CN108062390B - Method and device for recommending user and readable storage medium - Google Patents

Method and device for recommending user and readable storage medium Download PDF

Info

Publication number
CN108062390B
CN108062390B CN201711350589.8A CN201711350589A CN108062390B CN 108062390 B CN108062390 B CN 108062390B CN 201711350589 A CN201711350589 A CN 201711350589A CN 108062390 B CN108062390 B CN 108062390B
Authority
CN
China
Prior art keywords
user
video file
friend
description information
current user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711350589.8A
Other languages
Chinese (zh)
Other versions
CN108062390A (en
Inventor
王卓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Kugou Computer Technology Co Ltd
Original Assignee
Guangzhou Kugou Computer Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Kugou Computer Technology Co Ltd filed Critical Guangzhou Kugou Computer Technology Co Ltd
Priority to CN201711350589.8A priority Critical patent/CN108062390B/en
Publication of CN108062390A publication Critical patent/CN108062390A/en
Application granted granted Critical
Publication of CN108062390B publication Critical patent/CN108062390B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7834—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using audio features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Abstract

The invention discloses a method and a device for recommending users and a readable storage medium, and belongs to the technical field of the Internet. The method comprises the following steps: the method comprises the steps that a terminal obtains video description information of a first pairing video file of a current user and sends a matching instruction to a server, the server receives the matching instruction of the terminal, and the server screens out user identification of a recommended user of which the video description information is matched with the video description information of the current user from a first non-friend user set of the current user according to the matching instruction; and the server sends the user identification of the recommended user to the terminal. And the terminal receives the user identification of the recommended user of the server and displays the user identification of the recommended user on the recommendation interface of the current user. As the server recommends the user based on the video description information sent by the terminal, the video description information can show the personal feature information of the user, and the accuracy of recommending the user is improved.

Description

Method and device for recommending user and readable storage medium
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a method and an apparatus for recommending a user, and a readable storage medium.
Background
The social application is used as a most widely applied friend making platform in an internet website, and can help users to find strange users with the same interest and establish social relations through modes of character interaction, video interaction and the like, so that communication among the strange users is facilitated. Specifically, the terminal recommends the same type of strange users for the users in the social application according to the ages, the sexes and the like of the users, so that the users can quickly identify interested friends.
In the related art, the recommendation is generally made based on a restriction condition selected by a user. The process of recommending the user is as follows: the terminal displays a plurality of restriction conditions on the current interface, the restriction conditions being restrictions set based on age, sex, location, etc., for example, age 18-22 years, sex female, etc. The terminal acquires user identifications of a plurality of strange users according to the limiting conditions selected by the user from the server, and displays the user identifications of the strange users on the current interface.
In the process of implementing the invention, the inventor finds that the related art has at least the following problems:
the above method is actually a process of screening and recommending based on several specified constraints. However, the specified limiting conditions only include popular information such as ages, sexes and the like of the unfamiliar users, and real preferences of the unfamiliar users cannot be reflected, so that the users may not be interested in the recommended unfamiliar users, and the accuracy of the recommended users is low.
Disclosure of Invention
The invention provides a method and a device for recommending a user and a readable storage medium. The problem that the accuracy rate of recommending users is low in the prior art can be solved, and the technical scheme is as follows:
in a first aspect, a method for recommending a user is provided, where the method is applied in a terminal, and the method includes:
determining a first pairing video file of a current user;
acquiring video description information of the first pairing video file;
sending a matching instruction to a server, wherein the matching instruction carries the video description information and is used for indicating the server to return a user identifier of a recommended user recommended based on the video description information to a terminal;
and receiving the user identification of the recommended user of the server, and displaying the user identification of the recommended user on the recommendation interface of the current user.
Optionally, the obtaining video description information of the first paired video file includes:
acquiring an audio identifier of an audio file in the first pairing video file;
acquiring audio description information of the audio file according to the audio identifier;
and taking the audio identification and the audio description information as the video description information.
Optionally, the audio description information includes at least one of audio type, singer, author, and emotion-based tune.
Optionally, the obtaining video description information of the first paired video file includes:
and acquiring object information of a video picture in the first paired video file, and taking the object information as the video description information.
Optionally, the obtaining object information of a video frame in the first paired video file includes:
extracting a key frame image from the first paired video file;
according to the key frame images, determining reference images matched with the key frame images from a local object training set, wherein the object training set comprises reference images of various objects;
and acquiring object information corresponding to the reference image as object information in a video picture.
Optionally, after the user identifier of the recommending user is displayed on the recommending interface of the current user, the method further includes:
displaying a first button and a second button in the recommendation interface, wherein the first button is used for triggering a pairing request, and the second button is used for triggering a deletion request;
when the first button is detected to be triggered, sending a pairing request for pairing the current user and the recommended user to the server;
and when the current user is successfully paired with the recommended user, receiving a second paired video file of the recommended user returned by the server, and playing the second paired video file on a recommended interface of the current user.
Optionally, before determining the first paired video file of the current user, the method further includes:
acquiring the pairing conditions set by the current user;
and sending the pairing condition to the server so that the server returns the user identification of the recommended user to the terminal based on the video description information and the pairing condition.
Optionally, the determining a first paired video file of the current user includes:
when the terminal is detected to log in the server, acquiring the account state of the current user from the server;
when the account state indicates that the current user does not record the paired video file, acquiring the video file set by the current user, and taking the video file as the first paired video file;
and when the account state indicates that the current user records the paired video file, taking the recorded paired video file as the first paired video file.
In a second aspect, a method for recommending a user is provided, and the method is applied in a server, and the method includes:
receiving a matching instruction of a terminal, wherein the matching instruction carries video description information of a current user of the terminal, and the video description information is extracted from a first pairing video file of the current user by the terminal;
according to the matching instruction, screening out user identifications of recommended users of which the video description information is matched with the video description information of the current user from a first non-friend user set of the current user;
and sending the user identification of the recommended user to the terminal.
Optionally, the screening, according to the video description information, a user identifier of a recommended user whose video description information matches with the video description information of the current user from the first non-friend user set of the current user includes:
when the video description information comprises audio description information, selecting a user identifier of a non-friend user of which the audio description information is matched with the audio description information of the current user from the first non-friend user set, and taking the selected user identifier of the non-friend user as a user identifier of a recommended user; and/or the presence of a gas in the gas,
and when the video description information comprises object information, selecting the user identification of the non-friend user of which the object information is matched with the object information of the current user from the first non-friend user set, and taking the user identification of the selected non-friend user as the user identification of the recommended user.
Optionally, the selecting, from the first set of non-friend users, the user identifier of the non-friend user whose object information matches the object information of the current user includes:
determining the user type of the current user according to the object information of the current user;
and selecting the user identification of the non-friend user with the user type same as that of the current user from the first non-friend user set according to the user type of the current user.
Optionally, before the user identifier of the recommended user whose video description information matches with the video description information of the current user is screened from the first non-friend user set of the current user according to the video description information, the method further includes:
acquiring a second non-friend user set of the current user and acquiring a matching condition of the current user;
and selecting non-friend users meeting the matching conditions from the second non-friend user set to form the first non-friend user set.
Optionally, the selecting, from the second set of non-friend users, a non-friend user who meets the matching condition to form the first set of non-friend users includes:
selecting non-friend users meeting the matching condition from the second non-friend user set to form a third non-friend user set;
and forming the first non-friend user set from the non-friend users of the third non-friend user set meeting a preset screening rule, wherein the preset screening rule is a position screening rule and/or a time screening rule for matching video files.
Optionally, the method further includes:
determining user identifications of marked users marked by the current user in the first non-friend user set, wherein the marked users comprise users who send pairing requests and/or deletion requests by the terminal;
and deleting the user identification of the marked user from the first non-friend user set.
Optionally, the method further includes:
and when the user identification of the non-friend user sending the pairing request to the current user exists in the first non-friend user set, taking the user identification of the non-friend user sending the pairing request to the current user as the user identification of the recommended user.
Optionally, the taking the user identifier of the non-friend user who sends the pairing request to the current user as the user identifier of the recommended user includes:
selecting the user identification of the non-friend user meeting the position screening rule from the non-friend users sending the pairing request to the current user;
and taking the user identification of the selected non-friend user as the user identification of the recommended user.
Optionally, after sending the user identifier of the recommended user to the terminal, the method further includes:
receiving a pairing request which is sent by the terminal and paired with the recommended user;
and when the current user is successfully paired with the recommended user, acquiring a second paired video file of the recommended user, and sending the second paired video file to the terminal.
Optionally, the obtaining of the second paired video file of the recommended user includes:
when the paired video file of the recommended user comprises a paired video file of which the video description information is matched with the video description information of the current user, taking the paired video file of which the video description information is matched with the video description information of the current user as the second paired video file;
and when the paired video file of which the video description information is matched with the video description information of the current user is deleted, taking the paired video file with the latest uploading time as the second paired video file.
In a third aspect, an apparatus for recommending a user is provided, where the apparatus is applied in a terminal, and the apparatus includes:
the first determining module is used for determining a first pairing video file of a current user;
the first obtaining module is used for obtaining video description information of the first pairing video file;
the first sending module is used for sending a matching instruction to a server, wherein the matching instruction carries the video description information and is used for indicating the server to return a user identifier of a recommended user recommended based on the video description information to a terminal;
and the first receiving module is used for receiving the user identification of the recommended user of the server and displaying the user identification of the recommended user on the recommended interface of the current user.
Optionally, the first obtaining module includes:
the acquisition unit is used for acquiring the audio identifier of the audio file in the first pairing video file;
the acquiring unit is further configured to acquire audio description information of the audio file according to the audio identifier;
and the unit is used for taking the audio identification and the audio description information as the video description information.
Optionally, the audio description information includes at least one of audio type, singer, author, and emotion-based tune.
Optionally, the first obtaining module is further configured to obtain object information of a video picture in the first paired video file, and use the object information as the video description information.
Optionally, the obtaining unit is further configured to extract a key frame image from the first paired video file; according to the key frame images, determining reference images matched with the key frame images from a local object training set, wherein the object training set comprises reference images of various objects; and acquiring object information corresponding to the reference image as object information in a video picture.
Optionally, the apparatus further comprises:
the display module is used for displaying a first button and a second button in the recommendation interface, wherein the first button is used for triggering a pairing request, and the second button is used for triggering a deletion request;
the second sending module is used for sending a pairing request of pairing the current user and the recommended user to the server when the first button is detected to be triggered;
and the playing module is used for receiving a second matching video file of the recommended user returned by the server when the current user is successfully matched with the recommended user, and playing the second matching video file on the recommended interface of the current user.
Optionally, the apparatus further comprises:
the second acquisition module is used for acquiring the pairing conditions set by the current user;
and the third sending module is used for sending the pairing condition to the server so that the server returns the user identifier of the recommended user to the terminal based on the video description information and the pairing condition.
Optionally, the first determining module is further configured to, when it is detected that the terminal logs in the server, obtain the account status of the current user from the server; when the account state indicates that the current user does not record the paired video file, acquiring the video file set by the current user, and taking the video file as the first paired video file; and when the account state indicates that the current user records the paired video file, taking the recorded paired video file as the first paired video file.
In a fourth aspect, an apparatus for recommending a user is provided, and the apparatus is applied in a server, and the apparatus includes:
a second receiving module, configured to receive a matching instruction of a terminal, where the matching instruction carries video description information of a current user of the terminal, and the video description information is extracted by the terminal from a first pairing video file of the current user;
the screening module is used for screening out the user identification of the recommended user of which the video description information is matched with the video description information of the current user from the first non-friend user set of the current user according to the matching instruction;
and the fourth sending module is used for sending the user identification of the recommended user to the terminal.
Optionally, the screening module includes:
a first selecting unit, configured to select, when the video description information includes audio description information, a user identifier of a non-friend user whose audio description information matches with the audio description information of the current user from the first set of non-friend users, and use the user identifier of the selected non-friend user as a user identifier of a recommended user; and/or the presence of a gas in the gas,
and the second selection unit is used for selecting the user identification of the non-friend user of which the object information is matched with the object information of the current user from the first non-friend user set when the video description information comprises the object information, and taking the user identification of the selected non-friend user as the user identification of the recommended user.
Optionally, the second selecting unit is further configured to determine a user type of the current user according to the object information of the current user; and selecting the user identification of the non-friend user with the user type same as that of the current user from the first non-friend user set according to the user type of the current user.
Optionally, the apparatus further comprises:
a third obtaining module, configured to obtain a second non-friend user set of the current user, and obtain a matching condition of the current user;
and the selection module is used for selecting the non-friend users meeting the matching conditions from the second non-friend user set to form the first non-friend user set.
Optionally, the selecting module is further configured to select, from the second non-friend user set, a non-friend user who meets the matching condition to form a third non-friend user set; and forming the first non-friend user set from the non-friend users of the third non-friend user set meeting a preset screening rule, wherein the preset screening rule is a position screening rule and/or a time screening rule for matching video files.
Optionally, the apparatus further comprises:
a second determining module, configured to determine a user identifier of a tagged user tagged by the current user in the first non-buddy user set, where the tagged user includes a user for whom the terminal has sent a pairing request and/or a deletion request;
and the deleting module is used for deleting the user identification of the marked user from the first non-friend user set.
Optionally, the apparatus further comprises:
and the serving module is configured to, when a user identifier of a non-buddy user who sends a pairing request to the current user exists in the first non-buddy user set, use the user identifier of the non-buddy user who sends the pairing request to the current user as the user identifier of the recommended user.
Optionally, the acting module is further configured to select a user identifier of a non-buddy user who meets a location filtering rule from non-buddy users who send pairing requests to the current user; and taking the user identification of the selected non-friend user as the user identification of the recommended user.
Optionally, the apparatus further comprises:
the third receiving module is used for receiving a pairing request which is sent by the terminal and is paired with the recommended user;
and the fourth obtaining module is used for obtaining a second pairing video file of the recommended user and sending the second pairing video file to the terminal when the current user is successfully paired with the recommended user.
Optionally, the fourth obtaining module is further configured to, when the paired video file of the recommended user includes a paired video file whose video description information matches the video description information of the current user, use the paired video file whose video description information matches the video description information of the current user as the second paired video file; and when the paired video file of which the video description information is matched with the video description information of the current user is deleted, taking the paired video file with the latest uploading time as the second paired video file.
In a fifth aspect, there is provided an apparatus for recommending users, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a set of codes, or a set of instructions, and the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by the processor to implement the method for recommending users according to any of the first aspects or the method for recommending users according to any of the second aspects.
In a sixth aspect, there is provided a storage medium having stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded and executed by the processor to implement the method of recommending users according to any of the first aspects or the method of recommending users according to any of the second aspects.
In the embodiment of the invention, a terminal acquires video description information of a first pairing video file of a current user and sends a matching instruction to a server, the server receives the matching instruction of the terminal, and the server screens out a user identifier of a recommended user of which the video description information is matched with the video description information of the current user from a first non-friend user set of the current user according to the matching instruction; and the server sends the user identification of the recommended user to the terminal. And the terminal receives the user identification of the recommended user of the server and displays the user identification of the recommended user on the recommendation interface of the current user. As the server recommends the user based on the video description information sent by the terminal, the video description information can show the personal characteristic information of the user, so that a recommended user matched with the personal characteristic information is screened out for the current user, and the accuracy of the recommended user is improved.
Drawings
FIG. 1 is a schematic diagram of an implementation environment provided by an embodiment of the invention;
FIG. 2 is a flowchart of a method for recommending users according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for recommending users according to an embodiment of the present invention;
fig. 4 is a signaling interaction diagram of a method for recommending a user according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a terminal interface according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a terminal interface according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a terminal interface according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a terminal interface according to an embodiment of the present invention;
FIG. 9 is a block diagram of an apparatus for recommending users according to an embodiment of the present invention;
FIG. 10 is a block diagram of an apparatus for recommending users according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of a terminal according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of a server according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present invention, and referring to fig. 1, the implementation environment includes a first terminal 101 and a server 102 of a current user. The first terminal 101 and the server 102 are connected via a network. The first terminal 101 runs a social application program associated with the server 102, and can log in to the server 102 based on the social application program, so as to interact data with the server 102 to use the service provided by the server.
The first terminal 101 may obtain a pairing video file of the user from the server through the social application program, when the user needs to pair, the first terminal 101 obtains video description information of the pairing video file, performs data interaction with the server 102 based on the video description information, and sends a pairing instruction carrying the video description information to the server 102. For the server 102, the server 102 may screen out recommended friends from a plurality of non-friend users of the user based on the video description information, and return the recommended users to the first terminal 101, so that the first terminal 101 may display the recommended users to the user. The video description information can comprise audio information and object information of a video picture, personal characteristic information such as interests and hobbies of the user is reflected through the audio information and the object information, and recommendation is performed based on the personal characteristic information, so that the accuracy of recommending the user is improved.
Further, when the user and the recommended user are successfully paired, that is, when a pairing request is sent between the first terminal 101 of the user and the second terminal 103 of the recommended user, the first terminal 101 may also play the paired video file of the recommended user to the user, and the second terminal 103 may play the paired video file of the user to the recommended user.
The first terminal 101 and the second terminal 103 may be any terminals in which the social application is installed. For example, the first terminal 101 and the second terminal 103 may be any Device such as a mobile phone terminal, a PAD (Portable Android Device) terminal, or a computer terminal that installs the social application. Server 102 is a backend server of the social application. The server 102 may be a server, a server cluster composed of several servers, or a cloud computing server center.
Fig. 2 is a flowchart of a method for recommending a user according to an embodiment of the present invention, where the method may be applied to a terminal, and as shown in fig. 2, the method includes:
step 201: determining a first pairing video file of a current user;
step 202: acquiring video description information of the first pairing video file;
step 203: sending a matching instruction to a server, wherein the matching instruction carries the video description information and is used for indicating the server to return a user identifier of a recommended user recommended based on the video description information to a terminal;
step 204: and receiving the user identification of the recommended user of the server, and displaying the user identification of the recommended user on the recommendation interface of the current user.
Optionally, the obtaining video description information of the first paired video file includes:
acquiring an audio identifier of an audio file in the first pairing video file;
according to the audio identifier, acquiring the audio description information of the audio file from the corresponding relation between the audio identifier and the audio description information;
and taking the audio identification and the audio description information as the video description information.
Optionally, the audio description information includes at least one of audio type, singer, author, and emotion-based tune.
Optionally, the obtaining video description information of the first paired video file includes:
and acquiring object information of a video picture in the first paired video file, and taking the object information as the video description information.
Optionally, the obtaining of the object information of the video frame in the first paired video file includes:
extracting a key frame image from the first paired video file;
according to the key frame image, determining a reference image matched with the key frame image from a local object training set, wherein the object training set comprises reference images of various objects;
and acquiring object information corresponding to the reference image as object information in a video picture.
Optionally, after the recommending interface of the current user displays the user identifier of the recommending user, the method further includes:
displaying a first button and a second button in the recommendation interface, wherein the first button is used for triggering a pairing request, and the second button is used for triggering a deletion request;
when the first button is detected to be triggered, sending a pairing request for pairing the current user and the recommended user to the server;
and when the current user is successfully paired with the recommended user, receiving a second paired video file of the recommended user returned by the server, and playing the second paired video file on a recommended interface of the current user.
Optionally, before determining the first paired video file of the current user, the method further includes:
acquiring the pairing condition set by the current user;
and sending the pairing condition to the server so that the server returns the user identifier of the recommended user to the terminal based on the video description information and the pairing condition.
Optionally, the determining the first paired video file of the current user includes:
when the terminal is detected to log in the server, acquiring the account state of the current user from the server;
when the account state indicates that the current user does not record the paired video file, acquiring the video file set by the current user, and taking the video file as the first paired video file;
and when the account state indicates that the current user records the paired video file, taking the recorded paired video file as the first paired video file.
In the embodiment of the invention, a terminal acquires video description information of a first pairing video file of a current user and sends a matching instruction to a server, wherein the matching instruction carries the video description information and is used for indicating the server to return a user identifier of a recommended user recommended based on the video description information to the terminal; and the terminal receives the user identification of the recommended user of the server and displays the user identification of the recommended user on the recommendation interface of the current user. The terminal acquires the video description information of the first pairing video file of the current user from the server and sends the video description information of the first pairing video file of the current user to the server, so that the server can recommend the user based on the video description information sent by the terminal, the video description information can display the personal characteristic information of the user, the recommended user matched with the personal characteristic information can be screened out for the current user, and the accuracy of the recommended user is improved.
Fig. 3 is a flowchart of a method for recommending a user according to an embodiment of the present invention, where the method may be applied to a server, and as shown in fig. 3, the method includes:
step 301: receiving a matching instruction of a terminal, wherein the matching instruction carries video description information of a current user of the terminal, and the video description information is extracted from a first pairing video file of the current user by the terminal;
step 302: according to the video description information, screening out user identifications of recommended users of which the video description information is matched with the video description information of the current user from a first non-friend user set of the current user;
step 303: and sending the user identification of the recommended user to the terminal.
Optionally, the screening, according to the video description information, a user identifier of a recommended user whose video description information matches with the video description information of the current user from the first non-friend user set of the current user includes:
when the video description information comprises audio description information, selecting a user identifier of a non-friend user of which the audio description information is matched with the audio description information of the current user from the first non-friend user set, and taking the selected user identifier of the non-friend user as a user identifier of a recommended user; and/or the presence of a gas in the gas,
and when the video description information comprises object information, selecting the user identification of the non-friend user of which the object information is matched with the object information of the current user from the first non-friend user set, and taking the user identification of the selected non-friend user as the user identification of the recommended user.
Optionally, the selecting, from the first set of non-friend users, the user identifier of the non-friend user whose object information matches the object information of the current user includes:
determining the user type of the current user according to the object information of the current user;
and selecting the user identification of the non-friend user with the user type same as that of the current user from the first non-friend user set according to the user type of the current user.
Optionally, before the user identifier of the recommended user whose video description information matches the video description information of the current user is screened from the first non-friend user set of the current user according to the video description information, the method further includes:
acquiring a second non-friend user set of the current user and acquiring a matching condition of the current user;
and selecting non-friend users meeting the matching condition from the second non-friend user set to form the first non-friend user set.
Optionally, the selecting, from the second non-friend user set, a non-friend user who meets the matching condition to form the first non-friend user set includes:
selecting non-friend users meeting the matching condition from the second non-friend user set to form a third non-friend user set;
and forming the first non-friend user set from the non-friend users of the third non-friend user set meeting a preset screening rule, wherein the preset screening rule is a position screening rule and/or a time screening rule for matching video files.
Optionally, the method further includes:
determining the user identification of the marked user marked by the current user in the first non-friend user set, wherein the marked user comprises the user who sends the request for pairing and/or deleting by the terminal;
and deleting the user identification of the marked user from the first non-friend user set.
Optionally, the method further includes:
and when the user identification of the non-friend user sending the pairing request to the current user exists in the first non-friend user set, taking the user identification of the non-friend user sending the pairing request to the current user as the user identification of the recommended user.
Optionally, the step of using the user identifier of the non-friend user who sends the pairing request to the current user as the user identifier of the recommended user includes:
selecting the user identification of the non-friend user meeting the position screening rule from the non-friend users sending the pairing request to the current user;
and taking the user identification of the selected non-friend user as the user identification of the recommended user.
Optionally, after sending the user identifier of the recommended user to the terminal, the method further includes:
receiving a pairing request which is sent by the terminal and paired with the recommended user;
and when the current user is successfully paired with the recommended user, acquiring a second paired video file of the recommended user, and sending the second paired video file to the terminal.
Optionally, the obtaining the second paired video file of the recommended user includes:
when the video file to be paired of the recommended user comprises a video file to be paired of which the video description information is matched with the video description information of the current user, taking the video file to be paired of which the video description information is matched with the video description information of the current user as the second video file to be paired;
and when the paired video file of which the video description information is matched with the video description information of the current user is deleted, taking the paired video file with the latest uploading time as the second paired video file.
In the embodiment of the invention, a server receives a matching instruction of a terminal, wherein the matching instruction carries video description information of a current user of the terminal, and the video description information is extracted from a first pairing video file of the current user by the terminal; the server screens out user identifications of recommended users of which the video description information is matched with the video description information of the current user from the first non-friend user set of the current user according to the matching instruction; and the server sends the user identification of the recommended user to the terminal. And the terminal receives the user identification of the recommended user of the server and displays the user identification of the recommended user on the recommendation interface of the current user. As the server recommends the user based on the video description information sent by the terminal, the video description information can show the personal characteristic information of the user, so that a recommended user matched with the personal characteristic information is screened out for the current user, and the accuracy of the recommended user is improved.
Fig. 4 is a signaling interaction diagram of a recommended user according to an embodiment of the present invention, where the method may be applied to a server and a terminal, and is implemented by the terminal and the server interactively, as shown in fig. 4, the method includes:
step 401: the terminal determines a first paired video file of a current user.
In the embodiment of the invention, the first pairing video file is a video file of the current user, which is acquired by the terminal through a social application program, and the first pairing video file is used for displaying information such as personal portraits, personal interests and hobbies or personal life scenes of the current user. When the terminal detects that the current user logs into the personal account in the social application program, the terminal may display a recommended user for the current user based on the first paired video file.
The first pairing video file may be a video file acquired by the terminal in real time, or a pairing video file recorded in the account of the current user and uploaded to the server, and specifically, this step may be implemented by the following steps 4011 and 4012.
Step 4011: and when the terminal is detected to log in the server, the terminal acquires the account state of the current user from the server.
In this step, when the terminal opens the social application program, the terminal obtains an account identifier and a password input by the current user on a login page, and logs in the current user to log in a personal account on the social application program according to the account identifier and the password. And when the login is successful, the terminal sends an acquisition instruction to the server, the acquisition instruction is used for indicating the server to return the account state of the current user, the server receives the acquisition instruction of the terminal, inquires and sends the account state of the current user to the terminal, and the terminal receives the account state of the current user.
The account status is used to indicate whether the current user records a status of a video file for pairing, that is, the account status indicates that the current user does not record a pairing video file, or the current user records a pairing video file. The account identifier may be set and changed according to the user requirement, which is not specifically limited in the embodiment of the present invention. For example, the account identifier may be a mobile phone number, a mailbox, or the like of the user.
Step 4012: when the account state indicates that the current user does not record the paired video file, the terminal acquires the video file set by the current user and takes the video file as the first paired video file; when the account status indicates that the current user has recorded the paired video file, the terminal takes the recorded paired video file as the first paired video file.
(I): when the account state indicates that the current user does not record the paired video file, the terminal displays a prompt message on the current interface for prompting the user to set the paired video file for pairing, displays a video button on the current interface, acquires the video file set by the current user when the terminal detects that the video button is triggered, and determines the video file as a first paired video file. As shown in fig. 5, the terminal may set the prompt message and the video button in the same interface, for example, the prompt message may be: shoot a matching video and look for your favorite bar. The video button can be a plus sign button below, so that a user can see the prompt message conveniently and directly trigger the video button to set.
The terminal can record a video file of a current user in real time as a first pairing video file, and can also obtain a video file locally from the terminal as the first pairing video file. Therefore, when the terminal detects that the video button is triggered, the terminal displays a third button and a fourth button on the current interface, wherein the third button is used for triggering a first instruction for acquiring the video file from the local, and the fourth button is used for triggering a second instruction for recording the video file in real time. When the terminal detects that the third button is triggered, the terminal generates a first instruction for acquiring a video file from the local; and when the terminal detects that the fourth button is triggered, the terminal generates a second instruction for recording the video file in real time. Based on the two obtaining modes triggered by the current user, the mode of the terminal obtaining the video file set by the current user can be realized by the following two modes.
In a first manner, when the terminal records the video file in real time, the step of acquiring the video file set by the current user by the terminal may be: and the terminal records the current user through a camera in the terminal according to the second instruction to obtain a video file of the current user, acquires an audio file of the current user, inserts the audio information in the audio file into the video file, and determines the video file with the inserted audio information as a first pairing video file.
The terminal may obtain the audio identifier of the audio file of the current user before the camera is turned on for recording, and the step of obtaining the audio file of the current user by the terminal may be: before the terminal starts the camera, displaying audio identifiers of a plurality of candidate audio files to a current user, acquiring the audio identifier selected by the current user, and acquiring the audio file corresponding to the audio identifier from the server according to the audio identifier.
In a second manner, when the terminal directly obtains the video file from the local, the step of obtaining the video file set by the current user by the terminal may be: the terminal displays the file identification of the local video file on the current display interface according to the first instruction; and acquiring a file identifier of a video file selected by a current user, determining a storage path of the video file corresponding to the selected file identifier from the corresponding relation between the file identifier and the storage path according to the selected file identifier, and acquiring the video file from a storage space indicated by the storage path by the terminal. And the terminal acquires an audio file of the current user, inserts the audio information in the audio file into the video file, and determines the video file with the inserted audio information as a first pairing video file.
The method for the terminal to acquire the audio file of the current user is consistent with the above implementation method, and is not described here any more.
(II): when the account status indicates that the current user has recorded the paired video file, the terminal directly takes the recorded paired video file as the first paired video file. In the social application, each user may correspond to a plurality of paired video files, and therefore, the step of using the recorded paired video file as the first paired video file by the terminal may be: the terminal selects the paired video file with the latest uploading time from the plurality of paired video files, and determines the selected paired video file as a first paired video file. In fact, the terminal obtains the first paired video file from the server. The acquisition process may be: the method comprises the steps that a terminal sends an obtaining instruction for obtaining a first paired video file to a server, the server receives the obtaining instruction, a paired video file with the latest uploading time is selected from a plurality of paired video files according to the obtaining instruction, the paired video file is sent to the terminal, the terminal receives the paired video file, and the selected paired video file is determined to be the first paired video file.
Step 402: and the terminal acquires the video description information of the first pairing video file.
In this embodiment of the present invention, the video description information is information for describing an audio file of the first paired video file and/or information of a video frame in the first paired video file. The terminal can obtain the description information of the audio file in the first pairing video file, and directly takes the description information of the audio file as the video description information; or the terminal extracts the description information of the video picture from the first pairing video file, and takes the description information of the video picture as video description information; or, the terminal acquires the description information of the audio file and the description information of the video picture in the first paired video file, and the description information of the audio file and the description information of the video picture form the video description information.
(I): when the video description information includes description information of an audio file, the step of the terminal acquiring the video description information of the first pairing video file may be: the terminal acquires an audio identifier of an audio file in the first pairing video file; the terminal acquires the audio description information of the audio file according to the audio identifier; the terminal takes the audio identification and the audio description information as the video description information.
In an embodiment of the present invention, the audio description information includes at least one of an audio type, a singer, an author, and an emotion-based tune. The terminal may locally store the correspondence between the audio identifier and the audio description information and obtain the audio description information locally, or the terminal may obtain the audio description information from the server without storing the correspondence.
When the account status indicates that the current user does not record the paired video file, that is, when the terminal records the paired video file in real time or obtains the video file locally, the terminal obtains the audio description information from the server, and specifically, the step of obtaining the audio description information of the audio file by the terminal according to the audio identifier may be: the terminal directly obtains the audio identifier selected by the current user, sends an obtaining instruction to the server according to the audio identifier, the server receives the obtaining instruction, obtains the audio description information of the audio file from the corresponding relation between the audio identifier and the audio description information according to the audio identifier, sends the audio description information to the terminal, and the terminal receives the audio description information.
When the account status indicates that the current user has recorded the paired video file, the terminal may directly obtain the audio description information from the local, and the step of obtaining the audio description information of the audio file by the terminal according to the audio identifier may be: and the terminal acquires the audio description information of the audio file from the corresponding relation between the audio identification and the audio description information according to the audio identification.
(II): when the video description information includes object information of a video picture, the step of the terminal acquiring the video description information of the first pairing video file may be: and the terminal acquires the object information of the video picture in the first pairing video file and takes the object information as the video description information.
In the embodiment of the invention, the terminal can acquire and store the object training set in advance, and the object information in the video picture is identified through the object training set. Specifically, the step of the terminal acquiring the object information of the video frame in the first paired video file may be: and the terminal extracts a key frame image from the first pairing video file, determines a reference image matched with the key frame image from a local object training set according to the key frame image, and acquires object information corresponding to the reference image as object information in a video picture.
In this step, since the number of images included in the first paired video file is large, in order to improve recommendation efficiency, the terminal may extract a preset number of images from the plurality of images included in the first paired video file according to a preset extraction rule, and use the preset number of images as the key frame images. The preset extraction rule may be to extract the pixels once every preset time, or extract a preset number of pixels with the largest pixel value, or the like. The embodiment of the present invention is not particularly limited to this.
It should be noted that the object training set includes reference images of various objects; for example, a plurality of reference images for a "cat", a reference image for a dog, and a reference image for plants such as flowers and grass. The terminal can train a large number of pictures containing a specified object through a specified training tool in advance to obtain a plurality of reference images corresponding to the specified object, wherein the reference images can be used for identifying whether the video picture contains the specified object, then, the terminal can form a target training set by the plurality of reference images corresponding to each object, and store the target training set in a local storage space in a static library mode, so that when the terminal needs to identify the video picture, the target training set is directly obtained from the storage space.
In addition, in the embodiment of the present invention, when the video description information includes description information of an audio file and description information of a video picture, the terminal may acquire the description information of the audio file and the description information of the video picture through the implementation manners in (a) and (b), and directly compose the acquired description information of the audio file and the acquired description information of the video picture into the video description information. The specific implementation manner of obtaining the description information of the audio file and the description information of the video frame is the same as the above manner, and is not described here any more.
Further, the terminal can record the object information included in the first pairing video file, so that the object information can be directly obtained when subsequent recommendation is facilitated. For example, the object information of the first pairing video file is marked in the form of a tag.
Step 403: and the terminal sends a matching instruction to the server.
In the embodiment of the invention, the matching instruction carries the video description information, and the matching instruction is used for indicating the server to return the user identifier of the recommended user recommended based on the video description information to the terminal. And the terminal generates a matching instruction according to the video description information and sends the matching instruction to the server. Wherein the user identification may be a nickname for the current user.
In a possible implementation manner, in order to improve the efficiency and accuracy of recommending users, the terminal may further obtain the pairing conditions set by the current user and send the pairing conditions to the server, so that the server performs preliminary screening first and then performs further screening based on the video description information. The process may be: the terminal acquires the pairing condition set by the current user; the terminal sends the pairing condition to the server. The pairing condition may be a limiting condition set by the current user from the perspective of age, gender, constellation, and the like, and may be specifically set and changed according to the user requirement, which is not specifically limited in the embodiment of the present invention. For example, the pairing condition may be: age 18-25 years, gender women, constellation of Capricorn, etc.
Step 404: and the server receives a matching instruction of the terminal.
In this step, the server receives a matching instruction sent by the terminal, and obtains video description information of a first pairing video file of the current user from the matching instruction.
In a possible implementation manner, the terminal may further send the matching condition to the server, and the server receives the matching condition sent by the terminal, so that the subsequent server returns the user identifier of the recommended user to the terminal based on the video description information and the matching condition.
Step 405: and the server determines a first non-friend user set of the current user according to the matching instruction.
In the embodiment of the invention, the first non-friend user set is a user which is not successfully paired with the current user. After receiving the matching instruction, the server determines the friend user of the current user from the corresponding relation between the user identification and the friend list according to the user identification of the current user, determines users except the friend user of the current user in all users of the social application program as non-friend users of the current user, and forms the non-friend users into a first non-friend user set.
In a possible implementation manner, the server may further filter, according to the pairing condition, the non-friend user set of the current user to obtain a first non-friend user set, and therefore, the step of determining, by the server according to the matching instruction, the first non-friend user set of the current user may be: the server obtains a second non-friend user set of the current user, obtains the matching conditions of the current user, and selects non-friend users meeting the matching conditions from the second non-friend user set to form the first non-friend user set.
The server determines the non-friend users of the current user according to the user identification of the current user, and the non-friend users form a second non-friend user set; and the server makes the non-friend users meeting the matching condition in the second non-friend user set into a first non-friend user set of the current user according to the matching condition.
The matching condition may be a condition set by the user, such as age and gender, and further, the server may further perform further screening based on a geographic location of each non-friend user or an upload time of the paired video file, and the step of selecting, by the server, a non-friend user meeting the matching condition from the second non-friend user set to form the first non-friend user set may be: and the server selects non-friend users meeting the matching condition from the second non-friend user set to form a third non-friend user set, and selects non-friend users meeting a preset screening rule from the third non-friend user set to form the first non-friend user set, wherein the preset screening rule is a position screening rule and/or a time screening rule for matching video files.
The location filtering rule is a filtering rule based on a geographic location distance of the user, and specifically may be: the distance between the current user and the current user does not exceed a preset distance, or the identification of the geographic position is consistent with the identification of the geographic position of the current user, and the like. The time screening rule for the paired video files is a screening rule based on the uploading time of the paired video files of the user, and specifically may be: the uploading time is not more than the preset time from the uploading time of the current user, or the uploading time is the preset number closest to the uploading time of the current user, and the like.
(I): when the preset filtering rule is a location filtering rule, the step of selecting, by the server, non-friend users meeting the preset filtering rule from the third non-friend user set to form the first non-friend user set may be: the server acquires the geographic position of the current user and the geographic position of each non-friend user in the third non-friend user set, selects non-friend users, the distance between which and the current user does not exceed a preset distance, in the third non-friend user set according to the geographic position of the current user and the geographic position of each non-friend user, and forms the selected non-friend users into a first non-friend user set. Or, the server may further obtain the location identifier of the current user and the location identifier of each non-friend user in the third non-friend user set, select, according to the location identifier of the current user and the location identifier of each non-friend user, a non-friend user whose location identifier is the same as the location identifier of the current user in the third non-friend user set, and form the selected non-friend users into the first non-friend user set.
The location identifier may be a name of a city where the current user is located. The preset distance may be set and changed according to the user's needs, which is not specifically limited in the embodiment of the present invention. For example, the preset distance may be 10km, 20km, or the like.
(II): when the preset screening rule is a time screening rule for matching video files, the step of selecting, by the server, non-friend users meeting the preset screening rule from the third non-friend user set to form the first non-friend user set may be: the server obtains first uploading time of a first pairing video file of the current user and second uploading time of a pairing video file of each non-friend user in a third non-friend user set, non-friend users with the difference between the second uploading time and the first uploading time not exceeding preset time are selected in the third non-friend user set according to the first uploading time and the second uploading time, and the selected non-friend users form the first non-friend user set. Or the server obtains the first uploading time of the first paired video file of the current user and the second uploading time of the paired video file of each non-friend user in the third non-friend user set, selects a preset number of non-friend users with the minimum difference between the second uploading time and the first uploading time in the third non-friend user set according to the first uploading time and the second uploading time, and forms the selected non-friend users into the first non-friend user set.
The preset time and the preset number can be set and changed according to the needs of the user, and the embodiment of the invention is not particularly limited to this. For example, the preset time may be 12 hours, 2 days, etc. The predetermined number may be 10, 20, etc.
It should be noted that the server may further perform screening according to the location screening rule and the time screening rule for matching the video file, specifically, the server may perform screening according to the priority of the location screening rule and the priority of the time screening rule for matching the video file, taking the case that the priority of the time screening rule for matching the video file is greater than the priority of the location screening rule, the screening process of the first non-friend user set may be: and the server selects a plurality of non-friend users meeting the time screening rule of the paired video files from the third non-friend user set according to the time screening rule of the paired video files. Then, the server acquires the non-friend users meeting the position screening rule from the plurality of non-friend users according to the position screening rule. The server forms the non-friend users meeting the time screening rule and the position screening rule into a first non-friend user set.
In one possible design, the current user may mark the recommended user displayed by the terminal, and interact with the interested recommended user through the terminal, for example, send a pairing request; the current user may also ignore the recommending user when the recommending user is not interested. However, these tagged users are all users that the current user has already viewed, and there may be tagged users that the current user has already tagged in the first set of non-buddy users. In order to improve the accuracy and timeliness of the recommendation user, the server may also directly delete the tagged user from the first non-buddy user set, and correspondingly, the step of determining the first non-buddy user set of the current user by the server may further be: the server determines the user identification of the marked user marked by the current user in the first non-friend user set, wherein the marked user comprises the user who sends the pairing request and/or the deletion request by the terminal; the server deletes the user identification of the tagged user from the first set of non-buddy users.
Step 406: and the server screens out the user identification of the recommended user of which the video description information is matched with the video description information of the current user from the first non-friend user set of the current user according to the video description information.
In the embodiment of the present invention, the video description information is audio description information and/or object information, and accordingly, the step of the server performing screening based on the video description information may be implemented in the following two ways.
(I): when the video description information comprises audio description information, the server selects the user identification of the non-friend user of which the audio description information is matched with the audio description information of the current user from the first non-friend user set, and takes the user identification of the selected non-friend user as the user identification of the recommended user.
In this step, when the video description information includes audio description information, the video description information may further include an audio identifier corresponding to the audio description information, the server may first obtain, according to the audio identifier, a plurality of non-friend users whose audio identifiers are the same as the audio identifier of the current user from the first set of non-friend users, then select, from the plurality of non-friend users, a user identifier of a non-friend user whose audio description information matches the audio description information of the current user, and use the user identifier of the non-friend user selected based on the audio description information as the user identifier of the recommended user.
When there is no non-friend user whose audio identifier is the same as the audio identifier of the current user, or the number of non-friend users whose audio identifiers are the same as the audio identifier of the current user is small, the server may further perform screening of recommended users based on the audio description information, and the step of the server selecting the user identifier of the non-friend user whose audio description information matches the audio description information of the current user from the first set of non-friend users may further be: the server acquires audio description information of a pairing video file of each non-friend user in the first non-friend user set, determines whether the audio description information of the current user is matched with the audio description information of each non-friend user according to the audio description information of the current user, and determines the non-friend user of which the audio description information is matched with the audio description information of the current user as a recommended user.
Wherein the audio description information comprises at least one of audio type, singer, author, and emotion-based tune. When the audio description information includes one of an audio type, a singer, an author, and an emotion-based tune, taking the singer as an example, the step of the server determining whether the audio description information of the current user matches with the audio description information of each non-friend user may be: and the server determines the non-friend user with the same audio description information as the current user as a recommended user matched with the current user according to the audio description information of the current user, determines the non-friend user with the same audio description information as the current user as a non-friend user unmatched with the current user, and does not recommend the unmatched non-friend user subsequently.
When the audio description information includes a plurality of items of information among an audio type, a singer, an author, and an emotion-based tune, the server may determine a matching degree between the audio description information of the current user and the audio description information of each non-friend user according to a weight of each item. Specifically, taking the example that the audio description information includes the creator and the singer, the step of determining, by the server, whether the audio description information of the current user matches with the audio description information of each non-friend user may be: the server calculates a first matching degree between the audio description information of the current user and the audio description information of each non-friend user according to the author in the audio description information of the current user and the author in the audio description information of each non-friend user; and according to the singer in the audio description information of the current user and the singer in the audio description information of each non-friend user, calculating a second matching degree between the audio description information of the current user and the audio description information of each non-friend user, acquiring a first weight corresponding to the creator and a second weight corresponding to the singer in the audio description information, taking the sum of the product of the first weight and the first matching degree and the product of the second weight and the second matching degree as the matching degree corresponding to each non-friend user, and determining the non-friend user with the matching degree greater than a preset threshold value as a recommended user.
The first weight, the second weight and the preset threshold may be set and changed according to a user requirement, which is not specifically limited in the embodiment of the present invention. For example, the first weight may be 0.4, the second weight may be 0.6, and the predetermined threshold may be 10.
(II): when the video description information comprises object information, the server selects the user identification of the non-friend user of which the object information is matched with the object information of the current user from the first non-friend user set, and takes the user identification of the selected non-friend user as the user identification of the recommended user.
In this step, the server may perform recommendation directly based on the object information, or may perform recommendation based on a user type corresponding to the object information.
When the server makes a recommendation based on the object information, the step of the server selecting the user identifier of the non-friend user whose object information matches the object information of the current user from the first set of non-friend users may be: the server acquires the user identification of each non-friend user in the first non-friend user set, acquires the video description information of each non-friend user according to the user identification, compares whether the object information of the current user is the same as the object information of each non-friend user, and determines the user identification of the recommended user according to the user identification of the non-friend user whose object information is the same as the object information of the current user in the first non-friend user set.
When the server makes a recommendation based on the user type, the step may be: the server determines the user type of the current user according to the object information of the current user; and the server selects the user identification of the non-friend user with the user type same as that of the current user from the first non-friend user set according to the user type of the current user.
In the embodiment of the invention, the server acquires the user type of the current user according to the object information of the current user, acquires the user identification of each non-friend user in the first non-friend user set, acquires the user type of each non-friend user according to the user identification, compares whether the user type of the current user is the same as the user type of each non-friend user, and determines the user identification of the recommended user according to the user identification of the non-friend user with the same user type as the current user in the first non-friend user set.
For example, when the object information of a certain user is an animal such as a cat, a dog, etc., the server may divide the user type of the user into favorite small object types, and the server stores the correspondence between the object information and the user type, and then the step of obtaining the user type of the current user by the server according to the object information of the current user may be: and the server acquires the user type of the current user from the corresponding relation between the object information and the user type according to the object information of the current user.
It should be noted that, when the server filters the recommended user from the first non-friend user set, a non-friend user who has sent the pairing request to the current user may exist in the first non-friend user set, and the recommended user may be filtered by the above method for the non-friend user who has sent the pairing request to the current user or the non-friend user who has not sent the pairing request to the current user in the first non-friend user set.
In a possible design, since there may be a non-friend user who has sent a pairing request to the current user in the first non-friend user set, which indicates that the non-friend user is interested in the current user, in order to improve the probability of successful pairing among recommended users, the server may also preferentially recommend the non-friend user who has sent the pairing request to the current user, specifically, the preferentially recommending process may be: and when the user identification of the non-friend user sending the pairing request to the current user exists in the first non-friend user set, the server takes the user identification of the non-friend user sending the pairing request to the current user as the user identification of the recommended user.
Further, when the number of the non-friend users who have sent the pairing request is large, the server may further perform screening based on the pairing condition of the current user, and the step of the server taking the user identifier of the non-friend user who has sent the pairing request to the current user as the user identifier of the recommended user may be: and the server selects the user identification of the non-friend user meeting the position screening rule from the non-friend users sending the pairing request to the current user, and takes the selected user identification of the non-friend user as the user identification of the recommended user.
Step 407: and the server sends the user identification of the recommended user to the terminal.
In the embodiment of the invention, when the server sends the user identifier of the recommended user to the terminal, the server can also send some personal information of the recommended user, such as the information of the age, the geographic position or the professional field of the recommended user, so that the information amount of the recommended user is increased, the current user can know the recommended user from multiple angles, and the successful matching probability among the recommended users is greatly improved.
In a possible design, the server may further send the paired video file of the recommended user to the terminal, so that when the terminal displays the recommended user, the paired video file of the recommended user may also be played, so that the current user may further know personal information that the recommended user wants to show, and the recommendation efficiency of the recommended user is further improved.
Step 408: and the terminal receives the user identification of the recommended user of the server and displays the user identification of the recommended user on the recommendation interface of the current user.
And the terminal receives the user identification of the recommended user sent by the server and displays the user identification of the recommended user in a recommendation interface of the current user. And the terminal can also receive the personal information of the recommended user and the matched video file sent by the server, and the terminal displays the personal information of the recommended user and a cover image of the matched video file on a recommendation interface. As shown in fig. 6, the terminal may use a cover image of the pairing video file of the recommended user as a base map, and insert the user identifier and personal information such as the age, sex, position information, and constellation information of the user into the cover image.
In the embodiment of the invention, after the current user browses the recommended user in the recommendation interface, the terminal also needs to perform human-computer interaction with the terminal to inform whether the terminal is interested in the recommended user, so that the terminal also needs to display a first button and a second button in the recommendation interface, wherein the first button is used for triggering a pairing request, and the second button is used for triggering a deletion request; acquiring whether the current user is interested in the recommended user or not through the first button or the second button, and when the current user is interested in the recommended user, namely when the terminal detects that the second button is triggered, the terminal automatically deletes the user identifier of the recommended user and continuously displays the next recommended user for the current user; when the current user is interested in the recommended user, the terminal sends a pairing request to the server through the following step a, and further, when the recommended user is also interested in the current user, the current user and the recommended user are successfully paired.
Step a: when the first button is detected to be triggered, the terminal sends a pairing request for pairing the current user and the recommended user to the server; and when the current user is successfully paired with the recommended user, the terminal receives a second paired video file of the recommended user returned by the server, and plays the second paired video file on the recommended interface of the current user.
In the embodiment of the invention, when the first button is detected to be triggered, the terminal generates a pairing request according to the user identifier of the current user and the user identifier of the recommended user, sends the pairing request of the current user and the recommended user to the server, the server receives the pairing request which is sent by the terminal and is paired with the recommended user, sends the user identifier of the current user to the user terminal of the recommended user according to the pairing request, and the user terminal of the recommended user receives the user identifier of the current user and displays the user identifier of the current user on the recommended interface of the recommended user, so that the recommended user can know the user identifier of the current user interested in the recommended user, and the probability of successful pairing is greatly improved.
Further, when the recommending user is also interested in the current user, the recommending user may trigger an agreement pairing button in a terminal of the recommending user, when the terminal of the recommending user detects that the agreement pairing button is triggered, a pairing request for pairing the recommending user with the current user is sent to a server, and the server receives the pairing request sent by the terminal of the recommending user and determines that the current user is successfully paired with the recommending user.
When the server determines that the pairing is successful, a first message of successful pairing can be sent to the terminal of the recommended user, a second message of successful pairing can be sent to the terminal of the current user, the terminal of the current user receives the second message, the second message is displayed on the current display interface, and furthermore, the terminal of the current user can display the head portraits of the current user and the recommended user on the current display interface so as to enrich the content of the current interface. In addition, the terminal of the current user can also display a chat button on the current display interface, and when the chat button is triggered, the terminal of the current user sends a chat request to the server, so that the current user and the recommended user can conveniently start chatting, and the user experience is improved. As shown in fig. 7, when the pairing is successful, the terminal of the current user may display a second message on the current display interface: the pairing is successful. And the terminal displays the head portraits of the two successfully paired users on the current display interface.
Further, the server acquires a second paired video file of the recommended user, and sends the second paired video file to the terminal of the current user. And the terminal of the current user receives the second pairing video file and plays the second pairing video file on the recommendation interface of the current user.
Meanwhile, the server also obtains a first pairing video file of the current user and sends the first pairing video file to the terminal of the recommended user. And the terminal of the recommending user receives the first pairing video file and plays the first pairing video file on a recommending interface of the recommending user.
It should be noted that, a time when the recommending user triggers a pairing agreement button in a terminal of the recommending user may be delayed, a plurality of paired video files may be uploaded in an account of the recommending user, it is obvious that a video file browsed by the current user when the recommending user is interested in the recommending user is a paired video file matched with video description information of the current user, and when the time when the recommending user triggers the pairing agreement button is delayed, the recommending user may delete the paired video file matched with the video description information of the current user, therefore, in order to improve a probability of successful pairing, the server may screen out a second paired video file from the plurality of paired video files, and the step of acquiring the second paired video file of the recommending user by the server may be: when the video file to be paired of the recommended user comprises a video file to be paired of which the video description information is matched with the video description information of the current user, the server takes the video file to be paired of which the video description information is matched with the video description information of the current user as the second video file to be paired; and when the paired video file of which the video description information is matched with the video description information of the current user is deleted, the server takes the paired video file with the latest uploading time as the second paired video file.
The step in which the server determines whether the paired video file matches the video description information of the current user based on the uploading time of the paired video file, and then takes the paired video file whose video description information matches the video description information of the current user as the second paired video file may be: the server acquires the uploading time of each paired video file in the plurality of paired video files of the recommended user, acquires the trigger time of the recommended user for triggering a first button paired with the recommended user, and takes the paired video file which is not more than a preset time length away from the trigger time as a second paired video file matched with the video description information of the current user.
Of course, the current user may also not be interested in the recommended user displayed by the terminal, or the server does not screen out the recommended user matched with the video description information based on the video description information of the current user, sends an indication message of matching failure to the terminal, and the terminal receives the indication message of matching failure and displays the indication message on the current display interface. Further, the terminal may prompt the user to record the paired video file again, and recommend based on the new paired video file, as shown in fig. 8, when the terminal receives the indication message of the matching failure, the terminal may display the indication message at present: and if the recommended user is not matched, shooting a new matched video file, and expecting a new reason bar.
Further, a plurality of paired video files may exist in the account of the current user, and the server may recommend a recommended user who may be interested to the current user based on each of the plurality of paired video files. When the pairing is successful, each paired video file of the current user may correspond to a plurality of friend users successfully paired based on the paired video file, so that the current user can pair the plurality of friend users based on different paired video files, and the number of recommended users in the current user is enriched.
In the embodiment of the invention, a terminal acquires video description information of a first pairing video file of a current user and sends a matching instruction to a server, the server receives the matching instruction of the terminal, and the server screens out a user identifier of a recommended user of which the video description information is matched with the video description information of the current user from a first non-friend user set of the current user according to the matching instruction; and the server sends the user identification of the recommended user to the terminal. And the terminal receives the user identification of the recommended user of the server and displays the user identification of the recommended user on the recommendation interface of the current user. As the server recommends the user based on the video description information sent by the terminal, the video description information can show the personal characteristic information of the user, so that a recommended user matched with the personal characteristic information is screened out for the current user, and the accuracy of the recommended user is improved.
Fig. 9 is a block diagram of an apparatus for recommending a user according to an embodiment of the present invention, where the apparatus may be applied in a terminal, and the apparatus includes:
a first determining module 901, configured to determine a first paired video file of a current user;
a first obtaining module 902, configured to obtain video description information of the first paired video file;
a first sending module 903, configured to send a matching instruction to a server, where the matching instruction carries the video description information, and the matching instruction is used to instruct the server to return, to a terminal, a user identifier of a recommended user recommended based on the video description information;
a first receiving module 904, configured to receive a user identifier of a recommended user of the server, and display the user identifier of the recommended user on a recommendation interface of the current user.
Optionally, the first obtaining module 902 includes:
the acquiring unit is used for acquiring the audio identifier of the audio file in the first pairing video file;
the acquiring unit is further configured to acquire audio description information of the audio file according to the audio identifier;
and the unit is used for taking the audio identification and the audio description information as the video description information.
Optionally, the audio description information includes at least one of audio type, singer, author, and emotion-based tune.
Optionally, the first obtaining module 902 is further configured to obtain object information of a video picture in the first paired video file, and use the object information as the video description information.
Optionally, the obtaining unit is further configured to extract a key frame image from the first paired video file; according to the key frame image, determining a reference image matched with the key frame image from a local object training set, wherein the object training set comprises reference images of various objects; and acquiring object information corresponding to the reference image as object information in a video picture.
Optionally, the apparatus further comprises:
the display module is used for displaying a first button and a second button in the recommendation interface, wherein the first button is used for triggering a pairing request, and the second button is used for triggering a deletion request;
the second sending module is used for sending a pairing request for pairing the current user and the recommended user to the server when the first button is detected to be triggered;
and the playing module is used for receiving a second matching video file of the recommended user returned by the server when the current user is successfully matched with the recommended user, and playing the second matching video file on the recommended interface of the current user.
Optionally, the apparatus further comprises:
the second obtaining module is used for obtaining the pairing condition set by the current user;
and the third sending module is used for sending the pairing condition to the server so that the server returns the user identifier of the recommended user to the terminal based on the video description information and the pairing condition.
Optionally, the first determining module 901 is further configured to, when it is detected that the terminal logs in the server, obtain the account status of the current user from the server; when the account state indicates that the current user does not record the paired video file, acquiring the video file set by the current user, and taking the video file as the first paired video file; and when the account state indicates that the current user records the paired video file, taking the recorded paired video file as the first paired video file.
In the embodiment of the invention, a terminal acquires video description information of a first pairing video file of a current user and sends a matching instruction to a server, wherein the matching instruction carries the video description information and is used for indicating the server to return a user identifier of a recommended user recommended based on the video description information to the terminal; and the terminal receives the user identification of the recommended user of the server and displays the user identification of the recommended user on the recommendation interface of the current user. The terminal acquires the video description information of the first pairing video file of the current user from the server and sends the video description information of the first pairing video file of the current user to the server, so that the server can recommend the user based on the video description information sent by the terminal, the video description information can display the personal characteristic information of the user, the recommended user matched with the personal characteristic information can be screened out for the current user, and the accuracy of the recommended user is improved.
Fig. 10 is a block diagram of an apparatus for recommending a user according to an embodiment of the present invention, where the apparatus may be applied in a server, and the apparatus includes:
a second receiving module 1001, configured to receive a matching instruction of a terminal, where the matching instruction carries video description information of a current user of the terminal, and the video description information is extracted by the terminal from a first paired video file of the current user;
the screening module 1002 is configured to screen, according to the matching instruction, a user identifier of a recommended user whose video description information matches the video description information of the current user from the first non-friend user set of the current user;
a fourth sending module 1003, configured to send the user identifier of the recommended user to the terminal.
Optionally, the screening module 1002 includes:
a first selecting unit, configured to select, when the video description information includes audio description information, a user identifier of a non-friend user whose audio description information matches the audio description information of the current user from the first set of non-friend users, and use the user identifier of the selected non-friend user as a user identifier of a recommended user; and/or the presence of a gas in the gas,
and the second selection unit is used for selecting the user identification of the non-friend user of which the object information is matched with the object information of the current user from the first non-friend user set when the video description information comprises the object information, and taking the user identification of the selected non-friend user as the user identification of the recommended user.
Optionally, the second selecting unit is further configured to determine a user type of the current user according to the object information of the current user; and selecting the user identification of the non-friend user with the user type same as that of the current user from the first non-friend user set according to the user type of the current user.
Optionally, the apparatus further comprises:
a third obtaining module, configured to obtain a second non-friend user set of the current user, and obtain a matching condition of the current user;
and the selection module is used for selecting the non-friend users meeting the matching condition from the second non-friend user set to form the first non-friend user set.
Optionally, the selecting module is further configured to select a non-friend user meeting the matching condition from the second non-friend user set to form a third non-friend user set; and forming the first non-friend user set from the non-friend users of the third non-friend user set meeting a preset screening rule, wherein the preset screening rule is a position screening rule and/or a time screening rule for matching video files.
Optionally, the apparatus further comprises:
a second determining module, configured to determine a user identifier of a tagged user tagged by the current user in the first set of non-buddy users, where the tagged user includes a user to whom the terminal has sent a pair request and/or a delete request;
and the deleting module is used for deleting the user identification of the marked user from the first non-friend user set.
Optionally, the apparatus further comprises:
and the module is used for taking the user identifier of the non-friend user sending the pairing request to the current user as the user identifier of the recommended user when the user identifier of the non-friend user sending the pairing request to the current user exists in the first non-friend user set.
Optionally, the acting module is further configured to select a user identifier of a non-buddy user who meets the location filtering rule from non-buddy users who send pairing requests to the current user; and taking the user identification of the selected non-friend user as the user identification of the recommended user.
Optionally, the apparatus further comprises:
the third receiving module is used for receiving a pairing request which is sent by the terminal and is paired with the recommended user;
and the fourth obtaining module is used for obtaining a second pairing video file of the recommended user and sending the second pairing video file to the terminal when the current user is successfully paired with the recommended user.
Optionally, the fourth obtaining module is further configured to, when the paired video file of the recommended user includes a paired video file whose video description information matches the video description information of the current user, use the paired video file whose video description information matches the video description information of the current user as the second paired video file; and when the paired video file of which the video description information is matched with the video description information of the current user is deleted, taking the paired video file with the latest uploading time as the second paired video file.
In the embodiment of the invention, a server receives a matching instruction of a terminal, wherein the matching instruction carries video description information of a current user of the terminal, and the video description information is extracted from a first pairing video file of the current user by the terminal; the server screens out user identifications of recommended users of which the video description information is matched with the video description information of the current user from the first non-friend user set of the current user according to the matching instruction; and the server sends the user identification of the recommended user to the terminal. And the terminal receives the user identification of the recommended user of the server and displays the user identification of the recommended user on the recommendation interface of the current user. As the server recommends the user based on the video description information sent by the terminal, the video description information can show the personal characteristic information of the user, so that a recommended user matched with the personal characteristic information is screened out for the current user, and the accuracy of the recommended user is improved.
It should be noted that: in the device for recommending a user according to the above embodiment, when recommending a user, the division of the functional modules is merely used as an example, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the device for recommending users and the method embodiment for recommending users provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiment and are not described herein again.
Fig. 11 is a schematic structural diagram of a terminal according to an embodiment of the present invention. The terminal may be used to implement the functions performed by the terminal in the method of recommending users shown in the above embodiments. Specifically, the method comprises the following steps:
terminal 1100 can include, among other components, RF (Radio Frequency) circuitry 1110, memory 1120 including one or more computer-readable storage media, input unit 1130, display unit 1140, sensors 1150, audio circuitry 1160, transmission module 1170, processor 1180 including one or more processing cores, and power supply 1190. Those skilled in the art will appreciate that the terminal structure shown in fig. 11 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:
RF circuit 1110 may be used for receiving and transmitting signals during a message transmission or communication process, and in particular, for receiving downlink messages from a base station and then processing the received downlink messages by one or more processors 1180; in addition, data relating to uplink is transmitted to the base station. In general, RF circuitry 1110 includes, but is not limited to, an antenna, at least one Amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, and the like. In addition, the RF circuit 1110 can also communicate with a network and other terminals through wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to GSM (Global System for Mobile communications), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), and the like.
The memory 1120 may be used to store software programs and modules corresponding to the terminal as shown in the above exemplary embodiments, and the processor 1180 may execute various functional applications and data processing, such as implementing video-based interaction, by operating the software programs and modules stored in the memory 1120. The memory 1120 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the terminal 1100, and the like. Further, the memory 1120 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 1120 may also include a memory controller to provide the processor 1180 and the input unit 1130 access to the memory 1120.
The input unit 1130 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. In particular, input unit 1130 may include touch-sensitive surface 1131 as well as other input terminals 1132. The touch-sensitive surface 1131, also referred to as a touch display screen or a touch pad, may collect touch operations by a user (e.g., operations by a user on or near the touch-sensitive surface 1131 using a finger, a stylus, or any other suitable object or attachment), and drive the corresponding link device according to a preset program. Alternatively, touch-sensitive surface 1131 may include two portions, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 1180, and can receive and execute commands sent by the processor 1180. Additionally, touch-sensitive surface 1131 may be implemented using various types of resistive, capacitive, infrared, and surface acoustic waves. The input unit 1130 may include other input terminals 1132 in addition to the touch-sensitive surface 1131. In particular, other input terminals 1132 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.
The display unit 1140 may be used to display information input by or provided to the user and various graphical user interfaces of the terminal 1100, which may be made up of graphics, text, icons, video, and any combination thereof. The Display unit 1140 may include a Display panel 1141, and optionally, the Display panel 1141 may be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or the like. Further, touch-sensitive surface 1131 may cover display panel 1141, and when touch operation is detected on or near touch-sensitive surface 1131, the touch operation is transmitted to processor 1180 to determine the type of touch event, and processor 1180 then provides corresponding visual output on display panel 1141 according to the type of touch event. Although in FIG. 11, touch-sensitive surface 1131 and display panel 1141 are two separate components to implement input and output functions, in some embodiments, touch-sensitive surface 1131 and display panel 1141 may be integrated to implement input and output functions.
The terminal 1100 can also include at least one sensor 1150, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor that adjusts the brightness of the display panel 1141 according to the brightness of ambient light, and a proximity sensor that turns off the display panel 1141 and/or the backlight when the terminal 1100 moves to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), can detect the magnitude and direction of gravity when the mobile phone is stationary, and can be used for applications of recognizing the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be configured in the terminal 1100, detailed descriptions thereof are omitted.
Audio circuitry 1160, speakers 1161, and microphone 1162 may provide an audio interface between a user and terminal 1100. The audio circuit 1160 may transmit the electrical signal converted from the received audio data to the speaker 1161, and convert the electrical signal into a sound signal for output by the speaker 1161; on the other hand, the microphone 1162 converts the collected sound signal into an electric signal, receives it by the audio circuit 1160, converts it into audio data, processes it by the audio data output processor 1180, and transmits it to, for example, another terminal via the RF circuit 1110, or outputs it to the memory 1120 for further processing. Audio circuitry 1160 may also include an earbud jack to provide peripheral headset communication with terminal 1100.
The terminal 1100, via the transmission module 1170, can facilitate user emailing, web browsing, and streaming media, etc., which provides wireless or wired broadband internet access to the user. Although fig. 11 shows the transmission module 1170, it is understood that it does not belong to the essential constitution of the terminal 1100 and may be omitted entirely as needed within the scope not changing the essence of the invention.
The processor 1180 is a control center of the terminal 1100, links various parts of the entire handset using various interfaces and lines, and performs various functions of the terminal 1100 and processes data by operating or executing software programs and/or modules stored in the memory 1120 and calling data stored in the memory 1120, thereby performing overall monitoring of the handset. Optionally, processor 1180 may include one or more processing cores; preferably, the processor 1180 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated within processor 1180.
Terminal 1100 can also include a power supply 1190 (e.g., a battery) for providing power to various components, which can be logically coupled to processor 1180 via a power management system that can be configured to manage charging, discharging, and power consumption. Power supply 1190 may also include one or more dc or ac power supplies, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, or any other component.
Although not shown, the terminal 1100 may further include a camera, a bluetooth module, etc., which will not be described herein. Specifically, in the present embodiment, the display unit of the terminal 1100 is a touch screen display, and the terminal 1100 further includes a memory and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for implementing the operations performed by the terminal in the embodiments.
Fig. 12 is a schematic structural diagram of a server according to an embodiment of the present invention. Referring to fig. 12, server 1200 includes a processing component 1222 that further includes one or more processors and memory resources, represented by memory 1232, for storing instructions, such as application programs, that are executable by processing component 1222. The application programs stored in memory 1232 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1222 is configured to execute instructions to perform the method of recommending users described above.
The server 1200 may also include a power component 1226 configured to perform power management of the device 1200, a wired or wireless network interface 1250 configured to connect the device 1200 to a network, and an input output (I/O) interface 1258. The apparatus 1200 may operate based on an operating system, such as Windows Server, stored in the memory 1232TM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTMOr the like.
In an exemplary embodiment, a computer-readable storage medium, such as a memory, storing a computer program is also provided, which when executed by a processor implements the method of recommending users in the above embodiments. For example, the computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (18)

1. A method for recommending users is applied to a terminal, and the method comprises the following steps:
when the terminal is detected to log in a server, acquiring the account state of the current user from the server; when the account state indicates that the current user does not record the paired video file, acquiring the video file set by the current user, and taking the video file as a first paired video file, wherein the first paired video file comprises at least one of personal portraits, personal interests and hobbies or personal life scenes of the current user; when the account state indicates that the current user records a paired video file, taking the recorded paired video file as the first paired video file;
acquiring video description information of the first paired video file, wherein the video description information is used for describing information of an audio file and information of a video picture in the first paired video file;
sending a matching instruction to the server, wherein the matching instruction is used for indicating the server to return the user identification of the recommended user to the terminal; receiving a user identifier of a recommended user of the server, and displaying the user identifier of the recommended user on a recommendation interface of the current user;
the server is used for receiving the matching instruction, the matching instruction carries the video description information, and the user identification of the recommended user with the video description information matched with the video description information of the current user is screened out from the first non-friend user set of the current user according to the matching instruction;
the server is further used for determining the user identification of the marked user marked by the current user in the first non-friend user set, wherein the marked user comprises the user who sends the pairing request and/or the deletion request by the terminal; deleting the user identification of the tagged user from the first set of non-buddy users;
the server is further configured to select, as the user identifier of the recommended user, a user identifier of a non-friend user that satisfies a location screening rule from non-friend users who send pairing requests to the current user when the user identifiers of the non-friend users who send pairing requests to the current user exist in the first set of non-friend users.
2. The method of claim 1, wherein obtaining video description information of the first paired video file comprises:
acquiring an audio identifier of an audio file in the first pairing video file;
acquiring audio description information of the audio file according to the audio identifier;
and taking the audio identification and the audio description information as the video description information.
3. The method of claim 2, wherein the audio description information comprises at least one of audio type, singer, author, and emotion-based tune.
4. The method according to claim 1 or 2, wherein the obtaining video description information of the first paired video file comprises:
and acquiring object information of a video picture in the first paired video file, and taking the object information as the video description information.
5. The method of claim 4, wherein obtaining object information of video pictures in the first paired video file comprises:
extracting a key frame image from the first paired video file;
according to the key frame images, determining reference images matched with the key frame images from a local object training set, wherein the object training set comprises reference images of various objects;
and acquiring object information corresponding to the reference image as object information in a video picture.
6. The method of claim 1, wherein after the user identification of the recommending user is displayed on the recommending interface of the current user, the method further comprises:
displaying a first button and a second button in the recommendation interface, wherein the first button is used for triggering a pairing request, and the second button is used for triggering a deletion request;
when the first button is detected to be triggered, sending a pairing request for pairing the current user and the recommended user to the server;
and when the current user is successfully paired with the recommended user, receiving a second paired video file of the recommended user returned by the server, and playing the second paired video file on a recommended interface of the current user.
7. The method of claim 1, wherein prior to obtaining the account status of the current user from the server, the method further comprises:
acquiring the pairing conditions set by the current user;
and sending the pairing condition to the server so that the server returns the user identification of the recommended user to the terminal based on the video description information and the pairing condition.
8. A method for recommending users, the method is applied to a server, and the method comprises the following steps:
receiving a matching instruction of a terminal, wherein the matching instruction carries video description information of a current user of the terminal, the video description information is extracted by the terminal from a first pairing video file of the current user, the video description information refers to information used for describing an audio file and a video picture in the first pairing video file, the first pairing video file is determined according to an account state of the current user obtained from the server when the terminal detects that the terminal logs in the server, and the first pairing video file comprises at least one of personal portraits, personal interests and hobbies or personal life scenes of the current user;
the terminal is used for acquiring a video file set by the current user as the first pairing video file when the account state indicates that the current user does not record the pairing video file; when the account state indicates that the current user records a paired video file, taking the recorded paired video file as the first paired video file;
according to the matching instruction, screening out user identifications of recommended users of which the video description information is matched with the video description information of the current user from a first non-friend user set of the current user;
sending the user identification of the recommended user to the terminal;
the method further comprises the following steps:
determining user identifications of marked users marked by the current user in the first non-friend user set, wherein the marked users comprise users who send pairing requests and/or deletion requests by the terminal; deleting the user identification of the tagged user from the first set of non-buddy users;
the method further comprises the following steps:
and when the user identification of the non-friend user sending the pairing request to the current user exists in the first non-friend user set, selecting the user identification of the non-friend user meeting the position screening rule from the non-friend users sending the pairing request to the current user as the user identification of the recommended user.
9. The method of claim 8, wherein the screening out, according to the matching instruction, the user identifier of the recommended user whose video description information matches the video description information of the current user from the first set of non-friend users of the current user comprises:
when the video description information comprises audio description information, selecting a user identifier of a non-friend user of which the audio description information is matched with the audio description information of the current user from the first non-friend user set, and taking the selected user identifier of the non-friend user as a user identifier of a recommended user; and/or the presence of a gas in the gas,
and when the video description information comprises object information, selecting the user identification of the non-friend user of which the object information is matched with the object information of the current user from the first non-friend user set, and taking the user identification of the selected non-friend user as the user identification of the recommended user.
10. The method of claim 9, wherein selecting the user identification of the non-buddy user whose object information matches the object information of the current user from the first set of non-buddy users comprises:
determining the user type of the current user according to the object information of the current user;
and selecting the user identification of the non-friend user with the user type same as that of the current user from the first non-friend user set according to the user type of the current user.
11. The method of claim 8, wherein before the step of screening out the user identifier of the recommended user whose video description information matches with the video description information of the current user from the first set of non-friend users of the current user according to the matching instruction, the method further comprises:
acquiring a second non-friend user set of the current user and acquiring a pairing condition of the current user;
and selecting non-friend users meeting the pairing conditions from the second non-friend user set to form the first non-friend user set.
12. The method of claim 11, wherein the selecting non-friend users from the second set of non-friend users who satisfy the pairing condition to form the first set of non-friend users comprises:
selecting non-friend users meeting the pairing conditions from the second non-friend user set to form a third non-friend user set;
and forming the first non-friend user set from the non-friend users of the third non-friend user set meeting a preset screening rule, wherein the preset screening rule is a position screening rule and/or a time screening rule for matching video files.
13. The method of claim 8, wherein after sending the user identifier of the recommended user to the terminal, the method further comprises:
receiving a pairing request which is sent by the terminal and paired with the recommended user;
and when the current user is successfully paired with the recommended user, acquiring a second paired video file of the recommended user, and sending the second paired video file to the terminal.
14. The method of claim 13, wherein obtaining the second paired video file of the recommended user comprises:
when the paired video file of the recommended user comprises a paired video file of which the video description information is matched with the video description information of the current user, taking the paired video file of which the video description information is matched with the video description information of the current user as the second paired video file;
and when the paired video file of which the video description information is matched with the video description information of the current user is deleted, taking the paired video file with the latest uploading time as the second paired video file.
15. An apparatus for recommending a user, the apparatus being applied in a terminal, the apparatus comprising:
the first determining module is used for determining a first pairing video file of a current user;
the first obtaining module is used for obtaining video description information of the first paired video file, wherein the video description information is used for describing information of an audio file and information of a video picture in the first paired video file;
the first sending module is used for sending a matching instruction to a server, wherein the matching instruction is used for indicating the server to return a user identifier of a recommended user to the terminal;
the first receiving module is used for receiving the user identification of the recommended user of the server and displaying the user identification of the recommended user on the recommended interface of the current user;
the first determining module is further configured to obtain the account status of the current user from the server when it is detected that the terminal logs in the server; when the account state indicates that the current user does not record the paired video file, acquiring the video file set by the current user, and taking the video file as the first paired video file, wherein the first paired video file comprises at least one of personal portraits, personal interests and hobbies or personal life scenes of the current user; when the account state indicates that the current user records a paired video file, taking the recorded paired video file as the first paired video file;
the server is used for receiving the matching instruction, the matching instruction carries the video description information, and the user identification of the recommended user with the video description information matched with the video description information of the current user is screened out from the first non-friend user set of the current user according to the matching instruction;
the server is further used for determining the user identification of the marked user marked by the current user in the first non-friend user set, wherein the marked user comprises the user who sends the pairing request and/or the deletion request by the terminal; deleting the user identification of the tagged user from the first set of non-buddy users;
the server is further configured to select, as the user identifier of the recommended user, a user identifier of a non-friend user that satisfies a location screening rule from non-friend users who send pairing requests to the current user when the user identifiers of the non-friend users who send pairing requests to the current user exist in the first set of non-friend users.
16. An apparatus for recommending a user, the apparatus being applied in a server, the apparatus comprising:
a second receiving module, configured to receive a matching instruction of a terminal, where the matching instruction carries video description information of a current user of the terminal, the video description information is extracted by the terminal from a first paired video file of the current user, the video description information is information used for describing an audio file and a video picture in the first paired video file, the first paired video file is determined according to an account state of the current user, which is obtained from the server, when the terminal detects that the terminal logs in the server, and the first paired video file includes at least one of a personal portrait, a personal interest and a personal life scene of the current user;
the terminal is used for acquiring a video file set by the current user as the first pairing video file when the account state indicates that the current user does not record the pairing video file; when the account state indicates that the current user records a paired video file, taking the recorded paired video file as the first paired video file;
the screening module is used for screening out the user identification of the recommended user of which the video description information is matched with the video description information of the current user from the first non-friend user set of the current user according to the matching instruction;
a fourth sending module, configured to send the user identifier of the recommended user to the terminal;
the device also comprises a user identification used for determining a marked user marked by the current user in the first non-friend user set, wherein the marked user comprises a user who sends a pairing request and/or a deletion request by the terminal; means for deleting the user identification of the tagged user from the first set of non-buddy users;
the device further comprises a module for selecting the user identification of the non-friend user meeting the position screening rule from the non-friend users sending the pairing request to the current user as the user identification of the recommended user when the user identifications of the non-friend users sending the pairing request to the current user exist in the first non-friend user set.
17. An apparatus for recommending users, comprising a processor and a memory, wherein the memory has stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by the processor to implement the method for recommending users according to any of claims 1-7, or the method for recommending users according to any of claims 8-14.
18. A storage medium having stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded and executed by a processor to implement a method of recommending users as claimed in any of claims 1 to 7, or a method of recommending users as claimed in any of claims 8 to 14.
CN201711350589.8A 2017-12-15 2017-12-15 Method and device for recommending user and readable storage medium Active CN108062390B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711350589.8A CN108062390B (en) 2017-12-15 2017-12-15 Method and device for recommending user and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711350589.8A CN108062390B (en) 2017-12-15 2017-12-15 Method and device for recommending user and readable storage medium

Publications (2)

Publication Number Publication Date
CN108062390A CN108062390A (en) 2018-05-22
CN108062390B true CN108062390B (en) 2021-07-23

Family

ID=62139013

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711350589.8A Active CN108062390B (en) 2017-12-15 2017-12-15 Method and device for recommending user and readable storage medium

Country Status (1)

Country Link
CN (1) CN108062390B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109344646B (en) * 2018-09-11 2019-12-03 杭州飞弛网络科技有限公司 A kind of the user privacy information guard method and system of stranger's social activity
CN110958172B (en) * 2018-09-26 2022-09-23 上海掌门科技有限公司 Method, device and computer storage medium for recommending friends
CN109688422B (en) * 2019-01-16 2021-05-28 武汉瓯越网视有限公司 Video processing method and device
CN110399562B (en) * 2019-07-31 2021-07-27 广州市百果园信息技术有限公司 Information display device and method for social application, display terminal and medium
CN110928913B (en) * 2019-12-09 2023-10-03 腾讯科技（深圳）有限公司 User display method, device, computer equipment and computer readable storage medium
CN111259192B (en) * 2020-01-15 2023-12-01 腾讯科技（深圳）有限公司 Audio recommendation method and device
CN114726818B (en) * 2020-12-21 2024-01-23 腾讯科技（深圳）有限公司 Network social method, device, equipment and computer readable storage medium
CN115225603A (en) * 2022-06-29 2022-10-21 赤子城网络技术（北京）有限公司 User matching method and system in social application

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005048601A1 (en) * 2003-11-12 2005-05-26 Philips Intellectual Property & Standards Gmbh Program recommendation system
CN103064869A (en) * 2012-09-05 2013-04-24 常州嘴馋了信息科技有限公司 User profile editing system
CN105005777A (en) * 2015-07-30 2015-10-28 科大讯飞股份有限公司 Face-based audio and video recommendation method and face-based audio and video recommendation system
CN105791902A (en) * 2016-04-21 2016-07-20 广州酷狗计算机科技有限公司 User recommendation method and user recommendation device

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7715619B2 (en) * 2003-10-21 2010-05-11 Nec Corporation Image collation system and image collation method
US20100125795A1 (en) * 2008-07-03 2010-05-20 Mspot, Inc. Method and apparatus for concatenating audio/video clips
CN104572732A (en) * 2013-10-22 2015-04-29 腾讯科技（深圳）有限公司 Method and device for inquiring user identification and method and device for acquiring user identification
CN105468598B (en) * 2014-08-18 2020-05-08 大连民族学院 Friend recommendation method and device
CN105530607B (en) * 2015-12-14 2017-03-22 腾讯科技（深圳）有限公司 user recommending method, device and system
CN107368552A (en) * 2017-06-30 2017-11-21 广东欧珀移动通信有限公司 A kind of friend recommendation method, apparatus, storage medium, server and terminal

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005048601A1 (en) * 2003-11-12 2005-05-26 Philips Intellectual Property & Standards Gmbh Program recommendation system
CN103064869A (en) * 2012-09-05 2013-04-24 常州嘴馋了信息科技有限公司 User profile editing system
CN105005777A (en) * 2015-07-30 2015-10-28 科大讯飞股份有限公司 Face-based audio and video recommendation method and face-based audio and video recommendation system
CN105791902A (en) * 2016-04-21 2016-07-20 广州酷狗计算机科技有限公司 User recommendation method and user recommendation device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Social-group-based ranking algorithms for cold-start video recommendation;Chunfeng Yang 等;《International Journal of Data Science and Analytics》;20161115;第1卷(第3期);165-175 *
基于移动互联网交友的个性化推荐系统的设计与实现;曾逸飞;《中国优秀硕士学位论文全文数据库信息科技辑》;20170315(第03期);I138-6282 *

Also Published As

Publication number Publication date
CN108062390A (en) 2018-05-22

Similar Documents

Publication Publication Date Title
CN108062390B (en) Method and device for recommending user and readable storage medium
CN108496150B (en) Screen capture and reading method and terminal
US11153430B2 (en) Information presentation method and device
CN106302996B (en) Message display method and device
CN106131627B (en) A kind of method for processing video frequency, apparatus and system
CN108156508B (en) Barrage information processing method and device, mobile terminal, server and system
CN111274416A (en) Chat information searching method and electronic equipment
CN107908765B (en) Game resource processing method, mobile terminal and server
CN107948729B (en) Rich media processing method and device, storage medium and electronic equipment
CN108093130B (en) Method for searching contact person and mobile terminal
CN109495638B (en) Information display method and terminal
EP3646276A1 (en) Systems and methods for selecting content for high velocity users
CN108390998A (en) A kind of method and mobile terminal for sharing file
CN105227598B (en) Resource sharing method, device and system based on cloud storage
CN107562917B (en) User recommendation method and device
CN108307039B (en) Application information display method and mobile terminal
CN106020945B (en) Shortcut item adding method and device
CN113392178A (en) Message reminding method, related device, equipment and storage medium
CN109510897B (en) Expression picture management method and mobile terminal
US11908489B2 (en) Tap to advance by subtitles
CN110955788A (en) Information display method and electronic equipment
CN107844203B (en) Input method candidate word recommendation method and mobile terminal
CN110750198A (en) Expression sending method and mobile terminal
CN110784762A (en) Video data processing method, device, equipment and storage medium
CN111666498B (en) Friend recommendation method based on interaction information, related device and storage medium

Legal Events

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