WO2017162158A1 - Method and apparatus for recommending data - Google Patents

Method and apparatus for recommending data Download PDF

Info

Publication number
WO2017162158A1
WO2017162158A1 PCT/CN2017/077618 CN2017077618W WO2017162158A1 WO 2017162158 A1 WO2017162158 A1 WO 2017162158A1 CN 2017077618 W CN2017077618 W CN 2017077618W WO 2017162158 A1 WO2017162158 A1 WO 2017162158A1
Authority
WO
WIPO (PCT)
Prior art keywords
audio segment
segment data
multimedia
data
target terminal
Prior art date
Application number
PCT/CN2017/077618
Other languages
French (fr)
Inventor
Ke Zhou
Original Assignee
Le Holdings (Beijing) Co., Ltd.
Le Shi Internet Information & Technology Corp., Beijing
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 Le Holdings (Beijing) Co., Ltd., Le Shi Internet Information & Technology Corp., Beijing filed Critical Le Holdings (Beijing) Co., Ltd.
Publication of WO2017162158A1 publication Critical patent/WO2017162158A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44213Monitoring of end-user related data
    • H04N21/44222Analytics of user selections, e.g. selection of programs or purchase activity
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/233Processing of audio elementary streams
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866Management of end-user data
    • H04N21/25891Management of end-user data being end-user preferences
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/482End-user interface for program selection
    • H04N21/4826End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/65Transmission of management data between client and server
    • H04N21/658Transmission by the client directed to the server
    • H04N21/6582Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number

Definitions

  • the present disclosure relates to the field of data processing, and particularly to a method and apparatus for recommending data.
  • a broadband access to the Internet has become increasingly widespread at home along with the rapid development of network technologies so that it has become common to watch TV programs, movies, and other multimedia programs over the Internet as our entertainment at home.
  • the multimedia programs are watched on smart devices, e.g., smart TV sets, smart mobile phones, tablet computers, PCs, etc., over the Internet typically using their corresponding applications.
  • the providers of the smart devices may monitor when and which applications are run on the smart devices, but the providers cannot be provided with program watching records and other data of users, so that the providers cannot obtain a statistic of the program watching records and other data of the users, and consequently cannot recommend contents that are consistent with interests and hobbies of the users to the corresponding smart devices according to the records of the multimedia programs watched by the users on the smart devices.
  • the present disclosure is to provide a method, apparatus and non-transitory computer readable medium for recommending data.
  • the present disclosure provides a method for recommending data.
  • the method is applicable to the network server side and may include: obtaining constantly audio segment data detected by a target terminal; comparing each piece of the audio segment data with audios in pre-stored multimedia files, and obtaining a multimedia file matching with each piece of the audio segment data; obtaining file information of the multimedia file successfully matched in a preset period of time; obtaining an interest feature of the target terminal by analyzing the file information obtained in the preset period of time; and extracting and pushing to the target terminal a multimedia file matching with the interest feature of the target terminal.
  • the step of comparing each piece of the audio segment data with the audios in the pre-stored multimedia files, and obtaining the multimedia file matching with each piece of the audio segment data may include: separating multimedia audio data from the pre-stored multimedia files; comparing the audio segment data with audios in the multimedia audio data, and obtaining multimedia audio data matching with the audio segment data; and obtaining a corresponding multimedia file according to the multimedia audio data matching with the audio segment data.
  • the multimedia files may include movies, music, and/or teleplays; and after the step of comparing each piece of the audio segment data with audios in pre-stored multimedia files, and obtaining a multimedia file matching with each piece of the audio segment data, the method may further include: determining whether the number of the multimedia files matching with the audio segment data is more than or equal to 2; if the number of the multimedia files matching with the audio segment data is more than or equal to 2, then obtaining new audio segment data detected by the target terminal; matching the new audio segment data together with the audio segment data with the pre-stored multimedia files, and obtaining a new multimedia file matching with both the new audio segment data and the audio segment data; determining whether the number of the new multimedia files is more than or equal to 2; and if the number of the new multimedia files is 1, then replacing the new multimedia file with the multimedia file matching with the audio segment data.
  • the step of obtaining the interest feature of the target terminal by analyzing the file information obtained in the preset period of time includes: obtaining corresponding category information and tag information by analyzing the file information obtained in each of the preset period of time; assigning the corresponding category information and tag information with weights varying with time when the file information is obtained; and obtaining the interest feature of the target terminal by calculating with reference to the category information and the tag information in the file information obtained in the preset period of time and the corresponding weights.
  • the method before the step of obtaining constantly the audio segment data detected by the target terminal, the method further includes: obtaining key audio segment data by parsing the pre-stored multimedia files; and associating the key audio segment data with key picture and text information; and after the step of obtaining constantly audio segment data detected by a target terminal, the method may further include: determining whether the audio segment data match with the key audio segment data; and if the audio segment data match with the key audio segment data, then pushing the key picture and text information associated with the key audio segment data to the target terminal.
  • the apparatus may include: an audio segment data obtaining module configured to obtain constantly audio segment data detected by a target terminal; amultimedia file matching module configured to compare each piece of the audio segment data with audios in pre-stored multimedia files, and to obtain a multimedia file matching with each piece of the audio segment data; a file information obtaining module configured to obtain file information of the multimedia file successfully matched in a preset period of time; an interest feature analyzing module configured to obtain an interest feature of the target terminal by analyzing the file information obtained in the preset period of time; and a multimedia file pushing module configured to extract and push to the target terminal a multimedia file matching with the interest feature of the target terminal.
  • the multimedia file matching module is configured to: separate multimedia audio data from the pre-stored multimedia files; compare the audio segment data with audios in the multimedia audio data, and to obtain multimedia audio data matching with the audio segment data; and obtain a corresponding multimedia file according to the multimedia audio data matching with the audio segment data.
  • the multimedia files may include movies, music, and/or teleplays; and the multimedia file matching module is further configured to: determine whether the number of the multimedia files matching with the audio segment data is more than or equal to 2; if the number of the multimedia files matching with the audio segment data is more than or equal to 2, obtain new audio segment data detected by the target terminal; match the new audio segment data together with the audio segment data with the pre-stored multimedia files, and obtain a new multimedia file matching with both the new audio segment data and the audio segment data; determine whether the number of the new multimedia files is more than or equal to 2; and if the number of the new multimedia files is 1, replace the new multimedia file with the multimedia file matching with the audio segment data.
  • the interest feature analyzing module is configured to: obtain corresponding category information and tag information by analyzing the file information obtained in each of the preset period of time; assign the corresponding category information and tag information with weights varying with time when the file information is obtained; and obtain the interest feature of the target terminal by calculating with reference to the category information and the tag information in the file information obtained in the preset period of time and the corresponding weights.
  • the apparatus may further include: a key audio segment parsing module configured to obtain key audio segment data by parsing the pre-stored multimedia files; a picture and text information associating module configured to associate the key audio segment data with key picture and text information; a key audio segment matching module configured to determine whether the audio segment data match with the key audio segment data; and a picture and text information pushing module configured, if the audio segment data match with the key audio segment data, to push the key picture and text information associated with the key audio segment data to the target terminal.
  • a key audio segment parsing module configured to obtain key audio segment data by parsing the pre-stored multimedia files
  • a picture and text information associating module configured to associate the key audio segment data with key picture and text information
  • a key audio segment matching module configured to determine whether the audio segment data match with the key audio segment data
  • a picture and text information pushing module configured, if the audio segment data match with the key audio segment data, to push the key picture and text information associated with the key audio segment data to the target terminal.
  • the present disclosure provides an electronic device for recommending data.
  • the electronic device may include: at least one processor; and a memory communicably connected with the at least one processor for storing instructions executable by the at least one processor, wherein execution of the instructions by the at least one processor causes the at least one processor to perform a method according to any methods disclosed herein.
  • the present disclosure provides a non-transitory computer-readable storage medium storing executable instructions for recommending data.
  • the instructions when executed by an electronic device, may cause the electronic device to perform a method according to any methods disclosed herein.
  • the present disclosure provides a computer program product for recommending data.
  • the computer program product may include a computer program stored on a non-transitory computer-readable storage medium.
  • the computer program may include program code which, when executed on a computer, may cause the computer to perform a method according to any methods disclosed herein.
  • Fig. 1 is a schematic flow chart of a method for recommending data according to an embodiment of the present disclosure
  • Fig. 2 is a schematic flow chart of a method for recommending data according to another embodiment of the disclosure
  • Fig. 3 is a schematic structural diagram of modules in an apparatus for recommending data according to an embodiment of the disclosure.
  • Fig. 4 illustrates a storage medium processing apparatus.
  • the present disclosure is to provide a method and apparatus for recommending data so as to recommend data that meet the interest feature of the target terminal to the target terminal, and the recommended data are more satisfactory.
  • the method and apparatus for recommending data obtain constantly the audio segment data detected by the target terminal, obtain the multimedia file corresponding to the audio segment data as a result of audio comparison, obtain the corresponding file information, analyze the file information in the preset period of time for the interest feature of the target terminal, and recommend the multimedia file to the target terminal according to the interest feature, so that pertinent multimedia file can be recommended to the target terminal instead of some of the latest and the most popular interest features generally recommended, to thereby improve the favor of the user, and optimize the experience of the user.
  • a method for recommending data wherein the method can recommend data that meet the interest feature of the target terminal to the target terminal and the recommended data are more satisfactory.
  • Fig. 1 illustrates a schematic flow chart of a method for recommending data according to an embodiment of the disclosure.
  • the method for recommending data is applicable to the network server side and includes:
  • the step 101 is to obtain constantly audio segment data detected by a target terminal
  • the audio segment data detected by a target terminal refer to audio segment data detected and uploaded in real time by the target terminal to the network server side, and at this time, the target terminal needs to be provided therein accordingly with an audio acquiring module configured to detect the audio generated in the target terminal, where the audio generated in the target terminal refers to an audio carried in a multimedia program being played by the target terminal, that is, the audio of the current multimedia program can be acquired in real time even if the audio is mute; and the audio segment data here can be audio segment data detected at a preset acquisition interval of time and frequency; for example, the length of time of the audio segment data ranges from 15 to 30 seconds, the acquisition interval of time of each piece of audio segment data ranges from 0 to 30 seconds, etc. ;
  • the step 102 is to compare each piece of the audio segment data with audios in pre-stored multimedia files, and to obtain a multimedia file matching with each piece of the audio segment data, where the pre-stored multimedia files can be all the multimedia files pre-stored in a database at the network server side, or can be pre-filtered multimedia files for audio comparison stored in a folder in the database;
  • Audio comparison here can be the comparison of the audio segment data with the audio carried in the multimedia files, i.e., direct comparison of the audio segment data with the audio carried in the multimedia files without any conversion of the audio segment data into data in another format, e.g., a text;
  • the step 103 is to obtain file information of the multimedia file successfully matched in a preset period of time, wherein the preset period of time is a preset interval of time for extracting the file information, e.g., the last half of a month, the last month, the last quarter, etc., where the operation of the step 103 can be triggered by restarting the disabled target terminal, and at this time, the target terminal sends a recommended content obtainment instruction to the network server side so that the network server side obtains file information of the multimedia file successfully matched in the preset period of time in order to recommend contents to the target terminal;
  • the preset period of time is a preset interval of time for extracting the file information, e.g., the last half of a month, the last month, the last quarter, etc.
  • the file information of the multimedia file can include but will not be limited to the filename, creation time, showing time, length of time, level-1 category information, level-2 category information, atag preset by the operator, a tag preset by a user, etc;
  • the step 104 is to obtain an interest feature of the target terminal by analyzing the file information obtained in the preset period of time, where the file information in the preset period of time is obtained so that a historical record of watching on the target terminal in the preset period of time is obtained, and the file information can be analyzed accordingly for the interest feature representing a habit of watching on the target terminal in the preset period of time;
  • the step 105 is to extract and push to the target terminal a multimedia file matching with the interest feature of the target terminal from the pre-stored multimedia files, where the pushed multimedia file can include watching paths and preview pictures of pushed multimedia data so that the preview pictures are presented on a screen of the target terminal, and if a corresponding preview picture is clicked on, then corresponding data will be retrieved and watched over a watching path associated with the preview picture.
  • the method for recommending data obtains constantly the audio segment data detected by the target terminal, obtains the multimedia file corresponding to the audio segment data as a result of audio comparison, obtains the corresponding file information, analyzes the file information in the preset period of time for the interest feature of the target terminal, and recommends the multimedia file to the target terminal according to the interest feature, so that pertinent multimedia file can be recommended to the target terminal instead of some of the latest and the most popular interest features generally recommended, to thereby improve the favor of the user, and optimize the experience of the user.
  • the step 102 of comparing each piece of the audio segment data with the audios in the pre-stored multimedia files, and obtaining the multimedia file matching with each piece of the audio segment data further includes the following steps:
  • multimedia audio data are the audio components in the multimedia files, and the multimedia audio data can be obtained from the multimedia files by separating the audio from the multimedia file, although a detailed description thereof will be omitted here;
  • the audio segment data can be matched as a result of direct audio comparison without being converted into other data to thereby dispense with the steps of data conversion, and achieve higher accuracy.
  • the multimedia files include movies, music, and/or teleplays, and even advertisements.
  • the method further includes the followings steps:
  • the new audio segment data can be the next piece of audio segment data immediately succeeding to the audio segment data; and of course, the new audio segment data can alternatively be a still next audio segment data succeeding to the audio segment data, etc., as long as a matching result can be obtained;
  • the step 104 of obtaining an interest feature of the target terminal by analyzing the file information obtained in the preset period of time further includes the following steps:
  • the category information can include but will not be limited to level-1 category information and level-2 category information of the multimedia file
  • the tag information can include but will not be limited to a tag preset by the operator of the multimedia file, a tag preset for the multimedia file by a user, etc. ;
  • the interest feature can be a function of the category information and the tag information which is respective parameters with a feature vector of their weights so that data can be subsequently recommended based upon the interest feature by matching directly the feature vector with the feature vectors of the multimedia files to thereby obtain the matching multimedia file.
  • the method before the step 101 of obtaining constantly audio segment data detected by a target terminal, the method further includes the following steps:
  • the method further includes the following steps:
  • the key audio segment data refer to audio segment data, appearing at one or more positions in the multimedia file, which can be associated with the key picture and text information
  • the audio segment data acquired at this time will exactly match with the key audio segment data so that the network server side is triggered to push the key picture and text information associated with the key audio segment data to the target terminal
  • the key picture and text information can be a segment of video, a segment of music, a segment of animation, a segment of advertisement, etc.
  • the key audio segment data and the associated key picture and text information are set so that if the audio segment data matching with the key audio segment data appear in the multimedia file being watched on the target terminal, then some key picture and text information which may be interesting to the user or can improve the favor of the user can be pushed to the user, so that the watching user will not feel dull and tired, and can be provided with additional information.
  • FIG. 2 illustrates a schematic flow chart of a method for recommending data according to another embodiment of the disclosure.
  • the method for recommending data, applicable to the network server side includes:
  • the step 201 is to obtaining key audio segment data by parsing pre-stored multimedia files
  • the step 202 is to associate the key audio segment data with key picture and text information
  • the step 203 is to obtain constantly audio segment data detected by a target terminal
  • the step 204 is to determine whether the audio segment data match with the key audio segment data
  • the step 205 is, if the audio segment data match with the key audio segment data, to push the key picture and text information associated with the key audio segment data to the target terminal;
  • the step 206 is to compare each piece of the audio segment data with audios in the pre-stored multimedia files, and to obtain a multimedia file matching with each piece of the audio segment data;
  • the step 207 is to determine whether the number of the multimedia files matching with the audio segment data is more than or equal to 2;
  • the step 208 is, if the number of the multimedia files matching with the audio segment data is more than or equal to 2, to obtain new audio segment data detected by the target terminal;
  • the step 209 is to match the new audio segment data together with the audio segment data with the pre-stored multimedia files, and to obtain a new multimedia file matching with both the new audio segment data and the audio segment data;
  • the step 210 is to determine whether the number of the new multimedia files is more than or equal to 2;
  • the step 211 is, if the number of the new multimedia files is 1, to replace the new multimedia file with the multimedia file matching with the audio segment data;
  • the step 212 is, if the number of the new multimedia files is more than or equal to 2, to return to the step 208;
  • the step 213 is to obtain file information of the multimedia file successfully matched in a preset period of time
  • the step 214 is to obtain an interest feature of the target terminal by analyzing the file information obtained in the preset period of time;
  • the step 215 is to extract and push to the target terminal a multimedia file matching with the interest feature of the target terminal from the pre-stored multimedia files.
  • the method for recommending data obtains constantly the audio segment data detected by the target terminal, obtains the multimedia file corresponding to the audio segment data as a result of audio comparison, obtains the corresponding file information, analyzes the file information in the preset period of time for the interest feature of the target terminal, and recommends the multimedia file to the target terminal according to the interest feature, so that pertinent multimedia file can be recommended to the target terminal instead of some of the latest and the most popular interest features generally recommended, to thereby improve the favor of the user, and optimize the experience of the user.
  • Fig. 3 illustrates a schematic structural diagram of modules in an apparatus for recommending data according to an embodiment of the disclosure.
  • the apparatus for recommending data includes:
  • an audio segment data obtaining module 301 configured to obtain constantly audio segment data detected by a target terminal
  • the audio segment data detected by a target terminal refer to audio segment data detected and uploaded in real time by the target terminal to the network server side, and at this time, the target terminal needs to be provided therein accordingly with an audio acquiring module configured to detect the audio generated in the target terminal, where the audio generated in the target terminal refers to an audio carried in a multimedia program being played by the target terminal, that is, the audio of the current multimedia program can be acquired in real time even if the audio is mute; and the audio segment data here can be audio segment data detected at a preset acquisition interval of time and frequency; for example, the length of time of the audio segment data ranges from 15 to 30 seconds, the acquisition interval of time of each piece of audio segment data ranges from 0 to 30 seconds, etc. ;
  • a multimedia file matching module 302 configured to compare each piece of the audio segment data with audios in pre-stored multimedia files, and to obtain a multimedia file matching with each piece of the audio segment data, where the pre-stored multimedia files can be all the multimedia files pre-stored in a database at the network server side, or can be pre-filtered multimedia files for audio comparison stored in a folder in the database;
  • audio comparison here can be the comparison of the audio segment data with the audio carried in the multimedia files, i.e., direct comparison of the audio segment data with the audio carried in the multimedia files without any conversion of the audio segment data into data in another format, e.g., a text;
  • a file information obtaining module 303 configured to obtain file information of the multimedia file successfully matched in a preset period of time, wherein the preset period of time is a preset interval of time for extracting the file information, e.g., the last half of a month, the last month, the last quarter, etc., where file information obtaining module 303 can be triggered by restarting the disabled target terminal, and at this time, the target terminal sends a recommended content obtainment instruction to the network server side so that the network server side obtains file information of the multimedia file successfully matched in the preset period of time in order to recommend contents to the target terminal;
  • the file information of the multimedia file can include but will not be limited to the filename, creation time, showing time, length of time, level-1 category information, level-2 category information, atag preset by the operator, a tag preset by a user, etc;
  • an interest feature analyzing module 304 configured to obtain an interest feature of the target terminal by analyzing the file information obtained in the preset period of time, where the file information in the preset period of time is obtained so that a historical record of watching on the target terminal in the preset period of time is obtained, and the file information can be analyzed accordingly for the interest feature representing a habit of watching on the target terminal in the preset period of time;
  • a multimedia file pushing module 305 configured to extract and push to the target terminal a multimedia file matching with the interest feature of the target terminal, where the pushed multimedia file can include watching paths and preview pictures of pushed multimedia data so that the preview pictures are presented on a screen of the target terminal, and if a corresponding preview picture is clicked on, then corresponding data will be retrieved and watched over a watching path associated with the preview picture.
  • the apparatus for recommending data obtains constantly the audio segment data detected by the target terminal, obtains the multimedia file corresponding to the audio segment data as a result of audio comparison, obtains the corresponding file information, analyzes the file information in the preset period of time for the interest feature of the target terminal, and recommends the multimedia file to the target terminal according to the interest feature, so that pertinent multimedia file can be recommended to the target terminal instead of some of the latest and the most popular interest features generally recommended, to thereby improve the favor of the user, and optimize the experience of the user.
  • the multimedia file matching module 302 is configured:
  • multimedia audio data are the audio components in the multimedia files
  • multimedia audio data can be obtained from the multimedia files by separating the audio from the multimedia file, although a detailed description thereof will be omitted here;
  • the audio segment data can be matched as a result of direct audio comparison without being converted into other data to thereby dispense with the steps of data conversion, and achieve higher accuracy.
  • the multimedia files include movies, music, and/or teleplays, and even advertisements.
  • multimedia file matching module 302 is further configured:
  • the new audio segment data can be the next piece of audio segment data immediately succeeding to the audio segment data; and of course, the new audio segment data can alternatively be a still next audio segment data succeeding to the audio segment data, etc., as long as a matching result can be obtained;
  • the interest feature analyzing module 304 is configured:
  • the category information can include but will not be limited to level-1 category information and level-2 category information of the multimedia file
  • the tag information can include but will not be limited to a tag preset by the operator of the multimedia file, a tag preset for the multimedia file by a user, etc. ;
  • the interest feature can be a function of the category information and the tag information which is respective parameters with a feature vector of their weights so that data can be subsequently recommended based upon the interest feature by matching directly the feature vector with the feature vectors of the multimedia files to thereby obtain the matching multimedia file.
  • the apparatus for recommending data further includes:
  • a key audio segment parsing module 306 configured to obtain key audio segment data byparsing the pre-stored multimedia files
  • a picture and text information associating module 307 configured to associate the key audio segment data with key picture and text information
  • a key audio segment matching module 308 configured to determine whether the audio segment data match with the key audio segment data
  • a picture and text information pushing module 309 configured, if the audio segment data match with the key audio segment data, to push the key picture and text information associated with the key audio segment data to the target terminal;
  • the key audio segment data refer to audio segment data, appearing at one or more positions in the multimedia file, which can be associated with the key picture and text information
  • the audio segment data acquired at this time will exactly match with the key audio segment data so that the network server side is triggered to push the key picture and text information associated with the key audio segment data to the target terminal
  • the key picture and text information can be a segment of video, a segment of music, a segment of animation, a segment of advertisement, etc.
  • the key audio segment data and the associated key picture and text information are set so that if the audio segment data matching with the key audio segment data appear in the multimedia file being watched on the target terminal, then some key picture and text information which may be interesting to the user or can improve the favor of the user can be pushed to the user, so that the watching user will not feel dull and tired, and can be provided with additional information.
  • Fig. 4 illustrates a storage medium processing apparatus.
  • the storage medium processing apparatus includes a central processing unit (CPU) 71, a storage medium 72, and a bus 73 that connects the CPU 71 and the storage medium 72.
  • the storage medium 72 may store the computer executable instructions. When the computer executable instructions are executed by the CPU 71, the apparatus may perform the methods disclosed in this disclosure.
  • DRAM dynamic RAM
  • the present disclosure may include dedicated hardware implementations such as application specific integrated circuits, programmable logic arrays and other hardware devices.
  • the hardware implementations can be constructed to implement one or more of the methods described herein.
  • Applications that may include the apparatus and systems of various examples can broadly include a variety of electronic and computing systems.
  • One or more examples described herein may implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through the modules, or as portions of an application-specific integrated circuit.
  • the computing system disclosed may encompass software, firmware, and hardware implementations.
  • the terms "module, " "sub-module, " "unit, " or “sub-unit” may include memory (shared, dedicated, or group) that stores code or instructions that can be executed by one or more processors.

Abstract

The disclosure discloses a method and apparatus for recommending data, the method includes: obtaining constantly audio segment data detected by a target terminal; comparing each piece of the audio segment data with audios in pre-stored multimedia files, and obtaining a multimedia file matching with each piece of the audio segment data; obtaining file information of the multimedia file successfully matched in a preset period of time; obtaining an interest feature of the target terminal by analyzing the file information obtained in the preset period of time; and extracting and pushing to the target terminal a multimedia file matching with the interest feature of the target terminal.

Description

METHOD AND APPARATUS FOR RECOMMENDING DATA
CROSS REFERENCE
This application claims priority to Chinese Patent Application No. 2016101689294, filed on March 23, 2016, entitled “METHOD AND APPARATUS FOR RECOMMENDING DATA” , which is incorporated herein by reference in its entirety.
TECHNICAL FIELD
The present disclosure relates to the field of data processing, and particularly to a method and apparatus for recommending data.
BACKGROUND
A broadband access to the Internet has become increasingly widespread at home along with the rapid development of network technologies so that it has become common to watch TV programs, movies, and other multimedia programs over the Internet as our entertainment at home.
The multimedia programs are watched on smart devices, e.g., smart TV sets, smart mobile phones, tablet computers, PCs, etc., over the Internet typically using their corresponding applications. The providers of the smart devices may monitor when and which applications are run on the smart devices, but the providers cannot be provided with program watching records and other data of users, so that the providers cannot obtain a statistic of the program watching records and other data of the users, and consequently cannot recommend contents that are consistent with interests and hobbies of the users to the corresponding smart devices according to the records of the multimedia programs watched by the users on the smart devices.
SUMMARY
The present disclosure is to provide a method, apparatus and non-transitory computer readable medium for recommending data.
The present disclosure provides a method for recommending data. The method is applicable to the network server side and may include: obtaining constantly audio segment data detected by a target terminal; comparing each piece of the audio segment data with audios in pre-stored multimedia files, and obtaining a multimedia file matching with each piece of the audio segment data; obtaining file information of the multimedia file successfully matched in a preset period of time; obtaining an interest feature of the target terminal by analyzing the file  information obtained in the preset period of time; and extracting and pushing to the target terminal a multimedia file matching with the interest feature of the target terminal.
In some embodiments, the step of comparing each piece of the audio segment data with the audios in the pre-stored multimedia files, and obtaining the multimedia file matching with each piece of the audio segment data may include: separating multimedia audio data from the pre-stored multimedia files; comparing the audio segment data with audios in the multimedia audio data, and obtaining multimedia audio data matching with the audio segment data; and obtaining a corresponding multimedia file according to the multimedia audio data matching with the audio segment data.
In some embodiments, the multimedia files may include movies, music, and/or teleplays; and after the step of comparing each piece of the audio segment data with audios in pre-stored multimedia files, and obtaining a multimedia file matching with each piece of the audio segment data, the method may further include: determining whether the number of the multimedia files matching with the audio segment data is more than or equal to 2; if the number of the multimedia files matching with the audio segment data is more than or equal to 2, then obtaining new audio segment data detected by the target terminal; matching the new audio segment data together with the audio segment data with the pre-stored multimedia files, and obtaining a new multimedia file matching with both the new audio segment data and the audio segment data; determining whether the number of the new multimedia files is more than or equal to 2; and if the number of the new multimedia files is 1, then replacing the new multimedia file with the multimedia file matching with the audio segment data.
In some embodiments, the step of obtaining the interest feature of the target terminal by analyzing the file information obtained in the preset period of time includes: obtaining corresponding category information and tag information by analyzing the file information obtained in each of the preset period of time; assigning the corresponding category information and tag information with weights varying with time when the file information is obtained; and obtaining the interest feature of the target terminal by calculating with reference to the category information and the tag information in the file information obtained in the preset period of time and the corresponding weights.
In some embodiments, before the step of obtaining constantly the audio segment data detected by the target terminal, the method further includes: obtaining key audio segment data by parsing the pre-stored multimedia files; and associating the key audio segment data with key picture and text information; and after the step of obtaining constantly audio segment data detected by a target terminal, the method may further include: determining whether the audio  segment data match with the key audio segment data; and if the audio segment data match with the key audio segment data, then pushing the key picture and text information associated with the key audio segment data to the target terminal.
Another aspect of the disclosure further provides an apparatus for recommending data. The apparatus may include: an audio segment data obtaining module configured to obtain constantly audio segment data detected by a target terminal; amultimedia file matching module configured to compare each piece of the audio segment data with audios in pre-stored multimedia files, and to obtain a multimedia file matching with each piece of the audio segment data; a file information obtaining module configured to obtain file information of the multimedia file successfully matched in a preset period of time; an interest feature analyzing module configured to obtain an interest feature of the target terminal by analyzing the file information obtained in the preset period of time; and a multimedia file pushing module configured to extract and push to the target terminal a multimedia file matching with the interest feature of the target terminal.
In some embodiments, the multimedia file matching module is configured to: separate multimedia audio data from the pre-stored multimedia files; compare the audio segment data with audios in the multimedia audio data, and to obtain multimedia audio data matching with the audio segment data; and obtain a corresponding multimedia file according to the multimedia audio data matching with the audio segment data.
In some embodiments, the multimedia files may include movies, music, and/or teleplays; and the multimedia file matching module is further configured to: determine whether the number of the multimedia files matching with the audio segment data is more than or equal to 2; if the number of the multimedia files matching with the audio segment data is more than or equal to 2, obtain new audio segment data detected by the target terminal; match the new audio segment data together with the audio segment data with the pre-stored multimedia files, and obtain a new multimedia file matching with both the new audio segment data and the audio segment data; determine whether the number of the new multimedia files is more than or equal to 2; and if the number of the new multimedia files is 1, replace the new multimedia file with the multimedia file matching with the audio segment data.
In some embodiments, the interest feature analyzing module is configured to: obtain corresponding category information and tag information by analyzing the file information obtained in each of the preset period of time; assign the corresponding category information and tag information with weights varying with time when the file information is obtained; and obtain the interest feature of the target terminal by calculating with reference to the category  information and the tag information in the file information obtained in the preset period of time and the corresponding weights.
In some embodiments, the apparatus may further include: a key audio segment parsing module configured to obtain key audio segment data by parsing the pre-stored multimedia files; a picture and text information associating module configured to associate the key audio segment data with key picture and text information; a key audio segment matching module configured to determine whether the audio segment data match with the key audio segment data; and a picture and text information pushing module configured, if the audio segment data match with the key audio segment data, to push the key picture and text information associated with the key audio segment data to the target terminal.
The present disclosure provides an electronic device for recommending data. The electronic device may include: at least one processor; and a memory communicably connected with the at least one processor for storing instructions executable by the at least one processor, wherein execution of the instructions by the at least one processor causes the at least one processor to perform a method according to any methods disclosed herein.
The present disclosure provides a non-transitory computer-readable storage medium storing executable instructions for recommending data. The instructions, when executed by an electronic device, may cause the electronic device to perform a method according to any methods disclosed herein.
The present disclosure provides a computer program product for recommending data. The computer program product may include a computer program stored on a non-transitory computer-readable storage medium. The computer program may include program code which, when executed on a computer, may cause the computer to perform a method according to any methods disclosed herein.
It should be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
BRIEF DESCRIPTION OF THE DRAWINGS
One or more embodiments are illustrated by way of example, and not by limitation, in the figures of the accompanying drawings, wherein elements having the same reference numeral designations represent like elements throughout. The drawings are not to scale, unless otherwise disclosed.
Fig. 1 is a schematic flow chart of a method for recommending data according to an embodiment of the present disclosure;
Fig. 2 is a schematic flow chart of a method for recommending data according to another embodiment of the disclosure;
Fig. 3 is a schematic structural diagram of modules in an apparatus for recommending data according to an embodiment of the disclosure; and
Fig. 4 illustrates a storage medium processing apparatus.
Skilled artisans will appreciate that elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions and/or relative positioning of some of the elements in the figures may be exaggerated relative to other elements to help to improve understanding of various examples of the present application. Also, common but well-understood elements that are useful or necessary in a commercially feasible example are often not depicted in order to facilitate a less obstructed view of these various examples. It will further be appreciated that certain actions and/or steps may be described or depicted in a particular order of occurrence while those skilled in the art will understand that such specificity with respect to sequence is not actually required. It will also be understood that the terms and expressions used herein have the ordinary technical meaning as is accorded to such terms and expressions by persons skilled in the technical field as set forth above, except where different specific meanings have otherwise been set forth herein.
DETAILED DESCRIPTION
The present disclosure will be described in more detail in conjunction with specific embodiments and with reference to figures to make the objects, technical solutions and advantages of the present disclosure more clear and more apparent.
It is appreciated that the expressions “first” and “second” used in the embodiment of the present disclosure are only intended to distinguish two different entities or different parameters which have the same terminology. It can be seen that “first” and “second” are presented only for purpose of easy illustration and should not be understood as limiting the embodiments of the present disclosure. This will not be explained in the subsequent embodiments.
The terminology used in the present disclosure is for the purpose of describing exemplary embodiments only and is not intended to limit the present disclosure. As used in the present disclosure and the appended claims, the singular forms "a, ” "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It shall also be understood that the terms “or” and "and/or" used herein are intended to signify and include any or all possible combinations of one or more of the associated listed items, unless the  context clearly indicates otherwise.
Reference throughout this specification to "one embodiment, " "an embodiment, " "exemplary embodiment, " or the like in the singular or plural means that one or more particular features, structures, or characteristics described in connection with an embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment, " "in an exemplary embodiment, " or the like in the singular or plural in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics in one or more embodiments may include combined in any suitable manner
The present disclosure is to provide a method and apparatus for recommending data so as to recommend data that meet the interest feature of the target terminal to the target terminal, and the recommended data are more satisfactory.
The method and apparatus for recommending data according to the embodiment of the disclosure obtain constantly the audio segment data detected by the target terminal, obtain the multimedia file corresponding to the audio segment data as a result of audio comparison, obtain the corresponding file information, analyze the file information in the preset period of time for the interest feature of the target terminal, and recommend the multimedia file to the target terminal according to the interest feature, so that pertinent multimedia file can be recommended to the target terminal instead of some of the latest and the most popular interest features generally recommended, to thereby improve the favor of the user, and optimize the experience of the user.
In a technical solution according to an embodiment of the disclosure, there is provided a method for recommending data, wherein the method can recommend data that meet the interest feature of the target terminal to the target terminal and the recommended data are more satisfactory. Fig. 1 illustrates a schematic flow chart of a method for recommending data according to an embodiment of the disclosure.
The method for recommending data is applicable to the network server side and includes:
The step 101 is to obtain constantly audio segment data detected by a target terminal;
The audio segment data detected by a target terminal refer to audio segment data detected and uploaded in real time by the target terminal to the network server side, and at this time, the target terminal needs to be provided therein accordingly with an audio acquiring module configured to detect the audio generated in the target terminal, where the audio generated in the target terminal refers to an audio carried in a multimedia program being played  by the target terminal, that is, the audio of the current multimedia program can be acquired in real time even if the audio is mute; and the audio segment data here can be audio segment data detected at a preset acquisition interval of time and frequency; for example, the length of time of the audio segment data ranges from 15 to 30 seconds, the acquisition interval of time of each piece of audio segment data ranges from 0 to 30 seconds, etc. ;
The step 102 is to compare each piece of the audio segment data with audios in pre-stored multimedia files, and to obtain a multimedia file matching with each piece of the audio segment data, where the pre-stored multimedia files can be all the multimedia files pre-stored in a database at the network server side, or can be pre-filtered multimedia files for audio comparison stored in a folder in the database;
Audio comparison here can be the comparison of the audio segment data with the audio carried in the multimedia files, i.e., direct comparison of the audio segment data with the audio carried in the multimedia files without any conversion of the audio segment data into data in another format, e.g., a text;
The step 103 is to obtain file information of the multimedia file successfully matched in a preset period of time, wherein the preset period of time is a preset interval of time for extracting the file information, e.g., the last half of a month, the last month, the last quarter, etc., where the operation of the step 103 can be triggered by restarting the disabled target terminal, and at this time, the target terminal sends a recommended content obtainment instruction to the network server side so that the network server side obtains file information of the multimedia file successfully matched in the preset period of time in order to recommend contents to the target terminal;
The file information of the multimedia file can include but will not be limited to the filename, creation time, showing time, length of time, level-1 category information, level-2 category information, atag preset by the operator, a tag preset by a user, etc;
The step 104 is to obtain an interest feature of the target terminal by analyzing the file information obtained in the preset period of time, where the file information in the preset period of time is obtained so that a historical record of watching on the target terminal in the preset period of time is obtained, and the file information can be analyzed accordingly for the interest feature representing a habit of watching on the target terminal in the preset period of time; and
The step 105 is to extract and push to the target terminal a multimedia file matching with the interest feature of the target terminal from the pre-stored multimedia files, where the pushed multimedia file can include watching paths and preview pictures of pushed multimedia data so that the preview pictures are presented on a screen of the target terminal, and if a  corresponding preview picture is clicked on, then corresponding data will be retrieved and watched over a watching path associated with the preview picture.
As can be apparent from the embodiment above, the method for recommending data according to the embodiment of the disclosure obtains constantly the audio segment data detected by the target terminal, obtains the multimedia file corresponding to the audio segment data as a result of audio comparison, obtains the corresponding file information, analyzes the file information in the preset period of time for the interest feature of the target terminal, and recommends the multimedia file to the target terminal according to the interest feature, so that pertinent multimedia file can be recommended to the target terminal instead of some of the latest and the most popular interest features generally recommended, to thereby improve the favor of the user, and optimize the experience of the user.
Furthermore in some alternative embodiments, the step 102 of comparing each piece of the audio segment data with the audios in the pre-stored multimedia files, and obtaining the multimedia file matching with each piece of the audio segment data further includes the following steps:
separating multimedia audio data from the pre-stored multimedia files, where the multimedia audio data are the audio components in the multimedia files, and the multimedia audio data can be obtained from the multimedia files by separating the audio from the multimedia file, although a detailed description thereof will be omitted here;
comparing the audio segment data with the audios in the multimedia audio data, and obtaining multimedia audio data matching with the audio segment data; and
obtaining a corresponding multimedia file according to the multimedia audio data matching with the audio segment data.
The audio segment data can be matched as a result of direct audio comparison without being converted into other data to thereby dispense with the steps of data conversion, and achieve higher accuracy.
Preferably in some alternative embodiments, the multimedia files include movies, music, and/or teleplays, and even advertisements.
Since music episodes may appear in movies, advertisements, and teleplays, if the audio segment data are exactly a segment of some music, and the segment of the music also appears in a movie, a teleplay, or an advertisement, then there will be more than one matching results.
Thus after the step 102 of comparing each piece of the audio segment data with the audios in the pre-stored multimedia files, and obtaining the multimedia file matching with each  piece of the audio segment data, the method further includes the followings steps:
determining whether the number of the multimedia files matching with the audio segment data is more than or equal to 2;
if the number of the multimedia files matching with the audio segment data is more than or equal to 2, then obtaining new audio segment data detected by the target terminal, where the new audio segment data can be the next piece of audio segment data immediately succeeding to the audio segment data; and of course, the new audio segment data can alternatively be a still next audio segment data succeeding to the audio segment data, etc., as long as a matching result can be obtained;
matching the new audio segment data together with the audio segment data with the pre-stored multimedia files, and obtaining a new multimedia file matching with both the new audio segment data and the audio segment data;
determining whether the number of the new multimedia files is more than or equal to 2; and
if the number of the new multimedia files is 1, then replacing the new multimedia file with the multimedia file matching with the audio segment data.
If the number of the new multimedia files is more than or equal to 2, then the steps above will be repeated until only one matching multimedia file is determined.
With the embodiment above, if there is more than one matching multimedia file, then only one matching multimedia file will be determined to thereby improve the accuracy in the subsequent steps of analyzing the multimedia file for the interest feature.
Optionally in some embodiments, the step 104 of obtaining an interest feature of the target terminal by analyzing the file information obtained in the preset period of time further includes the following steps:
obtaining corresponding category information and tag information by analyzing the respective file information obtained in each of the preset period of time, where the category information can include but will not be limited to level-1 category information and level-2 category information of the multimedia file, and the tag information can include but will not be limited to a tag preset by the operator of the multimedia file, a tag preset for the multimedia file by a user, etc. ;
assigning the corresponding category information and tag information with weights varying with time when the file information is obtained, that is, there are a lower weight for the temporally older file information, and a higher weight for the temporally newer file information; and
obtaining the interest feature of the target terminal by calculating with reference to the category information and the tag information in the file information obtained in the preset period of time and the corresponding weights, where the interest feature can be a function of the category information and the tag information which is respective parameters with a feature vector of their weights so that data can be subsequently recommended based upon the interest feature by matching directly the feature vector with the feature vectors of the multimedia files to thereby obtain the matching multimedia file.
Preferably in some alternative embodiments, before the step 101 of obtaining constantly audio segment data detected by a target terminal, the method further includes the following steps:
obtaining key audio segment data by parsing the pre-stored multimedia files; and
associating the key audio segment data with key picture and text information; and
after the step of obtaining constantly audio segment data detected by a target terminal, the method further includes the following steps:
determining whether the audio segment data match with the key audio segment data; and
if the audio segment data match with the key audio segment data, then pushing the key picture and text information associated with the key audio segment data to the target terminal;
where the key audio segment data refer to audio segment data, appearing at one or more positions in the multimedia file, which can be associated with the key picture and text information, and if the multimedia file is played to the position of the key audio segment data, then the audio segment data acquired at this time will exactly match with the key audio segment data so that the network server side is triggered to push the key picture and text information associated with the key audio segment data to the target terminal; and the key picture and text information can be a segment of video, a segment of music, a segment of animation, a segment of advertisement, etc.
The key audio segment data and the associated key picture and text information are set so that if the audio segment data matching with the key audio segment data appear in the multimedia file being watched on the target terminal, then some key picture and text information which may be interesting to the user or can improve the favor of the user can be pushed to the user, so that the watching user will not feel dull and tired, and can be provided with additional information.
Another embodiment of the disclosure further provides a method for recommending data. Fig. 2 illustrates a schematic flow chart of a method for recommending data according to  another embodiment of the disclosure.
The method for recommending data, applicable to the network server side, includes:
The step 201 is to obtaining key audio segment data by parsing pre-stored multimedia files;
The step 202 is to associate the key audio segment data with key picture and text information;
The step 203 is to obtain constantly audio segment data detected by a target terminal;
The step 204 is to determine whether the audio segment data match with the key audio segment data;
The step 205 is, if the audio segment data match with the key audio segment data, to push the key picture and text information associated with the key audio segment data to the target terminal;
The step 206 is to compare each piece of the audio segment data with audios in the pre-stored multimedia files, and to obtain a multimedia file matching with each piece of the audio segment data;
The step 207 is to determine whether the number of the multimedia files matching with the audio segment data is more than or equal to 2;
The step 208 is, if the number of the multimedia files matching with the audio segment data is more than or equal to 2, to obtain new audio segment data detected by the target terminal;
The step 209 is to match the new audio segment data together with the audio segment data with the pre-stored multimedia files, and to obtain a new multimedia file matching with both the new audio segment data and the audio segment data;
The step 210 is to determine whether the number of the new multimedia files is more than or equal to 2;
The step 211 is, if the number of the new multimedia files is 1, to replace the new multimedia file with the multimedia file matching with the audio segment data;
The step 212 is, if the number of the new multimedia files is more than or equal to 2, to return to the step 208;
The step 213 is to obtain file information of the multimedia file successfully matched in a preset period of time;
The step 214 is to obtain an interest feature of the target terminal by analyzing the file information obtained in the preset period of time; and
The step 215 is to extract and push to the target terminal a multimedia file matching  with the interest feature of the target terminal from the pre-stored multimedia files.
As can be apparent from the embodiment above, the method for recommending data according to the embodiment of the disclosure obtains constantly the audio segment data detected by the target terminal, obtains the multimedia file corresponding to the audio segment data as a result of audio comparison, obtains the corresponding file information, analyzes the file information in the preset period of time for the interest feature of the target terminal, and recommends the multimedia file to the target terminal according to the interest feature, so that pertinent multimedia file can be recommended to the target terminal instead of some of the latest and the most popular interest features generally recommended, to thereby improve the favor of the user, and optimize the experience of the user.
In another technical solution according to an embodiment of the disclosure, there is provided an apparatus for recommending data, wherein the apparatus can recommend data that meet the interest feature of the target terminal to the target terminal and the recommended data are more satisfactory. Fig. 3 illustrates a schematic structural diagram of modules in an apparatus for recommending data according to an embodiment of the disclosure.
The apparatus for recommending data includes:
an audio segment data obtaining module 301 configured to obtain constantly audio segment data detected by a target terminal;
the audio segment data detected by a target terminal refer to audio segment data detected and uploaded in real time by the target terminal to the network server side, and at this time, the target terminal needs to be provided therein accordingly with an audio acquiring module configured to detect the audio generated in the target terminal, where the audio generated in the target terminal refers to an audio carried in a multimedia program being played by the target terminal, that is, the audio of the current multimedia program can be acquired in real time even if the audio is mute; and the audio segment data here can be audio segment data detected at a preset acquisition interval of time and frequency; for example, the length of time of the audio segment data ranges from 15 to 30 seconds, the acquisition interval of time of each piece of audio segment data ranges from 0 to 30 seconds, etc. ;
a multimedia file matching module 302 configured to compare each piece of the audio segment data with audios in pre-stored multimedia files, and to obtain a multimedia file matching with each piece of the audio segment data, where the pre-stored multimedia files can be all the multimedia files pre-stored in a database at the network server side, or can be pre-filtered multimedia files for audio comparison stored in a folder in the database;
audio comparison here can be the comparison of the audio segment data with the audio  carried in the multimedia files, i.e., direct comparison of the audio segment data with the audio carried in the multimedia files without any conversion of the audio segment data into data in another format, e.g., a text;
a file information obtaining module 303 configured to obtain file information of the multimedia file successfully matched in a preset period of time, wherein the preset period of time is a preset interval of time for extracting the file information, e.g., the last half of a month, the last month, the last quarter, etc., where file information obtaining module 303 can be triggered by restarting the disabled target terminal, and at this time, the target terminal sends a recommended content obtainment instruction to the network server side so that the network server side obtains file information of the multimedia file successfully matched in the preset period of time in order to recommend contents to the target terminal;
the file information of the multimedia file can include but will not be limited to the filename, creation time, showing time, length of time, level-1 category information, level-2 category information, atag preset by the operator, a tag preset by a user, etc;
an interest feature analyzing module 304 configured to obtain an interest feature of the target terminal by analyzing the file information obtained in the preset period of time, where the file information in the preset period of time is obtained so that a historical record of watching on the target terminal in the preset period of time is obtained, and the file information can be analyzed accordingly for the interest feature representing a habit of watching on the target terminal in the preset period of time; and
a multimedia file pushing module 305 configured to extract and push to the target terminal a multimedia file matching with the interest feature of the target terminal, where the pushed multimedia file can include watching paths and preview pictures of pushed multimedia data so that the preview pictures are presented on a screen of the target terminal, and if a corresponding preview picture is clicked on, then corresponding data will be retrieved and watched over a watching path associated with the preview picture.
As can be apparent from the embodiment above, the apparatus for recommending data according to the embodiment of the disclosure obtains constantly the audio segment data detected by the target terminal, obtains the multimedia file corresponding to the audio segment data as a result of audio comparison, obtains the corresponding file information, analyzes the file information in the preset period of time for the interest feature of the target terminal, and recommends the multimedia file to the target terminal according to the interest feature, so that pertinent multimedia file can be recommended to the target terminal instead of some of the latest and the most popular interest features generally recommended, to thereby improve the  favor of the user, and optimize the experience of the user.
Furthermore in some alternative embodiments, the multimedia file matching module 302 is configured:
to separate multimedia audio data from the pre-stored multimedia files, where the multimedia audio data are the audio components in the multimedia files, and the multimedia audio data can be obtained from the multimedia files by separating the audio from the multimedia file, although a detailed description thereof will be omitted here;
to compare the audio segment data with the audios in the multimedia audio data, and to obtain multimedia audio data matching with the audio segment data; and
to obtain a corresponding multimedia file according to the multimedia audio data matching with the audio segment data.
The audio segment data can be matched as a result of direct audio comparison without being converted into other data to thereby dispense with the steps of data conversion, and achieve higher accuracy.
Preferably in some alternative embodiments, the multimedia files include movies, music, and/or teleplays, and even advertisements.
Since music episodes may appear in movies, advertisements, and teleplays, if the audio segment data are exactly a segment of some music, and the segment of the music also appears in a movie, a teleplay, or an advertisement, then there will be more than one matching results.
Thus the multimedia file matching module 302 is further configured:
to determine whether the number of the multimedia files matching with the audio segment data is more than or equal to 2;
if the number of the multimedia files matching with the audio segment data is more than or equal to 2, to obtain new audio segment data detected by the target terminal, where the new audio segment data can be the next piece of audio segment data immediately succeeding to the audio segment data; and of course, the new audio segment data can alternatively be a still next audio segment data succeeding to the audio segment data, etc., as long as a matching result can be obtained;
to match the new audio segment data together with the audio segment data with the pre-stored multimedia file, and to obtain a new multimedia file matching with both the new audio segment data and the audio segment data;
to determine whether the number of the new multimedia files is more than or equal to 2; and
if the number of the new multimedia files is 1, to replace the new multimedia file with the multimedia file matching with the audio segment data.
With the embodiment above, if there is more than one matching multimedia file, then only one matching multimedia file will be determined to thereby improve the accuracy in the subsequent steps of analyzing the multimedia file for the interest feature.
Optionally in some embodiments, the interest feature analyzing module 304 is configured:
to obtain corresponding category information and tag information by analyzing the file information obtained in each of the preset period of time, where the category information can include but will not be limited to level-1 category information and level-2 category information of the multimedia file, and the tag information can include but will not be limited to a tag preset by the operator of the multimedia file, a tag preset for the multimedia file by a user, etc. ;
to assign the corresponding category information and tag information with weights varying with time when the file information is obtained, that is, there are a lower weight for the temporally older file information, and a higher weight for the temporally newer file information; and
to obtain the interest feature of the target terminal by calculating with reference to the category information and the tag information in the file information obtained in the preset period of time and the corresponding weights, where the interest feature can be a function of the category information and the tag information which is respective parameters with a feature vector of their weights so that data can be subsequently recommended based upon the interest feature by matching directly the feature vector with the feature vectors of the multimedia files to thereby obtain the matching multimedia file.
Preferably in some alternative embodiments, the apparatus for recommending data further includes:
a key audio segment parsing module 306 configured to obtain key audio segment data byparsing the pre-stored multimedia files;
a picture and text information associating module 307 configured to associate the key audio segment data with key picture and text information;
a key audio segment matching module 308 configured to determine whether the audio segment data match with the key audio segment data; and
a picture and text information pushing module 309 configured, if the audio segment data match with the key audio segment data, to push the key picture and text information associated with the key audio segment data to the target terminal;
where the key audio segment data refer to audio segment data, appearing at one or more positions in the multimedia file, which can be associated with the key picture and text information, and if the multimedia file is played to the position of the key audio segment data, then the audio segment data acquired at this time will exactly match with the key audio segment data so that the network server side is triggered to push the key picture and text information associated with the key audio segment data to the target terminal; and the key picture and text information can be a segment of video, a segment of music, a segment of animation, a segment of advertisement, etc.
The key audio segment data and the associated key picture and text information are set so that if the audio segment data matching with the key audio segment data appear in the multimedia file being watched on the target terminal, then some key picture and text information which may be interesting to the user or can improve the favor of the user can be pushed to the user, so that the watching user will not feel dull and tired, and can be provided with additional information.
Fig. 4 illustrates a storage medium processing apparatus. As shown in Fig. 4, the storage medium processing apparatus includes a central processing unit (CPU) 71, a storage medium 72, and a bus 73 that connects the CPU 71 and the storage medium 72. The storage medium 72 may store the computer executable instructions. When the computer executable instructions are executed by the CPU 71, the apparatus may perform the methods disclosed in this disclosure.
Those skilled in the art can appreciate that the description of any embodiment above is merely illustrative, but not intended to suggest that the scope of the disclosure (including the claims) be limited to these examples; and the embodiments, or the technical features in different embodiments can be combined with each other, the steps can be performed in any appropriate order, and there are numerous other possible variations of the different aspects of the disclosure as described above, without departing from the scope of the disclosure, although they have not be described here in details for the sake of conciseness.
Furthermore for the sake of a concise description and discussion, and in order not to obscure the disclosure, well-known power supply/ground connections of Integrated Circuit (IC) chips and other components may or may not be illustrated in the drawings. Moreover the apparatus can be illustrated in block diagrams so as not to obscure the disclosure, and also takes into account such a fact that the details of the implementations of the apparatus in the block diagrams are highly determined by the platform on which the disclosure will be put into practice (that is, all of the details shall fall into the scope understandable by those skilled in the art) . If  particular details (e.g., circuits) are set forth for the description of an exemplary embodiment of the disclosure, then it will be obvious to those skilled in the art that the disclosure can be put into practice without the particular details or with some change to the particular details. Accordingly such a description shall be construed to be illustrative but not limiting.
Although the disclosure has been described in connection with the particular embodiments thereof, numerous substitutions, modifications, and variations of these embodiments will be obvious to those skilled in the art. For example, other memory architectures (e.g., a dynamic RAM (DRAM) ) can use the embodiments described above.
The present disclosure may include dedicated hardware implementations such as application specific integrated circuits, programmable logic arrays and other hardware devices. The hardware implementations can be constructed to implement one or more of the methods described herein. Applications that may include the apparatus and systems of various examples can broadly include a variety of electronic and computing systems. One or more examples described herein may implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through the modules, or as portions of an application-specific integrated circuit. Accordingly, the computing system disclosed may encompass software, firmware, and hardware implementations. The terms "module, " "sub-module, " "unit, " or "sub-unit" may include memory (shared, dedicated, or group) that stores code or instructions that can be executed by one or more processors.
The embodiments of the disclosure are intended to encompass all such substitutions, modifications, and variations falling into the broad scope of the appended claims. Accordingly any omissions, modifications, equivalent substitutions, adaptations, etc., made thereto without departing from the spirit and principle of the disclosure shall fall into the scope of the disclosure as claimed.

Claims (13)

  1. A method for recommending data, wherein the method is applicable to a network server side and comprises:
    obtaining constantly audio segment data detected by a target terminal;
    comparing each piece of the audio segment data with audios in pre-stored multimedia files, and obtaining a multimedia file matching with each piece of the audio segment data;
    obtaining file information of the multimedia file successfully matched in a preset period of time;
    obtaining an interest feature of the target terminal by analyzing the file information obtained in the preset period of time; and
    extracting and pushing to the target terminal a multimedia file matching with the interest feature of the target terminal.
  2. The method according to claim 1, wherein the step of comparing each piece of the audio segment data with the audios in the pre-stored multimedia files, and obtaining the multimedia file matching with each piece of the audio segment data comprises:
    separating multimedia audio data from the pre-stored multimedia files;
    comparing the audio segment data with audios in the multimedia audio data, and obtaining multimedia audio data matching with the audio segment data; and
    obtaining a corresponding multimedia file according to the multimedia audio data matching with the audio segment data.
  3. The method according to claim 1, wherein the multimedia files comprise movies, music, and/or teleplays; and
    after the step of comparing each piece of the audio segment data with the audios in the pre-stored multimedia files, and obtaining the multimedia file matching with each piece of the audio segment data, the method further comprises:
    determining whether the number of the multimedia files matching with the audio segment data is more than or equal to 2;
    if the number of the multimedia files matching with the audio segment data is more than or equal to 2, then obtaining new audio segment data detected by the target terminal;
    matching the new audio segment data together with the audio segment data with the pre-stored multimedia files, and obtaining a new multimedia file matching with both the new audio segment data and the audio segment data;
    determining whether the number of the new multimedia files is more than or equal to 2; and
    if the number of the new multimedia files is 1, then replacing the new multimedia file with the multimedia file matching with the audio segment data.
  4. The method according to claim 1, wherein the step of obtaining the interest feature of the target terminal by analyzing the file information obtained in the preset period of time comprises:
    obtaining corresponding category information and tag information by analyzing the file information obtained in each of the preset period of time;
    assigning the corresponding category information and tag information with weights varying with time when the file information is obtained; and
    obtaining the interest feature of the target terminal by calculating with reference to the category information and the tag information in the file information obtained in the preset period of time and the corresponding weights.
  5. The method according to claim 1, wherein, before the step of obtaining constantly the audio segment data detected by the target terminal, the method further comprises:
    obtaining key audio segment data by parsing the pre-stored multimedia files;
    associating the key audio segment data with key picture and text information; and
    after the step of obtaining constantly audio segment data detected by a target terminal, the method further comprises:
    determining whether the audio segment data match with the key audio segment data; and
    if the audio segment data match with the key audio segment data, then pushing the key picture and text information associated with the key audio segment data to the target terminal.
  6. An apparatus for recommending data, comprising:
    an audio segment data obtaining module configured to obtain constantly audio segment data detected by a target terminal;
    a multimedia file matching module configured to compare each piece of the audio segment data with audios in pre-stored multimedia files, and to obtain a multimedia file matching with each piece of the audio segment data;
    a file information obtaining module configured to obtain file information of the multimedia file successfully matched in a preset period of time;
    an interest feature analyzing module configured to obtain an interest feature of the target terminal by analyzing the file information obtained in the preset period of time; and
    a multimedia file pushing module configured to extract and push to the target terminal a multimedia file matching with the interest feature of the target terminal.
  7. The apparatus according to claim 6, wherein the multimedia file matching module is configured to:
    separate multimedia audio data from the pre-stored multimedia files;
    compare the audio segment data with audios in the multimedia audio data, and to obtain multimedia audio data matching with the audio segment data; and
    obtain a corresponding multimedia file according to the multimedia audio data matching with the audio segment data.
  8. The apparatus according to claim 6, wherein the multimedia files comprise movies, music, and/or teleplays; and
    the multimedia file matching module is further configured to:
    determine whether the number of the multimedia files matching with the audio segment data is more than or equal to 2;
    ifthe number of the multimedia files matching with the audio segment data is more than or equal to 2, obtain new audio segment data detected by the target terminal;
    match the new audio segment data together with the audio segment data with the pre-stored multimedia files, and to obtain a new multimedia file matching with both the new audio segment data and the audio segment data;
    determine whether the number of the new multimedia files is more than or equal to 2; and
    if the number of the new multimedia files is 1, replace the new multimedia file with the multimedia file matching with the audio segment data.
  9. The apparatus according to claim 6, wherein the interest feature analyzing module is configured to:
    obtain corresponding category information and tag information by analyzing the file information obtained in each of the preset period of time;
    assign the corresponding category information and tag information with weights varying with time when the file information is obtained; and
    obtain the interest feature of the target terminal by calculating with reference to the category information and the tag information in the file information obtained in the preset period of time and the corresponding weights.
  10. The apparatus according to claim 6, wherein the apparatus further comprises:
    a key audio segment parsing module configured to obtain key audio segment data by parsing the pre-stored multimedia files;
    a picture and text information associating module configured to associate the key audio segment data with key picture and text information;
    a key audio segment matching module configured to determine whether the audio segment data match with the key audio segment data; and
    a picture and text information pushing module configured, if the audio segment data match with the key audio segment data, to push the key picture and text information associated with the key audio segment data to the target terminal.
  11. An electronic device for recommending data, comprising:
    at least one processor; and
    a memory communicably connected with the at least one processor for storing instructions executable by the at least one processor, wherein execution of the instructions by the at least one processor causes the at least one processor to perform a method according to any one of claims 1 to 5.
  12. A non-transitory computer-readable storage medium storing executable instructions for recommending data, wherein the instructions, when executed by an electronic device, cause the electronic device to perform a method according to any one of claims 1 to 5.
  13. A computer program product for recommending data, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program code which, when executed on a computer, causes the computer to perform a method according to any one of claims 1 to 5.
PCT/CN2017/077618 2016-03-23 2017-03-22 Method and apparatus for recommending data WO2017162158A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610168929.4A CN105847878A (en) 2016-03-23 2016-03-23 Data recommendation method and device
CN201610168929.4 2016-03-23

Publications (1)

Publication Number Publication Date
WO2017162158A1 true WO2017162158A1 (en) 2017-09-28

Family

ID=56582936

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/077618 WO2017162158A1 (en) 2016-03-23 2017-03-22 Method and apparatus for recommending data

Country Status (2)

Country Link
CN (1) CN105847878A (en)
WO (1) WO2017162158A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110798717A (en) * 2018-08-01 2020-02-14 腾讯科技(深圳)有限公司 Media resource pushing method and device, storage medium and electronic device

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105847878A (en) * 2016-03-23 2016-08-10 乐视网信息技术(北京)股份有限公司 Data recommendation method and device
CN113241098B (en) * 2021-06-02 2022-04-26 亿览在线网络技术(北京)有限公司 Target recommendation method based on audio recording

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110246495A1 (en) * 2010-04-01 2011-10-06 Sony Computer Entertainment Inc. Media fingerprinting for social networking
US20110285542A1 (en) * 2010-05-18 2011-11-24 International Business Machines Corporation Filtering method and system
CN102572573A (en) * 2010-12-30 2012-07-11 上海无戒空间信息技术有限公司 Method for pushing information according to played content
CN103021440A (en) * 2012-11-22 2013-04-03 腾讯科技(深圳)有限公司 Method and system for tracking audio streaming media
CN105847878A (en) * 2016-03-23 2016-08-10 乐视网信息技术(北京)股份有限公司 Data recommendation method and device

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090013004A1 (en) * 2007-07-05 2009-01-08 Rockbury Media International, C.V. System and Method for the Characterization, Selection and Recommendation of Digital Music and Media Content
US8949872B2 (en) * 2011-12-20 2015-02-03 Yahoo! Inc. Audio fingerprint for content identification
CN103488764B (en) * 2013-09-26 2016-08-17 天脉聚源(北京)传媒科技有限公司 Individualized video content recommendation method and system
CN103763585B (en) * 2014-01-10 2018-02-09 北京酷云互动科技有限公司 A kind of user's characteristic information acquisition methods, device and terminal device
CN104093079B (en) * 2014-05-29 2015-10-07 腾讯科技(深圳)有限公司 Based on the exchange method of multimedia programming, terminal, server and system
CN104731861B (en) * 2015-02-05 2019-10-01 腾讯科技(深圳)有限公司 Multi-medium data method for pushing and device
CN104750839B (en) * 2015-04-03 2019-02-15 魅族科技(中国)有限公司 A kind of data recommendation method, terminal and server

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110246495A1 (en) * 2010-04-01 2011-10-06 Sony Computer Entertainment Inc. Media fingerprinting for social networking
US20110285542A1 (en) * 2010-05-18 2011-11-24 International Business Machines Corporation Filtering method and system
CN102572573A (en) * 2010-12-30 2012-07-11 上海无戒空间信息技术有限公司 Method for pushing information according to played content
CN103021440A (en) * 2012-11-22 2013-04-03 腾讯科技(深圳)有限公司 Method and system for tracking audio streaming media
CN105847878A (en) * 2016-03-23 2016-08-10 乐视网信息技术(北京)股份有限公司 Data recommendation method and device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110798717A (en) * 2018-08-01 2020-02-14 腾讯科技(深圳)有限公司 Media resource pushing method and device, storage medium and electronic device
CN110798717B (en) * 2018-08-01 2021-08-20 腾讯科技(深圳)有限公司 Media resource pushing method and device, storage medium and electronic device

Also Published As

Publication number Publication date
CN105847878A (en) 2016-08-10

Similar Documents

Publication Publication Date Title
US11917242B2 (en) Identification and presentation of content associated with currently playing television programs
US10231023B2 (en) Media fingerprinting for content determination and retrieval
AU2016277657B2 (en) Methods and systems for identifying media assets
KR102076642B1 (en) Media content that overlays sequentially
CN109033149B (en) Information recommendation method and device, server and storage medium
US9740775B2 (en) Video retrieval based on optimized selected fingerprints
US20190138815A1 (en) Method, Apparatus, User Terminal, Electronic Equipment, and Server for Video Recognition
JP2021524686A (en) Machine learning to recognize and interpret embedded information card content
EP2722779A2 (en) Apparatus and method for scene change detection-based trigger for audio fingerprinting analysis
US20170164027A1 (en) Video recommendation method and electronic device
US10735792B2 (en) Using OCR to detect currently playing television programs
US20170195176A1 (en) Method and apparatus for recommending device configuration
EP3451679B1 (en) Method for providing media-content related information based on closed caption information, server, and computer-readable storage medium for executing the method
US11755936B2 (en) Systems and methods for determining that a media item is being presented
US20170171335A1 (en) Advertising push methods, devices, video servers and terminal equipment
WO2016192506A1 (en) Information query method, terminal device, system and computer storage medium
US20170171334A1 (en) Single-account multiple-preference recommendation method for video website and electronic device
US20150235264A1 (en) Automatic entity detection and presentation of related content
US20180300335A1 (en) Methods, systems, and media for presenting related media content items
WO2017162158A1 (en) Method and apparatus for recommending data
US20170161391A1 (en) Method and electronic device for video recommendation
CN107515870B (en) Searching method and device and searching device
JP2021504774A (en) Controlling the triggering of function calls from content items
CN108600780B (en) Method for pushing information, electronic device and computer readable medium
US9836535B2 (en) Method and system for content retrieval based on rate-coverage optimization

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 17769435

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 17769435

Country of ref document: EP

Kind code of ref document: A1