CN109829069B - Image auditing processing method and device, electronic equipment and storage medium - Google Patents

Image auditing processing method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN109829069B
CN109829069B CN201811626290.5A CN201811626290A CN109829069B CN 109829069 B CN109829069 B CN 109829069B CN 201811626290 A CN201811626290 A CN 201811626290A CN 109829069 B CN109829069 B CN 109829069B
Authority
CN
China
Prior art keywords
audited
image
images
page
audit
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811626290.5A
Other languages
Chinese (zh)
Other versions
CN109829069A (en
Inventor
邱泽潮
林协
李锦春
陈海峰
林子奇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Huaduo Network Technology Co Ltd
Original Assignee
Guangzhou Huaduo Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Huaduo Network Technology Co Ltd filed Critical Guangzhou Huaduo Network Technology Co Ltd
Priority to CN201811626290.5A priority Critical patent/CN109829069B/en
Publication of CN109829069A publication Critical patent/CN109829069A/en
Application granted granted Critical
Publication of CN109829069B publication Critical patent/CN109829069B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)

Abstract

The application discloses an image auditing processing method, an image auditing processing device, electronic equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining the display size of images to be audited and the container size of a current auditing page, calculating the display number of the images to be audited which can be contained in the current auditing page according to the display size and the container size, then carrying out feature identification on the images to be audited in the display number, classifying the images to be audited in the display number according to an identification result, and finally arranging the images to be audited which belong to the same classification in the images to be audited in the display number according to a preset rule. According to the method and the device, the display quantity of the receivable images to be audited is calculated, and the images to be audited which belong to the same classification after the characteristic identification classification are adjacently arranged, so that the images to be audited can be fully paved on the current audit page, the audit vision is improved, and the audit fluency and the audit efficiency of auditors can be improved.

Description

Image auditing processing method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of information technology, and in particular, to an image auditing method and apparatus, an electronic device, and a storage medium.
Background
With the continuous development of information technology, multimedia live broadcast is widely concerned by people in novel form and rich content, for example, one live broadcast can bring millions of traffic, so that the information transmission speed is high and is difficult to measure. However, many multimedia live broadcasts are now mixed with illegal contents, such as pornography, violence and the like, which disturb the normal life of people. In order to reduce the spread of the illegal contents, the illegal contents need to be discovered and eliminated in time.
The special characteristics of wide sources, large quantity and the like of the multimedia live broadcast bring great difficulty to supervision. In order to effectively monitor a large amount of multimedia live broadcasts, each platform needs a large amount of auditors to complete efficient and timely auditing, but the existing auditing method cannot well meet the actual use requirements of the auditors, so that the efficiency of the auditors is not high.
Disclosure of Invention
In view of the above problems, the present application provides an image auditing method and apparatus, an electronic device, and a storage medium, which can improve auditing efficiency.
In a first aspect, an embodiment of the present application provides an image review processing method, where the method includes: acquiring the display size of an image to be audited and the container size of a current audit page; calculating the display quantity of the images to be checked which can be contained in the current checking page according to the display size and the container size; performing feature recognition on the displayed quantity of images to be audited, and classifying the displayed quantity of images to be audited according to recognition results; and arranging the images to be checked belonging to the same classification in the displayed number of images to be checked according to a preset rule.
In a second aspect, an embodiment of the present application provides an image review processing apparatus, including: the acquisition module is used for acquiring the display size of the image to be audited and the container size of the current audit page; the calculation module is used for calculating the display quantity of the images to be checked which can be contained in the current checking page according to the display size and the container size; the classification module is used for performing feature recognition on the displayed number of images to be audited and classifying the displayed number of images to be audited according to the recognition result; and the arrangement module is used for arranging the images to be checked belonging to the same classification in the displayed number of images to be checked according to a preset rule.
In a third aspect, an embodiment of the present application provides an electronic device, which includes: a memory; one or more processors coupled with the memory; one or more programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of the first aspect as described above.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, in which program codes are stored, and the program codes can be called by a processor to execute the method according to the first aspect.
According to the image auditing processing method and device, the electronic equipment and the storage medium, the display size of the image to be audited and the container size of the current auditing page are obtained, the display number of the image to be audited, which can be contained in the current auditing page, is calculated according to the display size and the container size, then the displayed number of the image to be audited is subjected to feature recognition, the displayed number of the image to be audited is classified according to the recognition result, and finally the images to be audited, which belong to the same classification in the displayed number of the image to be audited, are arranged according to the preset rule. Therefore, the display quantity capable of being accommodated is calculated through the display size of the images to be audited and the container size of the current audit page, so that the current audit page can display a plurality of images to be audited and can be paved with pages, the quantity of auditors capable of auditing at one time is increased, the audit efficiency is improved, classification is performed through feature identification, the images to be audited in the same classification can be arranged adjacently, the audit vision is improved, and the audit smoothness and the audit efficiency of the auditors can be improved.
These and other aspects of the present application will be more readily apparent from the following description of the embodiments.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of an application environment suitable for use in embodiments of the present application;
FIG. 2 is a flow diagram illustrating audit logic suitable for use with embodiments of the present application;
FIG. 3 is a flow chart of an image review processing method according to an embodiment of the present application;
FIG. 4 is a flow chart of an image review processing method according to another embodiment of the present application;
FIG. 5 is a schematic diagram illustrating a display effect of a current review page provided by another embodiment of the present application;
fig. 6 is a schematic flowchart illustrating steps S610 to S660 according to another embodiment of the present application;
FIG. 7 is a diagram illustrating a switching of a current review page according to a first page switch instruction according to another embodiment of the present application;
FIG. 8 is a diagram illustrating a switching of a current review page according to a second page switch instruction according to another embodiment of the present application;
FIG. 9 shows a block diagram of an image review processing apparatus provided in an embodiment of the present application;
fig. 10 is a block diagram illustrating a configuration of an electronic device according to an embodiment of the present application, configured to execute an image review processing method according to an embodiment of the present application;
fig. 11 illustrates a storage unit for storing or carrying program codes for implementing an image review processing method according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, 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. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
At present, multimedia live broadcast is diversified, the live broadcast threshold is gradually reduced, more and more users can become anchor broadcasts, and the multimedia live broadcast is output outwards and self expression is realized. With the continuous enrichment of live broadcast contents and the continuous increase of live broadcast users, the auditing and monitoring work of multimedia live broadcast is challenged more and more. In order to effectively monitor a large amount of multimedia live broadcasts, machine auditing is introduced into a live broadcast platform to improve auditing efficiency, but the current machine auditing can only be simply screened and screened, and if more accurate auditing and judgment of illegal contents are to be realized, enough and trained auditors are still needed to carry out secondary auditing.
Although the existing manual auditing can judge more complex contents than machine auditing, the manual auditing cannot be general with machine auditing, nearly consistent auditing speed and accuracy can be kept while working for a long time, and in the actual auditing process, the manual auditing is easy to influence the auditing efficiency due to human factors such as distraction, so that the auditing efficiency can be improved by solving the distraction problem of auditors.
Based on the above problems, the inventor finds that the existing auditing method is difficult to provide a good display effect after a series of researches on the existing auditing method, so that auditors are easy to fatigue in the auditing process, the attention is dispersed, and the auditing efficiency is reduced. Therefore, how to improve the auditing vision and further improve the auditing efficiency is more and more important.
In the research process, the inventor researches the difficult point of the current live content auditing, more comprehensively considers the requirement of actual auditing, and provides the image auditing processing method and device, the electronic equipment and the storage medium of the embodiment of the application.
In order to better understand the image auditing method, device, electronic device and storage medium provided in the embodiments of the present application, a live broadcast network architecture and auditing logic suitable for the embodiments of the present application are described below.
Referring to fig. 1, fig. 1 is a diagram of an application scenario applicable to an embodiment of the present application. As shown in fig. 1, the client is installed in a terminal 200, and a plurality of terminals 200 and a server 100 are located in a wireless network or a wired network, and a plurality of terminals 200 and a server 100 can perform data interaction. Further, a plurality of terminals 200 may be connected to each other through the internet, or may be connected to each other through the internet with the server 100 as a transmission medium.
The terminal 200 may include, but is not limited to, an electronic device such as a notebook computer, a desktop computer, a tablet computer, a smart phone, and a wearable electronic device.
In some embodiments, the client is installed in the terminal 200, and may be, for example, an application installed in the terminal 200. If the user logs in through the account at the client, all information corresponding to the account can be stored in the storage space of the server 100. The server 100 may be an individual server, or a server cluster, or a local server, or a cloud server, which is not limited herein.
In some embodiments, the client may be a multimedia live broadcast auditing system, and auditors log in auditing accounts at the client, where different auditors correspond to different auditing accounts. The auditor audits the live broadcast data through the client, submits a punishment result according to the audit result obtained through the audit, and the punishment result is stored in the server 100.
Further, referring to fig. 2, fig. 2 is a schematic flowchart of an audit logic applicable to the embodiment of the present application. An auditing logic shown in fig. 2 may be adopted in the multimedia live broadcast auditing system, as shown in fig. 2, in some embodiments, live broadcast data may be audited by a machine first, and the live broadcast data may be preliminarily determined by image recognition and data analysis in the auditing stage of the machine to determine whether the live broadcast data is safe. After the determination, the secure live data is stored and archived, and the unsecure live data is stored as data to be audited in an audit data distribution queue, which in some embodiments is stored in the server 100.
The auditing data distribution queue comprises at least one piece of auditing data, the auditing data can be pictures, videos, audios and the like, and as one mode, the auditing data at least comprises one of pictures and video screenshots. And entering the to-be-audited data in the audit data distribution queue into a manual audit stage, specifically, auditing the to-be-audited data through a plurality of auditors and clients by manual audit.
In some embodiments, the server 100 distributes the to-be-audited data to the audit accounts corresponding to the auditors according to the audit data distribution queue, and the auditors can log in the audit accounts in the multimedia live broadcast audit system to obtain the to-be-audited data corresponding to the audit accounts for auditing.
The manual review at least comprises one of first manual review (manual first review) and second manual review (manual second review). The data to be audited at least comprises one of uncertain data, suspected violation data and data to be audited with high suspected violation degree. Specifically, as a mode, uncertain nuclear data to be reviewed can be distributed into a manual first review, suspected illegal nuclear data to be reviewed can be distributed into a manual second review, and further, the nuclear data to be reviewed, which is still suspected to be illegal through the judgment of the manual first review, can be distributed into the manual second review for the second manual review, so that the accuracy of illegal content judgment is improved.
It should be noted that, in the manual first-level review stage, violations or suspected violations can be found from the mass screenshots according to the auditing rules and submitted to the second-level review; in the manual secondary review stage, live broadcast content can be verified according to the auditing rule, judgment can be quickly made, and a reasonable processing mode can be selected. The audit rule is a basis for performing violation judgment on the data to be audited by the auditor, and as one mode, the auditor can determine violation types, such as pornography and violence, of the data to be audited according to the audit rule.
Further, punishing is performed on the anchor account corresponding to the illegal live broadcast which is determined to be illegal through manual review, the punishment may include but is not limited to a cover number, a fine, and the like, and a punishment result is stored in the server 100.
It should be noted that the flow diagrams of the audit logic and the audit logic provided in the embodiments of the present application are only for convenience of understanding, and the embodiments of the present application can be applied to various audit logics, so the flow diagrams of the audit logic and the audit logic are not limited to this scheme.
The following describes in detail an image auditing method, an apparatus, an electronic device, and a storage medium provided in embodiments of the present application with specific embodiments.
Referring to fig. 3, an embodiment of the present application provides an image auditing processing method, which can be applied to the terminal. As will be described in detail with respect to the flow shown in fig. 3, the image review processing method may specifically include the following steps:
step S310: and acquiring the display size of the image to be audited and the container size of the current audit page.
In this embodiment, the display size of the image to be checked at least includes the width and height of the image to be checked, and the container size of the current check page at least includes the width and height of the container of the current check page.
It can be understood that the image to be audited may be the data to be audited in the multimedia live audit system, the current audit page may be a page used for auditing the data to be audited in the multimedia live audit system, the current audit page includes a container, the image to be audited is displayed in the container of the current audit page, and the current audit page may include other page areas besides the container and may be used for displaying other information besides the image to be audited.
The current audit page is used for displaying an image to be audited, and the image to be audited is displayed in a container of the current audit page. The current review page includes, in addition to the container for displaying the images to be reviewed, other page areas, for example, the number of currently reviewed images, the number of displayed images to be reviewed in the current review page, and the size of the images to be reviewed displayed in the current review page may be displayed, so that the reviewer may obtain other information from the other page areas of the current review page.
It should be noted that the size of the container of the current review page, that is, the size of the area of the current review page for displaying the image to be reviewed, may be preset by the system or may be user-defined, and this is not limited in the embodiment of the present application. As a mode, the container size of the current audit page is preset by the system, repeated acquisition is not needed, and computing resources can be saved; as another mode, the size of the container of the current audit page can be user-defined, and an auditor can adjust the size of the area to be used for displaying the image to be audited on the current audit page according to own use habits and preferences in the audit process, so that the personalized requirements of the auditor are met, the audit experience is improved, and the audit efficiency is improved.
The display size of the image to be checked can be user-defined. As an embodiment, the display size of the image to be reviewed may be set on the current review page, so that the display size of the image to be reviewed may be adjusted. Specifically, the setting of the display size of the image to be audited may be selected by the auditor among a plurality of fixed proportions, or may be a value range is given, the auditor may select any proportion in the value range as the display size of the image to be audited, the proportion may be 75%, 100%, 150%, 200%, and the like.
In some embodiments, the display size of the image to be audited may be memorized, that is, the display size of the image to be audited that was set last time may be automatically memorized, and when the auditor logs out of the system and logs in the audit account again, the image to be audited may continue to be displayed according to the display size of the image to be audited that was set last time. Therefore, the using habits of the auditors can be memorized, the auditors can conveniently return to the system for auditing after the auditing is interrupted, the display size does not need to be set again, the images to be audited can be displayed according to the display size set last time and the auditing can be continuously carried out, the using operation is simplified, the auditing experience of the auditors is improved, and the auditing efficiency is improved.
Step S320: and calculating the display quantity of the images to be checked which can be contained in the current checking page according to the display size and the container size.
The display size is the display size of the image to be checked, and the container size is the container size of the current checking page. Specifically, according to the display size and the container size, the width of the container size can be divided by the width of the display size and rounded to obtain a first numerical value X, the height of the container size can be divided by the height of the display size and rounded to obtain a second numerical value Y, and the display number of the images to be audited which can be contained in the current audit page can be calculated according to the product of the first numerical value X and the second numerical value Y, so that the current audit page can be fully covered with the images to be audited in the display number, and full-screen display is realized. In some embodiments, the foregoing rounding, the fractional part can be directly discarded, leaving only the integer part, e.g., if the height of the container size divided by the height of the display size is equal to 2.8, where 2.8 is rounded to 2. Therefore, the display size of the image to be audited and the container size of the current auditing page are obtained, the display number of the image to be audited, which can be contained in the current auditing page, can be automatically calculated, full-screen display is realized, and due to the fact that the display size of the image to be audited can be self-defined, the display number of the image to be audited in the current auditing page can be flexibly adjusted by the auditor, personalized amplification and reduction are realized, and the use requirements of the auditor are met.
Step S330: and performing feature recognition on the displayed quantity of images to be audited, and classifying the displayed quantity of images to be audited according to the recognition result.
The feature recognition of the displayed number of images to be reviewed may be to input one image recognition model of the images to be reviewed, the image recognition model may be obtained by training one or more feature libraries, the feature libraries may include an action feature library, a portrait feature library, a movie feature library, and the like, and may also be a feature library capable of recognizing various features, specifically, the feature library may be a public database downloaded from a network, or a database built by a user, and is not limited herein. Furthermore, the feature library can be enriched continuously to train the image recognition model, and the accuracy of the feature recognition of the image recognition model is improved continuously.
Specifically, the feature is a characteristic or characteristic that one class of objects is distinguished from other classes of objects, and different objects can be distinguished through feature identification. For example, characteristics such as a portrait, a microphone, a game picture, a movie picture, an action and the like can be identified through characteristic identification, if the image to be audited contains the game picture, the image to be audited can be judged to belong to a game type according to the game picture obtained through identification, and the image to be audited is classified into a game category; if the images to be audited contain the movie pictures, the images to be audited can be judged to belong to the movie type according to the movie pictures obtained by identification, the images to be audited are divided into 'movie' classifications, and in addition, in some implementation modes, the images to be audited, of which the identification results cannot be obtained through feature identification, can be divided into one classification such as 'other' classifications. It can be understood that, through the feature identification, the features included in the image to be audited can be identified, the type of the image to be audited is judged, and the image to be audited is classified.
It should be noted that images to be audited belonging to the same category have certain commonality in terms of violation modes, violation areas, and the like, for example, in some embodiments, images to be audited belonging to the same category as "game" all include a game screen, and at this time, a violation portion appears in other areas other than the game screen with a greater probability, rather than the game screen, so that an auditor can exclude the game screen and perform observation and audit only for other areas when auditing images to be audited belonging to the category of "game". Therefore, when the auditor audits the images to be audited belonging to the same classification, the auditor can adopt the same auditing thinking, so that the smoothness of auditing judgment is improved, and the auditing efficiency can be further improved.
In some embodiments, the features can be identified according to the features of the image to be audited, the area proportion of the features in the image to be audited is calculated, and then the displayed number of images to be audited is classified according to the features and the area proportion. Images to be audited which have the same or similar characteristics and the same or similar characteristics have similar proportions on the screen are classified into a category. Specific identification methods can be referred to the embodiments described later.
Step S340: and arranging the images to be checked belonging to the same classification in the displayed number of images to be checked according to a preset rule.
The preset rules include that images to be audited belonging to the same category are arranged together, for example, arranged in the same row or the same column, so that the display effect of the current audit page can be improved. It should be noted that, because the common features exist among the images to be audited belonging to the same category, for example, 5 images to be audited only including the game interface are arranged in the same row, the auditor can quickly judge that the 5 images to be audited do not include the portrait, and the pornographic violation is not caused, so that by arranging the images to be audited of the same category together, the auditor can quickly audit according to the logic and standard of auditing the images, and even can make the audit judgment at the same time, without frequently switching the logic and standard, the audit fatigue is caused, thereby ensuring the audit fluency, and effectively improving the audit efficiency.
For example, the display number of the images to be audited can be calculated to be 12 according to the display size and the container size, feature recognition is performed on the 12 images to be audited, 3 classifications are obtained through recognition, the classifications are respectively 'game', 'movie', 'singing', and each classification corresponds to 4 images to be audited, at this time, the images to be audited belonging to the same classification can be arranged in the same row, for example, 4 images to be audited belonging to the classification of 'game' are arranged in the first row, 4 images to be audited belonging to the classification of 'movie' are arranged in the second row, and 4 images to be audited belonging to the classification of 'singing' are arranged in the third row. Because the images to be audited in the same classification have the same or similar characteristics, the vision has consistency, so that the auditing vision can be improved by arranging the images to be audited in the same classification together, and the auditing efficiency is improved.
According to the image auditing processing method provided by the embodiment of the application, the display quantity of the images to be audited which can be contained in the current auditing page is calculated by acquiring the display size of the images to be audited and the container size of the current auditing page, full-screen display is realized, the quantity of the images to be audited which can be audited by the auditor at one time is increased, and auditing efficiency is improved.
Referring to fig. 4, another embodiment of the present application provides an image auditing processing method, which can be applied to the terminal. As will be described in detail with respect to the flow shown in fig. 4, the image review processing method may specifically include the following steps:
step S410: and acquiring the display size of the image to be audited and the container size of the current audit page.
Step S420: and calculating the display quantity of the images to be checked which can be contained in the current checking page according to the display size and the container size.
For the detailed description of steps S410 to S420, reference may be made to steps S310 to S320 in the foregoing embodiment, which is not described herein again.
Step S430: and performing feature identification on the displayed number of images to be audited to obtain the features of each image to be audited and the area ratio of the features of each image to be audited to the corresponding image to be audited.
Specifically, as a mode, the area ratio of the feature to the image to be audited and the corresponding image to be audited can be obtained by calculating the ratio of the number of pixels occupied by the feature to the total pixels of the image to be audited. For example, the image to be checked is characterized by a portrait, and the area ratio is the area ratio of the portrait in the image to be checked, that is, the ratio of the number of pixels occupied by the portrait to the total number of pixels of the image to be checked, such as 50%, 30%, and the like.
Specifically, the features of the image to be audited can be obtained through feature identification, and the area ratio of the features to the corresponding image to be audited, that is, the area ratio of the features in the image, is obtained through calculation. For example, feature points such as five sense organs, head and shoulders and the like can be identified to identify a portrait, and then the area ratio of the portrait to the corresponding image to be audited is obtained according to the number of pixels occupied by the portrait.
Step S440: and classifying the displayed quantity of images to be audited according to the characteristics and the area proportion.
The image to be audited can be classified according to the features and the area proportion, for example, the image to be audited with the same or similar features can be classified according to the features and the area proportion of the features and the corresponding image to be audited, and the image to be audited with the same or similar features in the image to be audited with the similar area proportion can be classified into the same classification.
It can be understood that the images to be audited belonging to the same classification have the same or similar characteristics, and the images to be audited belonging to the same classification are arranged together, so that the consistency can be visually presented, and the auditing vision is improved.
For example, when the image to be audited belonging to the "game" classification is audited, the game picture can be excluded, and only other areas are observed and audited, and when the image to be audited belonging to the "dance" classification is audited, dressing and actions need to be focused to judge whether the dressing, the actions are not elegant and other violations occur. It can be understood that different auditing thoughts need to be switched for auditing images of different classifications, and the same auditing thought can be adopted for auditing images of the same classification, so that the smoothness of auditing judgment is kept, and the auditing efficiency is improved. In the prior art, images to be audited are not classified according to features, so that auditors cannot easily utilize common features to quickly audit the images to be audited in the same classification in the auditing process. The above examples are only for convenience of describing that the review thinking for reviewing the images of the same category has commonality, and the present embodiment is not limited thereto.
It should be noted that the displayed number of images to be reviewed may be classified according to the features and the area ratios of the features and the corresponding images to be reviewed, or may be classified according to the features and the area ratios of the other features and the corresponding images to be reviewed.
As a mode, the images to be reviewed may be classified according to the characteristics and the area ratios of the other characteristics and the corresponding images to be reviewed, for example, according to dance motions recognized in the images to be reviewed and the area ratio of the real portrait to the images to be reviewed, that is, the real portrait ratio. Wherein the real portrait is distinguished from the portrait in the picture and the image. Specifically, in some embodiments, if a dance action is recognized in the image to be audited, and the true portrait proportion is 70%, the image to be audited may be classified into a "dance" classification, and when the true portrait proportion is 0, the image to be audited may be determined to be a game screen, a movie screen, or another screen, and classified into a "game," "movie," or another "classification.
In some embodiments, different classifications can be prioritized according to the area ratio of the portrait to the corresponding image to be reviewed, for example, the area ratio is large, in the live broadcast field, a greater probability of pornographic violation occurs in the image to be reviewed with the larger portrait area ratio, and the probability of pornographic violation occurring in the image to be reviewed without the portrait is low, so for the image to be reviewed at the same or similar time, the classification with the larger portrait area ratio is preferentially displayed, for example, a classification with a greater real portrait proportion, such as a "dance" classification, can be preferentially displayed, so that the image to be reviewed with the higher violation probability can be preferentially reviewed, the image to be reviewed belonging to a "game" or "movie" classification can be deferred to be reviewed by the reviewer more timely for the content with the greater probability of violation, and the propagation of the violation content can be blocked in time, therefore, the efficiency of auditing the illegal contents can be improved.
Step S450: and arranging the images to be checked belonging to the same classification in the displayed number of images to be checked according to a preset rule.
The preset rule at least comprises one of arranging the images to be checked belonging to the same classification in the same row and the same class. Therefore, the full-screen display can be realized, the images to be audited in the same classification can be arranged together, the auditing effect is improved, the smoothness of auditing judgment can be improved, and the auditing efficiency is improved.
It should be noted that images to be audited belonging to the same category have the same or similar features, and since images to be audited having the same or similar features have commonalities in violation modes, violation areas, and the like, images to be audited having the same or similar features and having area ratios of the features that satisfy a certain threshold range can be classified into the same category, so that images to be audited belonging to the same category can adopt the same auditing thinking, thereby improving the smoothness of auditing judgment, and meanwhile, images to be audited having similar visual presentation effects between images to be audited having similar area ratios can have visual consistency between images to be audited belonging to the same category, thereby improving auditing vision. Therefore, the images to be audited with the same or similar characteristics and area proportions are divided into the same classification, so that auditors can adopt the same auditing thinking when auditing the images to be audited of the same classification, the smoothness of auditing judgment is improved, and the auditing efficiency is improved.
Step S460: and acquiring the variable blank area of the current audit page.
It should be noted that the variable blank area of the current audit page is changeable, and correspondingly, the current audit page further includes a fixed blank area, and the fixed blank area is unchangeable.
The current review page comprises other page areas besides a container for displaying the image to be reviewed. Specifically, when the current review page does not display any image to be reviewed, that is, the container does not include any image to be reviewed, the variable blank area of the current review page may be an area corresponding to the container, or an area in the container other than the fixed blank area. It will be appreciated that the variable blank area of the current audit page may be a variable blank area of a container of the current audit page. Further, when the current review page displays the images to be reviewed and as the display number of the images to be reviewed increases, the area of the variable blank area decreases accordingly.
In some embodiments, the fixed blank areas are distributed around the container of the current audit page, please refer to fig. 5, where fig. 5 shows a schematic diagram of the display effect of the container in the current audit page when the number of displays is 4, and the fixed blank areas include a left edge and a right edge of the container with a width x1Width y of upper edge of container downwards1Left width x of right edge of container2Width y of lower edge of container facing upwards2A region of (1), wherein the width x1Width y1Width x2And width y2The two or more groups of the present invention may be the same or partially the same or different, and the present embodiment is not limited herein. Specifically, the fixed blank area enables the image to be audited to maintain a width x at least with the left edge of the container when the image to be audited is displayed on the current audit page1At least a distance y from the upper edge of the container1At least a width x from the right edge of the container2At least a distance of width y from the lower edge of the container2The distance of the image to be audited is ensured to be completely displayed on the current audit page, and the audit vision is improved.
Specifically, the area of the container except for the fixed blank area and the image to be checked is the variable blank area, for example, please refer to the container B in fig. 5, and the variable blank area is the area of the container B except for the fixed blank area, fig. 1, fig. 2, fig. 3, and fig. 4. It should be noted that the container a and the container B in fig. 5 are the same container, and different names are only for convenience of description and do not limit the present embodiment.
Step S470: and allocating interval areas for the displayed number of images to be checked according to the variable blank areas, and arranging the displayed number of images to be checked at intervals according to the interval areas.
For example, referring to fig. 5, when the number of the display images is 4, after the interval areas are allocated to the 4 images to be checked according to the variable blank area, the 4 images to be checked in the container a are arranged at intervals as shown in the container B. The to-be-audited images with the display quantity can be fully paved in the container, the display effect can be finely adjusted according to the variable blank area, the full-screen display effect is further optimized, and audit vision is improved.
In some embodiments, the 4 images to be audited in the container a may be arranged at intervals or may be arranged without intervals, specifically, a blank area may be fixedly allocated to each image to be audited, so that before the display effect of the container B is achieved according to the blank area interval arrangement, the displayed number of images to be audited may be kept at a certain distance, so that each image to be audited may be independent from other images to be audited, and may not be visually connected into one piece, which may affect the appearance. And the full-screen display effect can be optimized after the arrangement according to the blank area interval.
Further, referring to fig. 6, fig. 6 is a schematic flowchart illustrating steps S610 to S660 in the image review processing method according to the embodiment. As will be described below with reference to the flowchart shown in fig. 6, the image review processing method may further include the following steps:
step S610: and pre-loading the image to be checked of the next checking page.
It should be noted that, when the to-be-audited image of the next audit page is loaded in advance, the to-be-audited images in the displayed number are loaded, that is, based on the foregoing steps, the to-be-audited images in the displayed number are loaded in advance according to the display size of the to-be-audited image and the audit size of the to-be-audited page, and the to-be-audited images are displayed according to the display size.
Specifically, when the auditor audits the images to be audited of the current audit page or before the auditor audits the images to be audited of the current audit page, the auditor can request the server to display the number of the images to be audited, and pre-load the images to be audited of the next audit page, so that when the auditor audits the images to be audited of the current audit page, the pre-loaded images to be audited of the next audit page can be directly displayed on the current audit page for the auditor to audit, and when the auditor changes the next batch of images to be audited to audit, the delay of waiting for data loading does not exist, the smoothness of the audit process is improved, and the audit efficiency is further improved.
Compared with the prior art, after the image to be audited of the current audit page is audited, the server is requested to continue auditing the new image to be audited in response to the request of the user, the auditor can not perceive the delay of acquiring the image to be audited in the audit process by preloading the image to be audited of the next audit page, and can perform feature recognition on the displayed number of images to be audited and realize the operation of classification arrangement by preloading, the auditor can not feel the delay at the front end, namely the current audit page, but can directly acquire the full-screen image to be audited which is already arranged according to the classification, thereby effectively relieving the system pressure, avoiding the influence of external factors such as network instability and the like on the audit process, smoothly acquiring the new image to be audited to continue auditing, and greatly reducing the waiting time for downloading and displaying the image to be audited, the auditing fluency is improved, the images to be audited in the same category can be arranged together, the current auditing page is fully paved according to the self-defined display size, full-screen display is realized, auditing vision is improved, and auditing efficiency is greatly improved.
Step S620: and locking the image to be audited of the current audit page and the image to be audited of the next audit page loaded in advance.
When the image to be audited of the next audit page is preloaded, the image to be audited of the preloaded next audit page can be locked, so that the image to be audited of the current audit page and the image to be audited of the preloaded next audit page are both in a locked state, and the same locked image to be audited cannot repeatedly appear in a plurality of audit pages, so that the image to be audited which is being audited by the auditors and the image to be audited which is preloaded by the auditors are not acquired by other auditors, one image to be auditors is ensured to complete auditing and submit an audit result, the waste of audit labor caused by repeated auditing can be effectively avoided, and the overall audit efficiency is improved.
As a mode, the displayed number of images to be audited is acquired from the audit data distribution queue, the images to be audited are not taken out from the audit data distribution queue, and only the locking tag is added, so that other auditors do not acquire the images to be audited with the locking tag when acquiring the images to be audited from the audit data distribution queue. After the image to be audited is unlocked, the image to be audited can be obtained again in the audit data distribution queue, so that the image to be audited can be guaranteed. Specifically, the lock on the image to be checked may be released by deleting the "lock" tab, or may be released in other manners, which is not limited in this embodiment.
In a specific scenario, for example, when an auditor suddenly interrupts auditing, the image to be audited, which has been loaded by the auditor, may be unlocked in the auditing data distribution queue, so that other auditors may obtain the unlocked image to be audited for auditing, thereby ensuring that the image to be audited can be audited in time.
As another mode, the displayed number of images to be audited can be taken out from the audit data distribution queue, so that the same image to be audited does not appear on multiple audit pages and cannot be acquired by other auditors. Further, when the image to be audited is returned to the audit data distribution queue, the image to be audited can be obtained again, and it is ensured that the image to be audited can be audited. Repeated auditing is avoided, and the overall auditing efficiency is improved.
It should be noted that steps S610 to S620 may be executed before step S410 to step S470, or after step S410 to step S470, and the execution of steps S610 to S620 is related to the first page switching instruction, for example, when the first page switching instruction is acquired, the execution of steps S610 to S620 may be triggered, and the specific execution manner is described in the above steps, and is not described herein again.
Step S630: a first page switch instruction is obtained.
The first page switching instruction may be obtained in response to an operation of a user, and specifically, the first page switching instruction may be obtained in response to a click operation of "next page" or "submit" on a current review page by the user, or in response to a touch operation of a shortcut key, such as "space", of the user. It can be understood that the instruction triggering manner may be preset by the system, or may be customized by the user, for example, different shortcut keys are set according to the use habit, and the specific instruction triggering manner is not limited in this embodiment.
Step S640: and submitting the previously stored image to be audited of the last audit page according to the first page switching instruction, storing the image to be audited of the current audit page, and displaying the pre-loaded image to be audited of the next audit page on the current audit page.
It should be noted that, in this embodiment, the storing of the image to be audited includes storing an audit result of the image to be audited and a result of the image to be audited. And the image to be audited may be modified before being submitted, that is, the auditor may modify the audit result for the image to be audited that is not submitted, specifically, for example, when the auditor is auditing the image to be audited of the current audit page like fig. 1, it is determined that fig. 1 is not in violation, and after the image to be audited of the current audit page is switched to the image to be audited of the next audit page loaded in advance according to the first page switching instruction, the auditor recognizes that the audit on the image 1 of the previous audit page is in error, and at this time, the audit result in fig. 1 may be modified before the next first page switching instruction is obtained. Specific modifications may be made with reference to the following steps.
It can be understood that when the auditor audits the image to be audited, the audit result is stored and then submitted, so that the image to be audited of the last audit page of the current audit page is submitted according to the first page switching instruction, delayed submission is ensured, the modification opportunity is reserved, and the system pressure can be relieved due to non-immediate submission.
And storing the image to be audited of the current audit page according to the first page switching instruction, and displaying the image to be audited of the next audit page loaded in advance on the current audit page, so that smooth page switching is realized, and an auditor can audit a new image to be audited without waiting for loading, namely the image to be audited of the next audit page loaded in advance. It should be noted that, after the image to be checked of the next pre-loaded review page is displayed on the current review page, the image to be checked of the current review page is switched to the image to be checked of the next pre-loaded review page, and the image to be checked of the previous review page of the current review page is switched to the image to be checked of the current review page.
Specifically, for example, please refer to fig. 7, fig. 7 shows a schematic diagram of switching a current review page according to a first page switching instruction in this embodiment, where an image to be reviewed of the current review page is represented by an image to be reviewed C, an image to be reviewed of a next review page that is loaded in advance is represented by an image to be reviewed D, an image to be reviewed of a previous stored previous review page is represented by an image to be reviewed E, at this time, the image to be reviewed E is submitted according to the first page switching instruction, the image to be reviewed C is stored, the image to be reviewed D is displayed on the current review page, and when a next first page switching instruction is immediately obtained, the stored image to be reviewed of the previous review page of the current review page, that is, the image to be reviewed C is submitted. Therefore, the page switching operation according to the first page switching instruction is completed, the delayed submission of the auditing result is realized, on one hand, when the next first page switching instruction is not obtained, the previously stored image E to be audited of the last audited page can be modified, on the other hand, the system pressure can be relieved through pre-loading, and the influence of external factors such as network instability and the like on auditing is avoided. Smooth page switching is realized by pre-loading, the verification smoothness is improved, meanwhile, the modification opportunity of the last verified page can be reserved, the self-checking of the verifier is facilitated, the verification omission is reduced, and the verification quality is improved.
Step S650: and acquiring a second page switching instruction.
The second page switching instruction may be obtained in response to an operation of the user, and specifically, the second page switching instruction may be obtained in response to a click operation of "previous page" or "return" on the current audit page by the user, or in response to a touch operation of a shortcut key of the user, such as an "Esc" key on a keyboard. It can be understood that the instruction triggering manner may be preset by the system, or may be customized by the user, for example, different shortcut keys are set according to the use habit, and the specific instruction triggering manner is not limited in this embodiment.
Step S660: and storing the image to be audited of the current audit page according to the second page switching instruction, and switching the image to be audited of the current audit page into the image to be audited of the last audit page.
It should be noted that before the to-be-audited image of the previous audit page obtains the next first page switching instruction, that is, before the audit result is submitted, the to-be-audited image of the previous audit page may be switched to the current audit page according to the second page switching instruction to be displayed, so that the auditor may modify the audit result of the to-be-audited image of the previous audit page.
Specifically, for example, when an auditor audits an image to be audited of a current audit page, like fig. 1, the auditor determines that fig. 1 does not violate the rule, stores an image to be audited, including the current audit page of fig. 1, as a previously stored image to be audited of a previous audit page, and displays a pre-loaded image to be audited of a next audit page on the current audit page, at this time, according to a second page instruction, the image to be audited, including the previous audit page of fig. 1, can be switched back to the current audit page for display, so that the auditor can select fig. 1 to modify an audit result, so that the auditor can perform self-checking, avoid causing unnecessary mistakes and omissions, and thus can improve the audit quality.
Furthermore, after the image to be audited of the previous audit page is modified, the stored image to be audited of the current audit page can be switched back through the first page switching instruction, so that an auditor can modify the image to be audited of the previous audit page at any time in the process of auditing the image to be audited of the current audit page, and after the modification is completed, the stored image to be audited of the current audit page is switched back to the current audit page for display according to the first page switching instruction. It should be noted that the stored image to be audited of the current audit page includes the audit result of the image to be audited by the auditor, that is, the auditor can continue to audit other images to be audited that are not audited, without repeatedly auditing the image to be audited that has been audited once, so that the audit efficiency can be improved.
Specifically, for example, referring to fig. 8, fig. 8 shows a schematic diagram of switching a current review page according to a second page switching instruction in this embodiment, where an image to be reviewed of the current review page is represented by an image to be reviewed C, an image to be reviewed of a next review page that is loaded in advance is represented by an image to be reviewed D, an image to be reviewed of a previous review page that is stored in advance is represented by an image to be reviewed E, at this time, the image to be reviewed C is stored according to the second page switching instruction, the previous stored image to be reviewed E is switched back to the current review page for display, and the image to be reviewed that is loaded in advance continues to be stored in a background for display. And after the modification of the audit result of the image E to be audited is completed, storing the modified image E to be audited through a first page switching instruction, displaying the stored image C to be audited on the current audit page, and continuing to audit. Therefore, the auditor can check the previous audit result by self, modify the audit result in time, reduce the error and the omission of the audit and improve the audit quality.
Furthermore, according to the next first page switching instruction, the pre-loaded image D to be audited can be displayed on the current audit page for auditors to audit, and a new image to be audited of the next audit page is continuously pre-loaded, so that the audit fluency is maintained.
In this embodiment, steps S650 to S660 may be executed before steps S630 to S640, and the execution sequence between the two steps is not limited.
It should be noted that, portions not described in detail in this embodiment may refer to the foregoing embodiments, and are not described herein again.
According to the image auditing processing method provided by the embodiment, the size of the images to be audited can be adjusted in a personalized manner on the basis of full-screen display by automatically calculating the display quantity of the images to be audited which can be accommodated by the current auditing page, the images to be audited of the same classification can be arranged together through characteristic identification and classification, the rapid auditing of auditors is facilitated, the interval between the images to be audited is distributed by acquiring the variable blank area of the current auditing page, the display effect can be further optimized on the basis of full-screen display and similar image gathering and arrangement, and the auditing vision is improved. And by loading the image to be audited of the next audit page in advance, the full-screen image to be audited which is well arranged according to the classification can be directly obtained, the influence of external factors such as system pressure and network instability on the audit process is effectively relieved, the audit smoothness is improved, and repeated audit can be avoided by locking the image to be audited. In addition, the submission of the audit result can be delayed, so that auditors can check the audit result in a self-defined manner, mistakes and omissions are reduced, and the audit quality is improved. Compared with the prior art, the method and the device have the advantages that system pressure can be relieved, influences of factors such as network instability on auditing efficiency are avoided, auditing fluency is improved, the images to be audited in the same classification can be arranged together, the current auditing page is fully paved according to the user-defined display size, full-screen display is achieved, auditing vision is improved, and auditing efficiency is greatly improved.
It should be understood that, although the steps in the flow charts of fig. 3, 4 and 6 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 3, 4, and 6 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.
Referring to fig. 9, fig. 9 is a block diagram illustrating an image review processing apparatus 900 according to an embodiment of the present application. As will be explained below with respect to the block diagram of modules shown in fig. 9, the image review processing apparatus 900 includes: an obtaining module 910, a calculating module 920, a classifying module 930, and an arranging module 940, wherein:
the obtaining module 910 is configured to obtain a display size of an image to be checked and a container size of a current checking page.
And a calculating module 920, configured to calculate the number of displayed images to be checked that can be accommodated by the current checking page according to the display size and the container size.
The classifying module 930 is configured to perform feature recognition on the displayed number of images to be checked, and classify the displayed number of images to be checked according to a recognition result.
And an arranging module 940, configured to arrange the images to be checked belonging to the same category in the displayed number of images to be checked according to a preset rule.
Further, the classification module 930 comprises a feature recognition unit and an image classification unit, wherein:
and the feature identification unit is used for performing feature identification on the displayed number of images to be audited to obtain the features of each image to be audited and the area proportion of the features of each image to be audited to the corresponding image to be audited.
And the image classification unit is used for classifying the displayed images to be examined according to the characteristics and the area proportion.
Further, the image review processing apparatus 900 further includes: blank acquisition module, interval arrangement module, first switching module, first processing module, image locking module, second switching module, second processing module, preloading module, wherein:
and the blank acquiring module is used for acquiring the variable blank area of the current audit page.
And the interval arrangement module is used for distributing interval areas for the images to be checked of the display quantity according to the variable blank areas and arranging the images to be checked of the display quantity at intervals according to the interval areas.
And the first switching module is used for acquiring a first page switching instruction.
And the first processing module is used for submitting the previously stored image to be audited of the previous audit page, storing the image to be audited of the current audit page and displaying the pre-loaded image to be audited of the next audit page on the current audit page according to the first page switching instruction.
And the image locking module is used for locking the image to be audited of the current audit page and the image to be audited of the next audit page loaded in advance, so that the same locked image to be audited can not repeatedly appear in a plurality of audit pages.
And the second switching module is used for acquiring a second page switching instruction.
And the second processing module is used for storing the image to be audited of the current audit page according to the second page switching instruction and switching the image to be audited of the current audit page into the image to be audited of the last audit page.
And the pre-loading module is used for pre-loading the image to be audited of the next audit page.
The image auditing device provided by the embodiment of the application is used for realizing the corresponding image auditing method in the method embodiments, has the beneficial effects of the corresponding method embodiments, and is not repeated herein.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and modules may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, the coupling or direct coupling or communication connection between the modules shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or modules may be in an electrical, mechanical or other form.
In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
Referring to fig. 10, a block diagram of an electronic device according to an embodiment of the present disclosure is shown. The electronic device 1000 may be an electronic device capable of running an application, such as a smart phone, a tablet computer, a notebook computer, and a desktop computer. The electronic device 1000 in the present application may include one or more of the following components: a processor 1010, a memory 1020, and one or more applications, wherein the one or more applications may be stored in the memory 1020 and configured to be executed by the one or more processors 1010, the one or more programs configured to perform a method as described in the aforementioned method embodiments.
Processor 1010 may include one or more processing cores. The processor 1010 interfaces with various components throughout the electronic device 1000 using various interfaces and circuitry to perform various functions of the electronic device 1000 and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1020 and invoking data stored in the memory 1020. Alternatively, the processor 1010 may be implemented in hardware using at least one of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1010 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 1010, but may be implemented by a communication chip.
The Memory 1020 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 1020 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 1020 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The data storage area may also store data created by the electronic device 1000 during use (e.g., phone book, audio-video data, chat log data), and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the present solution and does not constitute a limitation on the electronic devices to which the present solution applies, and that a particular electronic device may include more or less components than those shown, or combine certain components, or have a different arrangement of components.
Referring to fig. 11, a block diagram of a computer-readable storage medium according to an embodiment of the present disclosure is shown. The computer-readable storage medium 1100 stores therein program code that can be called by a processor to execute the methods described in the above-described method embodiments.
The computer-readable storage medium 1100 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable and programmable read only memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium 1100 includes a non-transitory computer-readable storage medium. The computer readable storage medium 1100 has storage space for program code 1110 for performing any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program code 1110 may be compressed, for example, in a suitable form.
In summary, according to the image review processing method and apparatus, the electronic device, and the storage medium provided in the embodiments of the present application, the display size of the image to be reviewed and the container size of the current review page are obtained, the display number of the images to be reviewed that can be accommodated by the current review page is calculated according to the display size and the container size, then feature recognition is performed on the images to be reviewed in the display number, the images to be reviewed in the display number are classified according to the recognition result, and finally the images to be reviewed belonging to the same classification in the images to be reviewed in the display number are arranged according to the preset rule. Therefore, the display quantity capable of being accommodated is calculated through the display size of the images to be audited and the container size of the current audit page, so that the current audit page can display a plurality of images to be audited and can be paved with pages, the quantity of auditors capable of auditing at one time is increased, the audit efficiency is improved, classification is performed through feature identification, the images to be audited in the same classification can be arranged adjacently, the audit vision is improved, and the audit smoothness and the audit efficiency of the auditors can be improved.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims (9)

1. An image review processing method, characterized by comprising:
acquiring the display size of an image to be audited and the container size of a current audit page;
calculating the display quantity of the images to be checked which can be contained in the current checking page according to the display size and the container size;
performing feature recognition on the displayed number of images to be audited, and classifying the displayed number of images to be audited according to recognition results;
arranging the images to be checked belonging to the same classification in the displayed number of images to be checked according to a preset rule;
acquiring a first page switching instruction;
and submitting the previously stored image to be audited of the last audit page according to the first page switching instruction, storing the image to be audited of the current audit page, and displaying the pre-loaded image to be audited of the next audit page on the current audit page.
2. The method according to claim 1, wherein the performing feature recognition on the displayed number of images to be reviewed and classifying the displayed number of images to be reviewed according to the recognition result includes:
performing feature identification on the displayed number of images to be audited to obtain the features of each image to be audited and the area proportion of the features of each image to be audited to the corresponding images to be audited;
and classifying the displayed images to be audited according to the characteristics and the area proportion.
3. The method according to claim 1, wherein after arranging the images to be reviewed belonging to the same category in the displayed number of images to be reviewed according to a preset rule, the method further comprises:
acquiring a variable blank area of the current audit page;
and distributing interval areas for the images to be checked of the display quantity according to the variable blank areas, and arranging the images to be checked of the display quantity at intervals according to the interval areas.
4. The method of claim 1, further comprising:
and locking the image to be audited of the current audit page and the image to be audited of the next audit page loaded in advance, so that the same locked image to be audited can not repeatedly appear in a plurality of audit pages.
5. The method of claim 1, further comprising:
acquiring a second page switching instruction;
and storing the image to be audited of the current audit page according to the second page switching instruction, and switching the image to be audited of the current audit page into the image to be audited of the last audit page.
6. The method of claim 1, wherein the pre-loaded image to be reviewed for the next review page is displayed before the current review page, the method further comprising:
and pre-loading the image to be checked of the next checking page.
7. An image review processing apparatus characterized by comprising:
the acquisition module is used for acquiring the display size of the image to be audited and the container size of the current audit page;
the calculation module is used for calculating the display quantity of the images to be checked which can be contained in the current checking page according to the display size and the container size;
the classification module is used for performing feature recognition on the displayed number of images to be audited and classifying the displayed number of images to be audited according to a recognition result;
the arrangement module is used for arranging the images to be checked belonging to the same classification in the displayed number of images to be checked according to a preset rule;
the first switching module is used for acquiring a first page switching instruction;
and the first processing module is used for submitting the previously stored image to be audited of the previous audit page, storing the image to be audited of the current audit page and displaying the pre-loaded image to be audited of the next audit page on the current audit page according to the first page switching instruction.
8. An electronic device, comprising:
a memory;
one or more processors coupled with the memory;
one or more programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-6.
9. A computer-readable storage medium, having stored thereon program code that can be invoked by a processor to perform the method according to any one of claims 1 to 6.
CN201811626290.5A 2018-12-28 2018-12-28 Image auditing processing method and device, electronic equipment and storage medium Active CN109829069B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811626290.5A CN109829069B (en) 2018-12-28 2018-12-28 Image auditing processing method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811626290.5A CN109829069B (en) 2018-12-28 2018-12-28 Image auditing processing method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN109829069A CN109829069A (en) 2019-05-31
CN109829069B true CN109829069B (en) 2021-03-12

Family

ID=66861359

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811626290.5A Active CN109829069B (en) 2018-12-28 2018-12-28 Image auditing processing method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN109829069B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110456955B (en) * 2019-08-01 2022-03-29 腾讯科技(深圳)有限公司 Exposed clothing detection method, device, system, equipment and storage medium
CN112435035A (en) * 2019-08-09 2021-03-02 阿里巴巴集团控股有限公司 Data auditing method, device and equipment
CN111178309B (en) * 2019-12-31 2023-03-28 蚂蚁财富(上海)金融信息服务有限公司 Service processing method and device
CN111325265B (en) * 2020-02-17 2023-09-01 中国银联股份有限公司 Detection method and device for tampered image
CN111460346A (en) * 2020-03-30 2020-07-28 网易(杭州)网络有限公司 Content auditing method and device, electronic equipment and storage medium
CN113537261A (en) * 2020-04-20 2021-10-22 华为技术有限公司 Image data processing method and related equipment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101281021A (en) * 2008-05-14 2008-10-08 天恒威科技(北京)有限公司 Wood automatic monitoring method and system
CN108009273A (en) * 2017-12-19 2018-05-08 北京小米移动软件有限公司 Method for displaying image, device and computer-readable recording medium

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7466875B1 (en) * 2004-03-01 2008-12-16 Amazon Technologies, Inc. Method and system for determining the legibility of text in an image
CN101714250A (en) * 2008-10-06 2010-05-26 北京福爱基业科技有限公司 Method for combining, arranging and displaying a plurality of pictures
CN103544253B (en) * 2013-10-15 2017-12-12 Tcl集团股份有限公司 A kind of realization method and system that picture is shown in a manner of waterfall stream
CN108734184B (en) * 2017-04-17 2022-06-07 苏宁易购集团股份有限公司 Method and device for analyzing sensitive image

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101281021A (en) * 2008-05-14 2008-10-08 天恒威科技(北京)有限公司 Wood automatic monitoring method and system
CN108009273A (en) * 2017-12-19 2018-05-08 北京小米移动软件有限公司 Method for displaying image, device and computer-readable recording medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于违禁图库的敏感图片识别系统的设计与实现;韩中海;《中国优秀硕士学位论文全文数据库 信息科技辑》;20120513;全文 *

Also Published As

Publication number Publication date
CN109829069A (en) 2019-05-31

Similar Documents

Publication Publication Date Title
CN109829069B (en) Image auditing processing method and device, electronic equipment and storage medium
CN109803152B (en) Violation auditing method and device, electronic equipment and storage medium
US20190205629A1 (en) Behavior predicton method, behavior predicton system, and non-transitory recording medium
CN109509010B (en) Multimedia information processing method, terminal and storage medium
CN111309213A (en) Comment display method and device, electronic equipment and storage medium
CN112416346B (en) Interface color scheme generation method, device, equipment and storage medium
CN109829379B (en) Information processing method, information processing apparatus, server, and storage medium
CN109558384B (en) Log classification method, device, electronic equipment and storage medium
CN113051317B (en) Data mining model updating method, system, computer equipment and readable medium
CN114095749A (en) Recommendation and live interface display method, computer storage medium and program product
CN107038224B (en) Data processing method and data processing device
US10936799B2 (en) Distributed dynamic display of content annotations
CN113111197A (en) Multimedia content recommendation method, device, equipment and storage medium
CN113573128A (en) Audio processing method, device, terminal and storage medium
CN109949090B (en) Client recommendation method and device, electronic equipment and medium
CN114330340B (en) Evaluation information processing method, electronic device and readable storage medium
CN114491093B (en) Multimedia resource recommendation and object representation network generation method and device
CN112333554B (en) Multimedia data processing method and device, electronic equipment and storage medium
CN113515336B (en) Live room joining method, creation method, device, equipment and storage medium
CN109922359B (en) User processing method, device, equipment and storage medium
CN110309415B (en) News information generation method and device and readable storage medium of electronic equipment
US20140365967A1 (en) Method and device for data screening
CN110659419A (en) Method for determining target user and related device
CN112533032A (en) Video data processing method and device and storage medium
CN117573847B (en) Visualized answer generation method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20190531

Assignee: GUANGZHOU CUBESILI INFORMATION TECHNOLOGY Co.,Ltd.

Assignor: GUANGZHOU HUADUO NETWORK TECHNOLOGY Co.,Ltd.

Contract record no.: X2021440000032

Denomination of invention: Image processing method, device, electronic equipment and storage medium

License type: Common License

Record date: 20210125

EE01 Entry into force of recordation of patent licensing contract
GR01 Patent grant
GR01 Patent grant