WO2019080637A1

WO2019080637A1 - Friend recommendation method and device

Info

Publication number: WO2019080637A1
Application number: PCT/CN2018/103176
Authority: WO
Inventors: 胡晨鹏
Original assignee: 上海掌门科技有限公司
Priority date: 2017-10-27
Filing date: 2018-08-30
Publication date: 2019-05-02
Also published as: CN107679249A

Abstract

Provided is a friend recommendation solution. In the solution, a user equipment acquires a user face image and uploads the user face image to a service device; the service device recognizes emotion information of a user based on the user face image, and determines, according to a pre-set matching rule, a friend user matching the emotion information of the user, and then sends recommendation information of the friend user to the user equipment; and the user equipment presents same to the user. Therefore, the current emotion of a user is taken into consideration when a friend is recommended to the user, so as to recommend, to the user, a friend satisfying a current social demand thereof, thereby improving the flexibility of friend recommendation and creating a good user experience.

Description

Friend recommendation method and device

Technical field

The present application relates to the field of information technology, and in particular, to a friend recommendation method and device.

Background technique

With the continuous development of Internet technology, Internet companies offer a variety of social networking products. The user can form a social circle through the social network product. For example, the user can make new friends and contact old friends through the network. If the number of friends of the user is small, the user cannot easily experience the convenience of social networking brought by the social network product. .

A friend relationship is one of the most important attributes in a social network. It has an important influence on the user's activity level. By promoting user friendship, the user's activity level can be improved. Therefore, for the user, the social platform can recommend a suitable friend to be in the To some extent, improve the user's stickiness. At present, there is no friend recommendation method with better user experience.

Application content

One of the purposes of the present application is to provide a friend recommendation scheme.

In order to achieve the above object, some embodiments of the present application provide a method for recommending a friend of a service device, the method comprising: acquiring a user face image uploaded by the user device; and identifying the user's emotion information based on the user face image; a preset matching rule, determining a friend user that matches the emotion information of the user; and sending the recommendation information of the friend user to the user equipment.

Some embodiments of the present application further provide a friend recommendation method on a user equipment side, where the method includes: acquiring a user face image, and transmitting the user face image to a service device; acquiring a friend user from the service device Recommendation information; presenting the recommendation information of the friend user to the user.

Some embodiments of the present application also provide an apparatus for implementing a friend recommendation, the apparatus comprising a memory for storing computer program instructions and a processor for executing computer program instructions, wherein the computer program instructions are When executed, the device is triggered to perform the friend recommendation method of the foregoing user equipment or service device end.

Some embodiments of the present application also provide a computer readable medium having stored thereon computer program instructions executable by a processor to implement a friend recommendation method of the aforementioned user equipment or service device side.

In the solution provided by some embodiments of the present application, after acquiring the user's facial image, the user equipment uploads the user facial image to the service device, and the service device identifies the user's emotional information based on the user facial image, and according to the preset a matching rule, determining a friend user that matches the emotional information of the user, and then transmitting the recommendation information of the friend user to the user device, and presented to the user by the user device, thereby considering when recommending the friend to the user The user's current emotions, thereby recommending friends who meet their current social needs, thereby improving the flexibility of friend recommendation and better user experience.

DRAWINGS

Other features, objects, and advantages of the present application will become more apparent from the detailed description of the accompanying drawings.

FIG. 1 is a schematic diagram of a system for implementing friend recommendation according to some embodiments of the present application;

2 is a flow chart of interaction between a user equipment and a service device when implementing friend recommendation according to some embodiments of the present application;

3 is a schematic flowchart of a solution of some embodiments of the present application applied to a social application software;

4 is a schematic diagram of an apparatus for implementing friend recommendation according to some embodiments of the present application;

The same or similar reference numerals in the drawings denote the same or similar components.

Detailed ways

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present application. It is a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

In a typical configuration of the present application, the devices of the terminal and the service network each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory. Memory is an example of a computer readable medium.

Computer readable media includes both permanent and non-persistent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), EEPROM, flash memory or other memory technology, compact disc (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette A tape, tape storage or other magnetic storage device or any other non-transportable medium can be used to store information that can be accessed by a computing device.

FIG. 1 is a schematic diagram of a system for implementing friend recommendation provided by some embodiments of the present application. The system includes a user equipment 110 and a service device 120. When a friend recommendation is implemented, between the user equipment 110 and the service device 120. The interaction process is shown in Figure 2 and includes the following processing steps:

Step S201, the user equipment acquires a user face image. In an actual scenario, the user equipment may be a mobile phone, a tablet computer, a computer, a wearable device, or the like, and the device may capture an image of the user through a built-in or external camera device to obtain a user's face. Part image. For example, when the user uses the social application installed in the mobile phone, the friend of the social application is opened, and the front camera of the mobile phone is activated to capture the facial image of the user, thereby implementing the friend recommendation function.

Step S202: The user equipment sends the user facial image to the service device, so that the service device can identify the user's emotion from the user's facial image, thereby implementing the friend recommendation. In order to improve the accuracy of the service device in recognizing the user's emotion from the user's face image, when the user's face image is provided, a plurality of key frames including the user's face image may be provided, for example, the user makes various expressions in the whole process. Several keyframes.

Thus, the user equipment can adopt the following processing manners: first, acquiring a continuous image including the user's face image, for example, capturing a video about the complete process of the user making an expression by the camera; and then extracting from the continuous image a plurality of key frames including a user's face image, the key frames may be a few key images in the process of the user making an expression, so as to accurately recognize the expression made by the user; A plurality of key frames containing the user's face image are transmitted to the service device such that the user's face image contained in several key frames is subjected to emotion recognition.

Step S203: The service device acquires a user face image uploaded by the user equipment.

Step S204, the service device identifies the user's emotion information based on the user's face image. The service device may include, but is not limited to, an implementation such as a network host, a single network server, a plurality of network server sets, or a cloud computing-based computer set. Here, the cloud is composed of a large number of host or network servers based on Cloud Computing, which is a kind of distributed computing, a super virtual computer composed of a group of loosely coupled computers.

In order to improve the accuracy of the emotion recognition, a plurality of key frames including the user's face image are collected for recognition, and the user's face image may be recognized by the depth learning engine to obtain the user's emotion information. When the emotion information is identified by this method, the feature extraction may be first performed on the user's face image, with the image feature value as the input value of the deep learning and the user's emotion information as the output value of the deep learning. For example, the image feature values may be color features, texture features, shape features, etc. in the image, which can describe the characteristics of the image to distinguish different images. In some embodiments of the present application, the characteristics of image feature values corresponding to various emotions may be preset in advance as a decision basis for each hidden layer in deep learning, thereby achieving accurate emotion recognition.

Step S205: The service device determines, according to a preset matching rule, a friend user that matches the emotion information of the user.

In some embodiments of the present application, the preset matching rule may be that the user's emotion information is matched with the candidate user's emotion information to obtain a matching result. Specifically, the step may be: if the emotional information of the user and the emotional information of the candidate user are in a preset relationship, the candidate user is determined as a friend user that matches the emotional information of the user. The preset relationship between the user's emotional information and the emotional information of the candidate user may be set according to actual needs. For example, some users may want to talk with people who have the same emotion when the mood is low, and some users may When you are feeling down, you may want to be able to enlighten yourself with someone who is in a good mood. Therefore, the preset relationship may be emotionally similar, opposite, or other specific association.

A candidate user is another user who also needs the service device to recommend a friend, for example, a user who also uploads a user's face image through the user device used by the user to perform emotion recognition. In an actual scenario, there are many other users who have social needs, and these other users interact with the service device using their respective user devices, so that the service device can recommend friends for them. As a result, the service device obtains a user's face image uploaded by many user devices, and performs emotion recognition on the user device to obtain emotional information of the user as a candidate user. Thus, the service device can maintain a database dedicated to storing emotional information of candidate users. In some embodiments of the present application, when determining a friend user that matches the user's emotional information, a friend user that matches the user's emotional information may be determined in the user repository, and the user repository is specifically used for The emotion information of the candidate user is stored, and the emotion information of the candidate user in the preset time is saved.

Since emotional information is a relatively short-term attribute, that is, the user's emotions may change at any time. For example, a user who is in a bad mood may become happy because of an emotional change in an event. Therefore, in some embodiments of the present application, the emotion information of the candidate user for performing matching may be valid information generated by the service device within a preset time, that is, only the candidate user is saved in the user warehouse within a preset time. Emotional information. For example, the preset time can be set to 10 minutes. When the emotional information generated by the candidate user exceeds 10 minutes, it is considered that the user's emotion has a greater possibility that it has changed, then it will be deleted from the user warehouse to avoid Cause inaccurate recommendations.

In the above implementation scenario, when the current user requests a recommended friend, the current user may also serve as a candidate user for other users. Therefore, after identifying the user's emotion information based on the user's facial image, the service device also saves the user's emotion information into the user warehouse as a candidate user when other user friends are recommended, and When the user's emotional information is stored in the user's warehouse for more than a preset time, the user's emotional information is deleted.

In other embodiments of the present application, the preset matching rule may also be that the user's emotion information is matched with the user image information of the candidate user to obtain a matching result. The user portrait information of the candidate user may be label information set by the candidate user for himself. For example, in the personal information option of the social application software, some users may set various labels for themselves, and these labels may indicate the user. Social attributes such as personality, personality traits, and self-awareness. In addition, the user portrait information may also be a social attribute determined by the service device after collecting various types of historical data about the candidate user, such as a shopping record by the user history, an age distribution of the chat object, and a transfer. Recording, etc., can analyze the user's preferences in social activities to determine the social attributes of the user.

Since the social attribute can reflect a certain preference of the user in the social activity, the specific social attribute is suitable for chatting with the user of the certain emotion, whereby the service device determines the user with the user according to the preset matching rule. When the emotional information matches the buddy user, the candidate user may be determined as a buddy user that matches the user's emotional information if the user's emotional information matches the candidate user's user portrait information.

Step S206: The service device sends the recommendation information of the friend user to the user equipment. The recommendation information may be related to adding a push message to the friend of the friend user, so that after receiving the request, the user device may view the specific information of the friend user, and determine whether to send a request for adding a friend to the friend user.

Step S207: The user equipment acquires recommendation information of the friend user from the service device.

In step S208, the user equipment presents the recommendation information of the friend user to the user. For example, the user interface of the social application software run by the user equipment may display whether to add a friend, and the user may click to view related information of the friend user in the interface. You can also choose whether to add or not. If you choose to add, it will automatically send a request to add a friend to the friend. Therefore, in the friend recommendation scheme provided by some embodiments of the present application, the current mood of the user is considered when recommending the friend to the user, so that the user is recommended to meet the current social needs of the user, thereby improving the flexibility of the friend recommendation. The experience is better.

FIG. 3 is a schematic flowchart of a solution of some embodiments of the present application applied to a social application software, where the social application software provides a service to a user adopting a C/S framework, that is, a client/server architecture, and the client runs. For various types of terminal devices used by users, such as mobile phones, tablets, computers, etc., the server can be an application server of the social application software, and provides support for various functions of the client. For example, in this embodiment, the friend recommendation function needs to be supported by the server. When the function is implemented, the specific interaction process is as follows:

In step S301, the user A enters the APP (application software) and opens the friend function.

Step S302, after detecting that the user opens the friend function, the client starts the camera to acquire a continuous image about the user's face.

Step S303, the client extracts a plurality of key frames including the user's face image from the continuous image, and uploads to the server.

Step S304, the depth learning engine of the server identifies the emotion of the user A at this time through the user's face image.

In step S305, the server adds the recognized emotion of the user to the warehouse L. The repository L is a user repository maintained by the server for storing information about the user who is using the dating function and has completed emotion recognition.

Step S306, the server searches the user repository L for other users similar or complementary to the user A according to the preset rule.

In step S307, the server returns the search result to the client.

Step S308, the client decodes the search result returned by the server.

In step S309, the client prompts the decoded result in the user interface.

In a solution provided by some embodiments of the present application, after acquiring a user facial image, the user equipment uploads the user facial image to the service device, and the service device identifies the user's emotional information based on the user facial image, and Determining, according to a preset matching rule, a friend user that matches the emotion information of the user, and then sending the recommendation information of the friend user to the user equipment, and being presented to the user by the user equipment, thereby recommending to the user When a friend considers the current emotion of the user, the user is recommended to the user who meets his current social needs, thereby improving the flexibility of the friend recommendation and the user experience is better.

In addition, a portion of the present application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide a method and/or technical solution in accordance with the present application. The program instructions for invoking the method of the present application may be stored in a fixed or removable recording medium, and/or transmitted by a data stream in a broadcast or other signal bearing medium, and/or stored in a program according to the program. The instruction runs in the working memory of the computer device. Here, some embodiments in accordance with the present application include an apparatus as shown in FIG. 4, the apparatus comprising one or more memories 410 storing computer readable instructions and a processor 420 for executing computer readable instructions, wherein When the computer readable instructions are executed by the processor, the apparatus is caused to perform methods and/or technical solutions based on the various embodiments of the foregoing application.

Moreover, some embodiments of the present application also provide a computer readable medium having stored thereon computer program instructions executable by a processor to implement the methods of the foregoing various embodiments of the present application and / or technical solutions.

It should be noted that the present application can be implemented in software and/or a combination of software and hardware, for example, using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device. In some embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Likewise, the software programs (including related data structures) of the present application can be stored in a computer readable recording medium such as a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some of the steps or functions of the present application may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

It is obvious to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the invention is defined by the appended claims instead All changes in the meaning and scope of equivalent elements are included in this application. Any reference signs in the claims should not be construed as limiting the claim. In addition, it is to be understood that the word "comprising" does not exclude other elements or steps. The plurality of units or devices recited in the device claims may also be implemented by a unit or device by software or hardware. The first, second, etc. words are used to denote names and do not denote any particular order.

Claims

A friend recommendation method on a service device side, wherein the method includes:

Obtaining a user face image uploaded by the user equipment;

Identifying user's emotional information based on the user's facial image;

Determining, according to a preset matching rule, a friend user that matches the emotional information of the user;

Sending the recommendation information of the friend user to the user equipment.
The method of claim 1, wherein the acquiring a user face image uploaded by the user equipment comprises:

Acquiring a plurality of key frames of the user's face image uploaded by the user equipment, wherein the key frames are from a continuous image including the user's face image.
The method of claim 1, wherein the identifying the user's emotional information based on the user facial image comprises:

The user's facial image is recognized by the deep learning engine to obtain the user's emotional information.
The method according to claim 1, wherein the determining a friend user that matches the emotion information of the user according to a preset matching rule comprises:

If the emotional information of the user and the emotional information of the candidate user are in a preset relationship, the candidate user is determined as a friend user that matches the emotional information of the user.
The method of claim 4, wherein determining a friend user that matches the user's emotional information comprises:

A friend user that matches the emotion information of the user is determined in the user warehouse, wherein the user warehouse stores emotion information of the candidate user within a preset time.
The method according to claim 5, further comprising: after identifying the user's emotion information based on the user's face image, further comprising:

Saving the user's emotion information into the user warehouse as a candidate user when other user friends are recommended;

When the user's emotional information is stored in the user's warehouse for more than a preset time, the user's emotional information is deleted.
The method according to claim 1, wherein the determining a friend user that matches the emotion information of the user according to a preset matching rule comprises:

If the emotional information of the user and the user portrait information of the candidate user meet a preset relationship, the candidate user is determined as a friend user that matches the emotional information of the user.
A friend recommendation method on a user equipment side, wherein the method includes:

Acquiring a user face image and transmitting the user face image to the service device;

Obtaining recommendation information of the friend user from the service device;

The recommendation information of the friend user is presented to the user.
The method of claim 1, wherein the acquiring the user's face image and transmitting the user's face image to the service device comprises:

Obtaining a continuous image containing the image of the user's face;

Extracting a plurality of key frames including the user's face image from the continuous image;

Sends a number of key frames containing the user's face image to the service device.
A device for implementing a friend recommendation, the device comprising a memory for storing computer program instructions and a processor for executing computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the right The method of any one of 1 to 9 is claimed.
A computer readable medium having stored thereon computer program instructions executable by a processor to implement the method of any one of claims 1 to 9.