CN112001662A - Method, device and equipment for risk detection of merchant image - Google Patents
Method, device and equipment for risk detection of merchant image Download PDFInfo
- Publication number
- CN112001662A CN112001662A CN202010963356.0A CN202010963356A CN112001662A CN 112001662 A CN112001662 A CN 112001662A CN 202010963356 A CN202010963356 A CN 202010963356A CN 112001662 A CN112001662 A CN 112001662A
- Authority
- CN
- China
- Prior art keywords
- risk
- image
- image processing
- merchant
- result
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/19007—Matching; Proximity measures
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the specification discloses a method, a device and equipment for risk detection of a merchant image. The scheme can be applied to the field of supervision or compliance. The scheme can comprise the following steps: when the risk inspection is carried out on the merchant image, the merchant image is processed in advance by adopting a preset image processing operation so as to store the generated image processing result, so that the risk inspection rule can directly inspect the pre-stored image processing result so as to obtain the image risk inspection result.
Description
Technical Field
The application relates to the technical field of compliance inspection, in particular to a method, a device and equipment for inspecting risks of merchant images.
Background
In the operation process of a merchant, propaganda information of the merchant is usually issued at a business platform or other websites, and therefore, when the merchant is subjected to compliance check, relevant information issued by the merchant at each business platform or website needs to be checked to identify whether the merchant has the problems of using risk propaganda information or performing illegal operation activities in the operation process. At present, an image to be checked containing merchant information is usually collected first, and then the merchant information contained in the image is manually checked for risks.
Based on this, a more efficient risk verification method for merchant images is needed.
Disclosure of Invention
The embodiment of the specification provides a method, a device and equipment for risk detection of a merchant image, so as to reduce the amount of resources required to be used when the risk detection is performed on the merchant image.
In order to solve the above technical problem, the embodiments of the present specification are implemented as follows:
the method for risk testing of the merchant image provided by the embodiment of the specification is applied to a risk testing server, and comprises the following steps:
when risk inspection is carried out on a merchant image at a target website, acquiring identification information of the merchant image;
acquiring an image processing result corresponding to the identification information according to a preset image processing result storage address; the image processing result is a processing result obtained by processing the merchant image by adopting a preset image processing operation in advance; the preset image processing operation is the image processing operation indicated by the preprocessing operation information of the application scene to which the merchant image belongs; the preset image processing operation at least comprises one of an optical character recognition operation and an object recognition operation;
and checking the image processing result by using a risk checking rule to obtain an image risk checking result.
The risk inspection device for a merchant image provided by the embodiment of the present specification is applied to a risk inspection server, and includes:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring identification information of a merchant image when the risk of the merchant image at a target website is checked;
the second acquisition module is used for acquiring an image processing result which has a corresponding relation with the identification information according to a preset image processing result storage address; the image processing result is a processing result obtained by processing the merchant image by adopting a preset image processing operation in advance; the preset image processing operation is the image processing operation indicated by the preprocessing operation information of the application scene to which the merchant image belongs; the preset image processing operation at least comprises one of an optical character recognition operation and an object recognition operation;
and the inspection module is used for inspecting the image processing result by using a risk inspection rule to obtain an image risk inspection result.
The risk check equipment of merchant image that this specification embodiment provided 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 content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
when risk inspection is carried out on a merchant image at a target website, acquiring identification information of the merchant image;
acquiring an image processing result corresponding to the identification information according to a preset image processing result storage address; the image processing result is a processing result obtained by processing the merchant image by adopting a preset image processing operation in advance; the preset image processing operation is the image processing operation indicated by the preprocessing operation information of the application scene to which the merchant image belongs; the preset image processing operation at least comprises one of an optical character recognition operation and an object recognition operation;
and checking the image processing result by using a risk checking rule to obtain an image risk checking result.
At least one embodiment provided in the present specification can achieve the following advantageous effects:
when the risk inspection is performed on the merchant image, the merchant image can be processed in advance by adopting a preset image processing operation to store the generated image processing result, so that the risk inspection rule can directly inspect the pre-stored image processing result to automatically generate the image risk inspection result. The scheme does not need manual examination and verification, and is beneficial to reducing the human resources consumed when the risk inspection is carried out on the merchant image. And each risk inspection rule can directly call the pre-stored image processing result, and each risk inspection rule is not required to perform one-time preset image processing operation on the merchant image, so that the frequency of the preset image processing operation required to be performed in the risk inspection process can be reduced, and the equipment resources required to be consumed in the risk inspection of the merchant image are reduced.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, 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 flowchart of a method for risk detection of a merchant image according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a merchant image to be inspected provided in an embodiment of the present description;
FIG. 3 is a schematic diagram of another merchant image to be verified provided in an embodiment of the present description;
FIG. 4 is a schematic structural diagram of a risk testing device corresponding to a merchant image in FIG. 1 provided in an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a risk verification apparatus corresponding to one merchant image in fig. 1 provided in an embodiment of the present specification.
Detailed Description
To make the objects, technical solutions and advantages of one or more embodiments of the present disclosure more apparent, the technical solutions of one or more embodiments of the present disclosure will be described in detail and completely with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present specification, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from the embodiments given herein without making any creative effort fall within the scope of protection of one or more embodiments of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
In the prior art, a rule engine (flagleader) is developed from an inference engine, and is a component embedded in an application program, which can separate a business decision from an application program code and write the business decision by using a predefined semantic module. The rules engine may interpret the business rules based on the received data input and make business decisions based on the business rules. Rule engines are becoming increasingly popular because the complexity of components that implement complex business logic can be reduced through the use of rule engines, and the maintenance and extensibility costs of applications can be reduced.
At present, when people set business rules for risk inspection of images of merchants by using a rule engine, corresponding image processing operations are generally required to be set for each business rule in advance, so that when each business rule is operated, specified image processing operations can be performed on input images, and then risk inspection is performed based on image processing results obtained through processing. It can be seen that when ten business rules are required to be adopted to respectively perform risk check on the same image, if the preset image processing operations of the ten business rules all include optical character recognition operations, ten optical character recognition operations are required to be performed on the same image, and since the contents of ten character recognition results generated for the image are usually consistent, waste of equipment resources is easily caused.
In order to solve the defects in the prior art, the scheme provides the following embodiments:
fig. 1 is a schematic flowchart of a method for risk detection of a merchant image according to an embodiment of the present disclosure. From a program perspective, the execution subject of the flow may be a risk check server or a program hosted by the risk check server.
As shown in fig. 1, the process may include the following steps:
step 102: when the risk of a merchant image at a target website is checked, acquiring the identification information of the merchant image.
In the embodiment of the present specification, when the business is subjected to compliance check, risk check is performed on information issued by the business at each target website to determine whether the information used by the business in the operation process is not compliant. The target website may include a business platform (i.e., an e-business platform) and various websites capable of publishing advertisement information.
A commerce platform generally refers to a platform that provides an online transaction negotiation environment for businesses or individuals. The business platform can provide a virtual network space for business activities established on the Internet and a management environment for ensuring smooth operation of the business; the system is an important place for coordinating and integrating information flow, cargo flow and fund flow in order, relevance and high-efficiency flow. Enterprises and merchants can make full use of shared resources such as network infrastructure, payment platform, security platform, management platform and the like provided by the electronic commerce platform to effectively develop own commercial activities at low cost. Since the merchant usually needs to conduct business at the business platform, the image containing the information related to the business used by the merchant can be intercepted from the merchant page at the business platform to obtain the image of the merchant to be verified.
And websites that may publish advertising information may include, but are not limited to, entertainment websites, enterprise websites, government websites, educational websites, and the like. The merchant can publish advertisements at the websites, and the advertisements can be displayed in the pages of the websites in the forms of pop-up windows, page windows, rolling captions and the like, so that the merchant image to be checked containing the merchant information can be obtained by screenshot of the pages of the websites. In the embodiment of the present specification, the acquisition source of the merchant image to be verified and the merchant information included in the merchant image are not particularly limited.
Step 104: acquiring an image processing result corresponding to the identification information according to a preset image processing result storage address; the image processing result is a processing result obtained by processing the merchant image by adopting a preset image processing operation in advance; the preset image processing operation is the image processing operation indicated by the preprocessing operation information of the application scene to which the merchant image belongs; the preset image processing operation at least comprises one of an optical character recognition operation and an object recognition operation.
In this embodiment of the present description, preprocessing operation information corresponding to each application scene may be preset according to an actual requirement, where the preprocessing operation information may indicate an image processing operation that needs to be performed on a merchant image acquired in the application scene. For example, for an advertisement service scene, since the collected merchant image usually includes a poster and a poster, it is necessary to identify whether there is a risk in the text and the object image included in the merchant image, so that the preprocessing operation information for the advertisement service scene may include an optical character recognition operation and an object recognition operation. For a transaction service scene, the acquired merchant image may contain transaction parameter information but not a commodity image, so that only whether the text contained in the merchant image has risk needs to be identified, and the preprocessing operation information for the payment service scene may only include an optical character identification operation. In the embodiments of the present specification, the type of image processing operation indicated by the preprocessing operation information corresponding to each service scene is not particularly limited.
In the embodiment of the present specification, the optical Character recognition operation may be implemented based on an optical Character recognition technology ocr (optical Character recognition). The optical character recognition technology may refer to a process of determining a character shape by detecting dark and light areas on an image using an electronic device, and then translating the shape into a computer text using a character recognition method; i.e. a technology of optically recognizing characters in an image and converting the characters into a text format.
And the object recognition operation can be implemented based on an object recognition model. The object recognition model usually needs to be trained in advance by using images containing the designated object and images not containing the designated object as training samples, so that the object recognition model can classify the input images and output a recognition result indicating whether the input images contain the designated object or not. The object recognition model can be implemented by using an existing object recognition model, for example, a Support Vector Machine (SVM), a MobileNet model, an eXtreme Gradient Boosting model (XGBoost), and the like can be used, or the object recognition model can be built by itself according to actual requirements, for example, the object recognition model is built based on a Convolutional Neural Network (CNN). In the embodiments of the present specification, the model structure of the object recognition model is not particularly limited.
In practical application, when a to-be-processed merchant image is acquired from a target website, an application scene to which the merchant image belongs may be determined, the merchant image is correspondingly processed by using a preset image processing operation corresponding to the application scene, various image processing results required to be used when the merchant image of the application scene is subjected to risk inspection are obtained, and the image processing results are stored so as to facilitate direct call of subsequent risk inspection rules.
Therefore, before step 104, the method may further include:
acquiring the merchant image from the target website; the merchant image has identification information. The identification information of the merchant image may refer to unique identification Information (ID) of the merchant image.
And determining preset image processing operation according to the preprocessing operation information of the application scene to which the merchant image belongs.
And processing the merchant image by utilizing the preset image processing operation to obtain an image processing result.
Storing the corresponding relation information between the image processing result and the identification information and the image processing result to a distributed cache; the distributed cache is a cache corresponding to a preset image processing result storage address.
Step 106: and checking the image processing result by using a risk checking rule to obtain an image risk checking result.
In the embodiment of the present specification, the risk verification rules required to be adopted for the merchant images to be verified in different application scenarios may not be completely consistent. And the risk detection rules required to be adopted for the images of the merchants to be detected, which are acquired from different websites in the same application scene, may not be completely consistent. Therefore, the risk inspection rule corresponding to the merchant image to be inspected needs to be adopted for risk inspection.
Thus, before step 104, the method may further include: determining a risk verification rule for the merchant image.
In this specification embodiment, the risk verification rule set for the application scenario to which the merchant image belongs may be determined as the risk verification rule for the merchant image. Alternatively, the risk verification rule having a correspondence relationship with the target website may be determined from risk verification rules set for the application scenario to which the merchant image belongs. This is not particularly limited.
Step 106 may use the determined risk check rules for the merchant image to check the image processing results required by the risk check rules to obtain image risk check results.
It should be understood that the order of some steps in the method described in one or more embodiments of the present disclosure may be interchanged according to actual needs, or some steps may be omitted or deleted.
In the method shown in fig. 1, the risk checking rule may directly call the pre-stored image processing result to check the pre-generated image processing result, so as to automatically generate the image risk checking result. The scheme does not need manual examination and verification, and is beneficial to reducing the human resources consumed when the risk inspection is carried out on the merchant image. And each risk inspection rule can directly call the pre-stored image processing result, and each risk inspection rule is not required to perform one-time preset image processing operation on the merchant image, so that the frequency of the preset image processing operation required to be performed in the risk inspection process can be reduced, and the equipment resources required to be consumed in the risk inspection of the merchant image are reduced.
Based on the process of fig. 1, some specific embodiments of the process are also provided in the examples of this specification, which are described below.
In the embodiments of the present specification, since the types of the preset image processing operations may include a plurality of types of the optical character recognition operation, the object recognition operation, and the like, the types of the image processing results generated and stored in advance may also be a plurality of types. However, one risk check rule may only use one type of image processing result during execution, and therefore, the risk check rule may only call the image processing result of the type that needs to be used during execution, and does not need to call other types of image processing results, so as to ensure normal operation of the risk check rule.
Thus, step 104: acquiring an image processing result having a corresponding relationship with the identification information according to a preset image processing result storage address, which may specifically include:
and determining a label of an image processing result required by each determined risk checking rule, wherein the label is used for identifying that the image processing result is a processing result obtained by processing an image by adopting a specified image processing operation. The specified image processing operation refers to one or more of preset image processing operations.
And acquiring an image processing result which has a corresponding relation with the identification information and is provided with the label from a preset image processing result storage address.
In the embodiments of the present specification, the labels possessed by the image processing results obtained by different image processing operations may be different. When the image processing result is stored, the image processing result carrying the corresponding label can be stored, so that the risk check rule can call the image processing result of the type required to be used.
In an embodiment of this specification, the verifying the image processing result by using a risk verification rule to obtain an image risk verification result may specifically include:
and if the acquired image processing result which has the corresponding relation with the identification information and the label is a character recognition result, checking whether the character recognition result contains a risk keyword by using the risk checking rule to obtain a first risk checking result.
And if the acquired image processing result which has the corresponding relation with the identification information and the label is an object identification result, checking whether the object identification result contains a risk object by using the risk checking rule to obtain a second risk checking result.
In the embodiment of the present specification, since the character recognition result may include not only text information recognized from the merchant image but also position information (for example, coordinate information) of each vocabulary in the recognized text information in the merchant image and the like. The object recognition result may include not only information indicating whether the specified object is recognized from the merchant image, but also position information (for example, coordinate information) of the recognized object in the merchant image after the specified object is recognized.
Thus, the first risk verification result generated by the risk verification rule may include: the risk keywords contained in the merchant image and the coordinate information of the risk keywords contained in the merchant image. And the second risk test result may include: the risk object contained in the merchant image and the coordinate information of the risk object contained in the merchant image.
For ease of understanding, the execution of the risk checking rules is illustrated.
Fig. 2 is a schematic diagram of a merchant image to be checked provided in an embodiment of the present specification. As shown in FIG. 2, the image of the merchant includes objects such as hands and money, and further includes "interior staff's work price, over-value for rush purchase! "etc. If the preset image processing operation corresponding to the merchant image only comprises character recognition operation, only optical character recognition processing needs to be carried out on the merchant image, so that the merchant image can obtain the information including' internal staff price, over-value shopping! "character recognition result of equal characters.
If a risk checking rule is used for checking whether the character recognition result contains risk keywords such as 'staff price', 'internal channel price' and the like, the risk checking rule is used for carrying out risk checking on the character recognition result, and a risk checking result which indicates that the character recognition result contains the risk keywords such as 'staff price' and 'internal staff price' can be obtained.
Since the character recognition result may also include the location information of the "staff's price" and the "internal staff' price" in the merchant image, for example, the location information of the term "internal staff price" may be: the position information of the terms of the coordinates of the upper left corner (0,50), the coordinates of the lower right corner (50,40) and the labor price can be as follows: coordinates in the upper left corner (20,50), and coordinates in the lower right corner (50, 40). The risk inspection result may further include coordinate information of the "staff's labor price" and the "internal staff's labor price" in the merchant image.
Fig. 3 is a schematic diagram of another merchant image to be verified provided in the embodiments of the present specification. As shown in FIG. 3, the merchant image includes objects such as playing cards, dice, etc., and also includes "small chess cards, large winners, registered cash! "etc. If the preset image processing operation corresponding to the merchant image comprises character recognition operation and object recognition operation, the merchant image does not need to be subjected to optical character recognition processing to obtain a product containing' small chess, large winner, registered cash! "character recognition result of equal characters. The merchant image is further classified by using one or more object recognition models to obtain corresponding object recognition results.
If a risk checking rule is used for checking whether the character recognition result contains risk keywords such as 'chess and card', 'gambling', 'small big' and the like, the risk checking rule is used for carrying out risk checking on the character recognition result to obtain a risk checking result indicating that the character recognition result contains the risk keywords such as 'chess and card', and the risk checking result can also contain coordinate information of the 'chess and card' character in a merchant image, and details are not repeated.
When the object recognition processing is performed on the merchant image, the first object recognition model may be used to recognize whether the merchant image includes an object related to drugs, and the second object recognition model may be used to recognize whether the merchant image includes an object related to gambling, so as to obtain an object recognition result based on the first object recognition model and the second object recognition model. Specifically, the object recognition result generated in this example may indicate that the merchant image includes an object related to gambling, or the object recognition result may indicate that the merchant image includes an object such as playing cards and dice.
The first object recognition model may be an object recognition model obtained by training an initial object recognition model by using images including objects related to drugs and images not including objects related to drugs as positive and negative training samples, respectively. The second object recognition model may be another object recognition model obtained by training the initial object recognition model using the image including the object related to the game and the image not including the object related to the game as positive and negative training samples. The object recognition model may be a two-class model or a multi-class model, which is not particularly limited.
If a risk checking rule is used for checking whether the object recognition result contains risk objects such as playing cards, dices, mahjong and the like, the risk checking rule is used for carrying out risk checking on the object recognition result, and a risk checking result indicating that the object recognition result contains the risk objects such as playing cards, dices and the like can be obtained.
Since the object recognition result may also include the position information of the "playing card" and the "dice" in the merchant image, for example, the position information of the "playing card" object may be: upper left corner coordinates (25,60), lower right corner coordinates (65, 20); the location information of a "die" may be: upper left corner coordinates (0,40), lower right corner coordinates (20, 25); the location information of the other "dice" may be: upper left corner coordinates (70,30), lower right corner coordinates (90,10), etc. The risk verification result may also include coordinate information of the "playing card" and the two "dice" in the merchant image.
In this embodiment, risk prompt information may be generated based on an image risk inspection result of the merchant image, so that a risk monitoring party performs risk control.
Specifically, step 106: the step of verifying the image processing result by using a risk verification rule to obtain an image risk verification result may further include:
generating risk prompt information according to at least one of the first risk test result and the second risk test result; the risk prompt information is used for prompting risk content existing in the merchant image and coordinate information of the risk content in the merchant image.
In practical application, if only the first risk verification result is generated, the risk content indicated by the risk indication information may refer to a risk keyword included in the merchant image. If only the second risk verification result is generated, the risk content prompted by the risk prompting information may refer to a risk object included in the merchant image. When the first risk test result and the second risk test result are generated, the risk content prompted by the risk prompting information may include both the risk keyword and the risk object, which is not described in detail again.
In this embodiment of the present specification, a risk keyword lexicon may be set for a risk checking rule used for checking a risk keyword included in a character recognition result, and then the checking whether the character recognition result includes the risk keyword using the risk checking rule may specifically include:
and utilizing the risk checking rule to check whether the character recognition result contains the risk keywords in the risk keyword lexicon corresponding to the risk checking rule.
In practical application, the risk keywords contained in the risk keyword thesaurus can be set according to practical requirements, for example, the risk keywords contained in the risk keyword thesaurus are added and deleted, and the like, so that the risk inspection rules are managed conveniently.
In this embodiment, a risk object library may be further set for a risk checking rule used for checking a risk object included in an object identification result, and then the checking whether the object identification result includes the risk object using the risk checking rule may specifically include:
and checking whether the risk object in the risk object library corresponding to the risk checking rule is contained in the object identification result by using the risk checking rule.
In practical application, the risk objects contained in the risk object library can be set according to practical requirements, for example, the risk objects contained in the risk object library are added and deleted, and the like, so that the risk inspection rules are managed conveniently.
After the risk object is newly added to the risk object library, the capability of using whether the merchant image contains the newly added risk object or not during the execution of the object identification operation is required, and specifically, the capability of identifying whether the merchant image contains the newly added risk object or not is required to be provided for the object identification model used for executing the object identification operation.
Therefore, if a risk object is newly added in the risk object library, the initial object recognition model can be trained by using the training sample corresponding to the newly added risk object, and the trained object recognition model is obtained.
Wherein the training samples corresponding to the newly added risk object may include: and the images containing the newly added risk objects and the images not containing the newly added risk objects are obtained, so that positive and negative training samples for training the presented object recognition model are obtained.
The processing the merchant image by using the preset image processing operation to obtain an image processing result may specifically include:
and if the preset image processing operation is the object recognition operation, performing object recognition processing on the merchant image by using the trained object recognition model to obtain an object recognition result indicating whether the merchant image contains the newly increased risk object. And using a historical object recognition model to perform object recognition processing on the merchant image to obtain an object recognition result which indicates whether the merchant image contains other risk objects in the risk object library.
Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method. Fig. 4 is a schematic structural diagram of a risk verification apparatus corresponding to one merchant image in fig. 1, which may be applied to a risk verification server according to an embodiment of the present disclosure. As shown in fig. 4, the apparatus may include:
a first obtaining module 402, configured to obtain identification information of a merchant image when performing risk check on the merchant image at a target website.
A second obtaining module 404, configured to obtain, according to a preset image processing result storage address, an image processing result having a corresponding relationship with the identification information; the image processing result is a processing result obtained by processing the merchant image by adopting a preset image processing operation in advance; the preset image processing operation is the image processing operation indicated by the preprocessing operation information of the application scene to which the merchant image belongs; the preset image processing operation at least comprises one of an optical character recognition operation and an object recognition operation.
And the checking module 406 is configured to check the image processing result by using a risk checking rule to obtain an image risk checking result.
The examples of this specification also provide some specific embodiments of the process based on the apparatus of fig. 4, which is described below.
Optionally, the apparatus in fig. 4 may further include:
the third acquisition module is used for acquiring the merchant image from the target website; the merchant image has identification information.
And the first determining module is used for determining preset image processing operation according to the preprocessing operation information of the application scene to which the merchant image belongs.
And the processing module is used for processing the merchant image by utilizing the preset image processing operation to obtain an image processing result.
The storage module is used for storing the corresponding relation information between the image processing result and the identification information and the image processing result to a distributed cache; the distributed cache is a cache corresponding to a preset image processing result storage address.
Optionally, the apparatus in fig. 4 may further include:
a second determination module to determine a risk verification rule for the merchant image.
The second obtaining module 402 may be specifically configured to:
and for each risk checking rule, determining a label of an image processing result required by the risk checking rule, wherein the label is used for identifying that the image processing result is a processing result obtained by processing an image by adopting a specified image processing operation.
And acquiring an image processing result which has a corresponding relation with the identification information and is provided with the label from a preset image processing result storage address.
Optionally, the checking module 406 may specifically include:
and the first checking unit is used for checking whether the character recognition result contains a risk keyword by using the risk checking rule if the acquired image processing result which has the corresponding relation with the identification information and the label is a character recognition result, so as to obtain a first risk checking result.
And the second checking unit is used for checking whether the object identification result contains a risk object or not by using the risk checking rule if the acquired image processing result which has the corresponding relation with the identification information and the label is the object identification result, so as to obtain a second risk checking result.
Optionally, the first risk test result may include: the risk keywords contained in the merchant image and the coordinate information of the risk keywords contained in the merchant image.
The second risk test result may include: the risk object contained in the merchant image and the coordinate information of the risk object contained in the merchant image.
Optionally, the apparatus in fig. 4 may further include:
the promotion information generation module is used for generating risk prompt information according to at least one of the first risk detection result and the second risk detection result; the risk prompt information is used for prompting risk content existing in the merchant image and coordinate information of the risk content in the merchant image.
Optionally, the second determining module may be specifically configured to:
and determining a risk checking rule set for the application scene to which the merchant image belongs.
Optionally, the second determining module may be specifically configured to:
and determining a risk checking rule having a corresponding relation with the target website from risk checking rules set for the application scene to which the merchant image belongs.
Optionally, the first inspection unit may be specifically configured to:
and utilizing the risk checking rule to check whether the character recognition result contains the risk keywords in the risk keyword lexicon corresponding to the risk checking rule.
Optionally, the apparatus in fig. 4 may further include:
and the first setting module is used for setting the risk keywords contained in the risk keyword thesaurus.
Optionally, the second inspection unit may be specifically configured to:
and checking whether the risk object in the risk object library corresponding to the risk checking rule is contained in the object identification result by using the risk checking rule.
Optionally, the apparatus in fig. 4 may further include:
and the second setting module is used for setting the risk objects contained in the risk object library.
Optionally, the apparatus in fig. 4 may further include:
and the model training unit is used for training the initial object recognition model by using a training sample corresponding to the newly increased risk object if the newly increased risk object is added in the risk object library to obtain a trained object recognition model.
The processing module may be specifically configured to:
and if the preset image processing operation is the object recognition operation, performing object recognition processing on the merchant image by using the trained object recognition model to obtain an object recognition result indicating whether the merchant image contains the newly increased risk object.
Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method.
Fig. 5 is a schematic structural diagram of a risk verification apparatus corresponding to one merchant image in fig. 1 provided in an embodiment of the present specification. As shown in fig. 5, 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 content of the first and second substances,
the memory 530 stores instructions 520 executable by the at least one processor 510 to enable the at least one processor 510 to:
when the risk of a merchant image at a target website is checked, acquiring the identification information of the merchant image.
Acquiring an image processing result corresponding to the identification information according to a preset image processing result storage address; the image processing result is a processing result obtained by processing the merchant image by adopting a preset image processing operation in advance; the preset image processing operation is the image processing operation indicated by the preprocessing operation information of the application scene to which the merchant image belongs; the preset image processing operation at least comprises one of an optical character recognition operation and an object recognition operation.
And checking the image processing result by using a risk checking rule to obtain an image risk checking result.
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, as for the verification device of merchant information shown in fig. 5, since it is basically similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
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 character system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate a dedicated integrated circuit chip. 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 functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that 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.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 the like) having computer-usable program code embodied therein.
The application 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 application 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 application 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 (27)
1. A risk checking method of a merchant image is applied to a risk checking server and comprises the following steps:
when risk inspection is carried out on a merchant image at a target website, acquiring identification information of the merchant image;
acquiring an image processing result corresponding to the identification information according to a preset image processing result storage address; the image processing result is a processing result obtained by processing the merchant image by adopting a preset image processing operation in advance; the preset image processing operation is the image processing operation indicated by the preprocessing operation information of the application scene to which the merchant image belongs; the preset image processing operation at least comprises one of an optical character recognition operation and an object recognition operation;
and checking the image processing result by using a risk checking rule to obtain an image risk checking result.
2. The method according to claim 1, before the obtaining of the image processing result having the corresponding relationship with the identification information, further comprising:
acquiring the merchant image from the target website; the merchant image has identification information;
determining preset image processing operation according to the preprocessing operation information of the application scene to which the merchant image belongs;
processing the merchant image by utilizing the preset image processing operation to obtain an image processing result;
storing the corresponding relation information between the image processing result and the identification information and the image processing result to a distributed cache; the distributed cache is a cache corresponding to a preset image processing result storage address.
3. The method according to claim 2, before acquiring the image processing result having the correspondence with the identification information according to the preset image processing result storage address, further comprising:
determining a risk verification rule for the merchant image;
the acquiring, according to a preset image processing result storage address, an image processing result having a correspondence with the identification information specifically includes:
for each risk checking rule, determining a label of an image processing result required by the risk checking rule, wherein the label is used for identifying that the image processing result is a processing result obtained by processing an image by adopting a specified image processing operation;
and acquiring an image processing result which has a corresponding relation with the identification information and is provided with the label from a preset image processing result storage address.
4. The method according to claim 3, wherein the verifying the image processing result by using a risk verification rule to obtain an image risk verification result specifically comprises:
and if the acquired image processing result which has the corresponding relation with the identification information and the label is a character recognition result, checking whether the character recognition result contains a risk keyword by using the risk checking rule to obtain a first risk checking result.
And if the acquired image processing result which has the corresponding relation with the identification information and the label is an object identification result, checking whether the object identification result contains a risk object by using the risk checking rule to obtain a second risk checking result.
5. The method of claim 4, the first risk test result comprising: the risk keywords contained in the merchant image and the coordinate information of the risk keywords contained in the merchant image;
the second risk test result comprises: the risk object contained in the merchant image and the coordinate information of the risk object contained in the merchant image.
6. The method of claim 5, wherein the verifying the image processing result using a risk verification rule further comprises, after obtaining an image risk verification result:
generating risk prompt information according to at least one of the first risk test result and the second risk test result; the risk prompt information is used for prompting risk content existing in the merchant image and coordinate information of the risk content in the merchant image.
7. The method according to claim 3, wherein the determining a risk verification rule for the merchant image specifically comprises:
and determining a risk checking rule set for the application scene to which the merchant image belongs.
8. The method according to claim 7, wherein the determining a risk verification rule for the merchant image specifically comprises:
and determining a risk checking rule having a corresponding relation with the target website from risk checking rules set for the application scene to which the merchant image belongs.
9. The method according to claim 4, wherein the verifying whether the character recognition result includes a risk keyword using the risk checking rule specifically includes:
and utilizing the risk checking rule to check whether the character recognition result contains the risk keywords in the risk keyword lexicon corresponding to the risk checking rule.
10. The method of claim 9, further comprising:
and setting the risk keywords contained in the risk keyword word bank.
11. The method according to claim 4, wherein the verifying whether the object identification result includes a risk object by using the risk verification rule specifically includes:
and checking whether the risk object in the risk object library corresponding to the risk checking rule is contained in the object identification result by using the risk checking rule.
12. The method of claim 11, further comprising:
setting the risk objects contained in the risk object library.
13. The method of claim 12, further comprising:
if a new risk object is added in the risk object library, training an initial object recognition model by using a training sample corresponding to the new risk object to obtain a trained object recognition model;
the processing the merchant image by using the preset image processing operation to obtain an image processing result specifically comprises:
and if the preset image processing operation is the object recognition operation, performing object recognition processing on the merchant image by using the trained object recognition model to obtain an object recognition result indicating whether the merchant image contains the newly increased risk object.
14. A risk verification device of a merchant image is applied to a risk verification server and comprises:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring identification information of a merchant image when the risk of the merchant image at a target website is checked;
the second acquisition module is used for acquiring an image processing result which has a corresponding relation with the identification information according to a preset image processing result storage address; the image processing result is a processing result obtained by processing the merchant image by adopting a preset image processing operation in advance; the preset image processing operation is the image processing operation indicated by the preprocessing operation information of the application scene to which the merchant image belongs; the preset image processing operation at least comprises one of an optical character recognition operation and an object recognition operation;
and the inspection module is used for inspecting the image processing result by using a risk inspection rule to obtain an image risk inspection result.
15. The apparatus of claim 14, further comprising:
the third acquisition module is used for acquiring the merchant image from the target website; the merchant image has identification information;
the first determining module is used for determining preset image processing operation according to the preprocessing operation information of the application scene to which the merchant image belongs;
the processing module is used for processing the merchant image by utilizing the preset image processing operation to obtain an image processing result;
the storage module is used for storing the corresponding relation information between the image processing result and the identification information and the image processing result to a distributed cache; the distributed cache is a cache corresponding to a preset image processing result storage address.
16. The apparatus of claim 15, further comprising:
a second determination module for determining a risk verification rule for the merchant image;
the second obtaining module is specifically configured to:
for each risk checking rule, determining a label of an image processing result required by the risk checking rule, wherein the label is used for identifying that the image processing result is a processing result obtained by processing an image by adopting a specified image processing operation;
and acquiring an image processing result which has a corresponding relation with the identification information and is provided with the label from a preset image processing result storage address.
17. The apparatus according to claim 16, wherein the inspection module comprises:
the first checking unit is used for checking whether the character recognition result contains a risk keyword or not by using the risk checking rule if the acquired image processing result which has a corresponding relation with the identification information and the label is a character recognition result, so as to obtain a first risk checking result;
and the second checking unit is used for checking whether the object identification result contains a risk object or not by using the risk checking rule if the acquired image processing result which has the corresponding relation with the identification information and the label is the object identification result, so as to obtain a second risk checking result.
18. The apparatus of claim 17, the first risk test result comprising: the risk keywords contained in the merchant image and the coordinate information of the risk keywords contained in the merchant image;
the second risk test result comprises: the risk object contained in the merchant image and the coordinate information of the risk object contained in the merchant image.
19. The apparatus of claim 18, further comprising:
the promotion information generation module is used for generating risk prompt information according to at least one of the first risk detection result and the second risk detection result; the risk prompt information is used for prompting risk content existing in the merchant image and coordinate information of the risk content in the merchant image.
20. The apparatus of claim 16, wherein the second determining module is specifically configured to:
and determining a risk checking rule set for the application scene to which the merchant image belongs.
21. The apparatus of claim 20, wherein the second determining module is specifically configured to:
and determining a risk checking rule having a corresponding relation with the target website from risk checking rules set for the application scene to which the merchant image belongs.
22. The apparatus of claim 17, the first inspection unit, in particular to:
and utilizing the risk checking rule to check whether the character recognition result contains the risk keywords in the risk keyword lexicon corresponding to the risk checking rule.
23. The apparatus of claim 22, further comprising:
and the first setting module is used for setting the risk keywords contained in the risk keyword thesaurus.
24. The apparatus of claim 17, the second inspection unit, in particular to:
and checking whether the risk object in the risk object library corresponding to the risk checking rule is contained in the object identification result by using the risk checking rule.
25. The apparatus of claim 24, further comprising:
and the second setting module is used for setting the risk objects contained in the risk object library.
26. The apparatus of claim 25, further comprising:
the model training unit is used for training an initial object recognition model by using a training sample corresponding to the newly increased risk object if the newly increased risk object is added in the risk object library to obtain a trained object recognition model;
the processing module is specifically configured to:
and if the preset image processing operation is the object recognition operation, performing object recognition processing on the merchant image by using the trained object recognition model to obtain an object recognition result indicating whether the merchant image contains the newly increased risk object.
27. A risk verification device for a merchant 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 content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
when risk inspection is carried out on a merchant image at a target website, acquiring identification information of the merchant image;
acquiring an image processing result corresponding to the identification information according to a preset image processing result storage address; the image processing result is a processing result obtained by processing the merchant image by adopting a preset image processing operation in advance; the preset image processing operation is the image processing operation indicated by the preprocessing operation information of the application scene to which the merchant image belongs; the preset image processing operation at least comprises one of an optical character recognition operation and an object recognition operation;
and checking the image processing result by using a risk checking rule to obtain an image risk checking result.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211132148.1A CN115511278A (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for risk detection of merchant image |
| CN202010963356.0A CN112001662B (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for risk detection of merchant image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010963356.0A CN112001662B (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for risk detection of merchant image |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211132148.1A Division CN115511278A (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for risk detection of merchant image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112001662A true CN112001662A (en) | 2020-11-27 |
| CN112001662B CN112001662B (en) | 2022-08-30 |
Family
ID=73468623
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211132148.1A Pending CN115511278A (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for risk detection of merchant image |
| CN202010963356.0A Active CN112001662B (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for risk detection of merchant image |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211132148.1A Pending CN115511278A (en) | 2020-09-14 | 2020-09-14 | Method, device and equipment for risk detection of merchant image |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN115511278A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140307966A1 (en) * | 2013-04-12 | 2014-10-16 | Samsung Electronics Co., Ltd. | Method of managing image and electronic device thereof |
| US20150268913A1 (en) * | 2014-03-19 | 2015-09-24 | Fuji Xerox Co., Ltd. | Image processing system, image processing device, and processing control device |
| US20170256023A1 (en) * | 2016-03-02 | 2017-09-07 | Alibaba Group Holding Limited | Solid state storage local image processing system and method |
| CN107292808A (en) * | 2016-03-31 | 2017-10-24 | 阿里巴巴集团控股有限公司 | Image processing method, device and image coprocessor |
| CN108491825A (en) * | 2018-03-30 | 2018-09-04 | 百度在线网络技术（北京）有限公司 | information generating method and device |
| CN109377240A (en) * | 2018-08-21 | 2019-02-22 | 中国平安人寿保险股份有限公司 | Trade company's management method, device, computer equipment and storage medium neural network based |
| CN110163204A (en) * | 2019-04-15 | 2019-08-23 | 平安国际智慧城市科技股份有限公司 | Businessman's monitoring and managing method, device and storage medium based on image recognition |
| CN110188717A (en) * | 2019-06-03 | 2019-08-30 | 中国通信建设第四工程局有限公司 | Image acquiring method and device |
| JP2019159629A (en) * | 2018-03-12 | 2019-09-19 | 富士ゼロックス株式会社 | Information processing system, information processing apparatus, and information processing program |
| CN110472981A (en) * | 2019-07-05 | 2019-11-19 | 中国平安人寿保险股份有限公司 | The recognition methods of risk order, device, computer equipment and storage medium |
| CN110543582A (en) * | 2019-08-05 | 2019-12-06 | 百度在线网络技术（北京）有限公司 | image-based query method and device |
| CN111078900A (en) * | 2019-11-19 | 2020-04-28 | 口碑(上海)信息技术有限公司 | Data risk identification method and system |
| CN111241367A (en) * | 2019-12-27 | 2020-06-05 | 航天信息股份有限公司 | Method and system for supervising network catering platform based on custom rule |
| CN111539739A (en) * | 2020-05-06 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Risk detection method, device and equipment |
-
2020
- 2020-09-14 CN CN202211132148.1A patent/CN115511278A/en active Pending
- 2020-09-14 CN CN202010963356.0A patent/CN112001662B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140307966A1 (en) * | 2013-04-12 | 2014-10-16 | Samsung Electronics Co., Ltd. | Method of managing image and electronic device thereof |
| US20150268913A1 (en) * | 2014-03-19 | 2015-09-24 | Fuji Xerox Co., Ltd. | Image processing system, image processing device, and processing control device |
| US20170256023A1 (en) * | 2016-03-02 | 2017-09-07 | Alibaba Group Holding Limited | Solid state storage local image processing system and method |
| CN107292808A (en) * | 2016-03-31 | 2017-10-24 | 阿里巴巴集团控股有限公司 | Image processing method, device and image coprocessor |
| JP2019159629A (en) * | 2018-03-12 | 2019-09-19 | 富士ゼロックス株式会社 | Information processing system, information processing apparatus, and information processing program |
| CN108491825A (en) * | 2018-03-30 | 2018-09-04 | 百度在线网络技术（北京）有限公司 | information generating method and device |
| CN109377240A (en) * | 2018-08-21 | 2019-02-22 | 中国平安人寿保险股份有限公司 | Trade company's management method, device, computer equipment and storage medium neural network based |
| CN110163204A (en) * | 2019-04-15 | 2019-08-23 | 平安国际智慧城市科技股份有限公司 | Businessman's monitoring and managing method, device and storage medium based on image recognition |
| CN110188717A (en) * | 2019-06-03 | 2019-08-30 | 中国通信建设第四工程局有限公司 | Image acquiring method and device |
| CN110472981A (en) * | 2019-07-05 | 2019-11-19 | 中国平安人寿保险股份有限公司 | The recognition methods of risk order, device, computer equipment and storage medium |
| CN110543582A (en) * | 2019-08-05 | 2019-12-06 | 百度在线网络技术（北京）有限公司 | image-based query method and device |
| CN111078900A (en) * | 2019-11-19 | 2020-04-28 | 口碑(上海)信息技术有限公司 | Data risk identification method and system |
| CN111241367A (en) * | 2019-12-27 | 2020-06-05 | 航天信息股份有限公司 | Method and system for supervising network catering platform based on custom rule |
| CN111539739A (en) * | 2020-05-06 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Risk detection method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115511278A (en) | 2022-12-23 |
| CN112001662B (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113886584A (en) | Information detection method, device and equipment for application program | |
| TWI743773B (en) | Method and device for identifying abnormal collection behavior based on privacy data protection | |
| CN109190007B (en) | Data analysis method and device | |
| US20180349781A1 (en) | Method and device for judging news quality and storage medium | |
| CN110263161B (en) | Information processing method, device and equipment | |
| CN109408829B (en) | Method, device, equipment and medium for determining readability of article | |
| CN111353488B (en) | Method, device and equipment for identifying risks in code image | |
| CN110781925B (en) | Software page classification method and device, electronic equipment and storage medium | |
| CN114648392B (en) | Product recommendation method and device based on user portrait, electronic equipment and medium | |
| CN110569502A (en) | Method and device for identifying forbidden slogans, computer equipment and storage medium | |
| CN112015869A (en) | Risk detection method, device and equipment for text to be issued | |
| CN113222022A (en) | Webpage classification identification method and device | |
| CN113051910B (en) | Method and device for predicting emotion of persona | |
| CN112200402B (en) | Risk quantification method, device and equipment based on risk portrait | |
| CN111985936A (en) | Method, device and equipment for checking merchant certificate information | |
| CN112001662B (en) | Method, device and equipment for risk detection of merchant image | |
| CN113837772A (en) | Method, device and equipment for auditing marketing information | |
| CN115525750A (en) | Robot phonetics detection visualization method and device, electronic equipment and storage medium | |
| CN111046658B (en) | Method, device and equipment for recognizing disorder text | |
| CN111985935A (en) | Method, device and equipment for checking merchant information | |
| CN114546553A (en) | Information display method, device, equipment and medium | |
| CN113949887A (en) | Method and device for processing network live broadcast data | |
| Zhao et al. | Multi-modal sarcasm generation: Dataset and solution | |
| CN112613891B (en) | Shop registration information verification method, device and equipment | |
| Dugar et al. | From pixels to words: A scalable journey of text information from product images to retail catalog |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |