Card application method and apparatus, and device, medium and product

Abstract

The present application belongs to the technical field of financial services. Disclosed are a card application method and apparatus, and a device, a medium and a product. The method comprises: acquiring a card face image generation request sent by a user terminal, wherein the card face image generation request comprises card face description content input by a user on a card application interface of the user terminal; on the basis of the card face image generation request, generating a card face image matching the card face description content; performing character copyright infringement detection on a character element in the card face image, so as to obtain a detection result; when the detection result indicates that the card face image causes copyright infringement, feeding copyright infringement prompt information back to the user terminal, wherein the copyright infringement prompt information is used for prompting the user to regenerate a card face image; and when the detection result indicates that the card face image does not cause copyright infringement, submitting a card application request to a financial end, so that the financial end uses the card face image in the card application request to perform card application.

Description

Card activation methods, devices, equipment, media and products

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application 202311001097.3, filed on August 9, 2023, entitled “Card Activation Method, Device, Equipment, Medium and Product,” the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application belongs to the field of financial services technology, and in particular relates to a card opening method, device, equipment, medium and product. Background Art

[0004] As people's living standards improve, more and more users are emphasizing personalized customization, hoping that their cards reflect their individuality and taste. This demand for personalized cards is growing, and the content of card customization is also becoming more diverse and personalized. Therefore, combining card issuance technology with personalized card customization services has become an inevitable trend. This approach not only leverages the rich creativity of card issuance models to meet users' aesthetic needs, but also reduces the cost of personalized card design, gaining a competitive advantage.

[0005] In related technologies, card images often contain unauthorized cartoon characters, which can easily bring infringement risks to users and banks. Once the card image is determined to be infringing, the card opening will usually fail.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide a card activation method, apparatus, device, medium, and product, which can solve the problem of user card activation failure due to card image infringement during card activation.

[0008] In a first aspect, an embodiment of the present application provides a card activation method, applied to an image generation platform, the method comprising:

[0009] Obtaining a card image generation request sent by a user terminal, wherein the card image generation request includes the card description content entered by the user on the card activation interface of the user terminal;

[0010] Generate a card image that matches the card description based on the card image generation request;

[0011] Perform image infringement detection on the image elements in the card image and obtain the detection results;

[0012] If the detection result indicates that the card image is infringing, an infringement prompt message is fed back to the user terminal, prompting the user to regenerate the card image;

[0013] When the detection result indicates that the card image is not infringing, a card activation request is submitted to the financial end so that the financial end can activate the card using the card image in the card activation request.

[0014] In a second aspect, an embodiment of the present application provides a card opening device, the device comprising:

[0015] an acquisition module, configured to acquire a card face image generation request sent by a user terminal, wherein the card face image generation request includes the card face description content input by the user in the card activation interface of the user terminal;

[0016] A generation module, configured to generate a card image matching the card description based on a card image generation request;

[0017] A detection module, configured to detect image infringement of image elements in the card image and obtain a detection result;

[0018] A feedback module, configured to provide a feedback message to the user terminal when the detection result indicates that the card image is infringing. The feedback message is used to prompt the user to regenerate the card image.

[0019] The card activation module is used to submit a card activation request to the financial end when the detection result indicates that the card image is not infringing, so that the financial end can use the card image in the card activation request to activate the card.

[0020] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the steps of the card activation method shown in the first aspect are implemented.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the card activation method shown in the first aspect are implemented.

[0022] In a fifth aspect, an embodiment of the present application provides a computer program product, which is stored in a non-volatile storage medium. When the computer program product is executed by at least one processor, it implements the steps of the card activation method shown in the first aspect.

[0023] In a sixth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the steps of the card activation method as in the first aspect.

[0024] Embodiments of the present application provide a card activation method, apparatus, device, medium, and product. When a user needs to activate a card, an image generation platform can obtain a card image generation request sent by a user terminal. The card image generation request includes the card description entered by the user on the card activation interface of the user terminal. Based on the card image generation request, a card image matching the card description can be generated. Furthermore, after generating the card image, the image generation platform can directly detect image infringement on the image elements in the card image and obtain a detection result. If the detection result indicates that the card image is infringing, the image generation platform can provide an infringement prompt to the user terminal, prompting the user to regenerate the card image. This prevents card activation failures when submitting a development request to a financial institution. The platform can then submit a card activation request to the financial institution only if the detection result indicates that the card image is not infringing. This ensures that the card image included in the card activation request is non-infringing, thereby ensuring that the financial institution successfully activates the card using the card image in the card activation request, thus preventing card activation failures for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0026] FIG1 is a schematic diagram of an example of an application scenario of a card activation method provided in an embodiment of the present application;

[0027] FIG2 is a flow chart of an embodiment of a card activation method provided in the first aspect of the present application;

[0028] FIG3 is an exemplary schematic diagram of a card surface image provided in the first aspect of the present application;

[0029] FIG4 is a flow chart of another embodiment of the card activation method provided in the first aspect of the present application;

[0030] FIG5 is a flow chart of another embodiment of the card activation method provided in the first aspect of the present application;

[0031] FIG6 is a flowchart of another embodiment of the card activation method provided in the first aspect of the present application;

[0032] FIG7 is a flowchart of another embodiment of the card activation method provided in the first aspect of the present application;

[0033] FIG8 is a schematic structural diagram of an embodiment of a card opening device provided in the second aspect of the present application;

[0034] FIG9 is a schematic structural diagram of an embodiment of an electronic device provided in the third aspect of this application. DETAILED DESCRIPTION

[0035] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0036] As people's living standards improve, more and more users are emphasizing personalized customization, hoping that their cards reflect their individuality and taste. This demand for personalized cards is growing, and the content of card customization is also becoming more diverse and personalized. Therefore, integrating card issuance technology with card customization services has become an inevitable trend. This approach not only leverages the rich creativity of card issuance models to meet users' aesthetic needs, but also reduces the cost of personalized card design and gains a competitive advantage. In related technologies, card images often contain unauthorized anime characters, which can easily pose infringement risks to users and banks. If the card image is determined to be infringing, the issuance of the card will usually fail.

[0037] To address the aforementioned issues, embodiments of the present application provide a card activation method, apparatus, device, medium, and product. When a user requests card activation, an image generation platform can obtain a card image generation request sent by a user terminal. The card image generation request includes the card description entered by the user on the card activation interface of the user terminal. Based on the card image generation request, a card image matching the card description can be generated based on the card image generation request. Furthermore, after generating the card image, the image generation platform can directly perform image infringement detection on the image elements in the card image to obtain a detection result. If the detection result indicates that the card image is infringing, the image generation platform can provide an infringement prompt to the user terminal, prompting the user to regenerate the card image. This prevents card activation failures when submitting a development request to the financial institution. The platform can then submit a card activation request to the financial institution only if the detection result indicates that the card image is not infringing. This ensures that the card image included in the card activation request is non-infringing, thereby ensuring that the financial institution successfully activates the card using the card image in the card activation request, thus preventing card activation failures for users.

[0038] The card activation method in the embodiment of the present application can be applied to the card activation scenario. The development method may involve a user terminal, an image generation platform and a financial terminal. The card activation architecture in the embodiment of the present application is described in detail below in conjunction with Figure 1.

[0039] FIG1 is a schematic diagram of an architecture of an example of an application scenario of a card activation method provided in an embodiment of the present application.

[0040] As shown in FIG1 , the architecture system of the card activation method may include a user terminal 11 , an image generation platform 12 and a financial terminal 13 .

[0041] The user terminal 11 is configured to receive a user's input for editing a card image, obtain a card description input by the user in response to the input, and generate a card image generation request based on the card description, thereby causing the image generation platform to generate a card image that matches the card image generation request. The user terminal 11 may be a terminal device, specifically a mobile phone, a tablet computer, a smart wearable device, etc., and the specific type of user terminal 11 is not limited herein.

[0042] The image generation platform 12 is configured to receive a card image generation request from the user terminal 11, generate a card image based on the card image generation request, and then perform image infringement detection on the card image. The image generation platform 12 can be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0043] The financial terminal 13 is used to provide card opening services, complete the financial card opening review and subsequent processes. The financial terminal 13 can be the backend service system of the card opening institution. The backend service system can include at least one server. For example, the backend service system can be an independent server, or a server cluster composed of multiple servers.

[0044] The card activation method provided in the embodiment of the present application is described in detail below with reference to specific embodiments in conjunction with the accompanying drawings.

[0045] In a first aspect, the present application provides a card activation method, which can be applied to the image generation platform 12, that is, the card activation method can be executed by the image generation platform 12. It should be noted that the above execution entity does not constitute a limitation on the present application.

[0046] FIG2 is a flow chart of an embodiment of a card activation method provided in the first aspect of the present application. As shown in FIG2 , the card activation method may include steps 210 to 250.

[0047] Step 210: Obtain a card image generation request sent by the user terminal, wherein the card image generation request includes the card description content entered by the user in the card activation interface of the user terminal;

[0048] Step 220: Generate a card image that matches the card description based on the card image generation request;

[0049] Step 230: Perform image infringement detection on the image elements in the card image to obtain a detection result;

[0050] Step 240: If the detection result indicates that the card image is infringing, feedback is given to the user terminal regarding infringement prompt information, which prompts the user to regenerate the card image.

[0051] Step 250: If the detection result indicates that the card image is not infringing, a card activation request is submitted to the financial end, so that the financial end activates the card using the card image in the card activation request.

[0052] In the card activation method provided by the embodiments of the present application, when a user needs to activate a card, an image generation platform can obtain a card image generation request sent by a user terminal. The card image generation request includes the card description entered by the user on the card activation interface of the user terminal. Based on the card image generation request, a card image matching the card description can be generated. Furthermore, after generating the card image, the image generation platform can directly perform image infringement detection on the image elements in the card image to obtain a detection result. If the detection result indicates that the card image is infringing, the image generation platform can provide an infringement prompt to the user terminal, prompting the user to regenerate the card image. This avoids card activation failures when submitting a development request to the financial institution. The platform can then submit a card activation request to the financial institution only if the detection result indicates that the card image is not infringing. This ensures that the card image included in the card activation request is non-infringing, thereby ensuring that the financial institution will successfully activate the card using the card image in the card activation request, thus avoiding card activation failures for users.

[0053] The specific implementation of the above steps is described in detail below in conjunction with the embodiments, as shown below.

[0054] Involving step 210, a card surface image generation request sent by a user terminal is obtained.

[0055] In step 210, a card face image generation request is used to generate a card face image for a financial card during the card activation process. The card face image generation request is generated based on the card face description content and carries the card face description content. The card face description content can be the user's description of the card face image, which is used to describe the card face style of the generated financial card. Therefore, the image generation platform can generate a card face in the style desired by the user based on the card face description content.

[0056] Specifically, the card face description content may include at least one keyword, and the keyword is used to describe the card face body, card face background, card face details, card face style, etc.

[0057] For example, the card description content may be, for example, "a cartoon image of a little white rabbit holding a carrot, with a grassy background."

[0058] In some embodiments, the user may also input the user information of the card opening user in the card opening interface of the user terminal so as to open a card for the user according to the user information.

[0059] In some embodiments, the card activation interface can be the application interface of the Cloud QuickPass application, which can provide users with card benefit customization and financial card face customization services, collect personal information required by users, and feedback the card activation results to users after the card activation is completed.

[0060] In step 220 , based on the card surface image generation request, a card surface image matching the card surface description content is generated.

[0061] In step 220, the card face image generation request carries the card face description content, so the image generation platform can customize the card face image based on the card face description content and generate a card face image that matches the card face description content. The card face image is the card face of the financial card.

[0062] For example, the card description content may be "a cartoon image of a potato, smiling with its tongue sticking out, and having two hands". The image generation platform may generate a card image as shown in FIG3 based on the card description content.

[0063] In some embodiments of the present application, the card face image generation request may also include the card face version, card face background and card face style selected by the user in the card opening interface of the user terminal. In this way, the card face image can be generated based on the card face version, card face style, card face background and card face description content.

[0064] Specifically, the card activation interface may provide a plurality of preset card face versions, card face backgrounds and card face styles for the user to choose from, and the user may select and input the desired card face version, card face background and card face style.

[0065] For example, the card surface versions may include horizontal and vertical cards, the card surface backgrounds may include starry sky, forest, grassland, mountain range, river, blue sky, etc., and the card surface styles may include realistic style, cyberpunk style, pixel style, etc.

[0066] In an embodiment of the present application, in addition to entering the card face description content in the card opening interface, the user can also flexibly select the card face version, card face background and card face style, providing users with more diverse customization options, improving the diversity and flexibility of the card face image generation method, and at the same time providing users with a more personalized, technologically advanced and interactive card customization service.

[0067] In some embodiments, the image generation platform can filter the card description content before generating the card image, remove violent, pornographic, politically sensitive words, etc., and obtain the card description content that meets the requirements, so as to generate a card image that matches the card description content that meets the requirements.

[0068] In some embodiments of the present application, the above step 220 of generating a card image that matches the card description may specifically include the following steps:

[0069] Parse the card image generation request to obtain the card description content;

[0070] By inputting the card surface description content into the diffusion model, a card surface image matching the card surface description content is generated.

[0071] Among them, the diffusion model is an image generation model used to generate card surface images, and the image generation model is the Stable Diffusion model of the AI ​​painting generation tool.

[0072] Therefore, the Stable Diffusion model can process text input and image input of various types and styles. By inputting card surface description content into the Stable Diffusion model, the Stable Diffusion model can be used to generate images of the card surface description content while avoiding common image generation problems such as blur, artifacts, repetition, and unnaturalness, thereby obtaining high-quality and highly stable card surface images.

[0073] In step 230 , image infringement detection is performed on the image elements in the card surface image to obtain a detection result.

[0074] In step 230, the image element is the main image in the card surface image. The card surface image may include at least one image element. For example, in FIG3, the "potato cartoon image" is an image element.

[0075] In some embodiments, the image generation platform may also perform violation detection on the card surface image in step 230 to detect whether the card surface image contains any illegal image content such as violence, pornography, or political sensitivity.

[0076] In related technologies, the same cartoon character may have different color versions, and color changes have a significant impact on the accuracy of infringement detection.

[0077] In some embodiments of the present application, in order to reduce the impact of color change on the accuracy of infringement detection, Figure 4 is a flowchart of another embodiment of the card activation method provided by the first aspect of the present application, and step 230 may include steps 410-430 shown in Figure 4.

[0078] Step 410, identifying the area to be detected where the image element is located in the card image;

[0079] Step 420 , converting the area to be detected into a first stick figure image in a stick figure style;

[0080] Step 430: Perform image infringement detection on the image elements in the first stick figure image to obtain a detection result.

[0081] In the embodiment of the present application, before performing image infringement detection on the image elements, by converting the image elements into a stick figure style, the impact of color change on the infringement detection accuracy can be reduced, thereby improving the reliability of infringement detection.

[0082] In some embodiments of the present application, the step 410 of identifying the area to be detected where the image element is located in the card image may specifically include:

[0083] Based on the target detection algorithm Faster RCNN, locate the ROI region of interest where the image elements in the card image are located;

[0084] The ROI area is expanded to obtain the area to be detected.

[0085] Specifically, the image generation platform uses the target detection algorithm (Faster Region-CNN, Faster R-CNN) to identify the preliminary position area of ​​the image elements in the card image, and records the preliminary position area as the region of interest (ROI), ROI = [(xroimin, yroimin), (xroimax, yroimax)].

[0086] The image generation platform performs area expansion processing with the preliminary position area ROI of the image element as the center to obtain the candidate position area of ​​each card surface element, and records the candidate position area as ROIE, ROIE = [(xroimin-a, yroimin-a), (xroimax+a, yroimax+a)], where a is a variable parameter set according to actual use, which can be set specifically according to needs, and this application does not make specific limitations on this.

[0087] In this embodiment of the present application, the region of interest of the image element is expanded to ensure that the image element is completely contained in the area to be detected. Based on this, when performing image infringement detection on the image element in the area to be detected, it is possible to ensure that the feature detection of the image element is not missed, thereby improving the reliability of image infringement detection.

[0088] In some embodiments, the target detection algorithm may also be You Look once (abbreviated as yolo).

[0089] In related technologies, the complex background near the image elements has a significant impact on the accuracy of infringement detection.

[0090] In some embodiments of the present application, in order to reduce the impact of the complex background near the image elements on the accuracy of infringement detection, Figure 5 is a flowchart of another embodiment of the card opening method provided by the first aspect of the present application. As shown in Figure 5, after step 410 and before step 420, the method may further include steps 510 and 520.

[0091] Step 510, performing foreground segmentation on the area to be detected to obtain a foreground area and a background area;

[0092] Step 520: Adjust the pixel values ​​of the pixels in the background area to preset pixel values.

[0093] Specifically, the image generation platform can perform foreground segmentation on the detection area based on an image segmentation algorithm to separate the foreground and background. The image segmentation algorithm can be GrabCut. The preset pixel value can be set according to specific needs, for example, to zero (black), to 255 (white), or to other values, and this application does not impose specific limitations on this.

[0094] In the embodiment of this application, Faster RCNN is first used to locate the type and preliminary location of the image element in the card image. Then, by expanding and segmenting the preliminary location, the image element is separated from the background area. Furthermore, by setting the pixels in the background area to preset pixel values, the background area is further clearly demarcated from the image element, and the precise boundary location of the image element is determined. This way, even if there is a complex background near the image element, the pixel values ​​can be adjusted to reduce the impact of the complex background on the accuracy of infringement detection, thereby improving the reliability and accuracy of infringement detection.

[0095] In some embodiments of the present application, step 420 of converting the area to be detected into a first stick figure image in a stick figure style may specifically include:

[0096] The image style conversion process is performed on the to-be-detected area based on the conditional adversarial generation network to obtain a first stick figure image.

[0097] Specifically, the image portion corresponding to the area to be detected can be input into the conditional adversarial generation network, so as to perform style conversion on the image portion.

[0098] For example, by inputting an image 601 into a conditional adversarial generative network, style conversion can be performed on it to obtain a first stick figure image 602 in a stick figure style.

[0099] In the embodiment of the present application, since the converted image is in a stick figure style, it is possible to extract the main contour features of the image and eliminate the influence of the color change of the cartoon image on the detection process, thereby improving the accuracy of subsequent infringement detection using image features.

[0100] In some embodiments, the CAGN can include a generator and a discriminator. In the generator, a random input z is taken from a pre-set random distribution and concatenated with the conditional input y to form a new implicit representation. In the discriminator, both real data x and generated data G(z) are input along with the conditional input y for discrimination. After cGAN training is complete, the generator G is used to process the input image.

[0101] In some embodiments of the present application, step 430 of performing image infringement detection on the image elements in the first stick figure image may specifically include:

[0102] Extracting a first image feature from the first stick figure image based on the SURF algorithm, and matching the first image feature with a second image feature of a preset image in the infringement database to obtain a number of feature matches between the first stick figure image and the preset image;

[0103] Screening preset image images whose number of feature matches with the first stick figure image is greater than a preset matching threshold as potential infringing objects;

[0104] An infringement analysis is performed on the first stick figure image based on the potential infringing object to obtain a detection result.

[0105] Specifically, if a first stick figure image corresponds to multiple first image features, and if multiple image features in the same preset image match multiple first image features, then the preset image may be determined to be a potential infringing object if the number of feature matches exceeds a preset matching threshold. The preset matching threshold can be set based on specific needs, for example, to 75%, 85%, or other values, and this application does not impose specific limitations on this.

[0106] Optionally, when there is at least one potential infringing object, the target potential infringing object with the largest number of corresponding feature matches can be directly selected, and the target potential infringing object can be used as the infringing object, and the detection result of "card surface image infringement" can be output; or, the list of potential infringing objects can be directly output for manual review, and the manual review can confirm whether there is an infringing object in the list of potential infringing objects and whether there is infringement in the card surface image.

[0107] In other embodiments of the present application, the location of the image elements can be identified after the style conversion of the card surface image. Figure 7 is a flowchart of another embodiment of the card opening method provided by the first aspect of the present application. Step 230 may include steps 710-730 shown in Figure 7.

[0108] Step 710, converting the card surface image into a second stick figure image in a stick figure style;

[0109] Step 720 , identifying the area to be detected where the image element is located in the second stick figure image;

[0110] Step 730: Perform image infringement detection on the image elements in the detection area to obtain a detection result.

[0111] Specifically, a card surface image can be input into the conditional adversarial generation network, so as to perform style conversion on the card surface image and obtain a second stick figure image in the style of a stick figure; then the image generation platform uses the target detection algorithm to identify the RIO area where the image elements in the second stick figure image are located, and expands the ROI area to obtain the area to be detected; the foreground of the area to be detected is segmented to obtain the foreground area and the background area; the pixel values ​​of the pixels in the background area are adjusted to preset pixel values; the image elements in the area to be detected are detected for image infringement to obtain the detection results.

[0112] In step 240, when the detection result indicates that the card image is infringing, infringement prompt information is fed back to the user terminal.

[0113] In step 240, if the generated card image contains infringement, infringement prompt information is fed back to the user terminal, prompting the user to modify and adjust the card description content, so as to re-receive the card image generation request sent by the user terminal and re-execute the image generation process until a card image with no infringement or violation of the image content is generated.

[0114] In some embodiments, the infringement prompt information may include an infringing image corresponding to the card image, so that the user can adjust and modify the card image with reference to the infringing image to prevent the modified card image from continuing to infringe the rights.

[0115] In step 250, when the detection result indicates that the card image is not infringing, a card activation request is submitted to the financial end, so that the financial end uses the card image in the card activation request to activate the card.

[0116] In step 250, the card activation request may include card activation user information. The financial end may activate the card based on the card activation user information, obtain a financial card with a card face image and card face style, and complete the card activation process.

[0117] In some embodiments of the present application, if the detection result indicates that the card image is not infringing, step 250 submits a card activation request to the financial end, which may specifically include the following steps:

[0118] If the detection result indicates that the card image is not infringing, a confirmation request carrying the card image is sent to the user terminal, where the confirmation request is used to instruct the user to confirm the card image;

[0119] When a confirmation message is received from the user terminal, a card activation request is submitted to the financial terminal so that the financial terminal activates the card using the card image in the card activation request.

[0120] In an embodiment of the present application, a confirmation request is returned to the user terminal, instructing the user to confirm the card face image generated by the image generation platform. Since the card face image is usually unchangeable, this confirmation operation can ensure that the user can check the image effect of the card face image and ensure that the card face after activation can meet the user's needs.

[0121] Based on the same inventive concept, the second aspect of the present application provides a card opening device. FIG8 is a structural diagram of an embodiment of the card opening device provided by the second aspect of the present application.

[0122] As shown in FIG. 8 , the card opening device 800 may specifically include: an acquisition module 810 , a generation module 820 , a detection module 830 , a feedback module 840 and a card opening module 850 .

[0123] The acquisition module 810 is configured to acquire a card image generation request sent by a user terminal, wherein the card image generation request includes the card description content input by the user in the card activation interface of the user terminal;

[0124] A generating module 820 is configured to generate a card image matching the card description based on the card image generation request;

[0125] A detection module 830 is used to detect image infringement of image elements in the card image and obtain a detection result;

[0126] Feedback module 840, configured to provide infringement prompt information to the user terminal when the detection result indicates that the card image is infringing. The infringement prompt information is used to prompt the user to regenerate the card image;

[0127] The card activation module 850 is used to submit a card activation request to the financial end when the detection result indicates that the card image is not infringing, so that the financial end can activate the card using the card image in the card activation request.

[0128] In the card activation device provided in an embodiment of the present application, when a user needs to activate a card, an image generation platform can obtain a card image generation request sent by a user terminal. The card image generation request includes the card description entered by the user on the card activation interface of the user terminal. Based on the card image generation request, a card image matching the card description can be generated. Furthermore, after generating the card image, the image generation platform can directly perform image infringement detection on the image elements in the card image to obtain a detection result. If the detection result indicates that the card image is infringing, the image generation platform can provide an infringement prompt to the user terminal, prompting the user to regenerate the card image. This avoids card activation failures when submitting a development request to the financial institution. If the detection result indicates that the card image is not infringing, the card activation request can be submitted to the financial institution, ensuring that the card image included in the card activation request is non-infringing. This ensures that the financial institution will successfully activate the card using the card image in the card activation request, thus avoiding card activation failures for users.

[0129] In some embodiments of the present application, the detection module 830 includes: an identification unit for identifying the area to be detected where the image elements in the card surface image are located; a style conversion unit for converting the area to be detected into a first stick figure image in a stick figure style; and an infringement detection unit for performing image infringement detection on the image elements in the first stick figure image to obtain a detection result.

[0130] In some embodiments of the present application, the recognition unit includes: a positioning subunit, which is used to locate the ROI area of ​​interest where the image elements in the card image are located based on the target detection algorithm FasterRCNN; and a region expansion unit, which is used to expand the ROI area to obtain the area to be detected.

[0131] In some embodiments of the present application, the device also includes: a foreground segmentation module, which is used to perform foreground segmentation on the area to be detected after obtaining the area to be detected and before converting the area to be detected into a first stick figure image in a stick figure style, so as to obtain a foreground area and a background area; and a pixel adjustment module, which is used to adjust the pixel values ​​of the pixel points located in the background area to preset pixel values.

[0132] In some embodiments of the present application, the style conversion unit is specifically configured to perform image style conversion processing on the area to be detected based on a conditional adversarial generative network to obtain a first stick figure image.

[0133] In some embodiments of the present application, the detection unit includes: a matching subunit, which is used to extract first image features from the first stick figure image based on the SURF algorithm, and match the first image features with second image features of a preset image in the infringement database to obtain the number of feature matches between the first stick figure image and the preset image; a screening subunit, which is used to screen preset image images whose number of feature matches with the first stick figure image is greater than a preset matching threshold as potential infringing objects; and an infringement analysis unit, which is used to perform infringement analysis on the first stick figure image based on the potential infringing objects to obtain a detection result.

[0134] In some embodiments of the present application, the detection module 830 includes: a style conversion unit, used to convert the card surface image into a second stick figure image in a stick figure style; an identification unit, used to identify the area to be detected where the image elements in the second stick figure image are located; and an infringement detection unit, used to perform image infringement detection on the image elements in the area to be detected to obtain a detection result.

[0135] In some embodiments of the present application, the generation module 820 includes: a parsing unit for parsing a card face image generation request to obtain a card face description content; and a generation unit for generating a card face image that matches the card face description content by inputting the card face description content into a diffusion model.

[0136] In some embodiments of the present application, the card activation module 850 includes: a sending unit, which is used to send a confirmation request carrying the card surface image to the user terminal when the detection result indicates that the card surface image is not infringing, and the confirmation request is used to instruct the user to confirm the card surface image; a submission unit, which is used to submit the card activation request to the financial end when receiving a confirmation message returned by the user terminal, so that the financial end uses the card surface image in the card activation request to activate the card.

[0137] In some embodiments of the present application, the card face image generation request also includes the card face version, card face background and card face style selected by the user in the card opening interface of the user terminal, and the card face image is generated based on the card face version, card face style, card face background and card face description content.

[0138] The third aspect of the present application further provides an electronic device. FIG9 is a schematic diagram of the structure of an embodiment of the electronic device provided in the third aspect of the present application. As shown in FIG9 , the electronic device 900 includes a memory 901, a processor 902, and a computer program stored in the memory 901 and executable on the processor 902.

[0139] In an example, the processor 902 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0140] The memory 901 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Therefore, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the card activation method in the embodiment according to the first aspect of the present application.

[0141] The processor 902 runs a computer program corresponding to the executable program code by reading the executable program code stored in the memory 901, so as to implement the card activation method in the embodiment of the first aspect.

[0142] In some examples, the electronic device 900 may further include a communication interface 903 and a bus 904. As shown in FIG9 , the memory 901, the processor 902, and the communication interface 903 are connected via the bus 904 and communicate with each other.

[0143] The communication interface 903 is mainly used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. Input devices and / or output devices can also be connected through the communication interface 903.

[0144] The bus 904 includes hardware, software, or both that couples the components of the electronic device 900 to each other. By way of example and not limitation, the bus 904 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-E) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of the above. Where appropriate, the bus 904 may include one or more buses. Although embodiments herein describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.

[0145] In a fourth aspect, the present application provides a computer-readable storage medium having a program or instruction stored thereon. When executed by a processor, the program or instruction can implement the card activation method described in the first aspect and achieve the same technical effect. To avoid repetition, the details are not repeated here. The computer-readable storage medium may include a non-transitory computer-readable storage medium, such as a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., but is not limited to this.

[0146] In a fifth aspect, the present application provides a computer program product, which is stored in a non-volatile storage medium. When the computer program product is executed by at least one processor, it implements the steps of the card activation method shown in the first aspect. The specific content of the card activation method can be found in the relevant description in the above embodiment and will not be repeated here.

[0147] In the sixth aspect of the present application, a chip is provided, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the embodiment of the card activation method shown in the first aspect, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0148] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0149] It should be clear that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. For device embodiments, user terminal embodiments, equipment embodiments, system embodiments, and computer-readable storage medium embodiments, the relevant parts can be referred to the description part of the method embodiment. This application is not limited to the specific steps and structures described above and shown in the figures. Those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of this application. In addition, for the sake of brevity, a detailed description of known method technologies is omitted here.

[0150] Aspects of the present application have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed via the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. This processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or the flowchart and the combination of the boxes in the block diagram and / or the flowchart can also be implemented by the dedicated hardware that performs the specified function or action, or can be implemented by the combination of dedicated hardware and computer instructions.

[0151] Those skilled in the art should understand that the above embodiments are illustrative rather than restrictive. Different technical features appearing in different embodiments can be combined to achieve beneficial effects. Based on a study of the drawings, the specification and the claims, those skilled in the art should be able to understand and implement other variations of the disclosed embodiments. In the claims, the term "comprising" does not exclude other devices or steps; the quantifier "one" does not exclude a plurality; the terms "first" and "second" are used to identify names rather than to indicate any specific order. Any figure marks in the claims should not be understood as limiting the scope of protection. The functions of multiple parts appearing in the claims can be implemented by a separate hardware or software module. The fact that certain technical features appear in different dependent claims does not mean that these technical features cannot be combined to achieve beneficial effects.

Claims

1. A card activation method, applied to an image generation platform, comprising: Obtaining a card face image generation request sent by a user terminal, wherein the card face image generation request includes a card face description content input by a user on a card opening interface of the user terminal; Based on the card surface image generation request, generate a card surface image matching the card surface description content; Performing image infringement detection on the image elements in the card surface image to obtain a detection result; If the detection result indicates that the card surface image is infringing, feeding back infringement prompt information to the user terminal, wherein the infringement prompt information is used to prompt the user to regenerate the card surface image; When the detection result indicates that the card image is not infringing, a card activation request is submitted to the financial end, so that the financial end activates the card using the card image in the card activation request.

2. The method according to claim 1, wherein: The performing image infringement detection on the image elements in the card surface image to obtain the detection result includes: Identify the area to be detected where the image element is located in the card surface image; Converting the area to be detected into a first stick figure image in a stick figure style; Perform image infringement detection on the image elements in the first stick figure image to obtain a detection result.

3. The method according to claim 2, wherein: The step of identifying the area to be detected where the image element in the card surface image is located includes: Based on the target detection algorithm Faster RCNN, locate the ROI region of interest where the image element is located in the card surface image; The ROI region is enlarged to obtain the region to be detected.

4. The method according to claim 3, wherein: After obtaining the area to be detected and before converting the area to be detected into a first stick figure image in a stick figure style, the method further includes: Performing foreground segmentation on the area to be detected to obtain a foreground area and a background area; The pixel values ​​of the pixels located in the background area are adjusted to preset pixel values.

5. The method according to claim 2, wherein: The step of converting the area to be detected into a first stick figure image in a stick figure style comprises: Perform image style conversion processing on the area to be detected based on a conditional adversarial generative network to obtain the first stick figure image.

6. The method according to claim 2, wherein: The performing image infringement detection on the image elements in the first stick figure image includes: Extracting a first image feature from the first stick figure image based on the SURF algorithm, and matching the first image feature with a second image feature of a preset image in the infringement database to obtain a number of feature matches between the first stick figure image and the preset image; Screening preset image images whose number of feature matches with the first stick figure image is greater than a preset matching threshold as potential infringing objects; The first stick figure image is subjected to infringement analysis based on the potential infringing object to obtain the detection result.

7. The method according to claim 1, wherein: The image infringement detection of the image elements in the card surface image includes: Converting the card surface image into a second stick figure image in a stick figure style; Identifying a region to be detected where the image element is located in the second stick figure image; Perform image infringement detection on the image elements in the area to be detected to obtain a detection result.

8. The method according to claim 1, wherein: The generating of a card surface image matching the card surface description content comprises: Parsing the card face image generation request to obtain the card face description content; By inputting the card surface description content into the diffusion model, a card surface image matching the card surface description content is generated.

9. The method according to claim 1, wherein: When the detection result indicates that the card image is not infringing, submitting a card opening request to the financial end includes: If the detection result indicates that the card surface image is not infringing, sending a confirmation request carrying the card surface image to the user terminal, wherein the confirmation request is used to instruct the user to confirm the card surface image; When receiving the confirmation message returned by the user terminal, a card opening request is submitted to the financial terminal, so that the financial terminal uses the card face image in the card opening request to open the card.

10. The method according to claim 1, wherein: The card face image generation request also includes the card face version, card face background and card face style selected by the user in the card opening interface of the user terminal, and the card face image is generated based on the card face version, the card face style, the card face background and the card face description content.

11. A card opening device, applied to an image generation platform, comprising: An acquisition module, configured to acquire a card face image generation request sent by a user terminal, wherein the card face image generation request includes a card face description content input by a user in a card opening interface of the user terminal; A generating module, configured to generate a card face image matching the card face description content based on the card face image generation request; A detection module, used to perform image infringement detection on the image elements in the card surface image to obtain a detection result; A feedback module, configured to feed back infringement prompt information to the user terminal when the detection result indicates that the card surface image is infringing, wherein the infringement prompt information is used to prompt the user to regenerate the card surface image; The card activation module is used to submit a card activation request to the financial end when the detection result indicates that the card surface image is not infringing, so that the financial end can activate the card using the card surface image in the card activation request.

12. An electronic device, comprising: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the card opening method according to any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the card opening method according to any one of claims 1 to 10.

14. A computer program product, wherein the computer program product is stored in a non-volatile storage medium, and when the computer program product is executed by at least one processor, the card activation method according to any one of claims 1 to 10 is implemented.

Images