WO2020026017A1

WO2020026017A1 - Image-based object recommendation method and apparatus, and device/terminal/server

Info

Publication number: WO2020026017A1
Application number: PCT/IB2018/056503
Authority: WO
Inventors: 黄龙飞; 蔡山清
Original assignee: 优视科技新加坡有限公司
Priority date: 2018-07-31
Filing date: 2018-08-27
Publication date: 2020-02-06
Also published as: CN109063119A

Abstract

The embodiments of the present application provide an image-based object recommendation method and apparatus, and a device/terminal/server. The method comprises: performing analysis according to acquired image data to obtain image feature information corresponding to the image data; performing integrated processing on the image feature information to obtain N-dimensional user feature information, wherein N is a natural number; and performing a pushing processing operation on objects of the same kind for users of the same kind according to the N-dimensional user feature information. The embodiments of the present application realize image-data-based object pushing by analyzing acquired image data.

Description

Image-based object recommendation method, device and device / terminal / server This application requires that the China Patent Office be filed on July 31, 2018, with application number 201810858651.2, and the invention name is "A method and device for image-based object recommendation And device / terminal / server "priority, the entire contents of which are incorporated in this application by reference.

Technical field

The present application relates to the field of computer technology, and in particular, to an image-based object recommendation method, apparatus, and device / terminal / server.

Background technique

With the development of mobile smart terminals, more and more users use smart terminals for image shooting or downloading. The methods of obtaining the images and the content of the images are usually very different. For example, some users are accustomed to shooting with beauty cameras, and some users are accustomed to shoot with professional cameras and download them to smart terminals. For another example, some users are used to taking images of people, and some users are used to taking food or landscapes.

Generally, the collection of user characteristics is based on user behavior, that is, access to websites, videos played, etc. For image shooting and image downloading, only stay in the aspect of image sharing. However, images captured or downloaded by users often have certain user characteristic information such as user preference information, and the prior art cannot push according to this user characteristic information.

Therefore, how to implement object recommendation based on images has become an urgent technical problem in the prior art.

Summary of the invention

Embodiments of the present application provide an image-based object recommendation method, device, and device / terminal / server, which implement object push based on image data by analyzing image data obtained.

According to an aspect of the embodiment of the present application, an image-based object recommendation method is provided, and the method includes: analyzing the obtained image data to obtain image feature information corresponding to the image data; and using the image feature information Performing comprehensive processing to obtain N-dimensional user characteristic information, where N is a natural number; and performing a similar object push processing operation on similar users according to the N-dimensional user characteristic information.

According to another aspect of the embodiments of the present application, there is also provided an image-based object recommendation device, the device includes: an image analysis module configured to be based on the obtained image data Performing analysis to obtain image feature information corresponding to the image data; an information obtaining module configured to comprehensively process the image feature information to obtain N-dimensional user feature information, where N is a natural number; a push processing module, configured for Based on the N-dimension user characteristic information, a similar object is pushed for a similar object.

According to still another aspect of the embodiments of the present application, a device / terminal / server is further provided, including: one or more processors; a storage device, configured to store one or more programs, and when the one or more programs are Being executed by the one or more processors, so that the one or more processors implement operations corresponding to the image-based object recommendation method as described above.

According to still another aspect of the embodiments of the present application, a computer-readable storage medium is further provided, in which a computer program is stored, and when the program is executed by a processor, implements operations corresponding to the image-based object recommendation method described above .

According to the technical solution provided by the embodiment of the present application, the embodiment of the present application obtains the corresponding image feature information by analyzing the image data, and comprehensively processes the image feature information to obtain the N-dimensional user feature information and the N-dimensional user feature information. Push similar objects. The embodiments of the present application can thus collect user characteristic information through image data, and then push similar objects. This makes up for the shortcomings of image data that can only be used for sharing, achieves more accurate user pushes, and improves the accuracy and comprehensiveness of user pushes. Sex.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a flowchart of the steps of an image-based object recommendation method according to the first embodiment of the present application; FIG.

FIG. 2 is a flowchart of steps of an implementation of step S101 of an image-based object recommendation method according to the first embodiment of the present application; FIG.

FIG. 3 is a flowchart of steps of another implementation of step S101 of an image-based object recommendation method according to the first embodiment of the present application; FIG.

FIG. 4 is a flowchart of steps in an implementation of step S103 of an image-based object recommendation method according to Embodiment 2 of the present application;

5 is a structural block diagram of an image-based object recommendation device according to Embodiment 3 of the present application;

6 is a structural block diagram of an implementation of an image analysis module of an image-based object recommendation device according to Embodiment 3 of the present application;

FIG. 7 is an image of an image-based object recommendation device according to Embodiment 3 of the present application Structural block diagram of another implementation of the analysis module;

8 is a structural block diagram of an implementation of a push processing module of an image-based object recommendation device according to Embodiment 4 of the present application;

FIG. 9 is a structural block diagram of a device / terminal / server according to Embodiment 5 of the present application. detailed description

The specific implementation of the embodiments of the present application will be further described in detail below with reference to the accompanying drawings (the same reference numerals in several drawings represent the same elements) and embodiments. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.

Those skilled in the art can understand that terms such as “first” and “second” in the embodiments of the present application are only used to distinguish different steps, devices, or modules, etc., and they do not represent any specific technical meaning, nor mean between them. Inevitable logical order.

Example one

Referring to FIG. 1, a flowchart of the steps of an image-based object recommendation method according to the first embodiment of the present application is shown.

It is worth noting that steps S 101 to S 103 described in this application do not represent the order of execution.

The image-based object recommendation method in this embodiment includes the following steps:

Step S101: Analyze the obtained image data to obtain image feature information corresponding to the image data.

Specifically, the image data obtained in the embodiment of the present application includes image data captured by a user using a smart terminal, or image data downloaded by a user from other shooting devices and the Internet.

The embodiment of the present application performs analysis processing according to the obtained image data, including image analysis processing and image description file processing, so as to obtain image feature information corresponding to the image data. In a specific implementation of the present application, referring to FIG. 2, the steps S 101 includes:

S 101 1. Analyze image feature data of the image data to obtain shooting feature information corresponding to the image data.

Specifically, the image feature data of the image data may come from analysis processing of the image itself, or from analysis processing of a description file of the image. The shooting feature information includes at least one of the following: the shooting scene of the image (night scene, daytime scene, etc.); the chroma, brightness, saturation, etc. of the image; the shooting tool of the image (mobile phone model, camera model, shooting APP, etc.) .

Therefore, the embodiment of the present application can obtain the shooting feature information of the image data according to the image feature data, so as to obtain the user feature information representing the user preference according to the shooting feature information. In another specific implementation of the present application, referring to FIG. 3, The step S101 includes:

S1012. Analyze content feature data of the image data to obtain content feature information corresponding to the image data.

The content characteristic information includes at least one of the following; a photographic subject (person, food, newspaper, movie ticket, painting, etc.); a shooting occasion (a downtown area, an amusement park, an exhibition hall, a restaurant, etc.).

Therefore, the embodiments of the present application can obtain content feature information of image data according to the image feature data, so as to obtain user feature information representing user preferences according to the content feature information.

In another specific implementation of the present application, the step S 101 includes steps S 101 1 and S 1012.

Step S102: Comprehensively process the image feature information to obtain N-dimensional user feature information, where N is a natural number.

In specific implementation of this application, the N-dimensional user feature information includes:

At least one of shooting scene information, shooting image information, shooting tool information, and shooting content information.

For example, the image feature information obtained by analyzing the image data is: an amusement park in a daytime scene, the image capturing tool is a Lycra camera, and the image capturing content includes people and food. The image feature information is comprehensively processed, and the N-dimensional user feature information is obtained as follows: a daytime playground is played, and a Leica camera is used to take a picture.

For another example, analysis based on image data to obtain image feature information is: a shopping mall in a daytime scene, the image capture tool is an Apple phone, and the image capture content includes people and food. The image characteristic information is comprehensively processed, and the N-dimensional user characteristic information is obtained as follows: shopping in a mall in the daytime, and taking photos using an Apple mobile phone.

Step S103: Perform similar objects on similar users according to the N-dimensional user characteristic information Push processing operations.

In the embodiment of the present application, based on the N-dimensional user characteristic information, a similar object corresponding to the N-dimensional user characteristic information is obtained and pushed to a corresponding user.

For example, if the N-dimensional user characteristic information is: playing in a playground in the daytime, and taking a picture using a Leica camera. The embodiment of the present application pushes information on dining, accommodation, and traffic around the playground to corresponding users, and the embodiment of the present application can also push the information about the Leica camera peripheral products, shooting skills, and play routes of the playground to the user.

For another example, if the N-dimensional user characteristic information is: shopping in a daytime mall, and using an Apple phone to take a photo. This embodiment of the present application pushes information about catering, promotions, and traffic around the mall to corresponding users, and this embodiment of the present application can also push users with information about Apple's peripheral products and shooting techniques.

Therefore, it can be known that the embodiment of the present application obtains the corresponding image feature information by analyzing the image data, and comprehensively processes the image feature information to obtain N-dimensional user feature information, and pushes similar objects according to the N-dimensional user feature information. The embodiments of the present application can thus collect user characteristic information through image data, and then push similar objects. This makes up for the shortcomings of image data that can only be used for sharing, achieves more accurate user pushes, and improves the accuracy and comprehensiveness of user pushes. Sex.

The image-based object recommendation method of this embodiment may be executed by any appropriate device having image-based object recommendation capabilities, including but not limited to: various device terminals or servers, including but not limited to PC, tablet, mobile Terminal, etc.

Example two

This embodiment includes the above steps S101 to S103. Referring to FIG. 4, the step S103 includes:

S1031. Based on the N-dimensional user feature information, perform collaborative N-dimensional clustering processing on similar users.

The collaborative clustering described in the embodiment of the present application includes at least one of the following: According to the user characteristic information, users having the same or similar user characteristic information are combined and classified into similar users. According to the user characteristic information, the objects satisfying the user characteristic information are combined and classified into similar objects. According to the user characteristic information, the corresponding relationships between users and objects are combined and classified into the same recommendation model. S1032. Obtain various types of object information corresponding to various types of users, and perform common push processing operations on the same types of users.

Specifically, the embodiment of the present application may recommend similar objects to similar users according to the result of the collaborative clustering process.

For example, recommend recent hot movies for all users who have taken movie tickets, recommend similar works for all users who have taken book covers, and so on.

Example three

Referring to FIG. 5, a structural diagram of an image-based object recommendation device according to Embodiment 3 of the present application is shown.

The image-based object recommendation device in this embodiment includes:

The image analysis module 501 is configured to perform analysis according to the obtained image data to obtain image feature information corresponding to the image data.

The information obtaining module 502 is configured to comprehensively process the image feature information to obtain N-dimensional user feature information, where N is a natural number.

The push processing module 503 is configured to perform a push processing operation on a similar object to a similar user according to the N-dimensional user characteristic information.

The embodiment of the present application performs analysis processing according to the obtained image data, including image analysis processing and image description file processing, so as to obtain image feature information corresponding to the image data. In a specific implementation of the present application, referring to FIG. 6, the image analysis module 501 includes: an image analysis unit 5011 configured to analyze image feature data of the image data to obtain shooting feature information corresponding to the image data.

Specifically, the image feature data of the image data may come from analysis processing of the image itself, or from analysis processing of a description file of the image.

The shooting feature information includes at least one of the following: the shooting scene of the image (night scene, daytime scene, etc.); the chroma, brightness, saturation, etc. of the image; the shooting tool of the image (mobile phone model, camera model, shooting APP, etc.) .

Therefore, the embodiment of the present application can obtain the shooting feature information of the image data according to the image feature data, so as to obtain the user feature information representing the user preference according to the shooting feature information. The image analysis module 501 includes: a content analysis unit 5012 configured to analyze content feature data of the image data to obtain content feature information corresponding to the image data.

In another specific implementation of the present application, the image analysis module 501 includes an image analysis unit 5011 and a content analysis unit 5012.

For another example, the analysis based on the image data to obtain image feature information is: a shopping mall in a daytime scene, the image capture tool is an Apple phone, and the image capture content includes people and food. The image feature information is comprehensively processed, and the N-dimensional user feature information is obtained as follows: shopping in a daytime mall, and taking photos using an Apple phone.

Embodiment 4

This embodiment includes the above-mentioned image analysis module 501, an information obtaining module 502, and a push processing module 503. Referring to FIG. 8, the push processing module 503 includes:

The collaborative clustering unit 5031 is configured to perform N-dimensional collaborative clustering processing on the same type of users according to the N-dimensional user characteristic information.

The common push unit 5032 is configured to obtain various types of object information corresponding to various types of users, and perform a common push processing operation on the similar objects to the similar users.

The collaborative clustering described in the embodiment of the present application includes at least one of the following: According to the user characteristic information, users having the same or similar user characteristic information are combined and classified into the same type. User. According to the user characteristic information, the objects satisfying the user characteristic information are combined and classified into similar objects. According to the user characteristic information, the corresponding relationships between users and objects are combined and classified into the same recommendation model.

The image-based object recommendation device of this embodiment may be executed by any appropriate device having image-based object recommendation capabilities, including but not limited to: various device terminals or servers, including but not limited to PCs, tablets, and mobiles Terminal, etc.

Example 5

Referring to FIG. 9, a structural block diagram of a device / terminal / server according to Embodiment 5 of the present application is shown. The specific embodiment of the present application does not limit the specific implementation of the device / terminal / server.

As shown in Figure 9, the device / terminal / server may include: one or more processors

(processor) 902, storage device (memory) 904.

among them:

The processor 902 is configured to execute a program 906, and may specifically perform relevant steps in the foregoing embodiment of the image-based object recommendation method.

Specifically, the program 906 may include program code, where the program code includes a computer operation instruction.

The processor 902 may be a central processing unit CPU, or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. One or more processors included in the device / terminal / server, which can be processors of the same type, such as one or more CPUs, or different types Processors, such as one or more CPUs and one or more ASICs.

The storage device 904 is configured to store one or more programs 906. The storage device 904 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 906 may be specifically configured to cause the processor 902 to perform the following operations: analyze the obtained image data to obtain image feature information corresponding to the image data; perform comprehensive processing on the image feature information to obtain N-dimensional user feature information, The N is a natural number; and a similar object is pushed to a similar user according to the N-dimensional user characteristic information.

In an optional implementation manner, the program 906 is further configured to analyze image feature data of the image data to obtain shooting feature information corresponding to the image data.

In an optional implementation manner, the program 906 is further configured to analyze content feature data of the image data to obtain content feature information corresponding to the image data.

In an optional implementation manner, the N-dimensional user characteristic information includes:

In an optional implementation manner, the program 906 is further configured to perform N-dimensional collaborative clustering processing on similar users according to the N-dimensional user characteristic information; obtain various types of object information corresponding to various types of users, and Users perform common push processing operations on similar objects.

It should be noted that according to the needs of implementation, each component / step described in the embodiment of the present application may be split into more components / steps, or two or more components / steps or partial operations of components / steps may be combined into New components / steps to achieve the purpose of the embodiments of the present application.

In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable medium, the computer program containing program code for performing a method shown in a flowchart. In such an embodiment, the computer The program may be downloaded and installed from a network through a communication section, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the aforementioned functions defined in the method of the present application are executed. It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the foregoing. The computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable memories Programming read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal that is included in baseband or propagated as part of a carrier wave, and which carries computer-readable program code. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable medium may send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device . Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, the programming languages including an object-oriented programming language such as Java, Smalltalk, C ++, and also conventional A procedural programming language such as "C" or a similar programming language. The program code can be executed entirely on the user's computer, partly on the user's computer, as an independent software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through the Internet using an Internet service provider) Connection).

The flowchart and block diagrams in the drawings illustrate a system, method, and system according to various embodiments of the present application. Architecture, functions, and operations of legal and computer program products. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a portion of a code, which module, program segment, or part of the code contains one or more functions for implementing a specified logical function Executable instructions. It should also be noted that in some alternative implementations, the functions marked in the blocks may also occur in a different order than those marked in the drawings. For example, two successively represented boxes may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented in a dedicated hardware-based system that performs the specified function or operation. Or, it can be implemented by a combination of dedicated hardware and computer instructions.

The units described in the embodiments of the present application may be implemented in a software manner, or may be implemented in a hardware manner. The described unit may also be provided in a processor, for example, it may be described as: A processor includes a receiving unit, a parsing unit, an information selecting unit, and a generating unit. Among them, the names of these units do not in any way constitute a limitation on the unit itself. For example, the receiving unit may also be described as a "unit for receiving a user's web browsing request".

As another aspect, the present application also provides a computer-readable storage medium having stored thereon a computer program, which is executed by a processor to implement a method as described in any one of the foregoing embodiments.

As another aspect, the present application further provides a computer-readable medium, which may be included in the device described in the foregoing embodiments; or may exist alone without being assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by the device, the device is caused to: perform analysis according to the obtained image data to obtain image feature information corresponding to the image data; The image feature information is comprehensively processed to obtain N-dimensional user feature information, where N is a natural number; and a similar user is pushed and operated on a similar object according to the N-dimensional user feature information.

The above description is only a preferred embodiment of the present application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solution of the specific combination of the above technical features, but also covers the above technical features or Other technical solutions formed by arbitrarily combining their equivalent features. For example, a technical solution formed by replacing the above features with technical features disclosed in the present application (but not limited to) with similar functions.

Claims

Claim

1. An image-based object recommendation method, characterized in that the method includes: analyzing the obtained image data to obtain image feature information corresponding to the image data;

Comprehensively processing the image feature information to obtain N-dimensional user feature information, where N is a natural number;

Push similar objects to the same user according to the N-dimensional user characteristic information.

2. The method according to claim 1, wherein the analyzing according to the obtained image data to obtain image feature information corresponding to the image data comprises:

Analyze image feature data of the image data to obtain shooting feature information corresponding to the image data.

3. The method according to claim 1 or 2, wherein the performing analysis based on the obtained image data to obtain image feature information corresponding to the image data comprises:

Analyze content feature data of the image data to obtain content feature information corresponding to the image data.

4. The method according to claim 1, wherein the N-dimensional user characteristic information comprises:

5. The method according to claim 1, wherein the performing a push processing operation on a similar user based on the N-dimensional user characteristic information comprises:

Perform N-dimensional collaborative clustering processing on similar users according to the N-dimensional user characteristic information;

Obtain various types of object information corresponding to various types of users, and perform common push processing operations on similar objects for similar users.

6. An image-based object recommendation device, characterized in that the device includes: an image analysis module configured to perform analysis based on the obtained image data to obtain image feature information corresponding to the image data;

An information obtaining module configured to comprehensively process the image feature information to obtain N-dimensional user feature information, where N is a natural number; The push processing module is configured to perform a push processing operation on a similar object to a similar user according to the N-dimensional user characteristic information.

7. The device according to claim 6, wherein the image analysis module comprises:

The image analysis unit is configured to analyze image feature data of the image data to obtain shooting feature information corresponding to the image data.

8. The device according to claim 6 or 7, wherein the image analysis module comprises:

The content analysis unit is configured to analyze content feature data of the image data to obtain content feature information corresponding to the image data.

9. The device according to claim 6, wherein the N-dimensional user characteristic information comprises:

10. The device according to claim 6, wherein the push processing module comprises:

A collaborative clustering unit configured to perform N-dimensional collaborative clustering processing on similar users based on the N-dimensional user characteristic information;

The common push unit is configured to obtain various types of object information corresponding to various types of users, and perform a common push processing operation on the same type of objects for the same type of users.

1 1. A device / terminal / server, including:

One or more processors;

A storage device for storing one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method according to any one of claims 1-5.

12. A computer-readable storage medium having stored thereon a computer program, characterized in that when the program is executed by a processor, the method according to any one of claims 1-5 is implemented.