A method, device and computing device for identifying illegal advertising content

Abstract

The present invention discloses a method, device and computing device for identifying illegal advertising content, including the following steps: in response to interaction with a first display area, triggering shooting of the advertising content to be identified, so as to display the first advertising collection image obtained after shooting in the first display area; in response to marking the part of the first advertising collection image involving illegal content to be determined using a marking frame in a first state, triggering shooting of the part corresponding to the illegal content to be determined, so as to obtain a second advertising collection image; establishing a link relationship between the part of the illegal content to be determined and the second advertising collection image; sending the first advertising collection image to a server, so that the server, in response to interaction with the part of the illegal content to be determined, retrieves the second advertising collection image and identifies it; in response to the identification result involving illegal content, changing the marking frame to a second state different from the first state. The present invention at least improves the identification effect of illegal advertising content.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device and computing equipment for identifying illegal advertising content. Background Art

[0002] In today's society, advertisements often occupy our daily lives. For example, commercial advertisements are a means of promoting products or providing services by disseminating information about products or services to consumers or users through advertising media in a paid manner.

[0003] Since advertisements may include the appearance of the product and related text descriptions, some advertisers place different forms of advertisements in many public places in order to attract users' attention and pursue profits. These advertisements may contain illegal images or text content, which may have a negative impact on society.

[0004] In order to solve the above-mentioned problem, it is necessary to conduct manual review of advertisements placed in public places. However, if it relies entirely on manual review, there may be problems such as manual review taking a long time and being prone to errors and omissions. Summary of the invention

[0005] In view of the above problems, the present invention is proposed to provide a method, apparatus and computing device for identifying illegal advertising content that overcome the above problems or at least partially solve the above problems.

[0006] According to one aspect of the present invention, a method for identifying illegal advertising content is provided, which includes the following steps:

[0007] In response to the interaction with the first display area, triggering shooting of the advertisement content to be identified in the real environment, so as to display a first advertisement collection image obtained after shooting in the first display area;

[0008] In response to marking a portion of the first advertisement collected image displayed in the first display area involving the to-be-determined illegal content using a marking frame in the first state, triggering shooting of a portion of the to-be-determined illegal content in the to-be-identified advertisement content in a real environment corresponding to the to-be-determined illegal content, to obtain a second advertisement collected image;

[0009] Establishing a link relationship between a portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image;

[0010] Sending the first advertisement collection image to a server, so that the server, in response to an interaction with a portion of the first advertisement collection image involving the illegal content to be determined, retrieves and identifies the second advertisement collection image;

[0011] In response to the recognition result sent by the server that the second advertisement collection image involves illegal content, the marking box corresponding to the to-be-determined illegal content displayed in the first display area is changed to a second state different from the first state.

[0012] Optionally, in the method according to the present invention, before displaying the first advertisement acquisition image obtained after shooting in the first display area, the method further includes:

[0013] Performing fuzziness recognition on the first advertisement captured image to obtain a corresponding fuzziness evaluation value;

[0014] Determining whether the first advertisement captured image is blurred based on a comparison between the blur evaluation value and a preset threshold;

[0015] When the comparison result shows that the first advertisement captured image is blurred, the shooting of the advertisement content to be identified in the real environment is triggered again to update the first advertisement captured image.

[0016] Optionally, in the method according to the present invention, performing blur recognition on the first advertisement collection image to obtain a corresponding blur evaluation value includes:

[0017] Converting the first advertisement captured image into a grayscale image;

[0018] Calculate the horizontal gradient value and the vertical gradient value of the grayscale image through a filter;

[0019] Dividing the horizontal gradient value and the vertical gradient value into intervals to obtain a plurality of intervals;

[0020] Counting the number of pixels corresponding to the gradient values ​​in the plurality of intervals;

[0021] Based on the statistical results, a gradient histogram is obtained;

[0022] The number of pixels in the high-frequency part of the gradient histogram is obtained and recorded as the blur evaluation value.

[0023] Optionally, in the method according to the present invention, using the marking frame to mark a portion of the first advertisement collection image displayed in the first display area involving the to-be-determined illegal content includes:

[0024] Determine the region shape and region area of ​​the portion of the first advertisement collection image involving the illegal content to be determined;

[0025] Based on the shape of the region, selecting a marking box of a corresponding shape from a preset list;

[0026] Based on the area of ​​the region, scaling the marking frame in equal proportion;

[0027] Use the proportionally scaled marking box to mark the part of the content to be determined as illegal.

[0028] Optionally, in the method according to the present invention, after establishing a link relationship between the portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image, the method further includes:

[0029] In response to an interaction with a portion of the first advertising collection image displayed in the first display area that involves content to be determined as illegal, triggering the display of the second advertising collection image in the second display area, wherein the display area of ​​the second display area is larger than that of the first display area.

[0030] Optionally, in the method according to the present invention, the second display area includes a text display area and a picture display area;

[0031] After obtaining the second advertisement collection image, the method further includes:

[0032] In response to the classification selection of the second advertisement collection image, classify the second advertisement collection image into a text violation content category to be determined and / or a picture violation content category to be determined;

[0033] After establishing a link relationship between the portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image, the method further includes:

[0034] In response to an interaction with a portion of the first advertising collection image displayed in the first display area involving illegal content to be determined, a second advertising collection image classified as text illegal content to be determined is triggered to be displayed in the text display area, and / or a second advertising collection image classified as picture illegal content to be determined is triggered to be displayed in the picture display area, wherein the display areas of the text display area and the picture display area are larger than the display area of ​​the first display area.

[0035] Optionally, in the method according to the present invention, the server, in response to the interaction with the portion of the first advertisement collection image involving the illegal content to be determined, retrieves and identifies the second advertisement collection image having a link relationship with the first advertisement collection image, including:

[0036] The server, in response to the interaction with the portion of the first advertisement collection image related to the content of the method to be determined, retrieves the second advertisement collection image and its classification that has a link relationship with the first advertisement collection image;

[0037] The server retrieves a corresponding recognition strategy based on the classification of the second advertisement collection image to recognize the second advertisement collection image.

[0038] Optionally, in the method according to the present invention, the method further comprises:

[0039] When the server identifies the second advertisement collection image as involving illegal content, the server obtains the sender information of the first advertisement collection image that has a link relationship with the second advertisement collection image, accumulates the number of times the identification result is that the second advertisement collection image involves illegal content, and generates a statistical form that corresponds the sender information to the accumulated number of times;

[0040] The server periodically issues the cumulative number of monetary rewards to the sender corresponding to the sender information based on the statistical form, and resets the statistical form after issuing the monetary rewards.

[0041] According to another aspect of the present invention, a method for identifying illegal advertising content is provided, which includes:

[0042] A display module is configured to trigger, in response to an interaction with the first display area, shooting of the advertisement content to be identified in the real environment, so as to display a first advertisement collection image obtained after shooting in the first display area;

[0043] a marking module configured to, in response to marking a portion of the first advertisement collection image displayed in the first display area involving the to-be-determined illegal content using a marking frame in a first state, trigger photographing a portion of the to-be-determined illegal content in the to-be-identified advertisement content in a real environment corresponding to the to-be-determined illegal content, and obtain a second advertisement collection image;

[0044] a linking module configured to establish a linking relationship between a portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image;

[0045] an identification module configured to send the first advertisement collection image to a server, so that the server retrieves and identifies the second advertisement collection image in response to an interaction with a portion of the first advertisement collection image involving the illegal content to be determined;

[0046] The changing module changes the marking box corresponding to the to-be-determined illegal content displayed in the first display area to a second state different from the first state in response to the recognition result sent by the server that the second advertisement collection image involves illegal content.

[0047] According to another aspect of the present invention, there is provided a computing device, comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be suitable for being executed by the at least one processor, and the program instructions include instructions for executing the above method.

[0048] According to the solution of the present invention, the user triggers the shooting of the advertising content to be identified by interacting with the first display area of ​​the terminal, and the shooting result is displayed in the first display area, so that the user can mark the part of the first advertising acquisition image involved in the illegal content to be determined; and at the same time, it can also trigger the shooting of the part corresponding to the illegal content to be determined, so as to establish a link relationship between the part of the first advertising acquisition image involved in the illegal content to be determined and the second advertising acquisition image. When the first advertising acquisition image is subsequently sent to the server, the server can retrieve the second advertising acquisition image based on the part of the first advertising acquisition image involved in the illegal content to be determined for identification, thereby improving the efficiency of identifying illegal content; finally, when the server feeds back the corresponding identification result, it can also change the state of the marking box involving the illegal content according to the identification result, thereby improving the convenience of user result acquisition and the efficiency of identifying illegal advertising content.

[0049] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0051] Figure 1 A schematic diagram of a computing device 100 according to one embodiment of the present invention is shown;

[0052] Figure 2 A flowchart of a method for identifying illegal advertisement content according to another embodiment of the present invention is shown;

[0053] Figure 3 A structural block diagram of an apparatus for identifying illegal advertisement content according to yet another embodiment of the present invention is shown. DETAILED DESCRIPTION

[0054] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0055] To solve the above problems in the prior art, the inventor proposes the solution of the present invention. An embodiment of the present invention provides a method for identifying illegal advertisement content, which can be executed in a computing device. Figure 1 FIG. 1 shows a block diagram of a computing device 100 according to an embodiment of the present invention. Figure 1 As shown, in a basic configuration 102, computing device 100 typically includes system memory 106 and one or more processors 104. A memory bus 108 may be used for communication between processor 104 and system memory 106.

[0056] Depending on the desired configuration, the processor 104 may be any type of processor, including but not limited to: a microprocessor (µP), a microcontroller (µC), a digital signal processor (DSP), or any combination thereof. The processor 104 may include one or more levels of cache, such as a level 1 cache 110 and a level 2 cache 112, a processor core 114, and registers 116. An example processor core 114 may include an arithmetic logic unit (ALU), a floating point unit (FPU), a digital signal processing core (DSP core), or any combination thereof. An example memory controller 118 may be used with the processor 104, or in some implementations, the memory controller 118 may be an internal part of the processor 104.

[0057] Depending on the desired configuration, the system memory 106 can be any type of memory, including but not limited to: volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.) or any combination thereof. The physical memory in a computing device generally refers to the volatile memory RAM, and the data in the disk needs to be loaded into the physical memory before it can be read by the processor 104. The system memory 106 may include an operating system 120, one or more applications 122, and program data 124. The application 122 is actually a plurality of program instructions, which are used to instruct the processor 104 to perform corresponding operations. In some embodiments, in some embodiments, the application 122 may be arranged to execute instructions on the operating system by one or more processors 104 using the program data 124. The operating system 120 may be, for example, Linux, Windows, etc., which includes program instructions for processing basic system services and performing hardware-dependent tasks. The application 122 includes program instructions for implementing various user-desired functions, and the application 122 may be, for example, a browser, instant messaging software, a software development tool (such as an integrated development environment IDE, a compiler, etc.), etc., but is not limited thereto. When the application 122 is installed into the computing device 100 , a driver module may be added to the operating system 120 .

[0058] When the computing device 100 starts running, the processor 104 reads and executes the program instructions of the operating system 120 from the memory 106. The application 122 runs on the operating system 120 and uses the interfaces provided by the operating system 120 and the underlying hardware to implement various functions desired by the user. When the user starts the application 122, the application 122 is loaded into the memory 106, and the processor 104 reads and executes the program instructions of the application 122 from the memory 106.

[0059] Computing device 100 also includes a storage device 132 including a removable storage 136 and a non-removable storage 138 , both of which are connected to storage interface bus 134 .

[0060] The computing device 100 may also include an interface bus 140 that facilitates communication from various interface devices (e.g., output devices 142, peripheral interfaces 144, and communication devices 146) to the basic configuration 102 via the bus / interface controller 130. Example output devices 142 include a graphics processing unit 148 and an audio processing unit 150. They can be configured to facilitate communication with various external devices such as a display or speakers via one or more A / V ports 152. Example peripheral interfaces 144 may include a serial interface controller 154 and a parallel interface controller 156, which may be configured to facilitate communication with external devices such as input devices (e.g., keyboards, mice, pens, voice input devices, touch input devices) or other peripherals (e.g., printers, scanners, etc.) via one or more I / O ports 158. Example communication devices 146 may include a network controller 160, which may be arranged to facilitate communication with one or more other computing devices 162 via a network communication link via one or more communication ports 164.

[0061] A network communication link may be an example of a communication medium. Communication media may generally be embodied as computer-readable instructions, data structures, program modules in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium. A "modulated data signal" may be a signal in which one or more of its data sets or changes thereto may be carried out in a manner that encodes information in the signal. As non-limiting examples, communication media may include wired media such as a wired network or a dedicated line network, and various wireless media such as sound, radio frequency (RF), microwave, infrared (IR) or other wireless media. The term computer-readable media used herein may include both storage media and communication media.

[0062] The computing device 100 also includes a storage interface bus 134 connected to the bus / interface controller 130. The storage interface bus 134 is connected to a storage device 132, which is suitable for data storage. Example storage devices 132 may include removable storage 136 (such as CD, DVD, USB flash drive, removable hard disk, etc.) and non-removable storage 138 (such as hard disk drive HDD, etc.).

[0063] In the computing device 100 according to the present invention, the application 122 includes a plurality of program instructions for executing the method 200 .

[0064] Figure 2 A flowchart of a method 200 according to another embodiment of the present invention is shown. The method 200 is suitable for being executed in a computing device (such as the aforementioned computing device 100).

[0065] like Figure 2As shown, the purpose of method 200 is to implement a method for identifying illegal advertising content, which starts with step S202. In step S202, the following steps are included: in response to the interaction with the first display area, triggering the shooting of the advertising content to be identified in the real environment, so as to display the first advertising captured image obtained after the shooting in the first display area.

[0066] For example, in this embodiment, the execution subject of the method can be a computer, a mobile phone, or an interactive device with display function, shooting function, communication function, etc.; here, in order to facilitate the introduction of the scheme involved in this embodiment, the execution subject is uniformly set to a mobile phone, but it should be noted that this should not be regarded as a limitation on the scheme of this embodiment.

[0067] In actual application scenarios, when a user finds that a sign, electronic screen or advertisement displayed in other forms in a public place may involve illegal content, the user can interact with the first display area of ​​the mobile phone, such as sliding, clicking and other interactive methods in touch interaction, thereby triggering and activating the shooting function of the mobile phone, allowing the user to use the shooting function to shoot the advertisement to be identified in the real environment. After the shooting is completed, the mobile phone will display the captured first advertisement image in the first display area.

[0068] In this embodiment, the above-mentioned illegal content may include textual illegal content and / or picture illegal content. The textual illegal content may, for example, include words such as "the world's number one" and "the world's strongest" that are not in line with fair competition or words that are not in line with public order and good morals; and the picture illegal content may, for example, include pictures involving bloody violence, restrictive pictures or pictures that are not authorized for use.

[0069] The inventors further discovered during the study that due to external or personal reasons when the user is taking pictures, the image quality of the first advertisement captured may be poor, blurry, or unclear, which will affect the subsequent display and recognition effects.

[0070] In order to solve the above problems, the inventors have proposed at least the following solutions:

[0071] Before displaying the first advertisement collection image obtained after shooting in the first display area, performing blur recognition on the first advertisement collection image to obtain a corresponding blur evaluation value;

[0072] Determining whether the first advertisement captured image is blurred based on a comparison between the blur evaluation and a preset threshold;

[0073] When the comparison result shows that the first advertisement captured image is blurred, the shooting of the advertisement content to be identified in the real environment is triggered again to update the first advertisement captured image.

[0074] In an embodiment, when a user uses a mobile phone to capture a first advertisement captured image, the mobile phone will first perform blurriness identification on the first advertisement captured image to obtain a blurriness evaluation value reflecting the degree of blurriness; then the blurriness evaluation value will be compared with a preset threshold value to determine whether the captured first advertisement captured image is blurry, and the comparison result will be displayed; if the comparison result shows that the first advertisement captured image is blurry, the mobile phone will reactivate the shooting function of the mobile phone, so that the user can use the shooting function again to shoot the advertisement to be identified in a real environment, until the blurriness comparison result of the captured first advertisement captured image is clear, and the corresponding first advertisement captured image will be displayed in the first display area.

[0075] For example, the above-mentioned fuzziness recognition of the first advertisement collection image to obtain the corresponding fuzziness evaluation value can be achieved by the following method:

[0076] Converting the first advertisement captured image into a grayscale image;

[0077] Calculate the horizontal gradient value and vertical gradient value of the grayscale image through the filter;

[0078] Divide the horizontal gradient value and the vertical gradient value into intervals to obtain several intervals;

[0079] Count the number of pixels corresponding to the gradient values ​​in several intervals;

[0080] Based on the statistical results, a gradient histogram is obtained;

[0081] The number of pixels in the high-frequency part is obtained according to the gradient histogram and recorded as the fuzziness evaluation value.

[0082] The following is a further detailed introduction to the method for obtaining the above-mentioned fuzziness evaluation value:

[0083] First, after the mobile phone captures the first advertisement captured image, the mobile phone converts the first advertisement captured image into a grayscale image; then, a filter is applied to the grayscale image to calculate its horizontal gradient value in the horizontal direction and the vertical gradient value in the vertical direction. The filter may be, for example, a Sobel filter; then, the horizontal gradient value and the vertical gradient value are divided into several intervals (for example, 0 to 255), and the number of pixels corresponding to the gradient value in each interval is counted, and a gradient histogram is established based on the statistical results, wherein the horizontal axis of the gradient histogram may represent the interval of the gradient value, and the vertical axis may represent the number of pixels in the corresponding interval; finally, the pixel value corresponding to the high-frequency part (usually corresponding to edge information) in the gradient histogram is obtained and recorded as the fuzziness evaluation value.

[0084] Among them, the smaller the number of pixels corresponding to the high-frequency part in the gradient histogram, the higher the possibility that the first advertisement collection image is blurred; therefore, a preset threshold can be pre-set through the mobile phone, and when the number of pixels in the high-frequency part is lower than the preset threshold, it can be determined that the first advertisement collection image is blurred.

[0085] In step S204, the following steps are included: in response to using the marking box in the first state to mark the part of the first advertising collection image displayed in the first display area that involves the illegal content to be determined, triggering the shooting of the part of the advertising content to be identified in the real environment that corresponds to the illegal content to be determined, to obtain a second advertising collection image.

[0086] In this embodiment, since the first advertisement collection image is taken based on the user's belief that the corresponding advertisement contains illegal content, and the first advertisement collection image may include multiple illegal contents to be determined, the area occupied and the position of each illegal content to be determined in the first advertisement collection image may be different, which may cause the following two problems: 1. The position of a certain illegal content to be determined is at the edge of the first advertisement collection image and cannot be accurately identified; 2. The area occupied by a certain illegal content to be determined is too small to be clearly identified.

[0087] In order to solve the above two problems respectively, the following methods can be used:

[0088] 1. In order to clearly mark the location of each illegal content to be determined in the first advertisement collection image, the user can use the mobile phone to use the marking box in the first state to mark the parts of the first advertisement collection image involving the illegal content to be determined in turn;

[0089] 2. In order to more clearly identify the image of each part of the first advertising captured image involving the illegal content to be determined, the user's mobile phone can activate the shooting function of the mobile phone again in response to the aforementioned marking operation, so that the user can use the shooting function again to only shoot the part of the advertising content to be identified in the real environment that corresponds to each illegal content to be determined, thereby obtaining a second advertising captured image.

[0090] For example, the above-mentioned operation of marking the portion of the first advertisement collection image displayed in the first display area involving the to-be-determined illegal content by using a marking frame includes:

[0091] Determine the region shape and region area of ​​the portion of the first advertisement collection image involving the illegal content to be determined;

[0092] Based on the area shape, select a marking box of the corresponding shape from the preset list;

[0093] Based on the area of ​​the region, the marked box is scaled proportionally;

[0094] Use the proportionally scaled marking box to mark the part of the content to be determined as illegal.

[0095] The following is a further detailed introduction to the above marking operation:

[0096] First, the user can use the mobile phone to determine in advance the region shape and region area of ​​the part of the first advertising collection image involving the illegal content to be determined. The determination method is, for example, that the user uses touch handwriting to circle the part of the first advertising collection image displayed in the first display area involving the illegal content to be determined; then, the mobile phone determines the corresponding region shape and region area based on the circled area of ​​the user; then, based on the region shape, selects a marking box of the corresponding shape from a preset list; then, based on the calculated region area, scales the selected marking box proportionally; finally, the scaled marking box is used to mark the part of the illegal content to be determined, so as to complete the complete marking operation.

[0097] In step S206, the following steps are included: establishing a link relationship between the portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image.

[0098] In this embodiment, since the first advertising collection image may include multiple illegal contents to be determined, and the second advertising collection image is an image corresponding to the portion of the illegal contents to be determined, the two are in a corresponding relationship; therefore, based on this corresponding relationship, the two can be linked, so that through the interaction of a certain illegal content to be determined, it can be linked to the second advertising collection image.

[0099] For example, after establishing a link relationship between the portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image, the method further includes:

[0100] In response to an interaction with a portion of the first advertising collection image displayed in the first display area involving content to be determined as illegal, a second advertising collection image is triggered to be displayed in the second display area, wherein the display area of ​​the second display area is larger than that of the first display area.

[0101] In this embodiment, there may be a certain gap between the second display area and the first display area, so as to facilitate the distinction between the contents in the first display area and the second display area; for example, after establishing a link relationship between the portion of the first advertising collection image involving the content to be determined in violation of the regulations and the second advertising collection image, the user can interact with the portion of the first advertising collection image involving the content to be determined in violation of the regulations displayed in the first display area, thereby triggering the display of the second advertising collection image in the second display area, thereby enabling the user to separately retrieve and display the second advertising collection image corresponding to each piece of content to be determined in the first advertising collection image, thereby facilitating the user to view the content details based on the second advertising collection image.

[0102] Here, the user's interaction method with the content to be determined as violating the regulations may be sliding, clicking, or other interaction methods in touch interaction; for example, since a marking box is provided corresponding to the content to be determined as violating the regulations, the user can interact with the marking box to display the second advertisement collection image in the second display area; in addition, when the second advertisement collection image corresponding to a certain piece of content to be determined as violating the regulations is displayed in the second display area, the user can change the display content of the second display area by interacting with another piece of content to be determined as violating the regulations.

[0103] It should be noted that the display area of ​​the second display region may be larger than the display area of ​​the first display region; or the display area of ​​the second display region may not be larger than the display area of ​​the first display region.

[0104] Furthermore, the second display area includes a text display area and a picture display area;

[0105] After obtaining the second advertisement collection image, the method may further include:

[0106] In response to the classification selection of the second advertisement collection image, classify the second advertisement collection image into a text violation content category to be determined and / or a picture violation content category to be determined;

[0107] After establishing a link relationship between the portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image, the method may further include:

[0108] In response to an interaction with a portion of the first advertising collection image displayed in the first display area involving illegal content to be determined, a second advertising collection image classified as text illegal content to be determined is triggered to be displayed in the text display area, and / or a second advertising collection image classified as picture illegal content to be determined is triggered to be displayed in the picture display area.

[0109] In this embodiment, the second display area can be divided into a text display area and a picture display area; after obtaining the second advertising collection image, the user can classify the second advertising collection image based on the mobile phone, thereby realizing the process of displaying the second advertising collection image classified as the type of text violation content to be determined in the text display area, and / or displaying the second advertising collection image classified as the type of picture violation content to be determined in the picture display area; thereby improving the regularity and cleanliness of the display.

[0110] In step S208, the following steps are included: sending the first advertisement collection image to the server, so that the server responds to the interaction with the part of the first advertisement collection image involving the illegal content to be determined, and retrieves and identifies the second advertisement collection image.

[0111] In this embodiment, since the first advertising collection image may include multiple illegal contents to be determined, and each illegal content to be determined is linked to a corresponding second advertising collection image, during the identification process, the first advertising collection image can be sent to the server, so that the server can sequentially retrieve the corresponding second advertising collection images based on the interaction of multiple parts of the first advertising collection image involving illegal contents to be determined, and complete the identification of all parts of the first advertising collection image involving illegal contents to be determined; compared with manual review, the speed and accuracy of the review can be greatly improved.

[0112] Furthermore, the server retrieves and identifies a second advertisement collection image having a link relationship with the first advertisement collection image in response to the interaction with the portion of the first advertisement collection image involving the to-be-determined illegal content, including:

[0113] In response to the interaction with the portion of the first advertisement collection image related to the content of the method to be determined, the server retrieves the second advertisement collection image and its classification that has a link relationship with the first advertisement collection image;

[0114] The server retrieves a corresponding recognition strategy based on the classification of the second advertisement collection image to recognize the second advertisement collection image.

[0115] For example, since the second advertisement collection image corresponding to the to-be-determined illegal content has a corresponding classification, the server can call up the corresponding recognition strategy based on its classification to identify different second advertisement collection images; among them, for the second advertisement collection image classified as the to-be-determined text illegal content class, the text part can be recognized by, for example, OCR recognition method, etc.; and for the second advertisement collection image classified as the to-be-determined picture illegal image class, the picture part can be recognized by, for example, neural network learning method, etc.; it should be noted that, since OCR recognition method and neural network learning method are both existing technologies, the specific technical content will not be elaborated on.

[0116] In this embodiment, since the second advertisement collection image corresponding to all parts of the first advertisement collection image involving the content to be determined as illegal has been manually classified into images / texts in advance before the first advertisement collection image is sent to the server for identification, after receiving the first advertisement collection image, the server can directly call up different identification strategies for different classifications for identification, thereby reducing the computing power of the server and improving the corresponding work efficiency.

[0117] In step S210, the following steps are included: in response to the recognition result sent by the server that the second advertisement collection image involves illegal content, the marking box corresponding to the to-be-determined illegal content displayed in the first display area is changed to a second state different from the first state.

[0118] For example, the change of the marking box from the first state to the second state can be understood as: the color of the marking box changes from the first color to a second color different from the first color (for example, from black to red), the thickness of the marking box changes from the first thickness to a second thickness different from the first thickness (for example, from 1mm to 2mm), and the line shape of the marking box changes from the first shape to a second shape different from the first shape (for example, from a straight line to a dotted line).

[0119] In this embodiment, since the server will identify all parts of the first advertising captured image that involve the illegal content to be determined, the identification result may include illegal content or no illegal content. In order to allow users to obtain the identification result more intuitively through their mobile phones; therefore, when the server identifies illegal content, the user's mobile phone will respond to the identification result by changing the mark box corresponding to the illegal content to be determined displayed in the first display area to a second state different from the first state, so as to facilitate the user to judge which content is illegal content according to the state change of the mark box, thereby improving the convenience of user-based result acquisition.

[0120] Furthermore, in order to increase the enthusiasm of users to report illegal content, the method for identifying illegal advertising content also includes:

[0121] When the server identifies the second advertisement collection image as involving illegal content, the server obtains the sender information of the first advertisement collection image that has a link relationship with the second advertisement collection image, accumulates the number of times the identification result is that the second advertisement collection image involves illegal content, and generates a statistical form that corresponds the sender information to the accumulated number of times;

[0122] The server periodically issues a monetary reward of the accumulated number of times to the sender corresponding to the sender information based on the statistical form, and resets the statistical form after issuing the monetary reward.

[0123] In this embodiment, the sender information may be the terminal code of the sender, such as the terminal code of the user's mobile phone, and the sender information may be used to identify the sender and the information is unique; and when the server's recognition result of the second advertising collection image is that it involves illegal content, the server will obtain the sender information of the first advertising collection image that has a link relationship with the second advertising collection image, and perform cumulative counting based on the recognition result, and establish a statistical form based on this; wherein, the statistical form includes the sender information and the corresponding cumulative count, so that the server can periodically reward the sender corresponding to the sender information with a sending amount based on the statistical form, thereby forming a periodic reward mechanism, thereby increasing the user's enthusiasm for use.

[0124] In order to introduce the above content more clearly and briefly, the following is a further explanation based on actual application scenarios:

[0125] When user A sends the first advertisement collection image to the server via mobile phone B, the server will first identify the parts of the first advertisement collection image involving all the illegal contents to be determined. If the server's identification result is that the first advertisement collection image contains several illegal contents, the server will obtain the sender information of the first advertisement collection image, that is, the terminal code of mobile phone B, and establish a relationship between the terminal code and the number of illegal contents involved based on this terminal code to form a statistical form; then, user A will be rewarded periodically according to the statistical form, for example, every month, and after the rewards are distributed, the data in the statistical form will be reset and cleared, so as to recalculate the rewards for the next cycle.

[0126] According to the scheme of this embodiment, the user triggers the shooting of the advertising content to be identified by interacting with the first display area of ​​the terminal, and the shooting result is displayed in the first display area, so that the user can mark the part of the first advertising collection image involved in the illegal content to be determined; and at the same time, it can also trigger the shooting of the part corresponding to the illegal content to be determined again, so as to establish a link relationship between the part of the first advertising collection image involved in the illegal content to be determined and the second advertising collection image. When the first advertising collection image is subsequently sent to the server, the server can retrieve the second advertising collection image based on the part of the first advertising collection image involved in the illegal content to be determined, thereby improving the efficiency of identifying illegal content; finally, when the server feeds back the corresponding recognition result, it can also change the state of the marking box involving the illegal content according to the recognition result, thereby improving the convenience of user result acquisition and the efficiency of identifying illegal advertising content.

[0127] Another embodiment of the present invention provides a device for identifying illegal advertisement content. Figure 3 The corresponding device block diagram is as follows:

[0128] A display module is configured to trigger, in response to an interaction with the first display area, shooting of the advertisement content to be identified in the real environment, so as to display a first advertisement collection image obtained after shooting in the first display area;

[0129] a marking module configured to, in response to marking a portion of the first advertisement collection image displayed in the first display area involving the to-be-determined illegal content using a marking frame in a first state, trigger photographing a portion of the to-be-determined illegal content in the to-be-identified advertisement content in a real environment corresponding to the to-be-determined illegal content, and obtain a second advertisement collection image;

[0130] a linking module configured to establish a linking relationship between a portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image;

[0131] an identification module configured to send the first advertisement collection image to a server, so that the server retrieves and identifies the second advertisement collection image in response to an interaction with a portion of the first advertisement collection image involving the illegal content to be determined;

[0132] The changing module changes the marking box corresponding to the to-be-determined illegal content displayed in the first display area to a second state different from the first state in response to the recognition result sent by the server that the second advertisement collection image involves illegal content.

[0133] The various techniques described herein may be implemented in combination with hardware or software, or a combination thereof. Thus, the method and apparatus of the present invention, or some aspects or parts of the method and apparatus of the present invention may be in the form of program codes (i.e., instructions) embedded in a tangible medium, such as a removable hard disk, a USB flash drive, a floppy disk, a CD-ROM, or any other machine-readable storage medium, wherein when the program is loaded into a machine such as a computer and executed by the machine, the machine becomes a device for practicing the present invention.

[0134] In the case where the program code is executed on a programmable computer, the computing device generally includes a processor, a storage medium readable by the processor (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device. The memory is configured to store the program code; the processor is configured to execute the method of the present invention according to the instructions in the program code stored in the memory.

[0135] By way of example and not limitation, readable media include readable storage media and communication media. Readable storage media stores information such as computer readable instructions, data structures, program modules or other data. Communication media generally embody computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and include any information transfer medium. Any combination of the above is also included within the scope of readable media.

[0136] In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the examples of the present invention. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to implement the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the preferred embodiment of the present invention.

[0137] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0138] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0139] Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

[0140] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device so disclosed may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0141] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0142] In addition, some of the embodiments are described herein as methods or combinations of method elements that can be implemented by a processor of a computer system or by other devices that perform the functions. Therefore, a processor with necessary instructions for implementing the method or method elements forms a device for implementing the method or method elements. In addition, the elements described herein of the device embodiments are examples of devices for implementing the functions performed by the elements for the purpose of implementing the invention.

[0143] As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe common objects merely indicates that different instances of similar objects are involved, and is not intended to imply that the objects so described must have a given order in time, space, order, or in any other manner.

[0144] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative and not restrictive with respect to the scope of the present invention, and the scope of the present invention is defined by the appended claims.

Claims

1. A method for identifying illegal advertising content, wherein: The following steps are involved: In response to the interaction with the first display area, triggering shooting of the advertisement content to be identified in the real environment, so as to display a first advertisement collection image obtained after shooting in the first display area; In response to marking a portion of the first advertisement collected image displayed in the first display area involving the to-be-determined illegal content using a marking frame in the first state, triggering shooting of a portion of the to-be-determined illegal content in the to-be-identified advertisement content in a real environment corresponding to the to-be-determined illegal content, to obtain a second advertisement collected image; Establishing a link relationship between a portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image; Sending the first advertisement collection image to a server, so that the server, in response to an interaction with a portion of the first advertisement collection image involving the illegal content to be determined, retrieves and identifies the second advertisement collection image; In response to the recognition result sent by the server that the second advertisement collection image involves illegal content, the marking box corresponding to the to-be-determined illegal content displayed in the first display area is changed to a second state different from the first state.

2. The method according to claim 1, wherein: Before displaying the first advertisement acquisition image obtained after shooting in the first display area, the method further includes: Performing fuzziness recognition on the first advertisement captured image to obtain a corresponding fuzziness evaluation value; Determining whether the first advertisement captured image is blurred based on a comparison between the blur evaluation value and a preset threshold; When the comparison result shows that the first advertisement captured image is blurred, the shooting of the advertisement content to be identified in the real environment is triggered again to update the first advertisement captured image.

3. The method according to claim 2, wherein: Performing fuzziness recognition on the first advertisement collected image to obtain a corresponding fuzziness evaluation value includes: Converting the first advertisement captured image into a grayscale image; Calculate the horizontal gradient value and the vertical gradient value of the grayscale image through a filter; Dividing the horizontal gradient value and the vertical gradient value into intervals to obtain a plurality of intervals; Counting the number of pixels corresponding to the gradient values ​​in the plurality of intervals; Based on the statistical results, a gradient histogram is obtained; The number of pixels in the high-frequency part of the gradient histogram is obtained and recorded as the blur evaluation value.

4. The method according to claim 1, wherein: Using the marking frame to mark a portion of the first advertisement collection image displayed in the first display area involving the to-be-determined illegal content includes: Determine the region shape and region area of ​​the portion of the first advertisement collection image involving the illegal content to be determined; Based on the shape of the region, selecting a marking box of a corresponding shape from a preset list; Based on the area of ​​the region, scaling the marking frame in equal proportion; Use the proportionally scaled marking box to mark the part of the content to be determined as illegal.

5. The method according to claim 1, wherein: After establishing a link relationship between the portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image, the method further includes: In response to an interaction with a portion of the first advertisement collection image displayed in the first display area that involves the to-be-determined illegal content, a trigger is provided to display the second advertisement collection image in the second display area.

6. The method according to claim 5, wherein: The second display area includes a text display area and a picture display area; After obtaining the second advertisement collection image, the method further includes: In response to the classification selection of the second advertisement collection image, classify the second advertisement collection image into a text violation content category to be determined and / or a picture violation content category to be determined; After establishing a link relationship between the portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image, the method further includes: In response to an interaction with a portion of the first advertising collection image displayed in the first display area involving illegal content to be determined, a second advertising collection image classified as text illegal content to be determined is triggered to be displayed in the text display area, and / or a second advertising collection image classified as picture illegal content to be determined is triggered to be displayed in the picture display area.

7. The method according to claim 6, wherein: The server, in response to the interaction with the portion of the first advertisement collection image involving the to-be-determined illegal content, retrieves and identifies the second advertisement collection image having a link relationship with the first advertisement collection image, including: The server, in response to the interaction with the portion of the first advertisement collection image related to the content of the method to be determined, retrieves the second advertisement collection image and its classification that has a link relationship with the first advertisement collection image; The server retrieves a corresponding recognition strategy based on the classification of the second advertisement collection image to recognize the second advertisement collection image.

8. The method according to claim 1, wherein: The method further comprises: When the server identifies the second advertisement collection image as involving illegal content, the server obtains the sender information of the first advertisement collection image that has a link relationship with the second advertisement collection image, accumulates the number of times the identification result is that the second advertisement collection image involves illegal content, and generates a statistical form that corresponds the sender information to the accumulated number of times; The server periodically issues the cumulative number of monetary rewards to the sender corresponding to the sender information based on the statistical form, and resets the statistical form after issuing the monetary rewards.

9. A device for identifying illegal advertising content, wherein: include: A display module is configured to trigger, in response to an interaction with the first display area, shooting of the advertisement content to be identified in the real environment, so as to display a first advertisement collection image obtained after shooting in the first display area; a marking module configured to, in response to marking a portion of the first advertisement collection image displayed in the first display area involving the to-be-determined illegal content using a marking frame in a first state, trigger photographing a portion of the to-be-determined illegal content in the to-be-identified advertisement content in a real environment corresponding to the to-be-determined illegal content, and obtain a second advertisement collection image; a linking module configured to establish a linking relationship between a portion of the first advertisement collection image involving the to-be-determined illegal content and the second advertisement collection image; an identification module configured to send the first advertisement collection image to a server, so that the server retrieves and identifies the second advertisement collection image in response to an interaction with a portion of the first advertisement collection image involving the illegal content to be determined; The changing module changes the marking box corresponding to the to-be-determined illegal content displayed in the first display area to a second state different from the first state in response to the recognition result sent by the server that the second advertisement collection image involves illegal content.

10. A computing device comprising: at least one processor; and A memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, and the program instructions include instructions for executing the method according to any one of claims 1 to 8.

Images