CN111353488B - Method, device and equipment for identifying risks in code image - Google Patents
Method, device and equipment for identifying risks in code image Download PDFInfo
- Publication number
- CN111353488B CN111353488B CN202010116270.4A CN202010116270A CN111353488B CN 111353488 B CN111353488 B CN 111353488B CN 202010116270 A CN202010116270 A CN 202010116270A CN 111353488 B CN111353488 B CN 111353488B
- Authority
- CN
- China
- Prior art keywords
- image
- code
- information
- code image
- risk
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 81
- 108091029480 NONCODE Proteins 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 19
- 238000010191 image analysis Methods 0.000 claims description 10
- 230000006399 behavior Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 13
- 238000003860 storage Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 12
- 208000001613 Gambling Diseases 0.000 description 10
- 230000006872 improvement Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000010801 machine learning Methods 0.000 description 6
- 238000012015 optical character recognition Methods 0.000 description 5
- 235000013399 edible fruits Nutrition 0.000 description 3
- 239000002574 poison Substances 0.000 description 3
- 231100000614 poison Toxicity 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 241000406668 Loxodonta cyclotis Species 0.000 description 2
- 241000700605 Viruses Species 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004900 laundering Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 235000011888 snacks Nutrition 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
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)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the specification discloses a method, a device and equipment for identifying risks in a code image. The scheme comprises the following steps: acquiring an image to be identified containing a code image; determining a non-code area outside the code image in the image to be identified; extracting information of the code-free area; and identifying risks in the code image according to the information of the code-free area.
Description
Technical Field
The present disclosure relates to the field of computer software technologies, and in particular, to a method, an apparatus, and a device for identifying a risk in a code image.
Background
The popularization of devices such as smart phones brings convenience to the life of people. By using various applications on the smartphone, various services can be performed accordingly. Many applications or services involve the identification of code images.
Some malicious users, or even lawless persons, are beginning to gain illegal interest using code image based techniques. For example, by scanning certain code images, the device may jump to a web page containing information such as yellow gambling poison. As another example, some lawbreakers use code images to conduct fraudulent transactions.
Since the code image itself is not readable information such as characters, it is not easy for the user to determine whether there is a risk in the code image. Therefore, how to identify the risks in the code image becomes a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
The embodiment of the specification provides a method, a device and equipment for identifying risks in a code image, and is used for solving the technical problem that risks exist in the code image.
In order to solve the above technical problem, the embodiments of the present specification are implemented as follows:
an embodiment of the present specification provides a method for identifying a risk in a code image, including:
acquiring an image to be identified containing a code image;
determining a non-code area outside the code image in the image to be identified;
extracting information of the code-free area;
and identifying risks in the code image according to the information of the code-free area.
An apparatus for identifying a risk in a code image provided by an embodiment of the present specification includes:
the image acquisition module is used for acquiring an image to be identified containing a code image;
a code-free region determining module, configured to determine a code-free region in the image to be identified, the region being other than the code image;
the information extraction module is used for extracting the information of the code-free area;
and the risk identification module is used for identifying the risk in the code image according to the information of the code-free area.
An apparatus for identifying a risk in a code image provided by an embodiment of the present specification includes:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring an image to be identified containing a code image;
determining a non-code area outside the code image in the image to be identified;
extracting information of the code-free area;
and identifying risks in the code image according to the information of the code-free area. .
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects: by determining the risk in the code image by recognizing the code-free region other than the code image, it is possible to improve the security of the user by the dimension other than the code image in the case where the risk existing in the code image cannot be recognized only by the recognition code image.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
Fig. 1 is a schematic diagram of a system architecture involved in a practical application scenario according to the solution of the present disclosure;
fig. 2 is a flowchart illustrating a method for identifying risks in a code image according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of an image to be recognized according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an apparatus for identifying risks in a code image according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an apparatus for identifying risks in a code image according to an embodiment of the present disclosure.
Detailed Description
The embodiment of the specification provides a payment assisting method, a payment assisting device and equipment.
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.
In the embodiment of the description, the risk of identifying the code image by using the code-free area in the image to be identified enables a user to judge the risk of the code image when the user does not identify the code image, so that the risk caused by identifying the code image can be effectively reduced, and the safety of the user is improved.
Fig. 1 is a schematic diagram of a system architecture involved in a practical application scenario of the solution of the present specification. In the system architecture, three ends are mainly involved: a terminal 1 for providing images, a terminal 22 for receiving images, and a server 3. The terminal 1 provides the image to be read to the terminal 2, the terminal 2 may identify the image through a scanning device, such as a mobile phone, and the server 3 has a wind control management capability, and may be used to execute all or part of the steps of the method in the embodiments of the present specification. In practical application, the server 3 may identify whether risk information exists in the image before the terminal 2 receives the image, or may identify the risk information based on the operation of the terminal 2 on the image after the terminal 2 receives the image, for example, when the terminal 2 scans the two-dimensional code image provided by the terminal 1 through a certain payment application APP, the wind control platform in the APP application may identify whether risk exists in the two-dimensional code image, so as to prompt the user to operate cautiously, and improve the safety of the user.
The following describes the embodiments of the present specification in detail.
Fig. 2 is a schematic flowchart of a method for identifying a risk in a code image according to an embodiment of the present disclosure, and from a program perspective, an execution subject of the process may be a program installed on an application server or an application client, and the process may be automatically executed at a proper time. The flow in fig. 2 may include the following steps:
s210: and acquiring an image to be identified containing the code image.
The method in the embodiment of the specification can be applied to risk identification of images containing illegal or illegal information, for example, risk identification of images containing information such as fraud, yellow gambling poison, money laundering and the like can be carried out.
S220: and determining a non-code area outside the code image in the image to be identified.
Fig. 3 is a schematic diagram of an image to be recognized according to an embodiment of the present disclosure. As shown in fig. 3, in the embodiment of the present specification, the image to be recognized 31 may include a code image 311 and a code-free area 312, where the code image 311 is an image that can be recognized and interpreted to obtain corresponding information, and specifically may include a two-dimensional code, a barcode, and the like; the non-code region 312 is a region outside the code image, and may include a region located at the periphery of the code image, or may include a region embedded in the middle of the code image, and the specific position is not limited herein; the codeless area 312 may also contain text, images, and the like.
S230: and extracting the information of the code-free area.
In practical application, the codeless area usually contains some texts or images, the texts may or may not be related to the content represented by the code image, for example, a user scans a code through certain social software to add a friend, a two-dimensional code pointing to a link of the added friend may be present in the code-scanned image, a nickname or number of the friend may be present above or below the two-dimensional code, a head portrait image of the friend may be further provided in the middle of the two-dimensional code, wherein the nickname or number of the friend or the head portrait image are related to the content represented by the two-dimensional code; for another example, a fraudster sends an image containing a fraud transfer link to a user through social software, the image appears as an image with friends added, the codeless region can also contain content such as a nickname or a number or an avatar image, but the link of the code image is a transfer link, and the content contained in the codeless region of the image is irrelevant to the content represented by the code image. In the embodiments of the present disclosure, information such as characters and images in the codeless region may be extracted for risk identification, for example, information such as key words, sentences, and fonts in the codeless region may be extracted, and information such as image content and shape in the codeless region may also be extracted.
S240: and identifying risks in the code image according to the information of the code-free area.
In the embodiment of the present specification, information of the codeless region may be extracted, and further, risk identification may be performed on the code image according to the information of the codeless region, or risk identification may be performed by combining the information of the codeless region and link content corresponding to the code image.
In the embodiment of the present description, the risk in the code image is determined by identifying the non-code area outside the code image, and the security of the user can be improved by the dimension outside the code image when the risk in the code image cannot be identified only by the identification code image.
Based on the function of the code image, the code image can be classified into a transaction code and a non-transaction code, wherein the transaction code can display a payment interface after scanning the code, and the non-transaction code can open a URL (Uniform Resource Locator) link after scanning.
The code scanning mode may include: direct code scanning by a camera, long-press picture recognition of code images in pictures, reading of code images in pictures from an album and the like.
In this embodiment of the present description, when the codeless region includes text information, the extracting information of the codeless region may specifically include: and extracting the character information of the code-free area.
When the character information exists in the code-free area, the character information in the code-free area can be extracted for risk assessment. For example, the text information existing in the codeless region can be extracted by using OCR (Optical Character Recognition) image Recognition.
The identifying the risk in the code image according to the information of the code-free region may specifically include: comparing the character information with the words in the keyword lexicon to obtain a comparison result; the words in the keyword lexicon are high-risk words; and judging whether the code image has risks or not according to the comparison result.
In the embodiment of the present specification, the text information extracted from the codeless region may be compared with the keyword lexicon to determine whether the codeless region contains high-risk words, and further determine whether the code image has risk. The keyword lexicon may be a word lexicon generated by using a machine learning model, for example, some illegal words related to illegal or illegal behaviors may be included in the keyword lexicon, or the word lexicon may be generated according to an information training model fed back by a user, such as words related to illegal contents such as word brushing, yellow gambling poison, and the like. When the text information extracted from the code-free area contains certain illegal words, the code image may have risks, and the user can be reminded to pay attention to or shield the link address corresponding to the image to ensure the safety of the user.
In order to further improve the accuracy of identifying the text information in the code-free area, identifying the risk in the code image according to the information in the code-free area may specifically include:
converting the text information into text feature vectors;
inputting the text feature vector into a pre-generated text risk identification model for analysis to obtain a text analysis result;
and judging whether the code image has risks or not according to the text analysis result.
In the embodiment of the present specification, text information extracted from a codeless region may be converted into a text feature vector, the text feature vector is input into a pre-generated text risk recognition model for analysis, and whether a risk exists in the code image is determined according to an obtained text analysis result. The pre-generated text risk identification model can be a machine learning model, and through the self-learning function of the machine learning model, some phrases or short sentences similar to the semantics of the phrases or short sentences in the model sample can be identified, and some related sentences and the like can also be identified. For example, in some network gambling transactions, the image to be recognized received by the user contains a code image related to gambling, and the text information in the code-free area contains prompt information of words such as "please complete payment within 1 minute and 30 seconds" or "please pay according to the displayed amount, otherwise, the prompt information is not responsible for the words, because each word in the text information is legal independently, but the whole words are possibly prompt information frequently appearing in the gambling transactions.
In addition to recognizing words in the text information, in an embodiment of the present specification, a font corresponding to the text information may be recognized, and recognizing a risk in the code image according to the information of the codeless area may specifically include:
identifying a font corresponding to the character information;
and if the font is an unknown font or the font is an unusual font, increasing the probability value of the risk in the code image.
In the embodiment of the description, a tool for identifying fonts can be used for identifying unknown fonts or uncommon fonts, and then the risk of the code image is judged. If the corresponding font cannot be found in the existing font library, judging that the font is an unknown font; and if the font can be found in an existing font library and can be identified, but the proportion of the font used in the situation corresponding to the code-free area or the code image is smaller than a set threshold value, judging the font to be an unused font.
In the embodiment of the present specification, an OCR (Optical Character Recognition) Recognition technology may be adopted to recognize the text information and the corresponding font, and the OCR Recognition technology may also recognize both the characters printed on the electronic screen and the paper, so as to improve the Recognition rate of the image and further improve the Recognition rate of the image risk.
In the method provided in the embodiment of the present specification, the recognition of the font corresponding to the text information in the codeless region may be used in combination with the recognition of the risk word and sentence, for example, a risk word is recognized in the codeless region of the image to be recognized, and an unknown font is recognized, so that the possibility of risk of the image to be recognized is high.
The codeless region of the image to be identified in the embodiment of this specification may further include image information, and the extracting information of the codeless region may specifically include:
and extracting the image information of the code-free area.
The identifying the risk in the code image according to the information of the code-free region may specifically include:
converting the image information into a graphic feature vector;
inputting the graphic feature vector into a pre-generated image risk identification model for analysis to obtain an image analysis result;
and judging whether the code image has risks or not according to the image analysis result.
In practical application, a codeless region of an image to be recognized may include some image information such as pictures and graphics, and in this embodiment of the present description, a pre-generated image risk recognition model may be used to analyze the pictures, graphics, and the like included in the codeless region, so as to determine whether a risk exists in the code image. The image risk identification model can be an image classification model and can be used for identifying the type of an image; and judging whether the image type belongs to the violation type. For example, a model for classifying the image of the yellow gambling virus can be used to identify the graphic information in the image to be imaged and determine whether the code image is a link related to the yellow gambling virus. In the embodiment of the specification, feedback information of a user can be collected, a training sample can be obtained, an image risk identification model can be trained, the model can be updated through the self-learning capability of a machine model, and the identification accuracy can be improved.
The image to be recognized in the embodiments of this specification may specifically include: the screenshot image, and/or a picture image in an album of the electronic device. For example, in an actual application, an offender or an illegal person may perform screenshot processing on an image generated by an application or store the image in an album of the electronic device. Considering that the image size of the original image may be reduced by screenshot or photographing, in this embodiment of the present description, risk identification may also be performed for the image size of the image, and identifying a risk in the code image according to the information of the code-free area specifically may include:
determining the image size of an image corresponding to the image information based on the image information;
judging whether the image size is smaller than a standard image size;
if so, increasing the probability value of the risk in the code image.
In this embodiment of the present description, a method for determining a risk in a code image according to an image size may be used in combination with the method for determining a risk according to image information, and after the image information is identified and determined, the image size of a corresponding image in the image information may be continuously determined, and if the image size is smaller than a standard image size, a probability value that a risk exists in the code image is increased, where the standard image size may be a preset standard image size, and a specific image size may be set according to an actual requirement. For example, after image information in an uncoded area in an image is identified by an image risk identification model, the probability that the image is a yellow-related image is found to be 60%, the image size is assumed to be 400 × 600, the set standard image size is 700 × 800, and the image size of the image information is compared to determine that the image size is smaller than the standard image size, so that the probability that the image is a yellow-related image can be increased to 70%. The standard image size may also be set to 5000 × 7000. In practical applications, the specific standard image size and the corresponding probability value increase condition may be set according to specific requirements, which are not specifically limited herein.
The method provided in the embodiment of the present description may further include incorporating a color difference value of an image in image information into a determination condition for risk identification, and identifying a risk in the code image according to the information of the codeless region specifically may include:
determining a color difference value of an image corresponding to the image information based on the image information;
judging whether the color difference value is larger than a standard color difference value or not;
if so, increasing the probability value of the risk in the code image.
In practical applications, the image containing the code image is generally a color image, for example, a payment code provided by a certain payment platform contains a blue background image, a payment code provided by another platform with a payment function contains a green background image, and the like. On the basis that some offenders or illegal persons usually directly use black-and-white images for carrying out illegal or illegal operation due to technical limitations or cost requirements, in order to improve the accuracy of identifying image risks, the embodiment of the present specification may compare the color difference value of the image corresponding to the image information with a preset standard color difference value, where the standard color difference value may be the color difference value of a color image. Assume that the standard color difference values are set to: and on the basis of the basis R, G, B, 140, 230, 200 (the basis RGB can be understood as the background color), the color difference value 300 in the color difference evaluation mode of delta E76 is obtained, the non-code area of the image to be recognized is a black-and-white image, and the color difference value of the image corresponding to the image information is greater than the standard color difference value 300, so that the probability value of the risk in the code image in the image to be recognized is increased.
In the embodiment of the present specification, a method for determining a risk in a code image according to a color difference value and the method for determining a risk according to image information may be used in combination, and when a color difference value of an image corresponding to image information of a non-code region is greater than a standard color difference value, a probability value of a risk in a code image is increased on the basis of determining that the code image has a risk according to the image information, so that accuracy of determining that the code image has a risk may be provided.
In this embodiment of the present description, the identifying a risk in the code image according to the information of the code-free region may specifically further include:
determining whether the code image is embedded in a background image of a specific contour based on the image information;
if so, increasing the probability value of the risk in the code image or determining the risk in the code image.
In practical applications, the offender or organization may also embed a code image linked with the offending content in a background image with a specific contour, such as a background image including a elephant image, a dice image, a circular contour, an oval contour, and so on. The background image in the violation image and the specific contour shape in the background image may be collected by using a database, the feature of the specific contour in the background image may be extracted by using a machine learning model, and self-learning may be performed, and whether the code image is embedded in the background image of the specific contour may be determined by using the machine learning model, which is not specifically limited in this embodiment of the present disclosure as long as whether the code image is embedded in the background image of the specific contour can be determined by using a manual screening method.
Also, the method of identifying a risk in a code image by determining whether or not the code image is embedded in a background image of a specific contour in the embodiments of the present specification may be used in combination with the above-described identification method, and when it is determined that the code image is embedded in a background image of a specific contour, the probability value of the risk in the code image may be increased. In practical applications, for some specific contours with specificity, the risk existing in the code image can also be determined directly according to the specific contour embedded in the code image. For example, a code image embedded in a background image of an elephant of a specific form is judged as an image at risk of gambling information.
In the method provided in the embodiment of the present specification, the risk of the code image may be determined according to the code-free region and the content information corresponding to the code image, and specifically, the method for identifying the risk in the code image provided in the embodiment of the present specification may further include:
identifying the code image to obtain content information corresponding to the code image; the code image at least comprises a bar code and a two-dimensional code;
and identifying risks in the code image according to the information of the code-free area and the content information.
Wherein, the identifying the risk in the code image according to the information of the code-free area and the content information may specifically include:
determining first description information of a source of the code image based on the text information;
determining second description information of a source of the code image based on the content information; the content information is link information corresponding to the code image;
and judging whether the first description information is matched with the second description information.
The first description information may be text information in a codeless region of the image to be recognized. Textual information in the codeless region may describe the source of the code image. The second description information may be information included in link information corresponding to the code image. In the information included in the link information, there may be some or all of the information describing the source of the code image. A determination may be made as to whether the two sources are the same or match.
In this embodiment of the present specification, first description information of a source of a code image may be determined according to text information in a code-free area of an image to be identified, link information corresponding to the code image may be obtained by identifying the code image, second description information of the source of the code image may be determined, and then it may be determined whether the code image has a risk by determining whether the first description information and the second description information match, and if not, it may be determined that the code image has a risk.
For example, a code image has a character of "xx public security bureau" in a non-code area of the image, and the source of the code image is determined to be xx public security bureau, however, a link of a certain network provider APP is obtained by identifying the code image in the image, that is, the first description information and the second description information do not match, and it can be judged that the code image has a risk.
In the embodiment of the description, the risk condition of the code image is judged according to the corresponding relation between the code image and the information in the code-free area, so that the accuracy of risk identification can be improved. Even if the code-free area and the link corresponding to the code image are judged to be the compliant content independently, the implicit risk can be identified, and the safety of the user is improved.
In order to further improve accuracy of risk identification, identifying the risk in the code image according to the information of the code-free region and the content information may specifically include:
determining first transaction information of a transaction corresponding to the code image based on the character information;
determining second transaction information for the transaction based on the content information;
and judging whether the first transaction information is matched with the second transaction information.
The first transaction information may specifically include: first merchant information of the transaction, and/or first commodity information of the transaction;
the second transaction information may specifically include: second merchant information for the transaction, and/or second merchandise information for the transaction.
In this embodiment of the present disclosure, if the first transaction information and the second transaction information do not match, it may be determined that a risk exists in the code image.
For example, the character information in the codeless area of an image contains a 'xxx canteen' character, the first transaction information of a transaction corresponding to the code image in the image can be determined to be the xxx canteen, the second transaction information with a transaction amount of ten thousand yuan can be obtained by identifying the code image, the normal canteen does not have ten thousand yuan per transaction amount under normal conditions, namely the first transaction information is not matched with the second transaction information, the code image can be judged to have risk, and the canteen has illegal operation or illegal operations such as money washing or gambling.
For another example, the text information in the code-free region of an image includes a character of "xx snack part", information of a mobile phone with the payment commodity name of "hua is xx" is obtained after the image of the identification code is identified, that is, the first transaction information is not matched with the second transaction information, and it can be determined that the code image has a risk.
The method for identifying risks in a code image provided by the embodiment of the present specification may further include:
acquiring code scanning time aiming at the code image;
determining a conventional code scanning time range of the transaction corresponding to the code image;
judging whether the code scanning time falls into the conventional code scanning time range or not;
and if the code image does not fall into the range, increasing the probability value of the risk in the code image or determining that the risk exists in the code image.
For example, a certain fruit distributor provides a payment code for paying for fruits, and a consumer usually purchases fruits between 8 am and 6 am, but the transaction record of the payment code has a record of a large number of code scanning times from 0 am to 1 am, and the code scanning time does not fall within the conventional code scanning time range, so that the probability value of risk in the payment code can be increased or the payment code can be determined to be at risk. It should be noted that, the conventional code scanning time range in the embodiment of the present specification may be set according to actual requirements, and the specific range is not limited here.
The method for identifying risks in a code image provided by the embodiment of the present specification may further include:
acquiring Location Based Services (LBS) information of a device for scanning the code image;
judging whether the transaction corresponding to the code image is an online transaction or not based on the LBS information;
if the transaction is online transaction, increasing the probability value of the risk in the code image or determining the risk in the code image;
and if the transaction is offline, determining that no risk exists in the code image.
The LBS (Location Based Services) uses various types of positioning technologies to obtain the current Location of the positioning device, and provides information resources and basic Services to the positioning device through the mobile internet.
The method for identifying risks in a code image provided by the embodiment of the specification is mainly used for online transactions of users, and whether the transactions corresponding to the code image are online transactions can be judged through LBS (location based service) information of code scanning equipment. For example, the code image is a payment code of a market, a certain user scans the code image through a mobile phone, if LBS information of the mobile phone indicates that the code scanning position is a residential building or a residential area, it can be determined that the user is conducting online transaction, if the LBS information of the mobile phone indicates that the code scanning position is a market or a downtown area, it can be determined that the user is conducting offline transaction, when the online transaction is determined, the probability value of the risk in the code image can be increased or the risk in the code image can be determined, and when the offline transaction is determined, it can be determined that the risk does not exist in the code image. This process may be processed by a machine learning model, for example, a classification model, or by other tools or methods, which are not limited in this respect.
The method for identifying risks in a code image provided by the embodiment of the present specification may further include:
identifying link information corresponding to the code image;
acquiring behavior information of the user related to the link information;
and identifying risks in the code image according to the link information and the behavior information.
Wherein, the identifying the risk in the code image according to the link information and the behavior information may specifically include:
judging whether the page corresponding to the link information is opened for multiple times;
if so, increasing the probability value of the risk in the code image or determining the risk in the code image.
For example, a fraudulent party provides a user with a code image corresponding to a transaction web page, in order to obtain the trust of the user, the fraudulent party may provide the user with a small fund first, the user may enter a corresponding page through the code image to obtain the fund, and then instruct the user to transfer a plurality of funds to the fraudulent party through the page, the user needs to open the page for a plurality of times to perform an operation, and when it is determined that the page is opened for a plurality of times, the probability value of the risk in the code image may be increased or the risk in the code image may be determined.
For another example, in some fraud events, a fraudster provides a code image linked with a payment interface to a victim, and in the whole fraud process, the fraudster may be instructed or allowed to pay for the same link for multiple times through the payment interface, and in practical applications, a normal transaction manner is that after one transaction is completed, a transaction page is closed or updated so as to avoid incorrect secondary transactions.
In order to further ensure the security of the user and reduce the risk of the user, the method for identifying the risk in the code image provided in the embodiment of the present specification may further include:
and marking the code image as a high-risk code image after the risk is identified to exist in the code image. The user may be prompted to notice the presence of the risk by means of the marker information in the code image.
In addition, the method for identifying risks in a code image provided by the embodiments of the present specification may further include:
and intercepting the transaction corresponding to the code image after recognizing that the risk exists in the code image.
The method for identifying risks in a code image provided by the embodiment of the present specification may further include:
and after recognizing that the code image has the risk, marking the code image which is displayed again within the set time by the display side of the code image as a high-risk code image.
The method for identifying risks in a code image provided by the embodiment of the present specification may further include:
after recognizing that the risk exists in the code image, judging whether the transaction amount of the transaction corresponding to the code image is larger than a set amount; and if so, intercepting the transaction.
In the method provided in the embodiment of the present specification, after a risk is identified in the code image, if it is determined that the transaction amount of the transaction corresponding to the code image is not greater than a set amount, the transaction corresponding to the code image identified as having the risk may not be immediately intercepted, so that the violation party or the fraud party cannot clearly know the failure trigger condition of the code image, which results in an effect of confusing the violation party or the fraud party, and further may increase the cost and risk of the fraud party. For example, when a cheating party performs cheating, the cheating party is provided with the two-dimensional code A for payment, the same two-dimensional code A is adopted when large-amount or small-amount transactions are performed, when small-amount transactions are performed, the cheating party receives the money of the cheating party through the two-dimensional code A, but when large-amount transactions are performed, the cheating party cannot receive the money of the cheating party through the two-dimensional code A, and because the cheating party does not set the transaction amount of the two-dimensional code A, when the transactions which cannot be performed occur, the cheating party cannot determine which link has a problem, and cannot determine whether the two-dimensional code A should be continuously used, the cost and the risk of the cheating party are increased.
The method can be normally used, but when a large amount of transaction is carried out, a user can confirm whether the code image has risks according to the identification or the prompt information and select whether to carry out the transaction, when the user determines that the code image has risks according to the identification or the prompt information, and after the user selects not to carry out the transaction any more, an illegal party or a cheating party can further prompt the user to carry out the transaction or resend the identification image or send a new image to the user, so that the cost and the risks of the cheating party can be increased.
In the method for identifying risks in a code image provided by the embodiment of the specification, the risk of the image to be read can be identified from multiple dimensions, and the safety of a user is improved.
Based on the same idea, embodiments of the present specification further provide an apparatus for identifying a risk in a code image, as shown in fig. 4, the apparatus may include:
an image obtaining module 410, configured to obtain an image to be identified including a code image;
a code-free region determining module 420, configured to determine a code-free region in the image to be identified, which is outside the code image;
an information extraction module 430, configured to extract information of the codeless region;
a risk identification module 440, configured to identify a risk in the code image according to the information of the code-free area.
The image to be recognized specifically may include: the screenshot image, and/or a picture image in an album of the electronic device.
The information extraction module may be specifically configured to: and extracting the character information of the code-free area.
The risk identification module may be specifically configured to:
comparing the character information with the words in the keyword lexicon to obtain a comparison result; the words in the keyword lexicon are high-risk words;
and judging whether the code image has risks or not according to the comparison result.
The risk identification module may be specifically configured to:
converting the text information into text feature vectors;
inputting the text feature vector into a pre-generated text risk identification model for analysis to obtain a text analysis result;
and judging whether the code image has risks or not according to the text analysis result.
The risk identification module may be specifically configured to:
identifying a font corresponding to the character information;
and if the font is an unknown font or the font is an unusual font, increasing the probability value of the risk in the code image.
The information extraction module may be specifically configured to:
and extracting the image information of the code-free area.
The risk identification module may be specifically configured to:
converting the image information into a graphic feature vector;
inputting the graphic feature vector into a pre-generated image risk identification model for analysis to obtain an image analysis result;
and judging whether the code image has risks or not according to the image analysis result.
The risk identification module may be further configured to:
determining the image size of an image corresponding to the image information based on the image information;
judging whether the image size is smaller than a standard image size;
if so, increasing the probability value of the risk in the code image.
The risk identification module may be further configured to:
determining a color difference value of an image corresponding to the image information based on the image information;
judging whether the color difference value is larger than a standard color difference value or not;
if so, increasing the probability value of the risk in the code image.
The risk identification module may be further configured to:
determining whether the code image is embedded in a background image of a specific contour based on the image information;
if so, increasing the probability value of the risk in the code image or determining the risk in the code image.
The apparatus for identifying risks in a code image provided in an embodiment of the present specification may be further configured to:
identifying the code image to obtain content information corresponding to the code image;
and identifying risks in the code image according to the information of the code-free area and the content information.
Wherein, the identifying the risk in the code image according to the information of the code-free area and the content information may specifically include:
determining first description information of a source of the code image based on the text information;
determining second description information of a source of the code image based on the content information; the content information is link information corresponding to the code image;
and judging whether the first description information is matched with the second description information.
Wherein, the identifying the risk in the code image according to the information of the code-free area and the content information specifically further comprises:
determining first transaction information of a transaction corresponding to the code image based on the character information;
determining second transaction information for the transaction based on the content information;
and judging whether the first transaction information is matched with the second transaction information.
The first transaction information may specifically include:
first merchant information of the transaction, and/or first commodity information of the transaction;
the second transaction information may specifically include:
second merchant information for the transaction, and/or second merchandise information for the transaction.
The apparatus for identifying risks in a code image provided in an embodiment of the present specification may be further configured to:
acquiring code scanning time aiming at the code image;
determining a conventional code scanning time range of the transaction corresponding to the code image;
judging whether the code scanning time falls into the conventional code scanning time range or not;
and if the code image does not fall into the range, increasing the probability value of the risk in the code image or determining that the risk exists in the code image.
The apparatus for identifying risks in a code image provided in an embodiment of the present specification may be further configured to:
acquiring LBS information of equipment for scanning codes according to the code image;
judging whether the transaction corresponding to the code image is an online transaction or not based on the LBS information;
if the transaction is online transaction, increasing the probability value of the risk in the code image or determining the risk in the code image;
and if the transaction is offline, determining that no risk exists in the code image.
The apparatus for identifying risks in a code image provided in an embodiment of the present specification may be further configured to:
identifying link information corresponding to the code image;
acquiring behavior information of the user related to the link information;
and identifying risks in the code image according to the link information and the behavior information.
The apparatus for identifying risks in a code image provided in an embodiment of the present specification may be further configured to:
and marking the code image as a high-risk code image after the risk is identified to exist in the code image.
The apparatus for identifying risks in a code image provided in an embodiment of the present specification may be further configured to:
and intercepting the transaction corresponding to the code image after recognizing that the risk exists in the code image.
The apparatus for identifying risks in a code image provided in an embodiment of the present specification may be further configured to:
and after recognizing that the code image has the risk, marking the code image which is displayed again within the set time by the display side of the code image as a high-risk code image.
The apparatus for identifying risks in a code image provided in an embodiment of the present specification may be further configured to:
after recognizing that the risk exists in the code image, judging whether the transaction amount of the transaction corresponding to the code image is larger than a set amount;
and if so, intercepting the transaction.
Based on the same idea, embodiments of the present specification further provide an apparatus for identifying a risk in a code image, as shown in fig. 5, where the apparatus 500 may include:
at least one processor 510; and the number of the first and second groups,
a memory 530 communicatively coupled to the at least one processor; wherein,
the memory 530 stores instructions 520 executable by the at least one processor 510 to enable the at least one processor 510 to:
acquiring an image to be identified containing a code image;
determining a non-code area outside the code image in the image to be identified;
extracting information of the code-free area;
and identifying risks in the code image according to the information of the code-free area.
Based on the same idea, the embodiments of the present specification further provide a non-volatile computer storage medium corresponding to fig. 2, storing computer-executable instructions configured to:
acquiring an image to be identified containing a code image;
determining a non-code area outside the code image in the image to be identified;
extracting information of the code-free area;
and identifying risks in the code image according to the information of the code-free area.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and for the relevant points, reference may be made to the partial description of the embodiments of the method.
The apparatus, the device, the nonvolatile computer storage medium, and the method provided in the embodiments of the present specification correspond to each other, and therefore, the apparatus, the device, and the nonvolatile computer storage medium also have advantageous technical effects similar to those of the corresponding method.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, the present specification embodiments may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The above description is only an example of the present specification, and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (25)
1. A method of identifying a risk in a code image, comprising:
acquiring an image to be identified containing a code image;
determining a non-code area outside the code image in the image to be identified;
extracting information of the code-free area;
identifying a risk in the code image according to the information of the code-free area;
the extracting information of the codeless region specifically includes: extracting image information of the code-free area;
the identifying the risk in the code image according to the information of the code-free area specifically includes:
converting the image information into a graphic feature vector;
inputting the graphic feature vector into a pre-generated image risk identification model for analysis to obtain an image analysis result;
and judging whether the code image has risks or not according to the image analysis result.
2. A method of identifying a risk in a code image, comprising:
acquiring an image to be identified containing a code image;
determining a non-code area outside the code image in the image to be identified;
extracting information of the code-free area;
identifying a risk in the code image according to the information of the code-free area;
the extracting information of the codeless region specifically includes: extracting the character information of the code-free area;
the identifying the risk in the code image according to the information of the code-free area specifically includes:
comparing the character information with the words in the keyword lexicon to obtain a comparison result; the words in the keyword lexicon are high-risk words;
and judging whether the code image has risks or not according to the comparison result.
3. The method according to claim 2, wherein the identifying the risk in the code image according to the information of the code-free region specifically comprises:
converting the text information into text feature vectors;
inputting the text feature vector into a pre-generated text risk identification model for analysis to obtain a text analysis result;
and judging whether the code image has risks or not according to the text analysis result.
4. The method according to claim 2, wherein the identifying the risk in the code image according to the information of the code-free region specifically comprises:
identifying a font corresponding to the character information;
and if the font is an unknown font or the font is an unusual font, increasing the probability value of the risk in the code image.
5. The method according to claim 1, wherein the identifying the risk in the code image according to the information of the code-free region specifically comprises:
determining the image size of an image corresponding to the image information based on the image information;
judging whether the image size is smaller than a standard image size;
if so, increasing the probability value of the risk in the code image.
6. The method according to claim 1, wherein the identifying the risk in the code image according to the information of the code-free region specifically comprises:
determining a color difference value of an image corresponding to the image information based on the image information;
judging whether the color difference value is larger than a standard color difference value or not;
if so, increasing the probability value of the risk in the code image.
7. The method according to claim 1, wherein the identifying the risk in the code image according to the information of the code-free region specifically comprises:
determining whether the code image is embedded in a background image of a specific contour based on the image information;
if so, increasing the probability value of the risk in the code image or determining the risk in the code image.
8. The method of claim 2, further comprising:
identifying the code image to obtain content information corresponding to the code image;
and identifying risks in the code image according to the information of the code-free area and the content information.
9. The method according to claim 8, wherein the identifying the risk in the code image according to the information of the code-free region and the content information specifically comprises:
determining first description information of a source of the code image based on the text information;
determining second description information of a source of the code image based on the content information; the content information is link information corresponding to the code image;
and judging whether the first description information is matched with the second description information.
10. The method according to claim 8, wherein the identifying the risk in the code image according to the information of the code-free region and the content information specifically comprises:
determining first transaction information of a transaction corresponding to the code image based on the character information;
determining second transaction information for the transaction based on the content information;
and judging whether the first transaction information is matched with the second transaction information.
11. The method according to claim 10, wherein the first transaction information specifically includes:
first merchant information of the transaction, and/or first commodity information of the transaction;
the second transaction information specifically includes:
second merchant information for the transaction, and/or second merchandise information for the transaction.
12. The method of claim 1, further comprising:
acquiring code scanning time aiming at the code image;
determining a conventional code scanning time range of the transaction corresponding to the code image;
judging whether the code scanning time falls into the conventional code scanning time range or not;
and if the code image does not fall into the range, increasing the probability value of the risk in the code image or determining that the risk exists in the code image.
13. The method of claim 1, further comprising:
acquiring LBS information of equipment for scanning codes according to the code image;
judging whether the transaction corresponding to the code image is an online transaction or not based on the LBS information;
if the transaction is online transaction, increasing the probability value of the risk in the code image or determining the risk in the code image;
and if the transaction is offline, determining that no risk exists in the code image.
14. The method according to claim 1, wherein the image to be recognized specifically comprises:
the screenshot image, and/or a picture image in an album of the electronic device.
15. The method of claim 1, further comprising:
identifying link information corresponding to the code image;
acquiring behavior information of the user related to the link information;
and identifying risks in the code image according to the link information and the behavior information.
16. The method of claim 1, further comprising:
and marking the code image as a high-risk code image after the risk is identified to exist in the code image.
17. The method of claim 1, further comprising:
and intercepting the transaction corresponding to the code image after recognizing that the risk exists in the code image.
18. The method of claim 1, further comprising:
and after recognizing that the code image has the risk, marking the code image which is displayed again within the set time by the display side of the code image as a high-risk code image.
19. The method of claim 1, further comprising:
after recognizing that the risk exists in the code image, judging whether the transaction amount of the transaction corresponding to the code image is larger than a set amount;
and if so, intercepting the transaction.
20. An apparatus to identify a risk in a code image, comprising:
the image acquisition module is used for acquiring an image to be identified containing a code image;
a code-free region determining module, configured to determine a code-free region in the image to be identified, the region being other than the code image;
the information extraction module is used for extracting the information of the code-free area;
the risk identification module is used for identifying risks in the code image according to the information of the code-free area;
the information extraction module is specifically configured to: extracting image information of the code-free area;
the risk identification module is specifically configured to:
converting the image information into a graphic feature vector;
inputting the graphic feature vector into a pre-generated image risk identification model for analysis to obtain an image analysis result;
and judging whether the code image has risks or not according to the image analysis result.
21. An apparatus to identify a risk in a code image, comprising:
the image acquisition module is used for acquiring an image to be identified containing a code image;
a code-free region determining module, configured to determine a code-free region in the image to be identified, the region being other than the code image;
the information extraction module is used for extracting the information of the code-free area;
the risk identification module is used for identifying risks in the code image according to the information of the code-free area;
the information extraction module is specifically configured to: extracting the character information of the code-free area;
the risk identification module is specifically configured to: comparing the character information with the words in the keyword lexicon to obtain a comparison result; the words in the keyword lexicon are high-risk words;
and judging whether the code image has risks or not according to the comparison result.
22. The apparatus of claim 21, wherein the risk identification module is specifically configured to:
converting the text information into text feature vectors;
inputting the text feature vector into a pre-generated text risk identification model for analysis to obtain a text analysis result;
and judging whether the code image has risks or not according to the text analysis result.
23. The apparatus of claim 20, further configured to:
and intercepting the transaction corresponding to the code image after recognizing that the risk exists in the code image.
24. An apparatus for identifying a risk in a code image, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring an image to be identified containing a code image;
determining a non-code area outside the code image in the image to be identified;
extracting information of the code-free area;
identifying a risk in the code image according to the information of the code-free area;
the extracting information of the codeless region specifically includes: extracting image information of the code-free area;
the identifying the risk in the code image according to the information of the code-free area specifically includes:
converting the image information into a graphic feature vector;
inputting the graphic feature vector into a pre-generated image risk identification model for analysis to obtain an image analysis result;
and judging whether the code image has risks or not according to the image analysis result.
25. An apparatus for identifying a risk in a code image, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring an image to be identified containing a code image;
determining a non-code area outside the code image in the image to be identified;
extracting information of the code-free area;
identifying a risk in the code image according to the information of the code-free area;
the extracting information of the codeless region specifically includes: extracting the character information of the code-free area;
the identifying the risk in the code image according to the information of the code-free area specifically includes:
comparing the character information with the words in the keyword lexicon to obtain a comparison result; the words in the keyword lexicon are high-risk words;
and judging whether the code image has risks or not according to the comparison result.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111184293.XA CN114758327B (en) | 2020-02-25 | 2020-02-25 | Method, device and equipment for identifying risks in code image |
CN202010116270.4A CN111353488B (en) | 2020-02-25 | 2020-02-25 | Method, device and equipment for identifying risks in code image |
PCT/CN2020/137902 WO2021169529A1 (en) | 2020-02-25 | 2020-12-21 | Method, apparatus and device for identifying risk in code image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010116270.4A CN111353488B (en) | 2020-02-25 | 2020-02-25 | Method, device and equipment for identifying risks in code image |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111184293.XA Division CN114758327B (en) | 2020-02-25 | 2020-02-25 | Method, device and equipment for identifying risks in code image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111353488A CN111353488A (en) | 2020-06-30 |
CN111353488B true CN111353488B (en) | 2021-09-21 |
Family
ID=71195773
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010116270.4A Active CN111353488B (en) | 2020-02-25 | 2020-02-25 | Method, device and equipment for identifying risks in code image |
CN202111184293.XA Active CN114758327B (en) | 2020-02-25 | 2020-02-25 | Method, device and equipment for identifying risks in code image |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111184293.XA Active CN114758327B (en) | 2020-02-25 | 2020-02-25 | Method, device and equipment for identifying risks in code image |
Country Status (2)
Country | Link |
---|---|
CN (2) | CN111353488B (en) |
WO (1) | WO2021169529A1 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111353488B (en) * | 2020-02-25 | 2021-09-21 | 支付宝(杭州)信息技术有限公司 | Method, device and equipment for identifying risks in code image |
CN113255857B (en) * | 2021-05-28 | 2022-09-06 | 支付宝(杭州)信息技术有限公司 | Risk detection method, device and equipment for graphic code |
CN113688650B (en) * | 2021-09-22 | 2022-06-17 | 支付宝(杭州)信息技术有限公司 | Method and device for identifying picture |
CN116861412A (en) * | 2023-06-26 | 2023-10-10 | 深圳市赛凌伟业科技有限公司 | Information security analysis method and system based on big data |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104424458A (en) * | 2013-08-23 | 2015-03-18 | 希姆通信息技术(上海)有限公司 | Image identification method and device, network server, image identification equipment and system |
CN109214224A (en) * | 2017-06-30 | 2019-01-15 | 阿里巴巴集团控股有限公司 | The Risk Identification Method and device of information coding |
CN109829349A (en) * | 2018-12-20 | 2019-05-31 | 天翼电子商务有限公司 | Promote two dimensional code safety in utilization method, system, storage medium and device |
CN110443031A (en) * | 2019-07-16 | 2019-11-12 | 阿里巴巴集团控股有限公司 | A kind of two dimensional code Risk Identification Method and system |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103150651A (en) * | 2011-12-06 | 2013-06-12 | Isl防伪***有限公司 | Individual commodity authentication and identification device, system and method |
CN103400264A (en) * | 2013-08-19 | 2013-11-20 | 陈曦 | Security verification method for two-dimensional code payment |
US20160323108A1 (en) * | 2015-04-29 | 2016-11-03 | International Business Machines Corporation | Accessing Content by Processing Secure Optical Codes |
CN106561029A (en) * | 2016-12-09 | 2017-04-12 | 北京安天电子设备有限公司 | Semi-connection two-dimensional code detecting method and system |
US9798954B1 (en) * | 2016-12-15 | 2017-10-24 | Federal Home Loan Mortgage Corporation | System, device, and method for image anomaly detection |
CN106599759A (en) * | 2016-12-22 | 2017-04-26 | 广东小天才科技有限公司 | Terminal information processing method and device |
CN107025480B (en) * | 2017-02-13 | 2020-02-04 | 阿里巴巴集团控股有限公司 | Image generation method and apparatus thereof |
CN107403216A (en) * | 2017-05-25 | 2017-11-28 | 阿里巴巴集团控股有限公司 | A kind of identification code generation and verification method and device |
CN107563244A (en) * | 2017-08-09 | 2018-01-09 | 维沃移动通信有限公司 | A kind of two-dimension code safe verification method and mobile terminal |
CN108510274B (en) * | 2018-04-07 | 2021-09-14 | 南京智握信息技术有限公司 | Method and device for visual identification of image and two-dimensional code combined verification |
CN108665041B (en) * | 2018-05-09 | 2021-08-03 | 深圳市码云可变数据科技有限公司 | Two-dimensional code generation and identification method and device, computer equipment and storage medium |
CN109272336A (en) * | 2018-09-20 | 2019-01-25 | 阿里巴巴集团控股有限公司 | A kind of risk trade company discovery method and apparatus |
CN109787883B (en) * | 2018-12-28 | 2022-01-21 | 广州华多网络科技有限公司 | Information processing method and device, electronic equipment and computer readable storage medium |
KR102159712B1 (en) * | 2019-07-29 | 2020-09-24 | 박준영 | Qr code, and terminal using the same |
CN210038912U (en) * | 2019-08-12 | 2020-02-07 | 北京百佑科技有限公司 | Two-dimensional code security equipment and entrance guard's equipment |
CN111353488B (en) * | 2020-02-25 | 2021-09-21 | 支付宝(杭州)信息技术有限公司 | Method, device and equipment for identifying risks in code image |
-
2020
- 2020-02-25 CN CN202010116270.4A patent/CN111353488B/en active Active
- 2020-02-25 CN CN202111184293.XA patent/CN114758327B/en active Active
- 2020-12-21 WO PCT/CN2020/137902 patent/WO2021169529A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104424458A (en) * | 2013-08-23 | 2015-03-18 | 希姆通信息技术(上海)有限公司 | Image identification method and device, network server, image identification equipment and system |
CN109214224A (en) * | 2017-06-30 | 2019-01-15 | 阿里巴巴集团控股有限公司 | The Risk Identification Method and device of information coding |
CN109829349A (en) * | 2018-12-20 | 2019-05-31 | 天翼电子商务有限公司 | Promote two dimensional code safety in utilization method, system, storage medium and device |
CN110443031A (en) * | 2019-07-16 | 2019-11-12 | 阿里巴巴集团控股有限公司 | A kind of two dimensional code Risk Identification Method and system |
Also Published As
Publication number | Publication date |
---|---|
CN114758327A (en) | 2022-07-15 |
CN111353488A (en) | 2020-06-30 |
CN114758327B (en) | 2024-06-14 |
WO2021169529A1 (en) | 2021-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111353488B (en) | Method, device and equipment for identifying risks in code image | |
CN107798571B (en) | Malice address/malice order identifying system, method and device | |
US20220012488A1 (en) | Receipt identification method, apparatus, electronic device and computer-readable storage medium | |
CN110826006B (en) | Abnormal collection behavior identification method and device based on privacy data protection | |
CN109190007B (en) | Data analysis method and device | |
CN113886584A (en) | Information detection method, device and equipment for application program | |
CN107025480B (en) | Image generation method and apparatus thereof | |
CN110175609B (en) | Interface element detection method, device and equipment | |
CN110781925B (en) | Software page classification method and device, electronic equipment and storage medium | |
CN110569502A (en) | Method and device for identifying forbidden slogans, computer equipment and storage medium | |
CN113011349A (en) | Element identification method and device of bill and storage medium | |
CN112184143B (en) | Model training method, device and equipment in compliance audit rule | |
CN115238688B (en) | Method, device, equipment and storage medium for analyzing association relation of electronic information data | |
CN112926471A (en) | Method and device for identifying image content of business document | |
CN113837638A (en) | Method, device and equipment for determining dialect | |
CN112966113A (en) | Data risk prevention and control method, device and equipment | |
CN111159354A (en) | Sensitive information detection method, device, equipment and system | |
CN113450215A (en) | Transaction data risk detection method and device and server | |
CN117197857A (en) | Face counterfeiting attack detection and face recognition method, device and equipment | |
CN110879832A (en) | Target text detection method, model training method, device and equipment | |
CN111091019B (en) | Information prompting method, device and equipment | |
CN113111734B (en) | Watermark classification model training method and device | |
CN113837772A (en) | Method, device and equipment for auditing marketing information | |
CN113949887A (en) | Method and device for processing network live broadcast data | |
CN110705439B (en) | Information processing method, device and equipment |
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 | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40030935 Country of ref document: HK |
|
GR01 | Patent grant | ||
GR01 | Patent grant |