CN113190705A - Anti-cheating method and device based on multi-picture uploading and electronic equipment - Google Patents
Anti-cheating method and device based on multi-picture uploading and electronic equipment Download PDFInfo
- Publication number
- CN113190705A CN113190705A CN202110383630.1A CN202110383630A CN113190705A CN 113190705 A CN113190705 A CN 113190705A CN 202110383630 A CN202110383630 A CN 202110383630A CN 113190705 A CN113190705 A CN 113190705A
- Authority
- CN
- China
- Prior art keywords
- pictures
- picture
- request
- cheating
- uploaded
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6227—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database where protection concerns the structure of data, e.g. records, types, queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Library & Information Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of network data security, and discloses a cheating prevention method and device based on multi-picture uploading and electronic equipment, wherein the cheating prevention method comprises the following steps: and responding to the picture search request, acquiring a plurality of uploaded pictures, comparing and judging the plurality of uploaded pictures, and judging as an abnormal operation request if the plurality of pictures are not similar or are the same. The anti-cheating method based on multi-picture uploading solves the problem of how to prevent cheating behaviors of abnormally uploaded picture capturing questions and analyzing data packets, ensures the data security of a photo search facilitator, prevents invalid cheating behaviors from occupying resources of a server, and ensures the use experience of normal users.
Description
Technical Field
The invention relates to the technical field of network data security, in particular to a cheating prevention method and device based on multi-picture uploading and electronic equipment.
Background
With the rapid development of network technology, more and more industries start to perform online services, and online education presents more and more service modes by means of network platforms.
OCR- -Optical Character Recognition technology, Optical Character Recognition, refers to the process of an electronic device (e.g., a scanner or a digital camera) examining a printed Character on paper, determining its shape by detecting dark and light patterns, and then translating the shape into computer text by Character Recognition methods; the method is characterized in that characters in a paper document are converted into an image file with a black-white dot matrix in an optical mode aiming at print characters, and the characters in the image are converted into a text format through recognition software for further editing and processing by word processing software. By means of the OCR technology, the on-line shooting and question searching service can shoot and upload and search related questions and analyze questions which cannot be done, help users to answer the questions and understand the questions, greatly facilitate learning of the users, and reduce time cost and learning cost of the users.
However, the problem of on-line photo search is that: how to avoid cheating actions of capturing questions and analyzing data packets by abnormal uploading of pictures? Common cheating behaviors are mostly photos which are copied in a large number of repeatability in a script mode and are automatically uploaded to a photographing and question searching server in batches to capture questions and analyze data packets, so that data loss of photographing and question searching service providers is caused, invalid cheating behaviors occupy resources of the server, and use of normal users can be influenced.
In view of the above, the present invention is particularly proposed.
Disclosure of Invention
The invention aims to: the problem of how to avoid cheating behaviors of capturing data packets by abnormally uploading pictures is solved.
In order to achieve the above purpose, the invention provides the following technical scheme:
a cheating prevention method based on multi-picture uploading comprises the following steps:
and responding to the picture search request, acquiring a plurality of uploaded pictures, comparing and judging the plurality of uploaded pictures, and judging as an abnormal operation request if the plurality of pictures are not similar or are the same.
As an embodiment of the present invention, the comparing and determining the plurality of uploaded pictures includes:
acquiring the uploading sequence of a plurality of pictures, and respectively calculating the similarity threshold values of two adjacent pictures through a similarity comparison algorithm; judging whether the multiple pictures are the same or not according to the similarity threshold values, and if so, judging that the multiple pictures are abnormal requests; if not, further judging whether all the similarity threshold values exceed a set range, if all the similarity threshold values exceed the set range, determining that all the pictures are not similar, and determining that the request is abnormal, if the similarity threshold values do not exceed the set range, determining that the request is normal;
preferably, before calculating the similarity threshold of two adjacent pictures respectively by using the similarity comparison algorithm, the method further includes: and respectively carrying out binarization and noise reduction on the plurality of pictures.
As an embodiment of the present invention, a cheating prevention method based on multi-picture uploading includes: in response to the current picture search request, directly acquiring one of the uploaded pictures in a set sequence as a main picture for a picture search matching process, and simultaneously acquiring a compressed file formed by packaging the other pictures in the sequence as an auxiliary picture for comparison and judgment for cheating prevention;
preferably, the first picture in the uploaded pictures is directly obtained as a main picture, and the rest pictures are sequentially packed into a compressed file as an auxiliary picture.
As an embodiment of the present invention, a cheating prevention method based on multi-picture uploading includes: when the abnormal request is judged, acquiring the associated user behavior of the current request ID, and feeding back a result, an error result or a normal result;
preferably, the associated user behavior of the current request ID includes whether a history annotation abnormal request tag exists, and/or a request magnitude of a current time node, and/or a request frequency in a certain history node, and the like.
As an embodiment of the present invention, a cheating prevention method based on multi-picture uploading includes: and when the request is judged to be normal, selecting one of the pictures as picture searching matching according to a set selection strategy.
As an embodiment of the present invention, before acquiring multiple uploaded pictures, the controlling of performing continuous multi-frame picture acquisition and uploading is further included.
As an embodiment of the present invention, the picture search instruction is a photograph question search instruction:
after receiving a photographing question searching instruction, controlling a photographing device to start photographing continuous n frames of pictures;
acquiring n-frame pictures obtained by photographing and the sequence of the pictures;
comparing and judging adjacent pictures;
and if the adjacent photos are different or are not similar, judging as an abnormal photographing and question searching request, otherwise, judging as a normal photographing and question searching request.
The invention also provides a cheating prevention device based on multi-picture uploading, which comprises the following steps:
the response module responds to the picture search request;
the acquisition module acquires a plurality of uploaded pictures;
and the comparison and judgment module is used for comparing and judging the plurality of uploaded pictures, and judging the operation request to be abnormal if the plurality of pictures are not similar or are the same.
The invention also provides an electronic device, which comprises a processor and a memory, wherein the memory is used for storing a computer executable program, and when the computer program is executed by the processor, the processor executes the anti-cheating method based on multi-picture uploading.
The invention also provides a computer readable medium, which stores a computer executable program, and when the computer executable program is executed, the anti-cheating method based on multi-picture uploading is realized.
Compared with the prior art, the invention has the beneficial effects that:
the anti-cheating method based on multi-picture uploading of the invention is characterized in that according to the essential difference of the behavior modes between the normal photo search user and the cheating user: the normal user carries out searching operation by a searching and photographing mode when facing the problem of needing searching, and the cheating user is a mode of automatically uploading scripts and cannot execute the operation behavior of searching and photographing, so that the problem photographing behavior of the user can be identified, and the normal request or the abnormal request can be judged.
Since the image needs to be collected by the camera in the searching photographing behavior, in order to identify the photographing behavior of the user, a plurality of pictures need to be collected continuously in the photographing process, and continuity exists among the plurality of pictures. Based on the behaviors, the anti-cheating method based on multi-picture uploading obtains a plurality of uploaded pictures, compares and judges the plurality of uploaded pictures, if the plurality of pictures are shot by a user, similarity and continuity are inevitable, and if the plurality of pictures are not similar or the plurality of pictures are the same, the anti-cheating method based on multi-picture uploading judges that the operation request is abnormal.
The anti-cheating method based on multi-picture uploading aims at the fact that the behavior of a cheating user is that a plurality of pictures are the same or are not similar (completely unrelated), so that the similarity and the same relation among the pictures can be judged by calculating the similarity threshold value of adjacent pictures. And aiming at the situation that the part of the multiple pictures is the same or the part of the multiple pictures is not similar, the abnormal request is not determined, so that the conditions are prevented from being limited too severely, the requirements on the use operation of the user are high, the error report rate is high, and the use experience of the user is influenced.
The anti-cheating method based on multi-picture uploading solves the problem of how to prevent cheating behaviors of abnormally uploaded picture capturing questions and analyzing data packets, ensures the data security of a photo search facilitator, prevents invalid cheating behaviors from occupying resources of a server, and ensures the use experience of normal users.
Description of the drawings:
FIG. 1 is a flow chart of an anti-cheating method based on multi-picture uploading of the present invention;
FIG. 2 is a flowchart illustrating comparison and judgment of multiple uploaded pictures in the anti-cheating method based on multi-picture uploading according to the present invention;
FIG. 3 is a flowchart illustrating a feedback process when an abnormal request is determined in the anti-cheating method based on multi-picture uploading according to the present invention;
FIG. 4 is a flow chart of the cheating prevention method based on multi-picture uploading, which is applicable to a scene of photographing and searching questions.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments.
Thus, the following detailed description of the embodiments of the invention is not intended to limit the scope of the invention as claimed, but is merely representative of some embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments of the present invention and the features and technical solutions thereof may be combined with each other without conflict.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that the terms "upper", "lower", and the like refer to orientations or positional relationships based on those shown in the drawings, or orientations or positional relationships that are conventionally arranged when the products of the present invention are used, or orientations or positional relationships that are conventionally understood by those skilled in the art, and such terms are used for convenience of description and simplification of the description, and do not refer to or imply that the devices or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, the anti-cheating method based on multi-picture uploading provided by this embodiment includes:
and responding to the picture search request, acquiring a plurality of uploaded pictures, comparing and judging the plurality of uploaded pictures, and judging as an abnormal operation request if the plurality of pictures are not similar or are the same.
The anti-cheating method based on multi-picture uploading of the embodiment is characterized in that according to the essential difference of behavior modes between a normal photo search user and a cheating user: the normal user performs the searching operation by the searching and photographing mode when facing the problem of searching, and the cheating user performs the operation behavior of searching and photographing by the automatic uploading of the script, so that the embodiment can identify the title photographing behavior of the user, thereby judging whether the request is a normal request or an abnormal request.
Since the image needs to be collected by the camera in the searching photographing behavior, in order to identify the photographing behavior of the user, a plurality of pictures need to be collected continuously in the photographing process, and continuity exists among the plurality of pictures. Based on the above behaviors, the anti-cheating method based on multi-picture uploading of the embodiment acquires multiple uploaded pictures, compares and judges the multiple uploaded pictures, if the multiple uploaded pictures are shot by a user, similarity and continuity inevitably exist, and if the multiple uploaded pictures are not similar or the multiple uploaded pictures are the same, the anti-cheating method based on multi-picture uploading is determined to be an abnormal operation request.
It should be noted that the normal shooting operation of the user needs to be obtained by shooting from the APP of the service provider, and the shooting process can be controlled by the APP to shoot a plurality of continuous photos, but the photo receiving port responds to the request instruction when receiving the photo, and both the shooting photo of the normal user and the abnormal photo of the cheating user are uploaded to the server through the same interface.
Therefore, the uploading and the photographing system are two parts which are separated in nature, the uploading is a server interface, all data in the server interface can be forged and tampered, and when the request is received, the request is not known to be transmitted through the photographing system. Therefore, the anti-cheating method based on multi-picture uploading of the embodiment compares and judges all pictures (possibly one or more) uploaded by the current picture search request, and the cheating behavior can be judged because the number of uploaded pictures is not consistent or the contents of the pictures are not consistent.
Further, referring to fig. 2, in the cheating prevention method based on multi-picture uploading of the present embodiment, the comparing and determining the multiple uploaded pictures includes:
acquiring the uploading sequence of a plurality of pictures, and respectively calculating the similarity threshold values of two adjacent pictures through a similarity comparison algorithm; judging whether the multiple pictures are the same or not according to the similarity threshold values, and if so, judging that the multiple pictures are abnormal requests; if not, further judging whether all the similarity threshold values exceed the set range, if all the similarity threshold values exceed the set range, determining that all the pictures are not similar, and determining that the request is abnormal, if the similarity threshold values do not exceed the set range, determining that the request is normal.
The anti-cheating method based on multi-picture uploading aims at the fact that the behavior of a cheating user is that a plurality of pictures are the same or the plurality of pictures are not similar (completely unrelated), and therefore the similarity and the same relation among the pictures can be judged by calculating the similarity threshold value of the adjacent pictures. And aiming at the situation that the part of the multiple pictures is the same or the part of the multiple pictures is not similar, the abnormal request is not determined, so that the conditions are prevented from being limited too severely, the requirements on the use operation of the user are high, the error report rate is high, and the use experience of the user is influenced.
The present embodiment performs picture similarity comparison on multiple images, including but not limited to: PSNR peak signal-to-noise ratio, perceptual hash algorithm, feature point calculation and the like.
Peak signal-to-noise ratio (PSNR), an objective criterion for evaluating images. It has local character, PSNR is an abbreviation for "Peak Signal Noise Ratio". peak's chinese meaning the vertex. And ratio means ratio or ratiometric. The whole means the peak signal of the arrival noise ratio, and the PSNR is generally an engineering project between the maximum signal and the background noise. Generally, after image compression, the output image is different from the original image to some extent. In order to measure the quality of processed images, we usually refer to the PSNR value to measure whether a certain processing procedure is satisfactory or not. It is the log of the mean square error between the original image and the processed image relative to (2^ n-1) ^2 (the square of the maximum value of the signal, n is the number of bits per sample), and its unit is dB. In this embodiment, the PSNR peak signal-to-noise ratio of two adjacent pictures is calculated, and the error between the two adjacent pictures can be determined according to the ratio, so as to determine the similarity between the two pictures.
The perceptual hash (hash) algorithm describes a class with a comparable hash function. The image features are used to generate unique (but not unique) fingerprints that are comparable.
Perceptual hashing is a different concept than cryptographic hashing (hash) functions like MD5 and SHA 1. The hash value of the cryptographic hash is random and the data is used to generate the hash action of the image random number seed, so that the same data will produce the same result and different data will produce different results. Comparing the hash values of two SHA1 tells us that we are actually two things, and if the hash values are different, the data are also different; if the hash values are the same, the data is similar. (the same hash value will produce different data because there may be a hash collision). In contrast, perceptual hashing is comparable — giving you a feeling of similarity between two data sets.
The perceptual hash algorithm functions to generate a "fingerprint" string for each picture, and then compare fingerprints of different pictures. The closer the results, the more similar the picture is.
The processing procedure of the perceptual hash (hash) algorithm:
and (3) reducing the size: the image is reduced to a size of 8 x 8 for a total of 64 pixels. The step has the effects of removing the details of the image, only retaining the basic information of structure/brightness and the like, and abandoning the image difference caused by different sizes/proportions;
simplifying the color: converting the reduced image into 64-level gray, namely that all pixel points have 64 colors in total;
calculating the average value: calculating the gray level average value of all 64 pixels;
comparing the gray levels of the pixels: comparing the gray scale of each pixel with the average value, and recording the average value greater than or equal to 1 and the average value smaller than 0;
calculating a hash value: the comparison results from the previous step are combined to form a 64-bit integer, which is the fingerprint of the image.
The order of the combination is not important as long as it is guaranteed that all images take the same order; after the fingerprint is obtained, different images can be compared to see how many of the 64 bits are different. In theory, this is equivalent to the "Hamming distance" (in the information theory, the Hamming distance between two equal-length character strings is the number of different characters at the corresponding positions of the two character strings). If the number of the different data bits does not exceed 5, the two images are very similar; if greater than 10, this indicates that these are two different images.
Calculating characteristic points: the feature2dmodule of OpenCV provides implementation from detection of Local image features (Local image features), extraction of feature vectors (feature vectors), to feature matching. The local image features include several common local image feature detection and description operators, such as FAST, SURF, SIFT, and ORB. For matching between high-dimensional feature vectors, OpenCV has two main ways:
1) BruteForce exhaustion;
2) the FLANN approximate K-nearest neighbor algorithm (an algorithm including various high-dimensional feature vector matching, such as a random forest, etc.).
Preferably, before calculating the similarity threshold of two adjacent pictures respectively by using the similarity comparison algorithm, the method further includes: and respectively carrying out binarization and noise reduction on the plurality of pictures. Therefore, the speed of calculation processing can be improved, and the time for carrying out picture similarity contrast on a plurality of images can be shortened.
The strategy of the anti-cheating method based on multi-picture uploading in the embodiment for acquiring the multiple pictures comprises the following steps: and in response to the current picture search request, the server directly acquires one of the uploaded pictures in a set sequence as a main picture for a picture search matching process, and simultaneously acquires a compressed file formed by packaging other pictures in sequence as an auxiliary picture for comparison and judgment for cheating prevention. The main graph of this embodiment is used for OCR discernment and search matching service, and the auxiliary graph is used for the action of practising fraud and judges, and after uploading to the server like this, OCR discernment and search matching service can be synchronous with the comparison judgement of preventing practising fraud, judge when normal operation at preventing practising fraud, and the search result is in time fed back, reduces response time, promotes user and uses experience.
Preferably, the server of the embodiment directly obtains a first picture of the uploaded pictures as a main picture, and the rest pictures are sequentially packaged into a compressed file as an auxiliary picture. Thus, the server can acquire the first picture more easily, and the sequence of the rest pictures is not influenced.
In addition, when the number of the pictures acquired by the server is not multiple, the server does not respond, feeds back information which does not meet the requirements of the user operation, and gives an operation guidance suggestion. Specifically, the determination may be made by determining whether or not there is a sub-map, and if there is no sub-map, the operation is determined to be an operation error and is not executed.
Referring to fig. 3, in the cheating prevention method based on multi-picture uploading in this embodiment, when it is determined that the request is an abnormal request, the associated user behavior of the current request ID is acquired, and a feedback is made that no result is returned, an error result is returned, or a normal result is returned.
Preferably, the associated user behavior of the current request ID includes whether a history annotation abnormal request tag exists, and/or a request magnitude of a current time node, and/or a request frequency in a certain history node, and the like.
And when the request ID has a history labeling abnormal request label and exceeds a certain number of times, the cheating user is identified, and/or when the request magnitude of the current time node exceeds a certain value, the cheating user is identified, and/or when the request frequency in a certain history node exceeds a certain value, the cheating user is identified.
The embodiment judges whether cheating is caused by combining the current abnormal request condition with the associated user behavior, so that the condition that the abnormal request caused by misoperation of a normal user is determined as cheating is avoided.
In the cheating prevention method based on multi-picture uploading, when the request is judged to be normal, one of the multiple pictures is selected to be used as a search question matching process according to a set selection strategy.
Preferably, the selection strategy is to select a main graph to be used as a problem searching and matching process. The selection strategy of this embodiment is to select the nth picture as the matching procedure of the search question, and if the nth picture does not exist, the operation is considered as an error and is not executed.
As an implementation manner of this embodiment, in this embodiment, the cheating prevention method based on multi-picture uploading further includes controlling an image acquisition device to acquire and upload consecutive multi-frame pictures before acquiring the multiple uploaded pictures.
According to the image acquisition device, the image acquisition is performed through the program, so that a normal user can acquire a plurality of images meeting requirements more easily, the operation requirements of the user are greatly reduced, and the execution of normal request behaviors of the user is ensured.
The cheating prevention method based on multi-picture uploading solves the problem of how to prevent cheating behaviors of abnormally uploaded picture capturing questions and analyzing data packets, ensures data security of a photo search service provider, prevents invalid cheating behaviors from occupying resources of a server, and ensures use experience of normal users.
Specifically, the cheating prevention method based on multi-picture uploading is implemented for an application scene of a photographing and searching question, and is characterized in that the picture searching instruction is a photographing and searching question instruction:
after receiving a photographing question searching instruction, controlling a photographing device to start photographing continuous n frames of pictures;
acquiring n-frame pictures obtained by photographing and the sequence of the pictures;
uploading the picture to a server, and comparing and judging adjacent pictures;
and if the adjacent photos are different or are not similar, judging as an abnormal photographing and question searching request, otherwise, judging as a normal photographing and question searching request.
Because the shooting behavior of the search question needs to acquire images through the camera, in order to identify the shooting behavior of the user, a plurality of pictures need to be continuously acquired in the shooting process, and the plurality of pictures have continuity. Based on the above behaviors, the anti-cheating method based on multi-picture uploading of the embodiment acquires multiple uploaded pictures, compares and judges the multiple uploaded pictures, if the multiple uploaded pictures are shot by a user, similarity and continuity inevitably exist, and if the multiple uploaded pictures are not similar or the multiple uploaded pictures are the same, the anti-cheating method based on multi-picture uploading is determined to be an abnormal operation request.
Further, in order to facilitate the user to perform the task shooting operation, the client of the embodiment only allows the user to take pictures to search the task, but cannot upload the local pictures, and calls the shooting device to shoot continuous n frames of pictures according to the set shooting mode by the client, so that the continuous n frames of pictures certainly belong to the normal shooting task searching request, and the user can more quickly pass the judgment of cheating prevention. In addition, the main picture is only required to be locally stored for the shot continuous n-frame pictures, and other pictures are not reserved after being uploaded to the server.
As another implementation manner of this embodiment, since the searching and photographing behavior needs to acquire an image through a camera, the anti-cheating method of this embodiment may encrypt information during a normal operation of photographing a picture, and a cheating operation is directly and automatically uploaded without a photographing process, so that encrypted information may not be stored in the picture. Based on the above behaviors, the anti-cheating method of the embodiment determines that the acquired encrypted information in the picture and the picture taken in normal operation definitely contain the encrypted information as a normal question searching request, and the picture automatically uploaded by the script can be identified as an abnormal operation behavior because the picture does not contain the encrypted information or the encrypted information is not matched.
It should be noted that the normal shooting question answering operation of the user needs to be obtained by shooting from the APP of the service provider, the shooting question process can be controlled through the APP to encrypt the shot photo, information encryption is completed while the user shoots, and the normal shooting uploading operation of the user cannot be influenced.
Further, in the embodiment, for the shot subject picture, the shooting time corresponding to the shot picture and the shooting user ID can be written into the picture according to the preset rule by adopting a digital watermark mode, and the writing of information can be completed while shooting, so that the method has timeliness and uniqueness.
In the anti-cheating method of this embodiment, after the picture is decrypted according to the preset decryption rule, if the encrypted information is not obtained, it is determined that the picture is subjected to the cheating operation. Because the cheating operation of automatic uploading of the script does not pass through the shooting process, the picture does not necessarily contain encryption information, abnormal operation screening can be carried out more quickly, and the operation is prevented from entering a subsequent flow and occupying system resources.
This embodiment provides an anti-cheating device based on many pictures are uploaded simultaneously, includes:
the response module responds to the picture search request;
the acquisition module acquires a plurality of uploaded pictures;
and the comparison and judgment module is used for comparing and judging the plurality of uploaded pictures, and judging the operation request to be abnormal if the plurality of pictures are not similar or are the same.
The anti-cheating device based on multi-picture uploading of the embodiment is characterized in that according to the essential difference of the behavior modes between the normal photographing search user and the cheating user: the normal user performs the searching operation by the searching and photographing mode when facing the problem of searching, and the cheating user performs the operation behavior of searching and photographing by the automatic uploading of the script, so that the embodiment can identify the title photographing behavior of the user, thereby judging whether the request is a normal request or an abnormal request.
Since the image needs to be collected by the camera in the searching photographing behavior, in order to identify the photographing behavior of the user, a plurality of pictures need to be collected continuously in the photographing process, and continuity exists among the plurality of pictures. Based on the above behaviors, the anti-cheating device based on multi-picture uploading of the embodiment includes that the acquisition module acquires a plurality of uploaded pictures, the comparison and judgment module compares and judges the plurality of uploaded pictures, if the plurality of pictures are taken by a user, similarity and continuity inevitably exist, and if the plurality of pictures are not similar or the plurality of pictures are the same, the anti-cheating device is judged to be an abnormal operation request.
It should be noted that the normal shooting operation of the user needs to be obtained by shooting from the APP of the service provider, and the shooting process can be controlled by the APP to shoot a plurality of continuous photos, but the photo receiving port responds to the request instruction when receiving the photo, and both the shooting photo of the normal user and the abnormal photo of the cheating user are uploaded to the server through the same interface.
Therefore, the uploading and the photographing system are two parts which are separated in nature, the uploading is a server interface, all data in the server interface can be forged and tampered, and when the request is received, the request is not known to be transmitted through the photographing system. Therefore, the anti-cheating device based on multi-picture uploading of the embodiment compares and judges all pictures (possibly one or more) uploaded by the current picture search request, and the cheating behavior can be judged because the number of uploaded pictures is not consistent or the picture content is not consistent.
The comparison judging module of the embodiment acquires the uploading sequence of a plurality of pictures, and respectively calculates the similarity threshold values of two adjacent pictures through a similarity comparison algorithm; judging whether the multiple pictures are the same or not according to the similarity threshold values, and if so, judging that the multiple pictures are abnormal requests; if not, further judging whether all the similarity threshold values exceed the set range, if all the similarity threshold values exceed the set range, determining that all the pictures are not similar, and determining that the request is abnormal, if the similarity threshold values do not exceed the set range, determining that the request is normal.
The anti-cheating device based on multi-picture uploading of the embodiment aims at the fact that the behavior of a cheating user is that a plurality of pictures are the same or that the plurality of pictures are not similar (completely unrelated), so that the anti-cheating device based on multi-picture uploading of the embodiment can judge the similarity and the same relation between the pictures by calculating the similarity threshold value of the adjacent pictures. And aiming at the situation that the part of the multiple pictures is the same or the part of the multiple pictures is not similar, the abnormal request is not determined, so that the conditions are prevented from being limited too severely, the requirements on the use operation of the user are high, the error report rate is high, and the use experience of the user is influenced.
The anti-cheating device based on multi-picture uploading further comprises an image processing module, and before the comparison and judgment module respectively calculates the similarity threshold values of two adjacent pictures through a similarity comparison algorithm, the image processing module respectively carries out binarization and noise reduction on the multiple pictures.
The binarization processing of the image is to set the gray value of a point on the image to be 0 or 255, that is, to make the whole image show obvious black and white effect. That is, a gray scale image with 256 brightness levels is selected by a proper threshold value to obtain a binary image which can still reflect the whole and local features of the image. In digital image processing, binary images are very important, and particularly in practical image processing, many systems are configured by binary image processing, and in order to perform processing and analysis of binary images, a grayscale image is first binarized to obtain a binarized image, which is advantageous in that when an image is further processed, the collective property of the image is only related to the positions of points with pixel values of 0 or 255, and the multi-level values of the pixels are not related, so that the processing is simplified, and the processing and compression amount of data is small.
The english name of Image Denoising is Image Denoising, a term of art in Image processing. Refers to the process of reducing noise in a digital image, sometimes referred to as image denoising.
The anti-cheating device based on multi-picture uploading further comprises an acquisition module, wherein the acquisition module responds to a current picture searching request, directly acquires one of the uploaded pictures in a set sequence as a main picture for a picture searching and matching process, and simultaneously acquires a compressed file formed by packaging other pictures in sequence as an auxiliary picture for comparison and judgment of cheating prevention. The acquisition module of this embodiment anti-cheating device acquires the main picture and is used for OCR discernment and search matching service, and the auxiliary graph is used for the action of practising fraud and judges, and after uploading to the server like this, OCR discernment and search matching service can be synchronous with the comparison judgement of preventing practising fraud and go on, judge when normal operation at preventing practising fraud, and the search result is in time fed back, reduces response time, promotes user and uses experience.
Preferably, the acquisition module directly acquires a first picture in the uploaded pictures as a main picture, and the rest pictures are packed into a compressed file in sequence as an auxiliary picture.
In addition, when the number of the pictures acquired by the acquisition module is not multiple, no response is made, information which does not meet the requirements of the user operation is fed back, and an operation guide suggestion is given. Specifically, the determination may be made by determining whether or not there is a sub-map, and if there is no sub-map, the operation is determined to be an operation error and is not executed.
The anti-cheating device based on multi-picture uploading further comprises a feedback module, and when the request is judged to be abnormal, the feedback module acquires the associated user behavior of the current request ID and feeds back a result, an error result or a normal result.
Preferably, the associated user behavior of the current request ID includes whether a history annotation abnormal request tag exists, and/or a request magnitude of a current time node, and/or a request frequency in a certain history node, and the like.
And when the request ID has a history labeling abnormal request label and exceeds a certain number of times, the cheating user is identified, and/or when the request magnitude of the current time node exceeds a certain value, the cheating user is identified, and/or when the request frequency in a certain history node exceeds a certain value, the cheating user is identified.
The anti-cheating device based on multi-picture uploading judges whether cheating is caused by combining the current abnormal request condition and the associated user behavior, and avoids the abnormal request caused by the misoperation of a normal user from being determined as the cheating condition.
The anti-cheating device based on multi-picture uploading further comprises a search matching module, and when the anti-cheating device is judged to be a normal request, the search matching module selects one of the multiple pictures to be used as picture search matching according to a set selection strategy.
The anti-cheating device based on multi-picture uploading further comprises an image acquisition module, and the image acquisition module is controlled to acquire continuous multi-frame pictures and upload the pictures before acquiring multiple uploaded pictures. The anti-cheating device of the embodiment controls the image acquisition device to acquire the pictures through the program, so that a normal user can acquire a plurality of pictures meeting the requirements more easily, the operation requirements of the user are greatly reduced, and the execution of normal request behaviors of the user is ensured.
The cheating prevention device based on multi-picture uploading solves the problem of how to prevent cheating behaviors of abnormally uploading pictures to pick up questions and analyze data packets, ensures data security of a photo search service provider, prevents invalid cheating behaviors from occupying resources of a server, and ensures use experience of normal users.
The anti-cheating device of the embodiment can be used for a photographing question searching service, and the picture searching instruction is a photographing question searching instruction:
after receiving a photographing question searching instruction, controlling a photographing device to start photographing continuous n frames of pictures;
acquiring n-frame pictures obtained by photographing and the sequence of the pictures;
uploading the picture to a server, and comparing and judging adjacent pictures;
and if the adjacent photos are different or are not similar, judging as an abnormal photographing and question searching request, otherwise, judging as a normal photographing and question searching request.
The specific process is shown in fig. 4, where the example process first determines whether a plurality of pictures are all similar, if not, the request is an abnormal request, if there are similar pictures, it needs to further determine whether all the pictures are the same picture, if yes, the request is an abnormal request, and if not (if there are some same pictures, it is also determined as no), the request is a normal request.
The embodiment also provides an electronic device, which includes a processor and a memory, where the memory is used to store a computer executable program, and when the computer program is executed by the processor, the processor executes the anti-cheating method based on multi-picture upload.
The embodiment also provides a computer readable medium, in which a computer executable program is stored, and when the computer executable program is executed, the anti-cheating method based on multi-picture uploading is implemented.
From the above description of the embodiments, those skilled in the art will readily appreciate that the present invention can be implemented by hardware capable of executing a specific computer program, such as the system of the present invention, and electronic processing units, servers, clients, mobile phones, control units, processors, etc. included in the system. The invention may also be implemented by computer software for performing the method of the invention, e.g. control software executed by a microprocessor, an electronic control unit, a client, a server, etc. It should be noted that the computer software for executing the method of the present invention is not limited to be executed by one or a specific hardware entity, and can also be realized in a distributed manner by non-specific hardware. For computer software, the software product may be stored in a computer readable storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or may be distributed over a network, as long as it enables the electronic device to perform the method according to the present invention.
The above embodiments are only used for illustrating the invention and not for limiting the technical solutions described in the invention, and although the present invention has been described in detail in the present specification with reference to the above embodiments, the present invention is not limited to the above embodiments, and therefore, any modification or equivalent replacement of the present invention is made; all such modifications and variations are intended to be included herein within the scope of this disclosure and the appended claims.
Claims (10)
1. An anti-cheating method based on multi-picture uploading is characterized by comprising the following steps:
responding to the picture search request, and acquiring a plurality of uploaded pictures;
and comparing and judging the multiple uploaded pictures, and if the multiple uploaded pictures are not similar or are the same, judging that the operation request is abnormal.
2. The anti-cheating method based on multi-picture uploading as claimed in claim 1, wherein the comparing and determining of the plurality of uploaded pictures comprises:
acquiring the uploading sequence of a plurality of pictures, and respectively calculating the similarity threshold values of two adjacent pictures through a similarity comparison algorithm;
judging whether the multiple pictures are the same according to the similarity threshold values,
if yes, judging the request to be abnormal;
if not, further judging whether all the similarity threshold values exceed the set range;
if the pictures exceed the set range, the pictures are not similar, and the abnormal request is judged;
if the similarity threshold value which does not exceed the set range exists, judging the request to be a normal request;
preferably, before calculating the similarity threshold of two adjacent pictures respectively by using the similarity comparison algorithm, the method further includes: and respectively carrying out binarization and noise reduction on the plurality of pictures.
3. The anti-cheating method based on multi-picture uploading as claimed in claim 1, wherein in response to a current picture search request, one of the uploaded pictures in a set order is directly obtained as a main picture for a picture search matching process, and a compressed file formed by packaging the rest of pictures in sequence is obtained as an auxiliary picture for comparison and judgment of cheating prevention;
preferably, the first picture in the uploaded pictures is directly obtained as a main picture, and the rest pictures are sequentially packed into a compressed file as an auxiliary picture.
4. The anti-cheating method based on multi-picture uploading as claimed in any one of claims 1-3, wherein when an abnormal request is determined, the associated user behavior of the current request ID is obtained, and a feedback of no result return, an error result return or a normal result return is made;
preferably, the associated user behavior of the current request ID includes whether a history annotation abnormal request tag exists, and/or a request magnitude of a current time node, and/or a request frequency in a certain history node.
5. The cheat-prevention method based on multi-picture uploading as claimed in any one of claims 1-2, wherein when a normal request is determined, one of the multiple pictures is selected according to a set selection policy for picture search matching.
6. The anti-cheating method based on multi-picture uploading as claimed in claim 1, wherein before obtaining the plurality of uploaded pictures, further comprising performing continuous multi-frame picture collection and uploading.
7. The anti-cheating method based on multi-picture uploading as claimed in any one of claims 1 to 6, wherein the picture search instruction is a photo title search instruction:
after receiving a photographing question searching instruction, controlling a photographing device to start photographing continuous n frames of pictures;
acquiring n-frame pictures obtained by photographing and the sequence of the pictures;
comparing and judging adjacent pictures;
and if the adjacent photos are different or are not similar, judging as an abnormal photographing and question searching request, otherwise, judging as a normal photographing and question searching request.
8. The utility model provides an anti-cheating device based on many pictures are uploaded which characterized in that includes:
the response module responds to the picture search request;
the acquisition module acquires a plurality of uploaded pictures;
and the comparison and judgment module is used for comparing and judging the plurality of uploaded pictures, and judging the operation request to be abnormal if the plurality of pictures are not similar or are the same.
9. An electronic device comprising a processor and a memory, the memory for storing a computer-executable program, characterized in that:
when the computer program is executed by the processor, the processor performs the anti-cheating method based on multi-picture upload according to any one of claims 1-7.
10. A computer-readable medium storing a computer-executable program, wherein the computer-executable program, when executed, implements the anti-cheating method based on multi-picture upload according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383630.1A CN113190705A (en) | 2021-04-09 | 2021-04-09 | Anti-cheating method and device based on multi-picture uploading and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383630.1A CN113190705A (en) | 2021-04-09 | 2021-04-09 | Anti-cheating method and device based on multi-picture uploading and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113190705A true CN113190705A (en) | 2021-07-30 |
Family
ID=76975432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110383630.1A Pending CN113190705A (en) | 2021-04-09 | 2021-04-09 | Anti-cheating method and device based on multi-picture uploading and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113190705A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070099683A1 (en) * | 2005-10-29 | 2007-05-03 | Similarity, Inc., A Delaware Corporation | Interactive pictures |
| CN106021542A (en) * | 2016-05-26 | 2016-10-12 | 珠海市魅族科技有限公司 | Image display method and image server, terminal |
| CN111865987A (en) * | 2020-07-21 | 2020-10-30 | 百度在线网络技术（北京）有限公司 | Cheating flow processing method, device, equipment and storage medium |
| CN112184702A (en) * | 2020-10-27 | 2021-01-05 | 携程计算机技术（上海）有限公司 | Picture cheating detection method and device, electronic equipment and storage medium |
| CN112579907A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Abnormal task detection method and device, electronic equipment and storage medium |
-
2021
- 2021-04-09 CN CN202110383630.1A patent/CN113190705A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070099683A1 (en) * | 2005-10-29 | 2007-05-03 | Similarity, Inc., A Delaware Corporation | Interactive pictures |
| CN106021542A (en) * | 2016-05-26 | 2016-10-12 | 珠海市魅族科技有限公司 | Image display method and image server, terminal |
| CN111865987A (en) * | 2020-07-21 | 2020-10-30 | 百度在线网络技术（北京）有限公司 | Cheating flow processing method, device, equipment and storage medium |
| CN112184702A (en) * | 2020-10-27 | 2021-01-05 | 携程计算机技术（上海）有限公司 | Picture cheating detection method and device, electronic equipment and storage medium |
| CN112579907A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Abnormal task detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11263440B1 (en) | Systems and methods for passive-subject liveness verification in digital media | |
| CN109756746B (en) | Video auditing method, device, server and storage medium | |
| US9596378B2 (en) | Method and apparatus for authenticating printed documents that contains both dark and halftone text | |
| US11003957B2 (en) | Method and apparatus for certificate identification | |
| US11070700B2 (en) | Method of extracting watermark data in an image with reference to a noise-based image located in the image based on a comparison process performed in the frequency domain | |
| US8842889B1 (en) | System and method for automatic face recognition | |
| CN110232369A (en) | A kind of face identification method and electronic equipment | |
| MXPA02008296A (en) | Improved method for image binarization. | |
| Huang et al. | Camera model identification with unknown models | |
| CN107111744A (en) | Impersonation attack is detected for the certification based on video | |
| JP2023521118A (en) | Liveness detection using devices containing illumination sources | |
| US20130314755A1 (en) | Image capture device for extracting textual information | |
| US8768058B2 (en) | System for extracting text from a plurality of captured images of a document | |
| CN110210467B (en) | Formula positioning method of text image, image processing device and storage medium | |
| US20090251597A1 (en) | Content conversion device | |
| WO2013177240A1 (en) | Textual information extraction method using multiple images | |
| CN113190705A (en) | Anti-cheating method and device based on multi-picture uploading and electronic equipment | |
| CN114241493A (en) | Training method and training device for augmenting training data of document analysis model | |
| CN118449925A (en) | Picture processing method, device, terminal equipment and storage medium | |
| JP2006304062A5 (en) | ||
| CN109977720B (en) | Method and device for rapidly analyzing two-dimensional code image | |
| US10984219B2 (en) | Fingerprint processing with liveness detection | |
| CN113179358A (en) | Anti-cheating method and device for problem answering and electronic equipment | |
| WO2017219562A1 (en) | Method and apparatus for generating two-dimensional code | |
| CN116502660B (en) | Digital resource application method and system based on two-dimensional code |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230612 Address after: 6001, 6th Floor, No.1 Kaifeng Road, Shangdi Information Industry Base, Haidian District, Beijing, 100085 Applicant after: Beijing Baige Feichi Technology Co.,Ltd. Address before: 100085 4002, 4th floor, No.1 Kaifa Road, Shangdi Information Industry base, Haidian District, Beijing Applicant before: ZUOYEBANG EDUCATION TECHNOLOGY (BEIJING) CO.,LTD. |