Card making machine system based on artificial intelligence and card making method

Abstract

The embodiment of the invention relates to the technical field of artificial intelligence, and discloses a card making machine system and a card making method based on artificial intelligence, and the card making machine system comprises a user interaction unit, an image generation module, an image preview and editing module, a printing control module, a printing module, a card making effect feedback unit and an artificial intelligence model correction module. According to the method, the image is automatically generated through the online artificial intelligence model, the design time is greatly shortened, and the card making efficiency is improved; meanwhile, the image previewing and editing module allows the user to quickly adjust and perfect the design, so that the card making process is further accelerated; and through the card making effect feedback unit and the artificial intelligence model correction module, the system can continuously learn and improve, so that the quality and accuracy of the generated image are improved as time goes on.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly relates to a card-making machine system and a card-making method based on artificial intelligence. Background Art

[0002] In the card-making industry, traditional card-making machines are generally used. These devices usually rely on preset templates and manual design to generate cards. Users cannot quickly generate personalized cards during the design process. This lack of flexibility limits users' creativity and cannot meet the increasingly diverse needs. Summary of the Invention

[0003] The main objective of the present invention is to provide a card-making machine system and a card-making method based on artificial intelligence, aiming to solve the technical problems of low card-making efficiency and low card-making flexibility in the prior art.

[0004] To achieve the above objective, in a first aspect, an embodiment of the present application provides a card-making machine system based on artificial intelligence. The card-making machine system includes: A user interaction unit, configured to receive the design requirements input by a target user, where the design requirements include an image style, design requirements, and template selection; An image generation module, configured to call an online artificial intelligence model to generate an image based on the design requirements input by the target user to obtain a prefabricated image; An image preview and editing module, configured to switch the state of the prefabricated image to the preview and editable state, and regenerate an image after editing confirmation to obtain a card-making target image; A printing control module, configured to transmit the card-making target image to a printing device and generate a card-making task to be processed; A printing module, configured to print the card-making target image onto a PVC card according to the card-making task to be processed to complete card-making and obtain a target card; A card-making effect feedback unit, configured to perform effect feedback on the production effect of the target card to obtain a feedback opinion library; and An artificial intelligence model correction module, configured to analyze the feedback opinion library and correct the online artificial intelligence model based on the analysis result to obtain a current online artificial intelligence model, where the current online artificial intelligence model is used to generate an image for the currently input design requirements.

[0005] In a possible implementation manner, the image generation module and the artificial intelligence model correction module are deployed on a cloud server, the user interaction unit and the image preview and editing module are deployed on a user terminal, the printing control module, the printing module, and the card-making effect feedback unit are deployed on a local card-making machine device, and the cloud server, the user terminal, and the local card-making machine device communicate through a wireless network.

[0006] In a possible implementation, the image generation module includes: An image generation sub-module, which is used to call an online artificial intelligence model to generate a preliminary prefabricated image according to the design requirements input by the target user through the user interaction unit; An image optimization sub-module, connected to the image generation sub-module, for receiving and processing the prefabricated image output by the image generation sub-module, and improving the clarity and visual effect of the image through an image optimization algorithm to obtain an optimized prefabricated image for use by the image preview and editing module; and, An image quality evaluation unit, for evaluating the image quality before and after image optimization, and outputting the prefabricated image for use by the image preview and editing module when the image quality meets the preset requirements.

[0007] In a possible implementation, the card-making effect feedback unit includes: An image recognition module, for performing image recognition on the target card after card-making to obtain a feedback image; A user evaluation interface, for collecting subjective evaluation feedback opinions of the target user on the production effect of the target card; A feedback opinion generation module, for analyzing the feedback image and the subjective evaluation feedback opinions to form a feedback opinion library, where the feedback opinion library includes feedback opinions deviating from the design requirements and feedback opinions close to the design requirements.

[0008] In a second aspect, an embodiment of the present application provides a card-making method, which is applied to a card-making machine system. The card-making machine system includes a user interaction unit, an image generation module, an image preview and editing module, a print control module, a print module, a card-making effect feedback unit, and an artificial intelligence model correction module. The method includes: Obtaining the design requirements input by the target user, where the design requirements include image style, design requirements, and template selection; Based on the design requirements input by the target user, calling an online artificial intelligence model to generate an image to obtain a prefabricated image, where the online artificial intelligence model includes a historical online artificial intelligence model and a current online artificial intelligence model; Switching the state of the prefabricated image to a previewable and editable state for the target user to preview and edit; In response to the target user's confirmation of editing the prefabricated image, regenerating an image to obtain a card-making target image; Transmitting the card-making target image to a printing device and generating a card-making task to be processed, and queuing the card-making task to be processed according to a certain rule to generate a card-making task queue to be processed; Print the corresponding card-making target image onto the PVC card according to the to-be-card-made task queue to complete card-making and obtain the target card.

[0009] In a possible implementation manner, after printing the corresponding card-making target image onto the PVC card according to the to-be-card-made task queue to complete card-making and obtain the target card, it further includes: Respond to the formation of a preset number of target feedback opinions in the card-making effect feedback unit, where the target feedback opinions include feedback opinions deviating from the design requirements and feedback opinions close to the design requirements; In the case where the proportion of the feedback opinions close to the design requirements is greater than or equal to the preset proportion, correct the online artificial intelligence model to obtain the current online artificial intelligence model; in the case where the proportion of the feedback opinions deviating from the design requirements is greater than or equal to the preset proportion, correct the online artificial intelligence model to obtain the current online artificial intelligence model, and trigger a design requirement confirmation reminder in the user interaction unit, where the design requirement confirmation reminder is used for the target user to confirm the input design requirements.

[0010] In a possible implementation manner, the card-making effect feedback unit includes an image recognition module, a user evaluation interface, and a feedback opinion generation module. Before the response to the formation of a preset number of target feedback opinions in the card-making effect feedback unit, it further includes: After card-making is completed, perform image recognition on the target card by the image recognition module to obtain a feedback image, and obtain a first feedback opinion according to the feedback image; Collect subjective evaluation feedback opinions of the target user on the production effect of the target card through the user evaluation interface to obtain a second feedback opinion; Obtain the target feedback opinion according to the first feedback opinion and the second feedback opinion corresponding to the first feedback opinion.

[0011] In a possible implementation manner, obtaining the target feedback opinion according to the first feedback opinion and the second feedback opinion corresponding to the first feedback opinion includes: Obtain the influence weights of the first feedback opinion and the second feedback opinion on the accuracy of the feedback opinion respectively; Obtain the target feedback opinion according to the first feedback opinion, the second feedback opinion, and the corresponding influence weights.

[0012] In a possible implementation manner, the invocation of the online artificial intelligence model to generate an image to obtain a prefabricated image includes: Obtain the historical card-making information of the target user; Determine the preview and editing proportion of the target user during the historical card-making process according to the historical card-making information of the target user; When the preview and editing ratio of the target user during the historical card-making process is less than the preset ratio, an historical online artificial intelligence model is used to generate an image. When the preview and editing ratio of the target user during the historical card-making process is greater than or equal to the preset ratio, a current online artificial intelligence model is used to generate an image. The historical online artificial intelligence model is an image generation model before the artificial intelligence model is corrected, and the current online artificial intelligence model is an image generation model after the artificial intelligence model is corrected.

[0013] In a possible implementation manner, the transmitting the card-making target image to a printing device and generating a card-making task to be processed, and queuing the card-making task to be processed according to a certain rule to generate a card-making task queue to be processed includes: Transmitting the card-making target image to a printing device and generating a card-making task to be processed, where the card-making task to be processed carries priority information; Inserting the card-making task to be processed into the original card-making task queue according to the priority information to generate a current card-making task queue to be processed.

[0014] Different from the prior art, the card-making machine system based on artificial intelligence provided in the embodiments of the present application includes a user interaction unit, an image generation module, an image preview and editing module, a printing control module, a printing module, a card-making effect feedback unit, and an artificial intelligence model correction module. A user can input design requirements through the user interaction unit. The image generation module calls an online artificial intelligence model to generate a prefabricated image according to the design requirements input by the user. Then the user can preview the generated prefabricated image in the image preview and editing module and perform necessary editing and adjustment on it. Once the editing is completed and confirmed, the module regenerates the image to form a final card-making target image. The printing control module is responsible for transmitting the card-making target image to a printing device and generating a card-making task to be processed to prepare for printing. The printing module prints the card-making target image on a PVC card according to the card-making task to be processed, completes the card-making process, and obtains a target card. The user or the system can feedback on the production effect of the target card through the card-making effect feedback unit to obtain a feedback opinion library. The artificial intelligence model correction module analyzes the data in the feedback opinion library and corrects the online artificial intelligence model based on the analysis result to improve the quality and accuracy of the generated image. The corrected model can be used as the current online artificial intelligence model to process new design requirements. In this way, by automatically generating an image through the online artificial intelligence model, the design time is greatly shortened and the card-making efficiency is improved; at the same time, the image preview and editing module allows the user to quickly adjust and improve the design, further accelerating the card-making process; through the card-making effect feedback unit and the artificial intelligence model correction module, the system can continuously learn and improve, so that the quality and accuracy of the generated image are improved over time. Description of the Drawings

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on the structures shown in these drawings.

[0016] Figure 1 It is a schematic structural diagram of a card-making machine system based on artificial intelligence in some embodiments of the present application; Figure 2 For Figure 1 It is a schematic module structure diagram of the image generation module in Figure 3 For Figure 1 It is a schematic module structure diagram of the card-making effect feedback unit in Figure 4 It is a schematic structural diagram of a local card-making machine device in some embodiments of the present application; Figure 5 It is a schematic flowchart of a card-making method in some embodiments of the present application; Figure 6 It is a schematic hardware structure diagram of a card-making machine system based on artificial intelligence in some embodiments of the present application.

[0017] The realization, functional characteristics and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the drawings. Specific Embodiments

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0019] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly.

[0020] In addition, the descriptions involving "first", "second", etc. in the present invention are for descriptive purposes only, and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, "and / or" throughout the text includes three scenarios. Taking A and / or B as an example, it includes the technical solution of A, the technical solution of B, and the technical solution where A and B are satisfied simultaneously. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on what can be achieved by those of ordinary skill in the art. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0021] In the card-making industry, traditional card-making machines are generally used. These devices usually rely on preset templates and manual design to generate cards. Users cannot quickly generate personalized cards during the design process. This lack of flexibility limits users' creativity and cannot meet the increasingly diverse needs.

[0022] In response to the above problems, as Figure 1 shown, the present application proposes a card-making machine system based on artificial intelligence. The card-making machine system includes: A user interaction unit 110 for receiving the design requirements input by a target user. The design requirements include image style, design requirements, and template selection. The user interaction unit 110 can be a touch screen, keyboard, mouse, etc. An image generation module 210 for calling an online artificial intelligence model to generate an image based on the design requirements input by the target user to obtain a prefabricated image. An image preview and editing module 120 for switching the state of the prefabricated image to the preview and editable state, and regenerating an image after editing confirmation to obtain a card-making target image. A printing control module 310 for transmitting the card-making target image to a printing device and generating a card-making task to be processed. A printing module 320 for printing the card-making target image onto a PVC card according to the card-making task to complete card-making and obtain a target card. A card-making effect feedback unit 330 for providing an effect feedback on the production effect of the target card to obtain a feedback opinion library; and, An artificial intelligence model correction module 220 for analyzing the feedback opinion library and correcting the online artificial intelligence model based on the analysis result to obtain a current online artificial intelligence model, which is used to generate an image for the currently input design requirements.

[0023] During actual use, the user can input design requirements through the user interaction unit 110. The image generation module 210 calls an online artificial intelligence model to generate a prefabricated image according to the design requirements input by the user. Then the user can preview the generated prefabricated image in the image preview and editing module 120 and make necessary edits and adjustments to it. Once the editing is completed and confirmed, the module will regenerate the image to form the final card-making target image. The print control module 310 is responsible for transmitting the card-making target image to the printing device and generating a card-making task to prepare for printing. The printing module 320 prints the card-making target image onto a PVC card according to the card-making task, completing the card-making process and obtaining the target card. The user or the system can obtain a feedback opinion library by feeding back on the production effect of the target card through the card-making effect feedback unit 330. The artificial intelligence model correction module 220 analyzes the data in the feedback opinion library and corrects the online artificial intelligence model based on the analysis results to improve the quality and accuracy of the generated images. The corrected model can be used as the current online artificial intelligence model to process new design requirements. In this way, the automatic generation of images by the online artificial intelligence model greatly shortens the design time and improves the card-making efficiency; at the same time, the image preview and editing module allows the user to quickly adjust and perfect the design, further accelerating the card-making process; through the card-making effect feedback unit and the artificial intelligence model correction module, the system can continuously learn and improve, making the quality and accuracy of the generated images improve over time.

[0024] It should be noted that the above-mentioned user interaction unit 110, image generation module 210, image preview and editing module 120, print control module 310, printing module 320, card-making effect feedback unit 330, and artificial intelligence model correction module 220 can be uniformly deployed in the same terminal device or separately deployed.

[0025] Specifically, in one embodiment, the image generation module 210 and the artificial intelligence model correction module 220 are deployed on the cloud server 200, the user interaction unit 110 and the image preview and editing module 120 are deployed on the user terminal 100, and the print control module 310, the printing module 320, and the card-making effect feedback unit 330 are deployed on the local card-making device 300. The cloud server 200, the user terminal 100, and the local card-making device 300 communicate through a wireless network.

[0026] In this way, the image generation module 210 and the artificial intelligence model correction module 220 are deployed on the cloud server 200, which can make full use of the powerful computing and storage capabilities of cloud services. The cloud server 200 can be elastically scaled according to requirements to ensure sufficient computing resources during peak periods or for complex tasks. The user interaction unit 110 and the image preview and editing module 120 are deployed on the user terminal 100, which can ensure that users can interact with the system in real time and quickly, and perform image preview and editing. This deployment method also reduces the load on the cloud server 200, enabling it to focus on more complex tasks. The print control module 310, the print module 320, and the card production effect feedback unit 330 are deployed on the local card production device 300, which can ensure the real-time performance and reliability of the printing and card production processes.

[0027] As Figure 2 shown, in one embodiment, the image generation module 210 includes an image generation sub-module 211, an image optimization sub-module 212, and an image quality assessment unit 213. Among them, the image generation sub-module 211 is used to call an online artificial intelligence model to generate a preliminary prefabricated image according to the design requirements input by the target user through the user interaction unit; the image optimization sub-module 212 is connected to the image generation sub-module 211 and is used to receive and process the prefabricated image output by the image generation sub-module, and improve the clarity and visual effect of the image through an image optimization algorithm to obtain an optimized prefabricated image for use by the image preview and editing module; the image quality assessment unit 213 is used to evaluate the image quality before and after image optimization, and output the prefabricated image for use by the image preview and editing module when the image quality meets the preset requirements.

[0028] Specifically, the user can input design requirements through the user interaction unit 110 (such as a touch screen, keyboard, mouse, etc.), and these requirements can include the size, color, style, theme, etc. of the image. After receiving these requirements, the image generation sub-module 211 calls a pre-trained online artificial intelligence model (such as a deep learning model) to generate a preliminary prefabricated image. In the embodiments of the present application, the artificial intelligence model has learned a large amount of image design knowledge and styles and can quickly generate an image that meets the requirements according to the input requirements. The image optimization sub-module 212 receives the preliminary prefabricated image output by the image generation sub-module 211 and applies a series of image optimization algorithms (such as sharpening, denoising, color correction, etc.) to improve the clarity and visual effect of the image. The optimized image will be provided to the image preview and editing module 120 for the user to further preview and edit. In the embodiments of the present application, the image quality evaluation unit 213 plays a key supervisory role during the operation of the image generation sub-module 211 and the image optimization sub-module 212. It uses one or more image quality evaluation metrics (such as peak signal-to-noise ratio, structural similarity index, etc.) to evaluate the quality of the image. Before and after image optimization, the image quality evaluation unit will conduct quality evaluation. If the quality of the optimized image meets the preset requirements (such as clarity, color accuracy, etc.), the image will be output to the image preview and editing module 120; if not, image optimization needs to be performed again.

[0029] In this way, the image generation module 210 of the embodiments of the present application can more efficiently process the user's image design requirements, while ensuring that the generated image has high quality and good visual effects. In addition, by combining the use of an online artificial intelligence model and image optimization algorithms, a more intelligent and personalized image design service can be realized.

[0030] As Figure 3 shown, in one embodiment, the card-making effect feedback unit 330 includes an image recognition module 331, a user evaluation interface 332, and a feedback opinion generation module 333. Among them, the image recognition module 331 is used to perform image recognition on the target card after card making to obtain a feedback image; the user evaluation interface 332 is used to collect subjective evaluation feedback opinions of the target user on the production effect of the target card; the feedback opinion generation module 333 is used to analyze the feedback image and the subjective evaluation feedback opinions to form a feedback opinion library, and the feedback opinion library includes feedback opinions that deviate from the design requirements and feedback opinions that are close to the design requirements.

[0031] Specifically, as Figure 4As shown in the figure, the image recognition module 331 is a camera installed at the card ejection slot 334 (i.e., the card ejection position) of the local card making device 300. After the local card making device 300 completes card making and ejects the card, the camera is activated and automatically captures an image of the target card as the feedback image. This image will be used for subsequent analysis and comparison to check whether the production quality of the card meets the design requirements. The user evaluation interface 332 is the touch screen of the local card making device 300. After the card making machine completes card making and ejects the card, an opinion feedback box will be automatically triggered on the touch screen. The user can enter their subjective evaluations, such as satisfaction, suggestions, or problems, etc., in the opinion feedback box through the touch screen. This subjective evaluation will be used as important feedback information for subsequent analysis and improvement. The feedback opinion generation module 333 first receives the feedback image from the image recognition module 331 and the subjective evaluation feedback opinions from the user evaluation interface 332. Then, it comprehensively analyzes this information to identify which feedback opinions deviate from the design requirements (such as the colors, fonts, patterns, etc. on the card do not meet the design requirements), and which feedback opinions are close to the design requirements (such as the user has a high overall satisfaction with the card). This information will be sorted out and stored in the feedback opinion library for subsequent analysis and improvement. In the embodiment of the present application, the feedback opinion library can be used as an important resource library, which records the feedback and opinions of users on the card making effect. By regularly analyzing the information in this library, the card making device or service provider can identify common problems and improvement points, so as to continuously optimize the card making process and improve the card making quality.

[0032] It should be noted that deviating from the design requirements means that there is a large deviation between the actual effect of the target card and the design requirements input by the user, and being close to the design requirements means that the actual effect of the target card is basically close to the design requirements input by the user.

[0033] The present application also proposes a card making method, which can be applied to the above-mentioned card making machine system based on artificial intelligence, such as Figures 1 - 5 As shown in the figure, the following takes the card making machine system based on artificial intelligence executing this card making method as an example for illustration. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from here. Please refer to the appendix Figure 5 This method includes the following steps S100 - step S600: Step S100, obtain the design requirements input by the target user, and the design requirements include image style, design requirements, and template selection; The design requirements of the target user refer to the specific styles and requirements of the cards that the user hopes to make. Specifically, the design requirements can include image style (such as modern, retro, minimalist, etc.), design requirements (such as colors, fonts, layout, etc.), and template selection (whether the user hopes to use a preset template or completely customize).

[0034] Exemplarily, the user can input the design requirements through the user terminal 100, or can input the design requirements through the local card-making device 300.

[0035] Step S200: Based on the design requirements input by the target user, call an online artificial intelligence model to generate an image to obtain a prefabricated image, where the online artificial intelligence model includes a historical online artificial intelligence model and a current online artificial intelligence model; Specifically, after the system receives the user's design requirements, it will call a pre-configured online artificial intelligence model. This model will automatically generate a prefabricated image according to the user's requirements. This image is the preliminary version of the card design for the user to preview. If the user is not satisfied with the prefabricated image, it can be edited, modified, and adjusted.

[0036] In one embodiment, the step S200: calling an online artificial intelligence model to generate an image to obtain a prefabricated image includes: obtaining the historical card-making information of the target user; determining the preview and editing ratio of the target user during the historical card-making process according to the historical card-making information of the target user; when the preview and editing ratio of the target user during the historical card-making process is less than a preset ratio, using the historical online artificial intelligence model to generate an image, and when the preview and editing ratio of the target user during the historical card-making process is greater than or equal to the preset ratio, using the current online artificial intelligence model to generate an image, where the historical online artificial intelligence model is an image generation model before the artificial intelligence model is corrected, and the current online artificial intelligence model is an image generation model after the artificial intelligence model is corrected.

[0037] In the embodiments of the present application, the system first collects all the card-making records of the target user before, including the design requirements for each card-making, the number of preview and editing times, the finally confirmed images, etc. The system calculates, for the historical card-making information, the ratio of the number of preview and editing times of the target user in each card-making process to the total number of card-makings. This ratio reflects the user's satisfaction with the prefabricated images and editing requirements. If the preview and editing ratio of the target user in the historical card-making process is less than the preset ratio (for example, less than 20%), this indicates that the user has a high satisfaction with the prefabricated images and does not require a large amount of editing. Since the historical online artificial intelligence model has more stable performance and can quickly generate images that meet the basic needs of users, in this case, the system uses the historical online artificial intelligence model (i.e., the image generation model before correction) to generate the prefabricated images. If the preview and editing ratio of the target user in the historical card-making process is greater than or equal to the preset ratio (for example, 20% or higher), this indicates that the user has a low satisfaction with the prefabricated images and requires a large amount of editing. Since the current online artificial intelligence model is more flexible and advanced and can generate more diverse and personalized images that meet the user's needs, in this case, the system uses the current online artificial intelligence model (i.e., the corrected image generation model) to generate the prefabricated images.

[0038] Thus, in the embodiments of the present application, in step S200, the process of calling the online artificial intelligence model to generate the prefabricated images is further refined to consider the historical card-making behavior and preferences of the target user. This refinement helps to more accurately meet the user's expectations and improve the card-making efficiency and user satisfaction.

[0039] Step S300: Switch the status of the prefabricated image to the preview and editable state for the target user to preview and edit; Specifically, after receiving the prefabricated image, the system will display the prefabricated image to the user and allow the user to preview it. At the same time, the image is in an editable state, and the user can further adjust and optimize the image.

[0040] Step S400: In response to the target user's confirmation of editing the prefabricated image, regenerate the image to obtain the card-making target image; Specifically, after the user completes the editing, the system will receive the user's confirmation and regenerate the image according to the user's modification as the target image for card-making.

[0041] Step S500: Transmit the card-making target image to the printing device and generate a card-making task to be processed, and queue the card-making task to be processed according to certain rules to generate a card-making task queue to be processed; Specifically, after receiving the card-making target image, the system sends the card-making target image to the printing device. At the same time, the system generates a card-making task to be processed and adds this task to the original task queue. This queue is sorted according to certain rules (such as first-come, first-served, priority, etc.).

[0042] In one embodiment, step S500: Transmitting the card-making target image to the printing device and generating a card-making task to be processed, and queuing the card-making task to be processed according to certain rules to generate a card-making task queue to be processed, includes: Transmitting the card-making target image to the printing device and generating a card-making task to be processed, where the card-making task to be processed carries priority information; Inserting the card-making task to be processed into the original card-making task queue to be processed according to the priority information to generate the current card-making task queue to be processed.

[0043] Specifically, the system first transmits the card-making target image (i.e., the image that the user hopes to print on the PVC card) to the printing device. After receiving the image, the printing device generates a card-making task to be processed according to the image content and system instructions. This card-making task to be processed not only contains image information but also carries priority information, which is used to indicate the processing order of this task in the card-making task queue to be processed. When a new card-making task to be processed is generated, the system inserts it into the appropriate position in the original queue according to the priority information it carries. Tasks with higher priority will be inserted at the front of the queue for priority processing; tasks with lower priority will be inserted at the back of the queue and wait for processing.

[0044] Exemplarily, the priority information can be confirmed according to the amount of card-making fees paid and the level of the card. The higher the card-making fees paid and the higher the card level, the higher the priority of card-making.

[0045] Step S600: Printing the corresponding card-making target image onto the PVC card according to the card-making task queue to be processed to complete card-making and obtain the target card.

[0046] Specifically, the printing device sequentially prints the card-making target image onto the PVC card according to the order in the task queue. After completion of printing, the target card required by the user can be obtained.

[0047] In this way, the card-making method of the present application realizes efficient connection from design to production through automated and intelligent means, not only improving the card-making efficiency and quality but also enhancing the user's sense of participation and satisfaction.

[0048] In one embodiment, after step S600: Printing the corresponding card-making target image onto the PVC card according to the card-making task queue to be processed to complete card-making and obtain the target card, it further includes: Step S700: In response to a preset number of target feedback opinions being formed in the card-making effect feedback unit, the target feedback opinions include feedback opinions deviating from the design requirements and feedback opinions close to the design requirements; Step S800: When the proportion of the feedback opinions close to the design requirements is greater than or equal to the preset proportion, calibrate the online artificial intelligence model to obtain the current online artificial intelligence model; when the proportion of the feedback opinions deviating from the design requirements is greater than or equal to the preset proportion, calibrate the online artificial intelligence model to obtain the current online artificial intelligence model, and trigger a design requirement confirmation reminder in the user interaction unit, where the design requirement confirmation reminder is used for the target user to confirm the input design requirements.

[0049] Specifically, in the embodiment of the present application, after detecting that a preset number of target feedback opinions are stored in the opinion feedback library, the adjustment of the online artificial intelligence model is started. When the proportion of the feedback opinions close to the design requirements in the opinion feedback library is greater than or equal to the preset proportion (such as 80%), it indicates that the online artificial intelligence model can accurately understand and meet the user's design requirements in most cases. However, there may still be a small number of misunderstandings. Analyze the feedback opinions deviating from the design requirements to adjust the online artificial intelligence model. When the proportion of the feedback opinions deviating from the design requirements in the opinion feedback library is greater than or equal to the preset proportion (such as 80%), it indicates that the system may not accurately understand or meet the user's design requirements. In this case, in addition to adjusting the online artificial intelligence model, the system also triggers a design requirement confirmation reminder in the user interaction unit to prompt the user to re-confirm the input design requirements. This step helps to reduce the poor card-making effect caused by user input errors or understanding deviations and improve the user's satisfaction with the final product.

[0050] In addition, through the setting of the preset number of target feedback opinions in the embodiment of the present application, the system can ensure that the analysis is carried out after collecting enough data, thereby improving the accuracy and reliability of the analysis.

[0051] Before the step S700: In response to a preset number of target feedback opinions being formed in the card-making effect feedback unit, it further includes: after card-making is completed, perform image recognition on the target card according to the image recognition module to obtain a feedback image, and obtain a first feedback opinion according to the feedback image; collect subjective evaluation feedback opinions of the target user on the production effect of the target card according to the user evaluation interface to obtain a second feedback opinion; obtain the target feedback opinion according to the first feedback opinion and the second feedback opinion corresponding to the first feedback opinion.

[0052] Specifically, after the card making is completed, the system first uses the image recognition module 331 (camera) to perform image recognition on the target card to obtain a feedback image. Then, based on the feedback image, the system generates a first feedback opinion through a built-in algorithm or a machine learning model. The first feedback opinion may include objective evaluations of aspects such as card making quality, image clarity, and color accuracy. The user can input feedback opinions on aspects such as card design, quality, and satisfaction on the touch interface of the local card making device 300 to form a second feedback opinion (the second feedback opinion and the corresponding first feedback opinion are feedback opinions on the production effect of the same card). Such subjective evaluations of the user usually reflect the user's direct feelings and expectations regarding the card production effect. Then, the influence weights of the first feedback opinion and the second feedback opinion on the accuracy of the feedback opinion are respectively obtained. These weights can be determined based on factors such as historical data, user preferences, and system settings, that is, the influence weights of the first feedback opinion and the second feedback opinion on the accuracy of the feedback opinion can be dynamically adjusted according to the actual situation. If the influence weight of the first feedback opinion on the accuracy of the feedback opinion is greater than the influence weight of the second feedback opinion on the accuracy of the feedback opinion, then the first feedback opinion is used as the final feedback opinion (i.e., the target feedback opinion). If the influence weight of the second feedback opinion on the accuracy of the feedback opinion is greater than the influence weight of the first feedback opinion on the accuracy of the feedback opinion, then the second feedback opinion is used as the final feedback opinion (i.e., the target feedback opinion).

[0053] In this way, by introducing a weight judgment mechanism in the embodiments of the present application, it is not only possible to more flexibly process the first feedback opinion and the second feedback opinion, thereby obtaining a more accurate and reliable final feedback opinion. This helps to reduce misjudgments and incorrect decisions caused by a single evaluation method or data deviation.

[0054] Please refer to the appendix Figure 6 , Figure 6 which is a schematic hardware structure diagram of a card making machine system based on artificial intelligence provided by some embodiments of the present application. The card making machine system based on artificial intelligence provided by the embodiments of the present application includes a memory 1100 and a processor 1200. Among them, the memory 1100 is used to store program codes, and the processor 1200 is used to call the program codes to execute the method as described above.

[0055] Among them, the processor 1200 is used to provide computing and control capabilities to control the AI-based card-making machine system to perform corresponding tasks. For example, it controls the AI-based card-making machine system to execute the card-making method in any of the above method embodiments. The method includes: obtaining the design requirements input by the target user, where the design requirements include image style, design requirements, and template selection; based on the design requirements input by the target user, calling an online AI model to generate an image to obtain a prefabricated image; switching the state of the prefabricated image to a previewable and editable state for the target user to preview and edit; in response to the target user's confirmation of editing the prefabricated image, regenerating an image to obtain a card-making target image; transmitting the card-making target image to a printing device and generating a card-making task to be processed, and queuing the card-making task to be processed according to certain rules to generate a card-making task queue to be processed; printing the corresponding card-making target image onto a PVC card according to the card-making task queue to be processed to complete card-making and obtain a target card.

[0056] The processor 1200 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0057] The memory 1100, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the card-making method in the embodiments of the present application. By running the non-transitory software programs, instructions, and modules stored in the memory 1100, the processor 1200 can implement the card-making method in any of the above method embodiments.

[0058] Specifically, the memory 1100 may include volatile memory (VM), such as random access memory (RAM); the memory 1100 may also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), or other non-transitory solid-state storage devices; the memory 1100 may further include a combination of the above types of memories.

[0059] In summary, the card-making machine system based on artificial intelligence in this application adopts the technical solution of any one of the above card-making method embodiments. Therefore, it at least has the beneficial effects brought by the technical solutions of the above embodiments, which will not be elaborated here one by one.

[0060] The embodiment of this application also provides a computer-readable storage medium, such as a memory including program code, and the above program code can be executed by a processor to complete the card-making method in the above embodiment. For example, the computer-readable storage medium may be a read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CDROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0061] The embodiment of this application also provides a computer program product, which includes one or more pieces of program code, and the program code is stored in a computer-readable storage medium. The processor of the card-making machine system based on artificial intelligence reads the program code from the computer-readable storage medium, and the processor executes the program code to complete the steps of the card-making method provided in the above embodiment.

[0062] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or can be completed by hardware related to program code. The program can be stored in a computer-readable storage medium, and the above-mentioned storage medium can be a read-only memory, a magnetic disk, or an optical disc, etc.

[0063] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0064] Through the description of the above embodiments, those of ordinary skill in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Those of ordinary skill in the art can understand that all or part of the processes of implementing the above method embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0065] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structural transformation made by using the description of the present invention and the content of the drawings under the inventive concept of the present invention, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present invention.

Claims

1. A card making machine system based on artificial intelligence, characterized in that: The card making machine system comprises: A user interaction unit, used to receive design requirements input by a target user, wherein the design requirements include image style, design requirements and template selection; An image generation module is used to generate images by calling an online artificial intelligence model to obtain prefabricated images based on the design requirements input by the target user; An image preview and editing module, used to switch the state of the prefabricated image to a preview and editable state, and to regenerate the image to obtain a card making target image after the editing is confirmed; The printing control module is used to transmit the card making target image to the printing device and generate the card making task to be made; A printing module, used for printing the card making target image onto a PVC card according to the card making task to complete the card making and obtain the target card; A card making effect feedback unit, used for providing effect feedback on the making effect of the target card to obtain a feedback opinion library; and The artificial intelligence model correction module is used to analyze the feedback library and correct the online artificial intelligence model based on the analysis results to obtain a current online artificial intelligence model, and the current online artificial intelligence model is used to generate an image for the currently input design requirements.

2. The artificial intelligence-based card making machine system according to claim 1, characterized in that: The image generation module and the artificial intelligence model correction module are deployed on the cloud server, the user interaction unit and the image preview and editing module are deployed on the user terminal, the printing control module, the printing module and the card making effect feedback unit are deployed on the local card making machine device, and the cloud server, the user terminal communicate with the local card making machine device via a wireless network.

3. The artificial intelligence-based card making machine according to claim 1, characterized in that: The image generation module comprises: An image generation submodule, wherein the image generation submodule is used to call an online artificial intelligence model to generate a preliminary prefabricated image according to the design requirements input by the target user through the user interaction unit; An image optimization submodule is connected to the image generation submodule, and is used to receive and process the prefabricated image output by the image generation submodule, improve the clarity and visual effect of the image through an image optimization algorithm, and obtain the optimized prefabricated image for use by the image preview and editing module; and The image quality evaluation unit is used to evaluate the image quality before and after image optimization, and output a pre-made image for use by the image preview and editing modules when the image quality meets the preset requirements.

4. The artificial intelligence-based card making machine according to claim 1, characterized in that: The card making effect feedback unit comprises: An image recognition module is used to perform image recognition on the target card after card making is completed to obtain a feedback image; A user evaluation interface is used to collect subjective evaluation feedback from target users on the production effect of the target card; The feedback generating module is used to analyze the feedback image and the subjective evaluation feedback to form a feedback library, wherein the feedback library includes feedback that deviates from the design requirements and feedback that is close to the design requirements.

5. A card making method, applied to a card making machine system, the card making machine system comprising a user interaction unit, an image generation module, an image preview and editing module, a print control module, a print module, a card making effect feedback unit and an artificial intelligence model correction module, the method comprising: Obtaining design requirements input by a target user, wherein the design requirements include image style, design requirements, and template selection; Based on the design requirements input by the target user, calling an online artificial intelligence model to generate an image to obtain a prefabricated image, wherein the online artificial intelligence model includes a historical online artificial intelligence model and a current online artificial intelligence model; Switching the state of the prefabricated image to a preview and editable state for the target user to preview and edit; In response to the target user editing and confirming the prefabricated image, regenerating the image to obtain a card making target image; The card making target image is transmitted to a printing device to generate a waiting card making task, and the waiting card making task is queued according to certain rules to generate a waiting card making task queue; According to the queue of tasks to be card-made, the corresponding card-making target image is printed on the PVC card to complete the card-making and obtain the target card.

6. The card making method according to claim 5, characterized in that: After printing the corresponding card-making target image onto the PVC card according to the waiting card-making task queue to complete the card-making and obtain the target card, the method further includes: In response to a preset number of target feedback opinions being formed in the card making effect feedback unit, the target feedback opinions include feedback opinions deviating from the design requirements and feedback opinions close to the design requirements; When the proportion of feedback opinions that are close to the design requirements is greater than or equal to a preset proportion, the online artificial intelligence model is corrected to obtain the current online artificial intelligence model; when the proportion of feedback opinions that deviate from the design requirements is greater than or equal to a preset proportion, the online artificial intelligence model is corrected to obtain the current online artificial intelligence model, and a design requirement confirmation reminder is triggered in the user interaction unit, and the design requirement confirmation reminder is used for the target user to confirm the input design requirements.

7. The card making method according to claim 6, characterized in that: The card making effect feedback unit includes an image recognition module, a user evaluation interface and a feedback opinion generation module. In response to a preset number of target feedback opinions being formed in the card making effect feedback unit, the module further includes: After the card making is completed, the target card is image-recognized according to the image recognition module to obtain a feedback image, and a first feedback opinion is obtained according to the feedback image; Collecting subjective evaluation feedback opinions of target users on the production effect of the target card according to the user evaluation interface to obtain second feedback opinions; Target feedback is obtained according to the first feedback and a second feedback corresponding to the first feedback.

8. The card making method according to claim 7, characterized in that: The obtaining target feedback according to the first feedback and the second feedback corresponding to the first feedback includes: Obtaining the influence weights of the first feedback and the second feedback on the accuracy of the feedback respectively; Target feedback is obtained according to the first feedback, the second feedback and the corresponding influence weights.

9. The card making method according to claim 5, characterized in that: The calling of the online artificial intelligence model to generate an image to obtain a prefabricated image includes: Obtain the historical card making information of the target user; Determining the proportion of preview editing by the target user in the historical card making process according to the historical card making information of the target user; When the ratio of preview and editing of the target user in the historical card making process is less than a preset ratio, the historical online artificial intelligence model is used to generate the image; when the ratio of preview and editing of the target user in the historical card making process is greater than or equal to the preset ratio, the current online artificial intelligence model is used to generate the image. The historical online artificial intelligence model is the image generation model before the artificial intelligence model is corrected, and the current online artificial intelligence model is the image generation model after the artificial intelligence model is corrected.

10. The card making method according to claim 5, characterized in that: The step of transmitting the card making target image to a printing device and generating a waiting card making task, and queuing the waiting card making tasks according to certain rules to generate a waiting card making task queue includes: Transmitting the card-making target image to a printing device and generating a card-making task to be made, wherein the card-making task to be made carries priority information; The waiting-for-card-making task is inserted into the original waiting-for-card-making task queue according to the priority information to generate a current waiting-for-card-making task queue.

Images