etc. When the activity area is a movie theater, the behavior is recorded as watching a movie.
根据人物的行为记录，生成媒体文件的备注信息。Generates a comment of the media file based on the behavior record of the character.
根据本实施例的技术方案，通过对照片、录像中可识别的一些人物特征， 如人物脸部图像位图特征、拍摄时所处位置等要素，在用户常用的应用中去查找相关照片生成前后信息，并进行匹配和后续处理，扫描出的结果通过字幕、水印、链接等方式提供用户更丰富的照片背景信息，解决了目前的图片、视频等查看时信息单一的问题，使我们的影像文件充分发挥作用。According to the technical solution of the embodiment, by searching for some character features in the photo and the video, such as the character image of the face image of the person, the position of the face image, and the like, the related photos are searched in the application commonly used by the user. Information, and matching and subsequent processing, the scanned results provide users with richer photo background information through subtitles, watermarks, links, etc., which solves the problem of single information when viewing pictures, videos, etc., so that our image files fully utilize.
根据本实施例的技术方案的一个具体示例如下：A specific example of the technical solution according to the present embodiment is as follows:
预置特征库，存储联系人的多媒体特征、脸部位图、声纹、地理位置、通话记录、短信记录等，然后将联系人与各项特征关联；媒体文件在生成时，通过媒体文件识别出的特征(照片人脸，身份特征，拍照地点等)在特征库中进行检索，进一步检索其他特征；基于获取的特征生成备注信息，将媒体文件的备注信息与媒体文件进行关联展示，为用户查看照片、录像时参考，备注信息可以以水印，链接，字幕等方式进行展示。目前信息社会条件下，联系人再也不仅仅只是姓名、号码、单位、职称这些简单的信息，更是还有指纹、眼纹、声纹、脸部特征、活动区域、所在公司、活动轨迹等等，这些早已是联系人不可或缺的一部分。根据本实施例的技术方案，智能终端就可以将备注信息展现给用户了，用户便可以根据备注信息了解照片、录像生成时的背景。The preset feature library stores the multimedia features of the contact, the face part map, the voiceprint, the geographical location, the call record, the short message record, etc., and then associates the contact with each feature; when the media file is generated, the media file is identified The features (photo face, identity feature, photo location, etc.) are retrieved in the feature database to further retrieve other features; the remark information is generated based on the acquired features, and the remark information of the media file is associated with the media file for display. When viewing photos and videos, the remarks can be displayed in the form of watermarks, links, subtitles, etc. Under the current information society, contacts are no longer just simple information such as name, number, unit, and job title, but also fingerprints, eye lines, voice prints, facial features, activity areas, companies, activity tracks, etc. Etc. These are already an integral part of the contact. According to the technical solution of the embodiment, the smart terminal can present the remark information to the user, and the user can know the background of the photo and the video generation according to the remark information.
本发明的一个实施例中还提供了一种计算机可读存储介质，计算机可读存储介质存储有一个或者多个程序，一个或者多个程序可被一个或者多个处理器执行，以实现以下步骤：Also provided in an embodiment of the present invention is a computer readable storage medium storing one or more programs, one or more programs executable by one or more processors to implement the following steps :
获取媒体文件中至少一个人物的特征。Get the characteristics of at least one character in the media file.
在本实施例中，对媒体文件的类型不进行限制，媒体文件可以是录音、照片、视频等各种类型的文件，也可以是混合媒体文件等。在本实施例中，对人物进行记录的方式包括但不限于对人物进行录音、拍摄照片或录制视频。在本实施例中，人物的特征包括但不限于用户的姓名、电话、声纹、脸部位图数据等。In this embodiment, the type of the media file is not limited. The media file may be various types of files such as a recording, a photo, a video, or the like, or may be a mixed media file or the like. In the present embodiment, the manner in which the person is recorded includes, but is not limited to, recording a character, taking a photo, or recording a video. In this embodiment, the characteristics of the person include, but are not limited to, the user's name, phone number, voice print, face part map data, and the like.
根据该至少一个人物的特征，生成媒体文件的备注信息。Remark information of the media file is generated according to the characteristics of the at least one character.
在本实施例中，在获取到人物的多个特征时，可以使用全部或部分特征生成备注信息。在本实施例中，对于生成备注信息的方式不进行限制，例如，获取到用户的姓名时，可以直接将用户姓名添加到照片的背景中形成背景信息，通过图像识别技术识别出餐馆标志时判断用户位于餐馆，则生成的备注信息可以是在餐馆吃饭。在本实施例中，备注信息可以在媒体文件打开时展示，包括播放录音、视频时作为字幕展示，打开照片时作为水印展示，可直接展示备注信息内容，也可展示备注信息的链接，点击链接后可查看备注信息内容。In this embodiment, when a plurality of features of the person are acquired, the note information may be generated using all or part of the features. In this embodiment, the manner of generating the remark information is not limited. For example, when the user's name is obtained, the user name may be directly added to the background of the photo to form background information, and the image identification technology is used to identify the restaurant logo. When the user is in a restaurant, the generated remark information can be eaten at a restaurant. In this embodiment, the remark information can be displayed when the media file is opened, including playing the recording and video as a subtitle display, and displaying the remark information directly when the photo is opened, and can also display the remark information link, and click the link. You can view the contents of the note information later.
在本实施例中，对于记录人物的媒体文件，人物是媒体文件的核心要素，人物的特征反应了媒体文件形成时与人物有关的信息，根据人物的特征生成备注信息，能够通过备注信息提示在媒体文件形成时该人物的活动，帮助用户回忆媒体文件形成时的场景。In the embodiment, for the media file of the recorded person, the character is the core element of the media file, and the character of the character reflects the information related to the character when the media file is formed, and generates the remark information according to the characteristics of the character, and can prompt the remark information by The activity of the character when the media file is formed helps the user to recall the scene when the media file is formed.
根据以上技术方案，可知本发明的媒体文件备注方法、装置、移动终端和存储介质至少具有以下优点：According to the above technical solution, it is known that the media file remarking method, apparatus, mobile terminal and storage medium of the present invention have at least the following advantages:
根据本发明的技术方案，对于记录人物的媒体文件，人物是媒体文件的核心要素，人物的特征反应了媒体文件形成时与人物有关的信息，根据人物的特征生成备注信息，能够通过备注信息提示在媒体文件形成时该人物的活动，帮助用户回忆媒体文件形成时的场景。According to the technical solution of the present invention, for recording a media file of a person, the character is a core element of the media file, and the character of the character reflects information related to the character when the media file is formed, and generates remark information according to the feature of the character, and can prompt by the remark information. The character's activity when the media file is formed helps the user recall the scene when the media file is formed.
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过 程、方法、物品或者装置中还存在另外的相同要素。It is to be understood that the term "comprises", "comprising", or any other variants thereof, is intended to encompass a non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes those elements. It also includes other elements that are not explicitly listed, or elements that are inherent to such a process, method, article, or device. An element that is defined by the phrase "comprising a ..." does not exclude the presence of additional elements in the process, method, article, or device that comprises the element.
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。The serial numbers of the embodiments of the present invention are merely for the description, and do not represent the advantages and disadvantages of the embodiments.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本发明各个实施例所述的方法。Through the description of the above embodiments, those skilled in the art can clearly understand that the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better. Implementation. Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk, The optical disc includes a number of instructions for causing a terminal (which may be a cell phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present invention.
上面结合附图对本发明的实施例进行了描述，但是本发明并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本发明的启示下，在不脱离本发明宗旨和权利要求所保护的范围情况下，还可做出很多形式，这些均属于本发明的保护之内。The embodiments of the present invention have been described above with reference to the drawings, but the present invention is not limited to the specific embodiments described above, and the specific embodiments described above are merely illustrative and not restrictive, and those skilled in the art In the light of the present invention, many forms may be made without departing from the spirit and scope of the invention as claimed.

Claims (10)

  1. 一种媒体文件备注方法，其特征在于，包括：A media file remarking method, comprising:
    获取媒体文件中至少一个人物的特征；Obtaining characteristics of at least one character in the media file;
    根据该至少一个人物的特征，生成所述媒体文件的备注信息。Generating remark information of the media file according to characteristics of the at least one character.
  2. 根据权利要求1所述的方法，其特征在于，所述获取媒体文件中至少一个人物的特征，包括：The method according to claim 1, wherein the obtaining the feature of the at least one character in the media file comprises:
    识别所述媒体文件中包含的所述至少一个人物的第一特征；Identifying a first feature of the at least one character included in the media file;
    根据该至少一个人物的第一特征，从预设的特征库中查找该至少一个人物的第二特征。And searching for a second feature of the at least one character from the preset feature library according to the first feature of the at least one character.
  3. 根据权利要求1所述的方法，其特征在于，所述根据该至少一个人物的特征，生成所述媒体文件的备注信息，包括：The method according to claim 1, wherein the generating the remark information of the media file according to the feature of the at least one character comprises:
    根据该至少一个人物的特征，获取该至少一个人物的行为记录；Obtaining a behavior record of the at least one character according to characteristics of the at least one character;
    基于该至少一个人物的行为记录，生成所述媒体文件的备注信息。Remark information of the media file is generated based on the behavior record of the at least one character.
  4. 根据权利要求3所述的方法，其特征在于，该至少一个人物的特征包括该至少一个人物的联系方式，所述根据该至少一个人物的特征，获取该至少一个人物的行为记录，包括：The method according to claim 3, wherein the feature of the at least one character comprises a contact manner of the at least one character, and the obtaining the behavior record of the at least one character according to the feature of the at least one character comprises:
    根据该至少一个人物的联系方式，查找该至少一个人物的联系记录作为该至少一个人物的行为记录。And searching for the contact record of the at least one character as a behavior record of the at least one character according to the contact manner of the at least one character.
  5. 根据权利要求3所述的方法，其特征在于，该至少一个人物的特征包括该至少一个人物用于登录应用的账号，所述根据该至少一个人物的特征， 获取该至少一个人物的行为记录，包括：The method according to claim 3, wherein the feature of the at least one character comprises an account number of the at least one character for logging in to the application, and the behavior record of the at least one character is obtained according to a feature of the at least one character, include:
    使用所述账号登录所述应用，从所述应用中查找该至少一个人物的行为记录。Logging in to the application using the account, and searching for the behavior record of the at least one character from the application.
  6. 根据权利要求3所述的方法，其特征在于，该至少一个人物的特征包括该至少一个人物的活动区域，所述根据该至少一个人物的特征，获取该至少一个人物的行为记录，包括：The method according to claim 3, wherein the feature of the at least one character comprises an activity area of the at least one character, and the obtaining the behavior record of the at least one character according to the feature of the at least one character comprises:
    根据该至少一个人物的活动区域，确定该至少一个人物的行为记录。A behavior record of the at least one character is determined based on an activity area of the at least one character.
  7. 根据权利要求3所述的方法，其特征在于，所述获取该至少一个人物的行为记录，包括：The method according to claim 3, wherein the obtaining a behavior record of the at least one character comprises:
    根据所述媒体文件的录制时间确定时间范围，查找该至少一个人物在所述时间范围内的行为记录。Determining a time range according to a recording time of the media file, and searching for a behavior record of the at least one character within the time range.
  8. 一种媒体文件备注装置，其特征在于，包括：A media file remarking device, comprising:
    特征获取模块，获取媒体文件中至少一个人物的特征；a feature acquisition module, acquiring characteristics of at least one character in the media file;
    备注生成模块，根据该至少一个人物的特征，生成所述媒体文件的备注信息。a memo generating module that generates remark information of the media file according to characteristics of the at least one character.
  9. 一种移动终端，其特征在于，所述移动终端包括处理器、存储器和通信总线；A mobile terminal, characterized in that the mobile terminal comprises a processor, a memory and a communication bus;
    所述通信总线用于实现处理器和存储器之间的连接通信；The communication bus is used to implement connection communication between a processor and a memory;
    所述处理器用于执行存储器中存储的媒体文件备注程序，以实现权利要求1至7中任一项所述的媒体文件备注方法的步骤。The processor is configured to execute a media file remarking program stored in the memory to implement the steps of the media file remarking method according to any one of claims 1 to 7.
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质 存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现权利要求1至7中任一项所述的媒体文件备注方法的步骤。A computer readable storage medium, characterized in that the computer readable storage medium stores one or more programs, the one or more programs being executable by one or more processors to implement claim 1 The step of the media file remarking method according to any one of the items 7.
PCT/CN2019/083714 2018-04-27 2019-04-22 Media file remarking method, apparatus, mobile terminal and storage medium WO2019206090A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810393790.2 2018-04-27
CN201810393790.2A CN110413802A (en) 2018-04-27 2018-04-27 Media file remarks method, apparatus, mobile terminal and storage medium

Publications (1)

Publication Number Publication Date
WO2019206090A1 true WO2019206090A1 (en) 2019-10-31

Family

ID=68294394

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/083714 WO2019206090A1 (en) 2018-04-27 2019-04-22 Media file remarking method, apparatus, mobile terminal and storage medium

Country Status (2)

Country Link
CN (1) CN110413802A (en)
WO (1) WO2019206090A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011065255A (en) * 2009-09-15 2011-03-31 Sharp Corp Data processing apparatus, data name generation method and computer program
CN102202173A (en) * 2010-03-23 2011-09-28 三星电子（中国）研发中心 Photo automatically naming method and device thereof
CN103186557A (en) * 2011-12-28 2013-07-03 宇龙计算机通信科技(深圳)有限公司 Method and device for automatically naming sound record or video files
CN103259915A (en) * 2012-02-20 2013-08-21 宇龙计算机通信科技(深圳)有限公司 Photo naming method and mobile terminal
CN103544721A (en) * 2013-10-30 2014-01-29 宇龙计算机通信科技(深圳)有限公司 Method and system for adding remark into picture and mobile terminal

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9509795B2 (en) * 2007-07-20 2016-11-29 Broadcom Corporation Method and system for tagging data with context data tags in a wireless system
CN101442704A (en) * 2007-07-20 2009-05-27 美国博通公司 Method and system for processing data in a wireless system
CN103677231A (en) * 2012-09-14 2014-03-26 邓巍 Mobile terminal for annotating photo and photo annotating method
CN103167167B (en) * 2013-02-01 2015-07-01 深圳市金立通信设备有限公司 Mobile terminal and extraction method of communication contact person information
US9953086B2 (en) * 2014-07-15 2018-04-24 Microsoft Technology Licensing, Llc Prioritizing media based on social data and user behavior
CN105100407A (en) * 2015-05-26 2015-11-25 努比亚技术有限公司 Method and device for automatically remarking contact
CN105320407A (en) * 2015-11-12 2016-02-10 上海斐讯数据通信技术有限公司 Pictured people social moment information acquisition method and apparatus

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011065255A (en) * 2009-09-15 2011-03-31 Sharp Corp Data processing apparatus, data name generation method and computer program
CN102202173A (en) * 2010-03-23 2011-09-28 三星电子（中国）研发中心 Photo automatically naming method and device thereof
CN103186557A (en) * 2011-12-28 2013-07-03 宇龙计算机通信科技(深圳)有限公司 Method and device for automatically naming sound record or video files
CN103259915A (en) * 2012-02-20 2013-08-21 宇龙计算机通信科技(深圳)有限公司 Photo naming method and mobile terminal
CN103544721A (en) * 2013-10-30 2014-01-29 宇龙计算机通信科技(深圳)有限公司 Method and system for adding remark into picture and mobile terminal

Also Published As

Publication number Publication date
CN110413802A (en) 2019-11-05

Similar Documents

Publication Publication Date Title
US8396246B2 (en) Tagging images with labels
US8867779B2 (en) Image tagging user interface
JP6349031B2 (en) Method and apparatus for recognition and verification of objects represented in images
CN105144156B (en) Metadata is associated with the image in personal images set
CN103119595B (en) Shared by the automatic media hitting by shutter
US20150139508A1 (en) Method and apparatus for storing and retrieving personal contact information
US20140304019A1 (en) Media capture device-based organization of multimedia items including unobtrusive task encouragement functionality
CN104519267A (en) Shooting control method and terminal equipment
US20180025215A1 (en) Anonymous live image search
US20130132393A1 (en) Method and system for displaying activities of friends and computer storage medium therefor
US20140293069A1 (en) Real-time image classification and automated image content curation
WO2013189317A1 (en) Human face information-based multimedia interaction method, device and terminal
US10769196B2 (en) Method and apparatus for displaying electronic photo, and mobile device
US10157190B2 (en) Image action based on automatic feature extraction
US9081801B2 (en) Metadata supersets for matching images
CN111491209A (en) Video cover determining method and device, electronic equipment and storage medium
WO2019062705A1 (en) Information output method and apparatus and electronic device
CN113568934A (en) Data query method and device, electronic equipment and storage medium
WO2018223997A1 (en) Method and apparatus for collecting and organising information
WO2021017277A1 (en) Image capture method and apparatus, and computer storage medium
WO2019206090A1 (en) Media file remarking method, apparatus, mobile terminal and storage medium
CN109427017A (en) A kind of reminding method and device
CN106251119A (en) A kind of event witness method and system
CN108418943A (en) The event recording method and device of address book contact
US20170109351A1 (en) Stateful tags

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19793416

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 11.03.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19793416

Country of ref document: EP

Kind code of ref document: A1