WO2020062788A1

WO2020062788A1 - Method and apparatus for intelligently recognizing picture, server, and storage medium

Info

Publication number: WO2020062788A1
Application number: PCT/CN2019/077515
Authority: WO
Inventors: 唐晟
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2018-09-30
Filing date: 2019-03-08
Publication date: 2020-04-02
Also published as: CN109492121A

Abstract

A method and apparatus for intelligently recognizing a picture, a server, and a storage medium. The method comprises: receiving a picture file (S1); computing the feature value of the picture file (S2); receiving an operation of following the picture file of a user and creating a list of follows of the user according to the operation, wherein the list of follows comprises the picture file and the corresponding feature value (S3); obtaining a target picture file currently viewed by the user, and computing the feature value of the target picture file (S4); querying the list of follows of the user according to the feature value of the target picture file to determine whether the target picture file has been followed (S5); and if the feature value of the target picture file exists in the list of interests of the user, determining that the target picture file has been followed and prompting the user not to follow the target picture file (S6). The method can solve problem that when a user follows a same picture for multiple times in the case that the user follows too many pictures and cannot recognize the same picture posted by different users, and can also classify picture files by means of a classifier.

Description

Method, device, server and storage medium for intelligently identifying pictures

This application claims the priority of a Chinese patent application filed on September 30, 2018 with the Chinese Patent Office under the application number 201811163462.X and entitled "Method, Device, Server, and Storage Medium for Intelligently Recognizing Pictures". Citations are incorporated in this application.

Technical field

The present application relates to the field of image recognition technology, and in particular, to a method, a device, a server, and a storage medium for intelligently identifying pictures.

Background technique

Social image browsing software like Instgram, Tumblr, etc., basically require users to register to use. And during use, the user can pay attention to the browsed pictures (such as likes and favorites) according to their own preferences. With the increase of the base of the pictures to be followed, users may not be able to identify whether the same picture posted by different users has been followed, which may cause repeated attention to the same picture.

Application content

In view of the above, it is necessary to propose a method, a device, a server, and a storage medium for intelligently identifying pictures, and filtering pictures by calculating feature values of the pictures, avoiding repeated attention of the same picture, and improving user experience.

A method for intelligently identifying a picture, the method includes:

Receiving an operation that a user follows a picture file, and establishing a user attention list according to the operation, wherein the attention list includes the picture file and a corresponding feature value thereof;

Get the target image file currently viewed by the user;

Calculating a feature value of the target picture file;

Querying the user's attention list according to the feature value of the target picture file to confirm whether the target picture file has been followed; and

When the feature value of the target picture file exists in the user's attention list, confirming that the target picture file has been followed, prompting the user that the user does not need to pay attention to the target picture file.

A device for intelligently identifying pictures, the device includes:

A establishing module, configured to receive an operation that a user follows an image file, and establish a user attention list according to the operation, wherein the attention list includes the image file and its corresponding feature value;

An acquisition module for acquiring a target image file currently viewed by a user;

A calculation module, configured to calculate a feature value of the target picture file;

A query module, configured to query the user attention list according to the feature value of the target picture file to confirm whether the target picture file has been followed; and

A prompting module is configured to confirm that the target picture file has been followed when the feature value of the target picture file exists in the user's attention list, and prompt the user that the user does not need to follow the target picture file.

A server includes a processor and a memory, and the processor implements the following steps when executing at least one computer-readable instruction stored in the memory:

Get the target image file currently viewed by the user;

Calculating a feature value of the target picture file;

A non-volatile readable storage medium stores at least one computer-readable instruction. When the at least one computer-readable instruction is executed by a processor, the following steps are implemented:

Get the target image file currently viewed by the user;

Calculating a feature value of the target picture file;

As can be known from the above technical solutions, the present application provides a method, device, server, and storage medium for intelligently identifying pictures, by establishing a user's attention list, where the attention list includes feature values, obtaining a picture file currently viewed by a user, and calculating The feature value of the picture file; comparing whether the feature value is consistent with the feature value in the attention list and prompting the user not to pay attention to the picture when the feature value is consistent with the feature value in the attention list file. Therefore, a problem that a user pays attention to the same picture multiple times when there are too many pictures that the user cannot recognize the same picture posted by different users can be solved. You can filter the pictures by calculating the feature values of the pictures to avoid the repeated attention of the same picture and improve the user experience.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is an application environment architecture diagram of a first preferred embodiment of a method for intelligently identifying pictures in this application.

FIG. 2 is a flowchart of a first preferred embodiment of a method for intelligently identifying pictures according to the present application.

FIG. 3 is a functional block diagram of the first preferred embodiment of the device for intelligently identifying pictures in the present application.

FIG. 4 is a schematic structural diagram of a preferred embodiment of a server in at least one example of the present application.

detailed description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

The terms "first", "second", "third" and the like in the description and claims of the present application and the above-mentioned drawings are used to distinguish different objects and are not used to describe a specific order. Furthermore, the term "including" and any variations of them are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device containing a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes Other steps or units inherent to these processes, methods, products or equipment.

As shown in FIG. 1, it is an application environment architecture diagram of a first preferred embodiment of a method for intelligently identifying pictures in this application.

The method for intelligently identifying pictures in the present application is applied in an environment composed of an electronic device 1 and a server 2. The electronic device 1 and the server 2 are connected through a wired or wireless network communication connection. The wired network may be any type of traditional wired communication, such as the Internet and a local area network. The wireless network may be any type of traditional wireless communication, such as radio, wireless fidelity (WIFI), cellular, satellite, and broadcast. Wireless communication technologies may include, but are not limited to, Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband code division multiple access (W-CDMA), CDMA2000, IMT Single Carrier, Enhanced Data Rate GSM Evolution (Enhanced Data Rates for GSM Evolution, EDGE), Long-Term Evolution (LTE) , Advanced Long Term Evolution Technology, Time-Division LTE (TD-LTE), Fifth Generation Mobile Communication Technology (5G), High Performance Radio Local Area Network (High Performance Radio Local Area Network, HiperLAN), High Performance Radio Wide Area Network (High Performance, Radio Wide Area, HiperWAN), Local Multipoint Distribution Service (LMDS), Worldwide Interoperability for Microwave Access (WiMAX), ZigBee, Bluetooth, Orthogonal Frequency Division Multiplexing (Flash Orthogonal Freq) uency-Division Multiplexing (Flash-OFDM), High-capacity Spatial Division Multiple Access (HC-SDMA), Universal Mobile Telecommunications System (UMTS), Universal Mobile Telecommunications System Time Division Dual (UMTS Time-Division Duplexing, UMTS-TDD), Evolved High Speed Packet Access (HSPA +), Time Division Synchronous Code Division Multiple Access (TD-SCDMA), evolution Data optimization (EV-DO), Digital Enhanced Cordless Telecommunications (DECT), and others.

The electronic device 1 may include a personal computer (PC), a personal digital assistant (PDA), a wireless handheld device, a tablet computer, a smart phone, and the like. The above-mentioned electronic device 1 is merely an example, and is not exhaustive, including but not limited to the above-mentioned electronic device 1. The movement can be used for human-computer interaction with a user through a keyboard, a mouse, a remote control, a touch pad, or a voice control device.

In this embodiment, an application is installed on the electronic device 1, and a user can upload a picture file through the application.

The application program may be any third-party application installed in the operating system of the electronic device 1, such as WeChat, Weibo, QQ, Instgram, Tumblr, Meitu Xiuxiu and other social software that can browse pictures. This plan does not limit this. The operating system includes an Android system, a Symbian system, a Windows system, an iOS (mobile operating system developed by Apple Inc.) system, and the like.

The electronic device 1 further includes a display screen, and the display screen may have a touch function, such as a Liquid Crystal (Crystal Display) LCD display or an Organic Light-Emitting Diode (OLED) display. The display screen is used to display information such as the picture file.

The server 2 is a device capable of automatically performing numerical calculations and / or information processing according to an instruction set or stored in advance, and its hardware includes, but is not limited to, a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), programmable gate array (Field-Programmable Gate Array, FPGA), digital processor (Digital Signal Processor, DSP), embedded equipment, etc.

FIG. 2 is a flowchart of a method for intelligently identifying a picture provided in Embodiment 2 of the present application. According to different requirements, the execution order in the flowchart can be changed, and some steps can be omitted.

Step S1. Receive a picture file.

In this embodiment, a picture file uploaded by an electronic device is received. The electronic device may include, but is not limited to, a personal computer (PC), a personal digital assistant (PDA), a wireless handheld device, a tablet computer, a smart phone, and the like. The above electronic devices are merely examples, not exhaustive, including but not limited to the above electronic devices.

In this embodiment, an application is installed on the electronic device, and a user can upload a picture file through the application.

The application program may be any third-party application installed in the operating system of the electronic device, such as WeChat, Weibo, QQ, Instgram, Tumblr, Meitu Xiuxiu and other social software that can browse pictures. This plan does not limit this. The operating system includes an Android system, a Symbian system, a Windows system, an iOS (mobile operating system developed by Apple Inc.) system, and the like.

Preferably, after receiving the picture file, the method further comprises the step of classifying the received picture file. The categories of pictures can include, but are not limited to, landscapes, people, animals, buildings, and so on.

It can be understood that this solution can perform multi-level classification on the types of pictures mentioned above. For example, first classify the picture files into landscapes, people, animals, buildings, etc .; then classify the picture files after the first category, for example, subdivide the animals into cats, Dogs, birds, fish, etc., divide characters into men and women, or into the elderly, middle-aged people, teenagers, and children.

Specifically, the step of classifying the received picture files includes:

a) Preprocessing the received picture file; the preprocessing mainly includes image segmentation, image enhancement, and morphological processing.

b) Feature extraction on pre-processed pictures; the feature extraction is mainly divided into two types: low-level visual features and intermediate semantic features. The low-level visual features mainly include simple features such as color, shape and texture, and SIFT, RIFT, Complex local invariant features such as HOG; the intermediate semantic features mainly include semantic attribute features, regional semantic concept features, and bag-of-words features.

c) Classify the pictures after feature extraction through a classifier. The classifier can help users establish accurate mapping relationships between image features and keyword categories, and extract image semantic information consistent with user perception.

Preferably, the method for classifying pictures after feature extraction by a classifier includes an image classification method based on a generated model and an image classification method based on a discriminative model. The image classification method based on the generated model is based on the joint probability distribution of image features and image categories, while the image classification method based on the discriminant model is based on the conditional probability distribution of image features and image categories.

Step S2: Calculate a feature value of the picture file.

In this embodiment, after classifying the picture files, different calculation methods may be selected according to different types of the picture files to calculate the feature values of the picture files.

For example, the feature value may be a vector of a certain dimension, such as (P1, P2, ..., Pn), which is an n-dimensional vector, and the n-dimensional vector may be used to describe a shape feature of an object in an image. In the prior art, the Hough transform may be used to calculate the feature value. The Hough transform is a commonly used algorithm, and details are not described herein again.

In this embodiment, a better calculation method for calculating the feature value of a picture file whose first-class category is a building is introduced, which may include the following steps:

A1: Extract the image of the contained building from the original image;

A2: fill the border of the cutout image with a single color as the background, and make the filled image the smallest square;

A3: the square image is fully scaled to an image of a first predetermined size, and the scaled image is divided into sub-image blocks of a second predetermined size;

A4: Calculate the luminance derivatives of adjacent pixels in the horizontal, vertical, positive 45 °, and negative 45 ° directions of the sub-image block, respectively. The number of extreme points of the derivative in the four directions and the four boundaries of the sub-image block. The total number of upper extreme points is used as a feature vector of the sub-image block;

A5: Use the feature vectors of all sub-image blocks as the feature vectors of the original image.

The above image feature extraction method mainly uses the difference in pixel brightness between the edge portion of the object displayed in the image and the surrounding background to find the edge of the object, so that the shape features of the object in the image can be extracted, which can be used as the The characteristic value of the image.

In addition, the singular value decomposition method can also be used to calculate the eigenvalues of the picture files whose first-level category is a person. The specific steps include:

B1: Set A ∈ R ^{m × n} as a face gray image, where m≥n, rank (A) = r;

B2: Obtain two orthogonal matrices and diagonal matrices as follows:

U = [u ₁ , u ₂ , ..., u _m ] ∈R ^{m × m} , U ^T U = I,

The orthogonal matrix is: V = [v ₁ , v ₂ , ..., v _n ] ∈R ^{n × n} , V ^T V = I

The diagonal matrix is: S = diag [λ ₁ , λ ₂ , ..., λ _r , 0,…, 0] ∈R ^{m × n} , λ ₁ ＞ λ ₂ ＞… ＞ λ _r ≥0;

B3: Make the formula,

among them,

A ^T A is the feature value and the AA ^T, u _i and v _i are the A ^T A and AA ^T corresponding to

Feature vector

B4: Obtain the projection form of the above formula, that is, the projection of image A on U and V is a diagonal matrix S, S = U ^T AV, and a vector composed of elements on the diagonal of S is the singular feature of image A value.

Step S3: Receive an operation that a user follows a picture file, and establish a watch list according to the operation, where the watch list includes the picture file and its corresponding feature value.

In this embodiment, when a user browses a picture file on an electronic device, the user can follow the picture file by clicking a button (such as a like button, a favorite button), and the button is displayed when the picture file is displayed Interface (such as the bottom left corner of the picture). The image file to be followed is stored in a database, the feature value of the image file to be followed is calculated, and the user attention list is established according to the image file to be followed and the characteristic value.

Step S4: Obtain a target picture file currently browsed by the user, and calculate a feature value of the target picture file.

In this embodiment, a picture file currently browsed by the user is obtained through a web crawler technology. Specific steps include:

1) A web crawler crawls a webpage content currently browsed by a user, where the webpage content includes a webpage structure; the webpage structure includes, but is not limited to, a webpage title, a webpage body content, pictures, sound, or video information.

2) Acquire the target picture file currently viewed by the user according to the webpage structure.

Preferably, after the method acquires the target picture file currently browsed by the user, the method further includes a step of classifying the obtained target picture file, and then selecting different types according to different categories of the obtained target picture file. The calculation method calculates a feature value of the target picture file.

Step S5: Query the user attention list according to the feature value of the target picture file to confirm whether the target picture file has been followed.

Specifically, when the feature value of the target picture file exists in the user's attention list, it is confirmed that the target picture file has been followed, and there is no need to repeat the attention, and the process proceeds to step S6;

When the feature value of the target picture file does not exist in the user's attention list, if it is confirmed that the target picture file has not been followed by the user, the process may be directly ended. That is, the feature value does not exist in the attention list, and when the user has not followed the target picture file before, the process ends.

It can be understood that when the feature value of the target picture file does not exist in the user's attention list, the user can follow the target picture file according to his preference.

Step S6: When the feature value of the target picture file exists in the user's attention list, prompting the user not to pay attention to the target picture file.

In this embodiment, the user may be reminded through a message prompt box, a pop-up page, or a voice prompt that the user does not need to pay attention to the target picture file. For example, a separate page pops up in the user ’s current webpage interface to display information that does not require attention to the target picture file, or a message prompt box appears in the user ’s electronic device to display the information that does not need to pay attention to the target picture file, The user is directly notified of the information that does not need to pay attention to the target picture file through a voice broadcast.

In an embodiment, the method may further include, when the feature value of the target picture file does not exist in the user attention list, confirming that the target picture file is not being followed, and prompting the user to pay attention to the target picture file And add the target picture file and its feature values to the watchlist, so that the watchlist can be updated.

It can be understood that the user may also be prompted to pay attention to the target picture file through a message prompt box, a pop-up page, or a voice prompt, and the details are not described herein again.

In summary, the method for intelligently identifying a picture provided by the present application includes receiving a picture file; calculating a feature value of the picture file; establishing a user attention list, wherein the attention list includes the feature value; and obtaining a user's current browsing And calculate the feature value of the picture file; compare whether the feature value is consistent with the feature value in the attention list; and when the feature value is consistent with the feature value in the attention list, Prompt the user not to pay attention to the picture file. Therefore, a problem that a user pays attention to the same picture multiple times when there are too many pictures that the user cannot recognize the same picture posted by different users can be solved. You can filter the pictures by calculating the feature values of the pictures to avoid the repeated attention of the same picture and improve the user experience.

The foregoing is only a specific implementation of this application, but the scope of protection of this application is not limited to this. For those of ordinary skill in the art, without departing from the creative concept of this application, they can also make Improvement, but these all belong to the protection scope of this application.

The functional modules and hardware structure of the server that implements the above-mentioned method for intelligently identifying pictures are respectively introduced below with reference to FIGS. 3 to 4.

FIG. 3 is a functional block diagram of the first preferred embodiment of the device for intelligently identifying pictures in this application.

In some embodiments, the device 30 for intelligently identifying pictures runs in a server. The device 30 for intelligently identifying pictures may include a plurality of functional modules composed of program code segments. The program code of each program segment in the device 30 for intelligently identifying pictures may be stored in a memory and executed by at least one processor to perform the function of intelligently identifying pictures.

In this embodiment, the device 30 for intelligently identifying pictures may be divided into a plurality of functional modules according to functions performed by the device 30. The functional modules may include: a establishing module 301, an obtaining module 302, a calculating module 303, a query module 304, and a prompting module 305. The module referred to in the present application refers to a series of computer-readable instruction segments that can be executed by at least one processor and can perform fixed functions, which are stored in a memory. In some embodiments, functions of each module will be described in detail in subsequent embodiments.

The establishing module 301 is configured to receive a picture file.

Specifically, the step of classifying the received picture files includes:

The calculation module 303 is configured to calculate a feature value of the picture file.

A1: Extract the image of the contained building from the original image;

B1: Set A ∈ R ^{m × n} as a face gray image, where m≥n, rank (A) = r;

B2: Obtain two orthogonal matrices and diagonal matrices as follows:

U = [u ₁ , u ₂ , ..., u _m ] ∈R ^{m × m} , U ^T U = I,

B3: Make the formula,

among them,

Feature vector

The establishing module 301 is further configured to receive an operation that a user follows a picture file, and establish a watch list according to the operation, where the watch list includes the picture file and a corresponding feature value.

The obtaining module 302 is configured to obtain a target picture file currently viewed by a user, and calculate a feature value of the target picture file.

The query module 304 is configured to query the user attention list according to the feature value of the target picture file to confirm whether the target picture file has been followed.

Specifically, when the feature value of the target picture file exists in the user's attention list, it is confirmed that the target picture file has been followed, and there is no need to repeat the attention;

When the feature value of the target picture file does not exist in the user's attention list, if it is confirmed that the target picture file has not been followed by the user, the process may be directly ended. That is, the feature value does not exist in the attention list, and the user has not followed the target picture file before.

The prompting module 305 is configured to prompt the user that the target picture file does not need to pay attention to when the feature value of the target picture file exists in the user's attention list.

In an embodiment, the prompting module 305 is further configured to confirm that the target picture file is not followed when the feature value of the target picture file does not exist in the user's attention list, and prompt the user to follow the target. A picture file, and adding the target picture file and its feature values to the watchlist, so that the watchlist can be updated.

In summary, the device 30 for intelligently identifying pictures provided in this application includes a building module 301, an obtaining module 302, a calculation module 303, a query module 304, and a prompting module 305. The establishment module 301 is configured to receive an operation that a user cares about a picture file, and establish a user attention list according to the operation, wherein the attention list includes the picture file and its corresponding feature value; the acquisition module 302 is used to The target picture file currently viewed by the user is obtained, and the calculation module 303 is used to calculate the feature value of the target picture file; the query module 304 is used to query the user attention list according to the feature value of the target picture file, Confirming whether the target picture file has been followed; and the prompting module 305 is configured to confirm that the target picture file has been followed when the feature value of the target picture file exists in the user attention list, and prompt the user No need to pay attention to the target picture file. Therefore, a problem that a user pays attention to the same picture multiple times when there are too many pictures that the user cannot recognize the same picture posted by different users can be solved. You can filter the pictures by calculating the feature values of the pictures to avoid the repeated attention of the same picture and improve the user experience.

The above integrated unit implemented in the form of a software functional module may be stored in a non-volatile readable storage medium. The above software function module is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a dual-screen device, or a network device) or a processor to execute the various embodiments described in this application. Part of the method.

The server 2 includes a database 41, a memory 42, at least one processor 43, computer-readable instructions 44 stored in the memory 42 and executable on the at least one processor 43, and at least one communication bus 45.

When the at least one processor 43 executes the computer-readable instructions 44, the steps in the embodiment of the method for intelligently identifying pictures described above are implemented.

Exemplarily, the computer-readable instructions 44 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 42 and processed by the at least one processor 43 Execute to complete this application. The one or more modules / units may be a series of computer-readable instruction instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer-readable instructions 44 in the server 2.

The server 2 is a device capable of automatically performing numerical calculations and / or information processing according to an instruction set or stored in advance, and its hardware includes, but is not limited to, a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), programmable gate array (Field-Programmable Gate Array, FPGA), digital processor (Digital Signal Processor, DSP), embedded equipment, etc. Those skilled in the art may understand that the schematic diagram 4 is only an example of the server 2 and does not constitute a limitation on the server 2. It may include more or fewer components than shown in the figure, or combine some components or different components. For example, the server 2 may further include an input / output device, a network access device, a bus, and the like.

The database 41 is a warehouse established on the server 2 to organize, store and manage data according to a data structure. Databases are generally divided into three types: hierarchical database, network database and relational database. In this embodiment, the database 41 is used to store information such as picture files and feature values.

The at least one processor 43 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), and application-specific integrated circuits (ASICs). ), Ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 43 may be a microprocessor, or the processor 43 may be any conventional processor, etc. The processor 43 is a control center of the server 2 and uses various interfaces and lines to connect the entire server 2 The various parts.

The memory 42 may be configured to store the computer-readable instructions 44 and / or modules / units, and the processor 43 may execute or execute the computer-readable instructions and / or modules / units stored in the memory 42 and The data stored in the memory 42 is called to implement various functions of the server 2. The memory 42 may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), etc .; the storage data area may be Data (such as audio data, phone book, etc.) created according to the use of the server 2 are stored. In addition, the memory 42 may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, an internal memory, a plug-in hard disk, a Smart Memory Card (SMC), and a Secure Digital (SD). Card, flash memory card (Flash card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.

The memory 42 stores program code, and the at least one processor 43 can call the program code stored in the memory 42 to perform related functions. For example, each module described in FIG. 3 (the establishment module 301, the acquisition module 302, the calculation module 303, the query module 304, and the prompt module 305) is a program code stored in the memory 42, and is processed by the at least one The device 43 executes the functions of the various modules to achieve the purpose of intelligently identifying pictures.

When the modules / units integrated in the server 2 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile readable storage medium. Based on this understanding, this application implements all or part of the processes in the methods of the above embodiments, and can also be completed by computer-readable instructions instructing related hardware. The computer-readable instructions can be stored in a non-volatile memory. In the read storage medium, when the computer-readable instructions are executed by a processor, the steps of the foregoing method embodiments can be implemented. The computer-readable instructions include computer-readable instruction codes, and the computer-readable instruction codes may be in a source code form, an object code form, an executable file, or some intermediate form. The non-volatile readable medium may include: any entity or device capable of carrying the computer-readable instruction code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), electric carrier signals, telecommunication signals, and software distribution media. It should be noted that the content contained in the non-volatile readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdictions. For example, in some jurisdictions, according to legislation and patent practices, non- Volatile readable media does not include electrical carrier signals and telecommunication signals.

Although not shown, the server 2 may further include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 43 through a power management system, so as to implement management through the power management system. Charge, discharge, and power management functions. The power source may also include one or more DC or AC power sources, a recharging system, a power failure detection circuit, a power converter or inverter, a power source status indicator, and any other components. The server 2 may further include a Bluetooth module, a Wi-Fi module, and the like, and details are not described herein again.

It should be understood that the embodiments are for illustrative purposes only and are not limited by this structure in the scope of patent applications.

In the several embodiments provided in this application, it should be understood that the disclosed electronic device and method may be implemented in other ways. For example, the embodiments of the electronic device described above are merely schematic. For example, the division of the units is only a logical function division, and there may be another division manner in actual implementation.

In addition, each functional unit in each embodiment of the present application may be integrated in the same processing unit, or each unit may exist separately physically, or two or more units may be integrated in the same unit. The integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional modules.

It is obvious to a person skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the application. Therefore, the embodiments should be regarded as exemplary and non-limiting in every respect. The scope of the present application is defined by the appended claims rather than the above description, and therefore is intended to fall within the claims. All changes that are within the meaning and scope of equivalent requirements are included in this application. Any reference signs in the claims should not be construed as limiting the claims involved. Furthermore, it is clear that the word "comprising" does not exclude other units or that the singular does not exclude the plural. A plurality of units or devices stated in the system claims may also be implemented by one unit or device through software or hardware. Words such as first and second are used to indicate names, but not in any particular order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application, but are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present application can be used. Modifications or equivalent substitutions can be made without departing from the spirit and scope of the technical solution of the present application.

Claims

A method for intelligently identifying a picture, characterized in that the method includes:

Receiving an operation that a user follows a picture file, and establishing a user attention list according to the operation, wherein the attention list includes the picture file and a corresponding feature value thereof;

Get the target image file currently viewed by the user;

Calculating a feature value of the target picture file;

Querying the user's attention list according to the feature value of the target picture file to confirm whether the target picture file has been followed; and

When the feature value of the target picture file exists in the user's attention list, confirming that the target picture file has been followed, prompting the user that the user does not need to pay attention to the target picture file.
The method for intelligently identifying a picture according to claim 1, wherein before the operation of receiving a user's attention to a picture file and establishing a user's attention list according to the operation, the method further comprises:

Receiving picture files uploaded by electronic equipment;

Calculate a feature value of the picture file.
The method for intelligently identifying a picture according to claim 2, wherein after receiving the picture file uploaded by the electronic device, the method further comprises:

Preprocess the received image file;

Feature extraction of pre-processed pictures; and

Classify the pictures after feature extraction.
The method for intelligently identifying a picture according to claim 2, wherein the calculating the feature value of the picture file comprises:

According to different types of the classified picture files, different calculation methods are used to calculate the feature values of the picture files.
The method for intelligently identifying pictures according to claim 2, wherein the method for classifying pictures after feature extraction by a classifier includes an image classification method based on a generated model and an image classification method based on a discrimination model.
The method for intelligently identifying pictures according to claim 1, wherein the obtaining a target picture file currently viewed by a user comprises:

A web crawler crawls webpage content currently viewed by a user, where the webpage content includes a webpage structure;

The target picture file currently browsed by the user is obtained according to the webpage structure.
The method for intelligently identifying pictures according to claim 6, wherein when the feature value of the target picture file does not exist in the user's attention list, confirming that the target picture file is not being followed, and prompting the user to pay attention The target picture file, and adding the target picture file and its feature value to the attention list.
A device for intelligently identifying pictures is characterized in that the device includes:

A establishing module, configured to receive an operation that a user follows an image file, and establish a user attention list according to the operation, wherein the attention list includes the image file and its corresponding feature value;

An acquisition module for acquiring a target image file currently viewed by a user;

A calculation module, configured to calculate a feature value of the target picture file;

A query module, configured to query the user attention list according to the feature value of the target picture file to confirm whether the target picture file has been followed; and

A prompting module is configured to confirm that the target picture file has been followed when the feature value of the target picture file exists in the user's attention list, and prompt the user that the user does not need to follow the target picture file.
A server is characterized in that the server includes a processor and a memory, and the processor implements the following steps when executing at least one computer-readable instruction stored in the memory:

Receiving an operation that a user follows a picture file, and establishing a user attention list according to the operation, wherein the attention list includes the picture file and a corresponding feature value thereof;

Get the target image file currently viewed by the user;

Calculating a feature value of the target picture file;

Querying the user's attention list according to the feature value of the target picture file to confirm whether the target picture file has been followed; and

When the feature value of the target picture file exists in the user's attention list, confirming that the target picture file has been followed, prompting the user that the user does not need to pay attention to the target picture file.
The server according to claim 9, characterized in that before the operation of receiving a user's attention to a picture file and establishing a user's attention list according to the operation, the processor further executes the at least one computer-readable instruction. Implement the following steps:

Receiving picture files uploaded by electronic equipment;

Calculate a feature value of the picture file.
The server according to claim 10, wherein after receiving the picture file uploaded by the electronic device, the processor executes the at least one computer-readable instruction to further implement the following steps:

Preprocess the received image file;

Feature extraction of pre-processed pictures; and

Classify the pictures after feature extraction.
The server according to claim 10, wherein, according to different types of the classified picture files, different calculation methods are used to calculate the feature values of the picture files.
The server according to claim 10, wherein the method for classifying pictures after feature extraction by a classifier includes an image classification method based on a generated model and an image classification method based on a discriminative model.
The server according to claim 9, wherein when acquiring the target picture file currently viewed by the user, the processor executes the at least one computer-readable instruction to further implement the following steps:

A web crawler crawls webpage content currently viewed by a user, where the webpage content includes a webpage structure;

The target picture file currently browsed by the user is obtained according to the webpage structure.
The server of claim 14, wherein the processor executes the at least one computer-readable instruction to further implement the following steps:

When the feature value of the target picture file does not exist in the user attention list, confirm that the target picture file is not being followed, prompt the user to pay attention to the target picture file, and add the target picture file and its feature value To the watchlist.
A non-volatile readable storage medium, characterized in that the non-volatile readable storage medium stores at least one computer-readable instruction, and when the at least one computer-readable instruction is executed by a processor, the following steps are implemented: :

Receiving an operation that a user follows a picture file, and establishing a user attention list according to the operation, wherein the attention list includes the picture file and a corresponding feature value thereof;

Get the target image file currently viewed by the user;

Calculating a feature value of the target picture file;

Querying the user's attention list according to the feature value of the target picture file to confirm whether the target picture file has been followed; and

When the feature value of the target picture file exists in the user's attention list, confirming that the target picture file has been followed, prompting the user that the user does not need to pay attention to the target picture file.
The storage medium of claim 16, wherein before the operation of receiving a user's attention to a picture file and establishing a user's attention list according to the operation, the at least one computer-readable instruction is further executed by a processor. Implement the following steps:

Receiving picture files uploaded by electronic equipment;

Calculate a feature value of the picture file.
The storage medium according to claim 17, wherein after receiving the picture file uploaded by the electronic device, when the at least one computer-readable instruction is executed by a processor, the following steps are further implemented:

Preprocess the received image file;

Feature extraction of pre-processed pictures; and

Classify the pictures after feature extraction.
The storage medium of claim 16, wherein when the target picture file currently viewed by the user is obtained, the at least one computer-readable instruction is executed by a processor to implement the following steps:

A web crawler crawls webpage content currently viewed by a user, where the webpage content includes a webpage structure;

The target picture file currently browsed by the user is obtained according to the webpage structure.
The storage medium of claim 19, wherein when the at least one computer-readable instruction is executed by a processor, the following steps are further implemented:

When the feature value of the target picture file does not exist in the user attention list, confirm that the target picture file is not being followed, prompt the user to pay attention to the target picture file, and add the target picture file and its feature value To the watchlist.