Part surface treatment cost determination method, apparatus, device, medium, and product

Abstract

The application relates to a kind of part surface treatment cost determination method, device, equipment, medium and product.The method comprises: obtaining the image of part, part type, reference scale information and the process type of surface treatment to part;Reference scale information represents the mapping relationship between the pixel size of image and real physical size;Determine the target bounding box of the area occupied by marked part in image;According to target bounding box, part type and reference scale information, determine the area parameter of process area in part for surface treatment;Based on area parameter, obtain the process cost of surface treatment to part.The method can improve the determination efficiency of part surface treatment cost.

Description

Technical Field

[0001] This application relates to the field of computer vision technology, and in particular to a method, apparatus, equipment, medium and product for determining the cost of surface treatment of components. Background Technology

[0002] In the cost estimation of surface treatment for parts, relevant technologies typically rely on the three-dimensional model of the parts to obtain geometric parameters, and then use these parameters to calculate the surface treatment cost. For example, a plugin integrated into a 3D CAD (Computer-Aided Design) environment can automatically extract dimensional information such as surface area and volume of the three-dimensional model of the parts, and call the unit price and rate from the process cost database to calculate the cost of various surface treatment processes.

[0003] However, the cost calculation of surface treatment for related technologies is highly dependent on the three-dimensional model of the parts. It is often necessary to construct a three-dimensional model of the parts before determining the surface treatment cost, which results in low efficiency in determining the surface treatment cost of the parts. Summary of the Invention

[0004] Based on this, this application addresses the aforementioned technical problems by providing a method, apparatus, equipment, medium, and product for determining the surface treatment cost of components, which can improve the efficiency of determining the surface treatment cost of components.

[0005] In a first aspect, this application provides a method for determining the cost of surface treatment of components, including:

[0006] Acquire images of the parts, part types, reference scale information, and the type of surface treatment process for the parts; the reference scale information represents the mapping relationship between the pixel size of the image and the actual physical size;

[0007] Determine the target bounding box of the area occupied by the marked component in the image;

[0008] Based on the target bounding box, component type, and reference scale information, determine the region parameters of the process area for surface treatment in the component;

[0009] Based on the region parameters, the process cost of surface treatment of the parts is obtained.

[0010] In the above-mentioned method for determining the surface treatment cost of components, the target bounding box of the area occupied by the component in the image is determined, which realizes the positioning of the overall area of ​​the component. Based on the target bounding box, component type and reference scale information, the regional parameters of the process area of ​​the component for surface treatment are determined, realizing the accurate conversion from image pixels to physical parameters. Based on the regional parameters, the process cost of surface treatment of the component is obtained. This method can effectively reduce the dependence on the three-dimensional model when determining the surface treatment cost of the component, thereby improving the processing efficiency of determining the surface treatment cost of the component.

[0011] In an optional embodiment of the first aspect, the region parameters of the process area for surface treatment in the component are determined according to the target bounding box, component type, and reference scale information, including: determining the size parameters of the target bounding box; obtaining a preset structural parameter template corresponding to the component type, the structural parameter template including the region structural parameters of different process areas in the component belonging to the component type, each region structural parameter including the size ratio relationship between the corresponding process area and the overall area of ​​the component; and determining the region parameters of the process area for surface treatment in the component according to the structural parameter template, the size parameters, and the reference scale information.

[0012] In this optional embodiment, by determining the size parameters of the target bounding box and obtaining a preset structural parameter template, the detection results of the overall area of ​​the component can be mapped to the regional parameters of each process area based on the size ratio relationship defined in the structural parameter template and in combination with the reference ratio information. This allows for accurate determination of the regional parameters of each process area based on the image of the component, thereby improving the processing efficiency of determining the surface treatment cost of the component.

[0013] In an optional embodiment of the first aspect, there are multiple process types; based on region parameters, the process cost of surface treatment of the parts is obtained, including: determining the process type-cost mapping relationship; based on the region parameters of the process area corresponding to each process type and the process type-cost mapping relationship, the process cost of surface treatment of the parts according to each process type is obtained respectively.

[0014] In this optional embodiment, the process cost of surface treatment of parts according to each process type is obtained based on the process type-cost mapping relationship and regional parameters corresponding to various process types. It supports adjusting the process cost calculation of different process types by flexibly configuring the process type-cost mapping relationship, thereby improving the scalability of determining the surface treatment cost of parts.

[0015] In an optional embodiment of the first aspect, determining the target bounding box of the region occupied by the marked component in the image includes: inputting the image and preset prompt words into a pre-trained open vocabulary detection model to obtain multiple candidate bounding boxes output by the open vocabulary detection model and the confidence score of each candidate bounding box; the prompt words are used to guide the open vocabulary detection model to analyze and infer the region occupied by the component in the image; and determining the target bounding box from each candidate bounding box based on the confidence score of each candidate bounding box.

[0016] In this optional embodiment, the open vocabulary detection model is used to detect components based on images and prompt words, and the target bounding box is determined according to the confidence of each of the multiple candidate bounding boxes. The generalization ability of the open vocabulary detection model can be used to achieve accurate positioning of components, which helps to reduce the operation process of repeatedly determining the surface treatment cost of components, thereby improving the processing efficiency of determining the surface treatment cost of components.

[0017] In an optional embodiment of the first aspect, the constraints on the open vocabulary detection model include: a bounding box confidence threshold, used to constrain the range of confidence values ​​of the candidate bounding boxes output by the open vocabulary detection model.

[0018] In this optional embodiment, the range of confidence values ​​for candidate bounding boxes is constrained by a bounding box confidence threshold to effectively filter them during the component detection process of the open vocabulary detection model. This ensures the credibility of the candidate bounding boxes output by the open vocabulary detection model and facilitates accurate component positioning.

[0019] In an optional embodiment of the first aspect, the constraints on the open vocabulary detection model include: a text matching degree threshold, used to constrain the range of values ​​for the text matching degree of the candidate bounding boxes output by the open vocabulary detection model, wherein the text matching degree is used to quantify the degree of association between the image region marked by the candidate bounding box and the prompt word.

[0020] In this optional embodiment, the range of text matching degree of candidate bounding boxes is constrained by the text matching degree threshold to effectively filter them during the component detection process of the open vocabulary detection model. This can ensure the credibility of the candidate bounding boxes output by the open vocabulary detection model and facilitate the accurate positioning of components.

[0021] In an optional embodiment of the first aspect, the method for determining the surface treatment cost of components further includes: generating a prompt message when the confidence scores of each candidate bounding box are all less than a preset confidence threshold, to indicate that the image does not support surface treatment cost determination.

[0022] In this optional embodiment, when the confidence scores of each candidate bounding box are all less than a preset confidence threshold, a prompt message is sent to indicate that the image does not support surface processing cost determination. This can avoid determining the surface processing cost based on unreliable detection results as much as possible, which helps to reduce the transmission of erroneous results and thus enhances the reliability of surface processing cost determination.

[0023] In an optional embodiment of the first aspect, the method for determining the surface treatment cost of components further includes: in response to a cost information access operation triggered by a user account, generating access response information based on the access permissions possessed by the user account, at least according to the surface treatment cost; and pushing the response information to the terminal corresponding to the user account to display the access response information on the terminal.

[0024] In this optional embodiment, corresponding access response information is generated based on the access permissions of the user account and pushed to the user account's terminal, thereby realizing security control over component cost information and ensuring the data security of component cost information.

[0025] Secondly, this application also provides a device for determining the cost of surface treatment of parts, comprising:

[0026] The multi-dimensional information acquisition module is used to acquire images of parts, part types, reference scale information, and the process type for surface treatment of parts; the reference scale information represents the mapping relationship between the pixel size of the image and the actual physical size;

[0027] The component detection module is used to determine the target bounding box of the area occupied by the marked component in the image;

[0028] The region parameter determination module is used to determine the region parameters of the process area for surface treatment in the part based on the target bounding box, part type and reference scale information;

[0029] The process cost determination module is used to obtain the process cost of surface treatment of parts based on regional parameters.

[0030] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0031] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0032] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the above aspects.

[0033] Regarding the beneficial effects of any of the technical solutions in the second to fifth aspects mentioned above, refer to the beneficial effects of the corresponding technical solutions in the first aspect; repeated examples will not be listed here. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a schematic diagram illustrating an optional application environment for a method of determining the surface treatment cost of components in one embodiment.

[0036] Figure 2 This is a schematic diagram of an optional process for determining the surface treatment cost of components in one embodiment;

[0037] Figure 3 This is a schematic diagram of an optional process for determining region parameters in one embodiment;

[0038] Figure 4 This is a schematic diagram of an optional process for determining the surface treatment cost of components in yet another embodiment;

[0039] Figure 5 This is a schematic diagram of an optional process for obtaining surface treatment costs based on the process costs of various process types in one embodiment;

[0040] Figure 6 This is a schematic diagram of an optional process for cost information access management in one embodiment;

[0041] Figure 7 This is a schematic diagram of an optional structure of a component surface treatment cost determination device in one embodiment;

[0042] Figure 8 This is a schematic diagram of an optional internal structure of a computer device in one embodiment. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0044] The terms "first," "second," etc., used in this application may be used to describe various elements, but these elements are not limited by these terms. These terms are used only to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0045] The method for determining the cost of surface treatment of components provided in this application can be applied to, for example... Figure 1 In the application environment shown, terminal 101 communicates with server 102 via a network, and a data storage system stores the data that server 102 needs to process. The data storage system can be integrated onto server 102 or located in the cloud or on another network server. Terminal 101 can take pictures of components to obtain images of the components and send these images to server 102. In some embodiments, the user can also send the component type, reference scale information, and the type of surface treatment process for the component to server 102 via terminal 101. Server 102 can perform component detection based on the image, mark the target bounding box of the area occupied by the component in the image, and determine the region parameters of the process area for surface treatment of the component based on the target bounding box, component type, and reference scale information. Server 102 can obtain the process cost of surface treatment of the component based on the region parameters. In some embodiments, server 102 can send the surface treatment cost of the component to terminal 101 for feedback to the user via terminal 101.

[0046] In some embodiments, the method for determining the surface treatment cost of a component can also be implemented independently by either terminal 101 or server 102. For example, terminal 101 can directly calculate the surface treatment cost based on the component's image, component type, reference scale information, and the type of surface treatment process applied to the component. Alternatively, server 102 can obtain the component's image, component type, reference scale information, and the type of surface treatment process applied to the component from a data storage system, and calculate the surface treatment cost based on these information to obtain the component's surface treatment cost.

[0047] Terminal 101 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 102 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0048] In one exemplary embodiment, such as Figure 2 As shown, a method for determining the cost of surface treatment of components is provided, which can be applied to... Figure 1 Taking computer devices such as terminals and / or servers as an example, the explanation includes the following steps S201 to S204. Wherein:

[0049] Step S201: Obtain the image of the component, the component type, the reference scale information, and the process type for surface treatment of the component; the reference scale information represents the mapping relationship between the pixel size of the image and the actual physical size.

[0050] In this context, "components" refers to physical objects for which surface treatment costs need to be determined. Components may include automotive parts such as bumpers, doors, and wheel rims, as well as various parts that can be treated with surface treatment processes, including but not limited to the housings, frames, buttons, or camera trim of electronic devices, air conditioner housings, rice cooker inner pots, and toilet seats. Surface treatment cost refers to the cost incurred in modifying, protecting, or functionalizing the surface of components (such as spraying, electroplating, and high-gloss injection molding). Spraying can be a process of applying paint to the surface of a component; electroplating can be a process of depositing a metal plating layer on the surface of a component using electrochemical methods; and high-gloss injection molding can be a process of creating a high-gloss surface on a component using a high-temperature, high-pressure mold. In some embodiments, surface treatment cost may include the total price of various surface treatment processes, or it may include the individual treatment costs of each surface process.

[0051] Images of components can be obtained by photographing the component itself, such as from a frontal view. Component types are used to distinguish different components, each corresponding to a different physical structure. For example, a bumper has an upper and lower body, and a door has an inner and outer panel. For instance, if the component is a wheel rim, the component type could be the string "wheel rim" or "wheel rim"; similarly, if the component is a bumper, the component type could be the string "bumper".

[0052] Reference scale information is used to characterize the mapping relationship between the pixel size of an image and the actual physical size, thereby enabling the conversion from image pixels to actual physical parameters. The reference scale information can be pre-calibrated and provided by the user. For example, the reference scale information may include a reference scale coefficient of 0.5 mm / pixel, indicating that in the image of a component, each pixel corresponds to a physical size of 0.5 mm. If the length of the bumper in the image is 1000 pixels, then based on 1000 × 0.5, the actual length of the bumper can be calculated to be 500 mm.

[0053] A process type refers to a category of surface treatment processes applied to components. Process types can include, but are not limited to, one or more of the following: spraying, electroplating, high-gloss injection molding, anodizing, powder coating, water transfer printing, and PVD (Physical Vapor Deposition) coating. Different types of components may correspond to different process types. For example, when a component is a vehicle bumper, the corresponding process types may include spraying, electroplating, and high-gloss injection molding; similarly, when a component is a mobile phone frame, the corresponding process types may include anodizing, spraying, and PVD coating.

[0054] Optionally, the computer device can acquire images of the parts for which surface treatment costs need to be calculated, the part type, reference scale information, and the type of surface treatment process applied to the parts. The images of the parts can be taken by the user; the part type can be specified by the user, such as through selection or input; the reference scale information can be configured by the user, such as a reference scale factor of 0.5 mm / pixel; and the type of surface treatment process can also be configured by the user, such as including at least one of spraying, electroplating, and high-gloss injection molding.

[0055] Step S202: Determine the target bounding box of the area occupied by the marked component in the image.

[0056] The target bounding box is used to define the area occupied by the component in the component's image data. The target bounding box can be a rectangle, which can be represented by the coordinates of its center point and its width and height (cx, cy, w, h), or by the coordinates of its top-left and bottom-right corners (x1, y1, x2, y2). Here, cx is the x-coordinate of the center point of the rectangle, cy is the y-coordinate of the center point, w is the width of the rectangle, and h is the height of the rectangle; x1 and y1 can be the x and y coordinates of the top-left corner of the rectangle, and x2 and y2 can be the x and y coordinates of the bottom-right corner. For example, if the component image is a 1024×1024 pixel photograph of a lampshade, with the lampshade located at the center, the target bounding box obtained after detection can include a rectangular area with center coordinates (512, 512) and width and height (800, 800), indicating that the lampshade is located within the rectangular area corresponding to this target bounding box.

[0057] For example, a computer device can perform component detection based on an image of a component to detect target bounding boxes used to mark the area occupied by the component in the image. In some embodiments, the computer device can determine a cue word corresponding to the component type and perform component detection based on the image and the cue word to obtain the target bounding box corresponding to the component in the image. For example, if the component type is "wheel rim", the corresponding cue word may include "wheelrim"; if the component type is "grille panel", the corresponding cue word may include "radiator grille". In some embodiments, the computer device can construct the corresponding cue word in real time after determining the component type, or it can pre-construct candidate cue words for various types of components and determine the required cue word from the candidate cue words of the corresponding type after determining the component type. For example, the computer device can pre-construct corresponding candidate cue words for various types of components, and one or more candidate cue words can be constructed for each type of component. After determining the type of the current component, the computer device can query the corresponding pre-constructed candidate cue words according to the type of the current component and determine the cue word required for this component detection from the candidate cue words.

[0058] Computer devices can invoke a pre-trained component recognition model and input the component image and prompts into the model for component detection. Guided by the prompts, the component recognition model can analyze and infer the region occupied by the component in the image data and output a target bounding box to mark the region occupied by the component in the image. In some embodiments, the component recognition model may include a pre-trained neural network model, such as at least one of various models including but not limited to GLIP (Grounded Language-Image Pre-training), SiamRPN (Siamese Region Proposal Network), GroundingDINO (Grounding Detection Transformer with Improved deNoising anchors), OWL-ViT (Open-World Localization Vision Transformer), CLIP (Contrastive Language-Image Pre-training). The component recognition model can support multimodal input. It receives image data and prompts, and under the guidance of the prompts, analyzes and infers the area occupied by the component in the image data, and outputs the corresponding target bounding box.

[0059] Step S203: Determine the region parameters of the process area for surface treatment in the component based on the target bounding box, component type, and reference scale information.

[0060] In this context, a process area refers to the region of a component that requires a specific type of surface treatment. For example, when the component is a bumper, the bumper surface can be divided into several process areas, such as the upper and lower body painting areas, the chrome-plated trim area, and so on. The upper and lower body painting areas are where the painting process is applied, while the chrome-plated trim area is where the electroplating process is applied. The process area can be determined comprehensively based on the component type provided by the user, reference scale information, and the target bounding box obtained from component inspection.

[0061] Region parameters are used to describe the physical characteristics of the process region. These parameters can include the geometric dimensions of the process region, as well as parameters derived from those dimensions. For example, for a process region corresponding to an electroplating process, its region parameters can include geometric dimensions such as region length and height, and can also include the area occupied for calculating the number of parts arranged within the electroplating tank. Similarly, for a process region corresponding to a high-gloss injection molding process, its region parameters can include geometric dimensions such as region length and height, and can also include the injection volume and injection weight calculated based on the region length and height.

[0062] Optionally, the computer device can determine the regional parameters of the process area for surface treatment in the component by integrating the target bounding box, component type, and reference scale information. For example, the computer device can determine the physical dimensions of the overall region of the component, such as the length and height of the component, based on the pixel-dimensional dimensions of the target bounding box and the reference scale information. For each process type specified by the user, the computer device can obtain the regional parameters of the corresponding process area for that process type according to the preset parameter mapping rules corresponding to the component type and the physical dimensions of the overall region of the component. The parameter mapping rules can be pre-configured for different component types according to actual needs. The parameter mapping rules can include the dimensional ratio relationship between the process areas corresponding to various process types in that component type and the overall region of the component. Based on this dimensional ratio relationship and the physical dimensions of the overall region of the component, the regional parameters of the process areas corresponding to various process types can be determined.

[0063] For example, for automotive component A, the computer device can determine the target bounding box of component A, with pixel dimensions of 1000 pixels wide and 500 pixels high. If the reference scale is 2 millimeters per pixel, the physical dimensions of the overall area of ​​component A can be determined to be 2000 millimeters long and 1000 millimeters high. The computer device can determine a preset parameter mapping rule based on the component type of component A. For the first process type, this parameter mapping rule defines that the length of its process area is equal to the overall length multiplied by a first coefficient, and the height is equal to the overall height multiplied by a second coefficient. For the second process type, this rule defines that the length of its process area is equal to the overall length multiplied by a third coefficient, and the height is equal to the overall height multiplied by a fourth coefficient, with a preset thickness of 5 millimeters. Based on the parameter mapping rules and the physical dimensions of the overall area of ​​component A, the computer equipment can determine the area parameters of the process area corresponding to the first process type, including a length of 1500 mm, a height of 400 mm, and an area of ​​0.6 square meters; and the area parameters of the process area corresponding to the second process type, including a length of 500 mm, a height of 300 mm, and a volume of 0.00075 cubic meters. This achieves the mapping from the image pixel dimension to the real physical dimension, and obtains the area parameters of the process area for surface treatment in the component under the real physical dimension.

[0064] In some embodiments, the computer device can determine a preset statistical model corresponding to the component type to which the component belongs, and obtain the region parameters of the process areas corresponding to each process type based on the physical dimensions of the overall region of the component. The statistical model can pre-learn the mapping relationship between the physical dimensions of the overall region of the component and the physical dimensions of each process area based on a large amount of historical data. The computer device can input the physical dimensions of the overall region of the component into the statistical model, so that the statistical model outputs the region parameters of the process areas in the component undergoing surface treatment. In some embodiments, the computer device can query the CAD database corresponding to the component type to which the component belongs, to determine the design parameters of the component from the CAD database, and determine the region parameters of the process areas in the component undergoing surface treatment based on the queried design parameters. In some embodiments, the computer device can determine a preset partitioning model corresponding to the component type to which the component belongs, and segment the image region of the target bounding box based on the partitioning model to determine the region parameters of the process areas in the component undergoing surface treatment. Among them, the partition segmentation model can be trained based on a large number of manually labeled training images. The partition segmentation model can include instance segmentation models, such as Mask R-CNN (Mask Region-based Convolutional Neural Network) and YOLACT (You Only Look At Coefficients), or semantic segmentation models, such as DeepLabV3+ (Deep Labelling Version 3 Plus) and U-Net (U-shaped network).

[0065] Step S204: Based on the region parameters, obtain the process cost of surface treatment of the parts.

[0066] Process cost refers to the cost incurred for surface treatment according to a specific process type and its corresponding area parameters. Process cost can be calculated based on the process type and its corresponding area parameters. When the surface treatment of a part involves multiple process types, the process cost for each process type can be determined based on each process type and its corresponding area parameters.

[0067] For example, for each process type, the computer device can obtain the process cost of surface treatment of the parts based on the regional parameters of the process area for that process type. For instance, for each process type, the computer device can determine a preset process type-cost mapping relationship corresponding to that process type. This process type-cost mapping relationship can include a cost calculation formula for that process type. Based on the cost calculation formula in the process type-cost mapping relationship and the regional parameters of the corresponding process area for that process type, the process cost of that process type can be calculated. In some embodiments, the cost mapping relationship can also include a regression model trained based on historical pricing data. The regression model can include, but is not limited to, at least one of linear regression, multinomial regression, decision tree regression and random forest regression, and neural network regression models. Based on the regression model and the regional parameters of the corresponding process area for that process type, the process cost of that process type can be calculated. After traversing various process types, the process cost of surface treatment of the parts can be obtained. For example, the computer device can sum the process costs of each process type to obtain the process cost of surface treatment of the parts.

[0068] In the above-mentioned method for determining the surface treatment cost of components, the target bounding box of the area occupied by the component in the image is determined, which realizes the positioning of the overall area of ​​the component. Based on the target bounding box, component type and reference scale information, the regional parameters of the process area of ​​the component for surface treatment are determined, realizing the accurate conversion from image pixels to physical parameters. Based on the regional parameters, the process cost of surface treatment of the component is obtained. This method can effectively reduce the dependence on the three-dimensional model when determining the surface treatment cost of the component, thereby improving the processing efficiency of determining the surface treatment cost of the component.

[0069] In one exemplary embodiment, such as Figure 3 As shown, the process of determining region parameters involves determining the region parameters of the process area for surface treatment in the component based on the target bounding box, component type, and reference scale information, including steps S301 to S303. Wherein:

[0070] Step S301: Determine the size parameters of the target bounding box.

[0071] The size parameters describe the geometric size of the area occupied by the target bounding box in the image. These parameters may include, but are not limited to, the pixel width and / or pixel height of the target bounding box. The size parameters can be calculated based on the coordinate information of the target bounding box. For example, the pixel width can be determined by the difference between the maximum and minimum values ​​of the target bounding box along the horizontal axis in the image coordinate system, and the pixel height can be determined by the difference between the maximum and minimum values ​​of the target bounding box along the vertical axis in the image coordinate system.

[0072] Optionally, the computer device can determine the size parameters of the target bounding box. For example, the computer device can subtract the x-coordinate value of the top-left vertex from the x-coordinate value of the bottom-right vertex of the target bounding box to obtain the pixel width of the target bounding box; and subtract the y-coordinate value of the top-left vertex from the y-coordinate value of the bottom-right vertex of the target bounding box to obtain the pixel height of the target bounding box. The size parameters of the target bounding box can be obtained based on the pixel width and pixel height.

[0073] Step S302: Obtain the preset structural parameter template corresponding to the component type. The structural parameter template includes the regional structural parameters of different process areas in the component belonging to the component type. Each regional structural parameter includes the dimensional ratio between the corresponding process area and the overall area of ​​the component.

[0074] The structural parameter template can include the regional structural parameters of different process areas in the component belonging to the component type. Each regional structural parameter includes the dimensional ratio between the corresponding process area and the overall area of ​​the component. Based on the dimensional ratio and the physical dimensions of the overall area of ​​the component, the regional parameters corresponding to different process areas in the component belonging to the component type can be determined. For example, when the component is a bumper, the structural parameter template for the bumper can include the structural parameters of the upper body painting area and the chrome-plated trim area. The structural parameters of the upper body painting area can include the dimensional ratio between the upper body painting area and the overall component area. For example, the dimensional ratio of the upper body painting area can include a length ratio coefficient of 0.6 and a height ratio coefficient of 0.5, meaning the ratio of the length of the upper body painting area to the length of the overall bumper area is 0.6, and the ratio of the height of the upper body painting area to the height of the overall bumper area is 0.5. The structural parameters of the chrome-plated trim area can include the dimensional ratio between the chrome-plated trim area and the overall component area, such as a length ratio coefficient of 0.3 and a height ratio coefficient of 0.1, meaning the ratio of the length of the chrome-plated trim area to the length of the overall bumper area is 0.3, and the ratio of the height of the chrome-plated trim area to the height of the overall bumper area is 0.1.

[0075] For example, the computer device can obtain a preset structural parameter template corresponding to the component type. For instance, the computer device can use the component type as an index to query the structural parameter template corresponding to the component type from a preset template library. The template library can store pre-configured structural parameter templates corresponding to various component types. Each structural parameter template includes the regional structural parameters of different process areas in the component belonging to the corresponding component type. Each regional structural parameter can include the dimensional ratio between the corresponding process area and the overall area of ​​the component.

[0076] Step S303: Determine the area parameters of the process area for surface treatment in the component based on the structural parameter template, dimensional parameters, and reference scale information.

[0077] Optionally, the computer device can combine structural parameter templates, dimensional parameters, and reference scale information to determine the region parameters of the process area for surface treatment in the component. In some embodiments, the computer device can use the reference scale information to convert the dimensional parameters of the target bounding box into the physical dimensions of the overall region of the component in the real world; for example, pixel width and pixel height can be converted into physical length and physical height in millimeters, respectively. The computer device can calculate the region parameters of the process area for surface treatment in the component based on the physical dimensions of the overall region of the component and the dimensional scale relationship in the structural parameter template.

[0078] For example, if the component is a car bumper, the computer equipment can obtain the target bounding box dimensions as a pixel width of 800 and a pixel height of 400, with a reference ratio of 2 mm per pixel. Based on these dimensions and the reference ratio, the physical dimensions of the overall bumper area can be determined to be a physical length of 1600 mm and a physical height of 800 mm. The computer equipment can then determine the dimensional ratios of the upper body painting area based on a preset structural parameter template corresponding to the bumper, including a length ratio coefficient of 0.6 and a height ratio coefficient of 0.5. Based on these ratios, the physical length of the upper body painting area can be determined to be 960 (1600 × 0.6) mm, the physical height to be 400 (800 × 0.5) mm, and the painting area to be 0.384 square meters. Thus, based on the physical length, physical height, and painting area of ​​the upper body painting area, the region parameters of the upper body painting area can be obtained. After traversing the process areas corresponding to various process types within the bumper, the region parameters of the process areas where surface treatment is performed on the bumper can be obtained.

[0079] In this exemplary embodiment, by determining the size parameters of the target bounding box and obtaining a preset structural parameter template, the detection results for the overall area of ​​the component can be mapped to the regional parameters of each process area based on the size ratio relationship defined in the structural parameter template and in combination with the reference ratio information. This allows for accurate determination of the regional parameters of each process area based on the image of the component, thereby improving the processing efficiency of determining the surface treatment cost of the component.

[0080] In one exemplary embodiment, there are multiple process types; based on region parameters, the process cost of surface treatment of parts is obtained, including: determining the process type-cost mapping relationship; based on the region parameters of the process area corresponding to each process type and the process type-cost mapping relationship, the process cost of surface treatment of parts according to each process type is obtained respectively.

[0081] The process type-cost mapping relationship can include cost calculation formulas for the corresponding process type. Based on these formulas and the region parameters of the corresponding process area, the process cost for that process type can be calculated. For example, the process type-cost mapping relationship can include at least one cost calculation formula for each of various process types such as spraying, electroplating, and high-gloss injection molding. The process type-cost mapping relationship can be pre-configured by the user according to actual needs.

[0082] For example, when there are multiple types of surface treatment processes for components, the computer device can obtain a preset process type-cost mapping relationship. For each process type, the computer device can calculate the process cost of that process type based on the corresponding process type-cost mapping relationship and the regional parameters of the corresponding process area. For instance, the computer device can substitute the regional parameters of the process area corresponding to that process type into the cost calculation formula included in the process type-cost mapping relationship to calculate the process cost of that process type. After traversing various process types, the process cost of surface treatment of components according to each process type can be obtained separately.

[0083] In this exemplary embodiment, the process cost of surface treatment of parts according to each process type is obtained based on the process type-cost mapping relationship and regional parameters corresponding to various process types. It supports adjusting the process cost calculation of different process types by flexibly configuring the process type-cost mapping relationship, thereby improving the scalability of determining the surface treatment cost of parts.

[0084] In an exemplary embodiment, determining the target bounding box of the region occupied by the marked component in an image includes: inputting the image and preset prompt words into a pre-trained open vocabulary detection model to obtain multiple candidate bounding boxes output by the open vocabulary detection model and the confidence score of each candidate bounding box; the prompt words are used to guide the open vocabulary detection model to analyze and infer the region occupied by the component in the image; and determining the target bounding box from each candidate bounding box based on the confidence score of each candidate bounding box.

[0085] Specifically, target bounding boxes can be determined using a pre-trained component recognition model. This model can include an open-vocabulary detection model, which can locate and identify target objects in an image based on arbitrary text descriptions (rather than a pre-defined fixed list of categories), thus enabling the detection of target objects not learned during training. For example, an open-vocabulary detection model can include, but is not limited to, at least one of GLIP, Grounding DINO, OWL-ViT, and CLIP models. Component detection using an open-vocabulary detection model eliminates the need for pre-fixed identifiers for various component types and for fine-tuning the model using local data. It allows for the localization of the region occupied by a component in an image based on prompts, making it suitable for scenarios where only image input is available and a dedicated detection dataset is lacking.

[0086] The prompts can be pre-set based on the components, such as by component type. This provides the open vocabulary detection model with the required component types to guide its analysis and inference of the area occupied by the component in the image data. For example, if the component type is the string "rim", the pre-set prompts for that component could include the strings "rim" or "wheel rim", or the text "Please perform image recognition according to the rim features".

[0087] Candidate bounding boxes are initially identified by the open vocabulary detection model in an image and are used to define the regions occupied by components within the image. For example, candidate bounding boxes can be rectangles, which can be represented by the coordinates of their center point and width / height (cx, cy, w, h), or by the coordinates of their top-left and bottom-right corners (x1, y1, x2, y2). The confidence score of a candidate bounding box represents the degree of certainty the open vocabulary detection model has regarding whether the obtained candidate bounding box actually contains a component. Each candidate bounding box can have a corresponding confidence score. The confidence score of a candidate bounding box can be a value from 0 to 1, and a higher confidence score indicates a higher degree of certainty from the open vocabulary detection model that the candidate bounding box contains a component.

[0088] For example, a computer device can invoke a pre-trained open vocabulary detection model and input images of components and preset prompts into the open vocabulary detection model. The open vocabulary detection model can then detect components based on the images and prompts. Guided by the prompts, the open vocabulary detection model can analyze and infer the region occupied by the component in the image data and output multiple candidate bounding boxes corresponding to the component in the image, along with the confidence score of each candidate bounding box. In some embodiments, the open vocabulary detection model can match each image region in the component image with the prompts and determine candidate bounding boxes corresponding to the component in the image based on the matching scores, outputting multiple candidate bounding boxes and their respective confidence scores. The computer device can then combine the confidence scores of each candidate bounding box to determine the target bounding box. For example, the computer device can determine the candidate bounding box with the highest confidence score as the target bounding box. For instance, if the open vocabulary detection model outputs two candidate bounding boxes, with candidate bounding box 1 having a confidence score of 0.91 and candidate bounding box 2 having a confidence score of 0.67, the computer device can determine candidate bounding box 1 as the target bounding box.

[0089] In this exemplary embodiment, the open vocabulary detection model is used to detect components based on images and prompt words, and the target bounding box is determined according to the confidence of each of the multiple candidate bounding boxes. The generalization ability of the open vocabulary detection model can be used to achieve accurate positioning of components, which helps to reduce the operation process of repeatedly determining the surface treatment cost of components, thereby improving the processing efficiency of determining the surface treatment cost of components.

[0090] In an exemplary embodiment, the constraints on the open vocabulary detection model include: a bounding box confidence threshold, which is used to constrain the range of confidence values ​​of the candidate bounding boxes output by the open vocabulary detection model.

[0091] The bounding box confidence threshold is used to constrain the range of confidence values ​​for candidate bounding boxes output by the open vocabulary detection model. By setting this threshold, the confidence of candidate bounding boxes output by the open vocabulary detection model can be kept within the desired range. For example, the bounding box confidence threshold can constrain the open vocabulary detection model to output candidate bounding boxes with confidence values ​​exceeding the threshold, ensuring that the confidence of each candidate bounding box output by the open vocabulary detection model exceeds the threshold. The bounding box confidence threshold can be preset according to the application scenario of component detection and the desired detection accuracy and recall rate. For example, in the rim detection scenario, the bounding box confidence threshold can be preset to 0.4, thus constraining the open vocabulary detection model to only output candidate bounding boxes with confidence values ​​exceeding 0.4.

[0092] Optionally, constraints can be imposed on the open vocabulary detection model to control its output. For example, a bounding box confidence threshold can be set to constrain the range of confidence values ​​for the candidate bounding boxes output by the open vocabulary detection model. In some embodiments, the open vocabulary detection model can perform component detection based on an image under the guidance of prompts, generating bounding boxes corresponding to the components and their confidence values. The open vocabulary detection model can then judge the generated bounding boxes according to the bounding box confidence threshold to determine whether they need to be output. For example, bounding boxes with confidence values ​​exceeding the threshold can be output as candidate bounding boxes; bounding boxes with confidence values ​​not exceeding the threshold can be discarded. This allows the open vocabulary detection model to output candidate bounding boxes with confidence values ​​exceeding the threshold and their corresponding confidence values.

[0093] In this exemplary embodiment, the range of confidence values ​​for candidate bounding boxes is constrained by a bounding box confidence threshold to effectively filter them during the component detection process of the open vocabulary detection model. This ensures the credibility of the candidate bounding boxes output by the open vocabulary detection model and facilitates accurate component positioning.

[0094] In an exemplary embodiment, the constraints on the open vocabulary detection model include: a text matching degree threshold, which is used to constrain the range of text matching degree values ​​of the candidate bounding boxes output by the open vocabulary detection model. The text matching degree is used to quantify the degree of association between the image region marked by the candidate bounding box and the prompt word.

[0095] The text matching threshold is used to constrain the range of text matching scores for candidate bounding boxes output by the open vocabulary detection model. By setting this threshold, the text matching scores of candidate bounding boxes can be kept within the desired range. Text matching score quantifies the correlation between the image region marked by the candidate bounding box and the prompt word. A higher text matching score indicates a stronger correlation between the image region and the prompt word, meaning the image region marked by the candidate bounding box better meets the detection requirements of the prompt word and is more likely to belong to the area occupied by the component. For example, the text matching threshold can constrain the open vocabulary detection model to output candidate bounding boxes with text matching scores exceeding the threshold, ensuring that each candidate bounding box output by the open vocabulary detection model has a text matching score exceeding the threshold. The text matching threshold can be preset according to the application scenario of component detection and the desired detection accuracy and recall. For example, in the rim detection scenario, the text matching threshold can be preset to 0.3, thus constraining the open vocabulary detection model to only output candidate bounding boxes with text matching scores exceeding 0.3.

[0096] Optionally, constraints can be imposed on the open vocabulary detection model to control its output. For example, a text matching threshold constraint can be set to limit the range of the text matching threshold values ​​for the candidate bounding boxes output by the open vocabulary detection model. In some embodiments, the open vocabulary detection model can perform component detection based on images under the guidance of prompt words, generate bounding boxes corresponding to the components, and determine the degree of association between the image regions marked by the bounding boxes and the prompt words, thereby obtaining the text matching degree of the bounding boxes. The open vocabulary detection model can judge the generated bounding boxes according to the text matching threshold to determine whether they need to be output. For example, bounding boxes with a text matching degree exceeding the text matching threshold can be output as candidate bounding boxes; bounding boxes with a text matching degree not exceeding the text matching threshold can be discarded by the open vocabulary detection model, thereby enabling the open vocabulary detection model to output candidate bounding boxes with a text matching degree exceeding the text matching threshold.

[0097] In some embodiments, constraints such as a bounding box confidence threshold and a text matching threshold can be applied to the open vocabulary detection model simultaneously, thereby enabling the open vocabulary detection model to output candidate bounding boxes with confidence exceeding the bounding box confidence threshold and text matching exceeding the text matching threshold.

[0098] In this exemplary embodiment, the range of text matching degree values ​​for candidate bounding boxes is constrained by a text matching degree threshold to effectively filter them during the component detection process of the open vocabulary detection model. This ensures the credibility of the candidate bounding boxes output by the open vocabulary detection model and facilitates accurate component positioning.

[0099] In an exemplary embodiment, the method for determining the surface treatment cost of components further includes: generating a prompt message when the confidence scores of each candidate bounding box are all less than a preset confidence threshold, to indicate that the image does not support surface treatment cost determination.

[0100] The confidence threshold is used to evaluate the overall reliability of all candidate bounding boxes output by the open vocabulary detection model for the current component image. The confidence threshold value can be adjusted according to different component types, image acquisition conditions, or accuracy requirements; for example, it can include a pre-set confidence threshold of 0.55 or 0.6. If the confidence of each candidate bounding box does not exceed the pre-set confidence threshold, it can be determined that there is no reliable component region in the image, and anomaly handling can be triggered. For example, a prompt message can be generated to indicate that the current image does not support surface processing cost determination and that the component image needs to be replaced. The form of the prompt message can be flexibly configured according to actual needs; for example, the prompt message can include various forms of information such as text, images, audio, and video.

[0101] For example, the computer device can compare the confidence scores of each candidate bounding box with a preset confidence threshold. If the confidence score of each candidate bounding box is less than the confidence threshold, it can be determined that there is no reliable component region in the image. The computer device can then generate a prompt message and output it to the user interface to indicate that the image does not support surface processing cost determination. For instance, if an open vocabulary detection model outputs three candidate bounding boxes with confidence scores of 0.35, 0.32, and 0.22 respectively, and the confidence threshold is 0.55, the computer device can generate a prompt message indicating that no reliable component region was detected in the current component image, and surface processing cost determination is not supported. The message requests that the image be replaced or the detection conditions adjusted for re-detection. When at least one candidate bounding box has a confidence score exceeding the confidence threshold, the computer device can determine the target bounding box from among the candidate bounding boxes.

[0102] In this exemplary embodiment, when the confidence scores of each candidate bounding box are all less than a preset confidence threshold, a prompt message is sent to indicate that the image does not support surface processing cost determination. This can avoid determining the surface processing cost based on unreliable detection results as much as possible, which helps to reduce the transmission of erroneous results and thus enhances the reliability of surface processing cost determination.

[0103] In an exemplary embodiment, the method for determining the surface treatment cost of components further includes: in response to a cost information access operation triggered by a user account, generating access response information based on the access permissions possessed by the user account, at least according to the surface treatment cost; and pushing the response information to the terminal corresponding to the user account to display the access response information on the terminal.

[0104] User accounts are used to identify different users, and may include identifiers such as username and user ID. Cost information access is an interactive operation triggered by a user's account to request surface treatment cost information for components. For example, a user can trigger cost information access by clicking the "View Cost Details" button on the terminal or sliding the "View Cost Details" slider in the terminal's application. Access permissions can be pre-configured for user accounts to control the range of information that an account can access. For example, for a regular user account, access permissions can be configured to only support access to summarized surface treatment costs, cost ranges, or cost composition percentages; for an administrator account, access permissions can be configured to support access to complete cost details, including but not limited to at least one of the following: unit price parameters for each process, process costs for various process types, and summarized surface treatment costs. Access response information is the information content responding to the user account's cost information access operation. Access response information can be generated based at least on surface treatment costs, such as including at least the surface treatment costs of the components.

[0105] For example, a user can trigger a cost information access operation on a terminal using their user account. For instance, a user can click the "View Cost Details" button on the terminal to trigger the cost information access operation. The terminal can then send an access message to a computer device based on this operation. The computer device can respond to the user's cost information access operation based on the received access message and determine the access permissions granted to the user account. For example, the computer device can query the user account's access permissions based on the account identifier. The computer device can generate access response information based on the user account's access permissions, at least based on the surface treatment cost. Different access permissions can correspond to different access response information, and the access response information can at least include the surface treatment cost of the components. The computer device can push the access response information to the user's terminal for intuitive display on the terminal.

[0106] In this exemplary embodiment, corresponding access response information is generated based on the access permissions of the user account and pushed to the user account's terminal, thereby achieving security control over component cost information and ensuring the data security of component cost information.

[0107] This application also provides an application scenario in which the above-described method for determining the surface treatment cost of components is applied. Specifically, the application of the method for determining the surface treatment cost of components in this scenario is as follows:

[0108] The components in this application scenario can be automotive parts, such as bumpers, wheel rims, and doors. The surface treatment cost of automotive parts (such as painting, electroplating, and high-gloss injection molding) accounts for 20% to 40% of the total manufacturing cost of the parts, and is an important part of cost accounting.

[0109] In technologies related to determining the surface treatment costs of automotive parts, manual measurement or the creation of 3D models is often required to obtain the dimensional information of the parts. However, in the early design stages, when only part images or renderings are available, dimensional information cannot be automatically obtained. Furthermore, before the part is finalized, designers may only provide renderings, requiring a rapid assessment of the cost differences between different surface treatment options to aid design decisions. Related technologies cannot support rapid cost evaluation based solely on 2D images. Therefore, these technologies typically scatter image recognition, parameter conversion, process cost calculation, and result display across different tools, lacking a unified data flow and access control. Especially in scenarios where only renderings or photographs are available, even if the part area is identified, it is difficult to directly convert it into calculable and securely distributable surface treatment cost estimates.

[0110] Based on this, the component surface treatment cost determination method provided in this application, when applied to automotive component scenarios, stably converts component regions in images into region parameters that can be calculated for different process types. This effectively reduces reliance on 3D models and allows for accurate determination of component surface treatment costs based on component images. The component surface treatment cost determination method also supports outputting access response information according to user roles. The access response information can include cost information at different granularities, improving data security.

[0111] In this application scenario, the user-provided input request can be abstracted as follows: ,in, It can provide users with input requests through terminals to computer devices to request a determination of the surface treatment cost of parts; Images of components uploaded by users. For component type, As for the process type, For reference scale information, it may include a reference scale factor. A user role or user identity that represents a user account. Computer devices can... The image is read as an RGB image array, and fields such as width, height, depth, material, and whether cutout rate correction is enabled are parsed into structured parameters. Then, it enters the detection, parameter conversion, cost calculation, and permission filtering process. Therefore, the output of the image visual inspection processing is not a direct cost, but rather a set of intermediate engineering parameters. ,in, For the target bounding box, The confidence level of the target bounding box. For area parameters, For volume parameters, For weight parameters, For the hollowness ratio parameter, The color area ratio result is based on the intermediate engineering parameter set. It is possible to determine the regional parameters of the corresponding process areas for various process types in the parts, thereby enabling the determination of the process cost for surface treatment of the parts based on the regional parameters.

[0112] According to the cost calculation chain, the total cost of computer equipment can be expressed as... The cost of each component can be determined by the parameters of the structured region after visual recognition. The total cost of the components includes the cost of surface treatment processes and the cost of raw materials for the components. The process cost of spraying can be calculated based on the spraying area; The process cost of electroplating can be calculated based on the area occupied by the electroplating and the number of plates. The process cost of high-gloss injection molding can be calculated based on the volume and weight of the high-gloss injection molding. The cost of raw materials for components can be calculated, for example, based on the weight of the components. Among these, It can be used as the process cost for surface treatment of parts. This indicates a summation.

[0113] In the method for determining the cost of surface treatment of parts provided in this application, such as Figure 4 As shown, it includes:

[0114] Step S401: Obtain the image, component type, process type, and reference scale information of the component. The input data can be provided by the user to the computer device via a terminal.

[0115] Step S402: Component detection is performed using an open vocabulary detection model. The computer device can call a pre-trained open vocabulary detection model to detect components based on their images, obtaining multiple candidate bounding boxes.

[0116] Step S403: Determine the target bounding box. The computer device can determine the target bounding box from the candidate bounding boxes based on their respective confidence levels.

[0117] Step S404: Determine the region parameters of the process area for surface treatment in the component based on the target bounding box, component type, and reference scale information.

[0118] Step S405: Cost calculation for the spraying process.

[0119] Step S406: Calculation of electroplating process cost.

[0120] Step S407, cost calculation for high-gloss injection molding process.

[0121] Step S408: Obtain the process cost of surface treatment for the parts. The computer equipment can obtain the process cost of surface treatment for the parts based on the sum of the costs of spraying, electroplating, and high-gloss injection molding.

[0122] Step S409: Feedback the complete cost details to the user account with the administrator role. When a user triggers a cost information access operation through their user account, the computer device can determine the user's identity based on the access permissions granted to the user account. If the user account belongs to an administrator account, the computer device can return access response information including the complete cost details to the user.

[0123] Step S410: Feedback the de-identified information to the user account of a regular user. When the user account is a regular account, the computer device can return access response information including the de-identified information to the user.

[0124] The overall process may include: →RGB array→ Boundary box → Spraying area calculated based on structural parameter template Electroplating area Electroplating volume And the weight of injection molded parts or chrome-plated materials →Invoke spraying, electroplating, high-gloss injection molding, and weight prediction→ to obtain the surface treatment cost of the parts. → Field-level data masking is performed based on the current_user.is_admin attribute, thereby returning access response information. Each intermediate quantity in this process can fall into the formula variable system, allowing the same bounding box and parameter conversion results to be reused for the same component under different process type combinations, which helps improve the efficiency of determining surface treatment costs.

[0125] The following explanation uses a car bumper as an example. The computer device can receive images of the parts, part type, reference scale information, and the surface treatment process type for the parts. The reference scale information can be entered by the user. The computer device can perform part detection on the input image to locate the entire area of ​​the part in the image, obtaining the target bounding box and confidence level of the part. In some embodiments, Grounding DINO can be used to perform part detection on the bumper image. The prompt can include the text prompt "car bumper," or it can use the part name or decorative part prompt. The bounding box retention conditions can include a bounding box confidence threshold of box_threshold=0.35 (only bounding boxes with a confidence level ≥ 0.35 are retained) and a text matching threshold of text_threshold=0.25 (only bounding boxes with a text matching score ≥ 0.25 are retained). The output of the part detection processing can be uniformly written as... ,in, It is an open vocabulary detection model; For text prompts; For the first 1 candidate bounding box or , For the first The x-coordinates of the center points of the candidate bounding boxes For the first The y-coordinates of the center points of the candidate bounding boxes For the first The width of each candidate bounding box. For the first The height of each candidate bounding box For the first The minimum x-coordinate value of each candidate bounding box. For the first The minimum y-coordinate value of each candidate bounding box. For the first The maximum x-coordinate value in each candidate bounding box For the first The maximum ordinate value in each candidate bounding box; For the first The confidence level of each candidate bounding box. For the first The text matching degree of each candidate bounding box. Computer devices can be selected. , For the first The confidence level of each candidate bounding box. For the target bounding box, To obtain the maximum value, and the confidence level in the target bounding box. When the value is below the confidence threshold, a low confidence status is output as a prompt, giving subsequent cost results a verification attribute.

[0126] In some embodiments, detection models such as YOLOv8 (You Only Look Once version 8) and DETR (Detection Transformer) can also be used to detect components in the bumper image. In some embodiments, if the confidence of each candidate bounding box is lower than a preset confidence threshold (e.g., 0.6), the computer device can include a warning message in the output and allow continued generation of surface processing costs with low confidence markers for user review.

[0127] Computer devices can detect the pixel width of the target bounding box ( ) and pixel height ( Based on this, combined with the structural parameter templates corresponding to the component types and the reference scale coefficients in the reference scale information, (Unit: mm / pixel), calculate the area parameters of the corresponding process area for each process type in the component. For the bumper, the area parameters of the corresponding process area for each process type in the bumper can be determined according to the following template:

[0128] The paint area of ​​the bumper can be calculated using... Convert millimeter square meters to square meters, where The area to be coated in the spraying process. The length of the area to be coated. This refers to the height of the area to be coated. For high-gloss injection molded or chrome-plated materials, estimation can be done using... , ,in, For volume; The length of the process area; The width of the process area; Configure the thickness (THICKNESS_MM). The weight of the injection molded part or chrome-plated material; This refers to the density coefficient (DENSITY_COEFFICIENT). For bumpers, this could be:

[0129] Upper body (body color painted area): Length ,high ;

[0130] Lower body (high-gloss black sprayed area): Length ,high ;

[0131] Chrome-plated trim: Length ,high ;

[0132] High-gloss injection molded parts: Length ,high .

[0133] The dimensional ratios of 0.6, 0.4, 0.3, and 0.2 can be derived from the structural parameter template of the bumper, which can be adjusted through configuration parameters. For other part types, structural parameter templates corresponding to their structures can be created, mapping the overall area of ​​the component to different process areas. In some embodiments, the mapping of the target bounding box to the region parameters of the corresponding process areas for various process types can also be achieved based on statistical models, CAD parameter queries, or partitioning models.

[0134] Computer equipment can support unified calculations for surface treatment processes of multiple types. For example... Figure 5 As shown, after obtaining the regional parameters of the corresponding process areas for each process type, the computer equipment can calculate the costs of spraying, electroplating, and high-gloss injection molding respectively according to the cost calculation formulas included in the cost mapping relationships of each process type. The total cost of surface treatment of the parts is then obtained by summing the costs of spraying, electroplating, and high-gloss injection molding. Different process types can share the same set of input / output interfaces, but each has its own independent cost mapping relationship. In some embodiments, the cost mapping relationship may also include a regression model trained based on historical pricing data, thereby allowing the process cost of each process type to be obtained from the regional parameters of the corresponding process areas using the regression model.

[0135] In some embodiments, the cost calculation formula for the spraying process can be: ,in, The cost of the spraying process, i.e., the cost of the spraying process. For the area to be sprayed, Price per unit area for spraying It can be determined by the surface type (surface_type) and the part name (part_name). This is the paint processing fee (PAINT_PROCESSING_FEE).

[0136] The cost calculation formula for electroplating processes can be further calculated. , ,in, This refers to the area occupied by the electroplating process, i.e., the electroplating area. For the length of the component, For the height of the components, This represents the theoretical capacity of the electroplating tank. The width of the electroplating tank. The spacing between components, The height of the electroplating tank. This is the floor function. When When >200, take , then calculate , , , .in, For actual effective production capacity, For equipment costs, For the hourly equipment rate, The cycle time per unit. For labor costs, For the number of workers, The hourly labor rate, For the cost of electroplating materials, The unit price of electroplating materials per unit area. For the electroplating area, Management costs. The final electroplating process cost. .in, The cost of electroplating process for a single component, For additional investment costs, For waste material costs.

[0137] For calculating the process cost of spraying, the spraying area is used as the basis. Based on this, select the corresponding unit price according to the process type (body color / high gloss black):

[0138]

[0139] When the component is a bumper, For the spraying area ( (square millimeters), calculated from the length × height of the bumper; The unit price for spraying (yuan / ) ); Processing fee (RMB).

[0140] For calculating the process cost of electroplating, multiple electroplating types can be supported (such as bright hexavalent chromium, matte hexavalent chromium, semi-matte hexavalent chromium, bright trivalent chromium, matte trivalent chromium, black trivalent chromium, etc.), based on the area occupied by the electroplated parts in the electroplating bath:

[0141]

[0142] in, This refers to the process cost of electroplating, i.e., the cost of the electroplating process itself; material costs. ,in This is the material cost coefficient (0.7~1.0 yuan / m²). The yield rate is 0.75~0.90%. Fabric component coefficient (0.3~0.5). Equipment processing fee. Among them, the beat time Seconds, equipment hourly rate Yuan / hour. Labor cost. Among them, the hourly rate of labor Yuan / hour, number of workers people, The number of parts that can be simultaneously mounted in the electroplating tank (calculated from the area of ​​the parts and the size of the electroplating tank). Cycle time is the time required for the electroplating production line to complete a full electroplating cycle, which directly determines the equipment capacity and allocated costs.

[0143] For cost calculation of high-gloss injection molding, based on the volume of the injection molded part (calculated from length × height × thickness), the following formula can be used:

[0144]

[0145] in, To reduce the process cost of high-gloss injection molding, For the volume and density coefficient of the injection molded part High-gloss injection molding unit price Yuan / kg.

[0146] Computer equipment can sum the costs of all processes across all process types, as shown in the following formula:

[0147]

[0148] in, For the surface treatment cost of parts, For the first The computer equipment can summarize the process costs of each process type to obtain the process cost of surface treatment of parts, and retain detailed breakdowns of costs for subsequent permission filtering and result display.

[0149] In role-based cost information access management, users can trigger cost information access operations through their user accounts. Computer devices can determine the user's role based on the user account, thereby determining the user's access permissions and generating access response information according to the corresponding access permissions. For example... Figure 6As shown, user accounts can trigger access to cost information. The computer device can determine access permissions. If the user account is determined to be an administrator account, the computer device can return access response information including complete cost details, such as process costs for each process type, unit price parameters, component dimensions, and surface treatment costs for components (summed from the process costs of various process types). If the user account is determined to be a regular account, the computer device can return access response information including anonymized information, such as cost composition percentages and component surface treatment costs, thus hiding sensitive parameters such as specific unit prices and processing rates for regular accounts. The computer device can perform permission filtering before returning access response information; that is, cost-sensitive fields are filtered before distribution, achieving security control without relying on front-end hiding, reducing the risk of data leakage associated with front-end hiding schemes.

[0150] In some embodiments, a computer device can distinguish the role of the currently logged-in user account using the `current_user.is_admin` attribute of Flask-Login (a user session management extension library). Flask-Login is a user authentication extension for the Python Flask web framework, providing interfaces for user session management and `current_user` access to currently logged-in user information, thereby enabling user role differentiation. For example, cost information access control can also be implemented based on attribute-based access control (ABAC) or field-level rule engines.

[0151] The method for determining the cost of component surface treatment provided in this application, through image detection and template parameter conversion, can converge the steps that were originally scattered in manual measurement, Excel calculation, and experience correction into a unified data flow, effectively reducing manual measurement and repetitive calculation. Moreover, even in the absence of a 3D model, calculable regional parameters can be generated based on the component image and reference scale information, facilitating early cost comparison. Furthermore, various process types such as spraying, electroplating, and high-gloss injection molding can share a unified input / output interface, facilitating combined calculations and itemized cost monitoring. The method for determining the cost of component surface treatment provided in this application can obtain the confidence level of the target bounding box, regional parameters, and the process cost of each process type, making it easier for business personnel to locate and verify abnormal results. When new component types need to be supported, only the corresponding structural parameter templates and regional parameters need to be added, without redesigning the detection process, demonstrating scalability based on component type.

[0152] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0153] Based on the same inventive concept, this application also provides a component surface treatment cost determination apparatus for implementing the component surface treatment cost determination method described above. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more component surface treatment cost determination apparatus embodiments provided below can be found in the limitations of the component surface treatment cost determination method described above, and will not be repeated here.

[0154] In one exemplary embodiment, such as Figure 7 As shown, a component surface treatment cost determination device 700 is provided, including: a multi-dimensional information acquisition module 701, a component detection module 702, a region parameter determination module 703, and a process cost determination module 704, wherein:

[0155] The multi-dimensional information acquisition module 701 is used to acquire images of parts, part types, reference scale information, and the process type for surface treatment of parts; the reference scale information represents the mapping relationship between the pixel size of the image and the actual physical size;

[0156] Component detection module 702 is used to determine the target bounding box of the area occupied by the marked component in the image;

[0157] The region parameter determination module 703 is used to determine the region parameters of the process area for surface treatment in the part based on the target bounding box, part type and reference scale information;

[0158] The process cost determination module 704 is used to obtain the process cost of surface treatment of parts based on region parameters.

[0159] In some embodiments, the region parameter determination module 703 is further configured to determine the size parameters of the target bounding box; obtain a preset structural parameter template corresponding to the component type, the structural parameter template including the region structural parameters of different process areas in the component belonging to the component type, each region structural parameter including the size ratio between the corresponding process area and the overall area of ​​the component; and determine the region parameters of the process area in the component that is subjected to surface treatment based on the structural parameter template, the size parameters and the reference ratio information.

[0160] In some embodiments, there are multiple process types; the process cost determination module 704 is also used to determine the process type-cost mapping relationship; based on the regional parameters of the process area corresponding to each process type and the process type-cost mapping relationship, the process cost of surface treatment of the parts according to each process type is obtained respectively.

[0161] In some embodiments, the component detection module 702 is further configured to input an image and preset prompt words into a pre-trained open vocabulary detection model to obtain multiple candidate bounding boxes output by the open vocabulary detection model and the confidence level of each candidate bounding box; the prompt words are used to guide the open vocabulary detection model to analyze and infer the region occupied by the component in the image; and the target bounding box is determined from each candidate bounding box based on the confidence level of each candidate bounding box.

[0162] In some embodiments, the constraints on the open vocabulary detection model include at least one of the following: a bounding box confidence threshold, used to constrain the range of confidence values ​​of the candidate bounding boxes output by the open vocabulary detection model; and a text matching threshold, used to constrain the range of text matching values ​​of the candidate bounding boxes output by the open vocabulary detection model, wherein the text matching degree is used to quantify the degree of association between the image region marked by the candidate bounding box and the prompt word.

[0163] In some embodiments, the component surface treatment cost determination device 700 further includes a prompting module, which generates a prompting message when the confidence scores of each candidate bounding box are all less than a preset confidence threshold, so as to indicate that the image does not support surface treatment cost determination.

[0164] In some embodiments, the component surface treatment cost determination device 700 further includes an access response module, which is used to generate access response information based on the access permissions of the user account, at least according to the surface treatment cost, in response to a cost information access operation triggered by a user account; and push the response information to the terminal corresponding to the user account to display the access response information on the terminal.

[0165] Each module in the aforementioned component surface treatment cost determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0166] In one exemplary embodiment, a computer device and / or terminal is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores various data involved in the method for determining the surface treatment cost of components. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for determining the surface treatment cost of components.

[0167] Those skilled in the art will understand that Figure 8 The structure shown is a block diagram of a partial structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0168] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0169] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0170] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0171] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0172] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program mentioned can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0173] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0174] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining the cost of surface treatment of components, characterized in that, The method includes: The system acquires images of the components, component type, reference scale information, and the surface treatment process type for the components; the reference scale information represents the mapping relationship between the pixel size of the image and the actual physical size. Determine the target bounding box of the region occupied by the component in the image; Based on the target bounding box, the component type, and the reference scale information, determine the region parameters of the process area for surface treatment in the component; Based on the region parameters, the process cost of surface treatment of the component is obtained.

2. The method according to claim 1, characterized in that, Based on the target bounding box, the component type, and the reference scale information, the region parameters of the process area for surface treatment in the component are determined, including: Determine the size parameters of the target bounding box; Obtain a preset structural parameter template corresponding to the component type. The structural parameter template includes the regional structural parameters of different process areas in the component belonging to the component type. Each regional structural parameter includes the dimensional ratio between the corresponding process area and the overall area of ​​the component. Based on the structural parameter template, the dimensional parameters, and the reference scale information, the area parameters of the process area for surface treatment in the component are determined.

3. The method according to claim 1, characterized in that, The process types are diverse; based on the region parameters, the process cost for surface treatment of the components is obtained, including: Determine the process type-cost mapping relationship; Based on the regional parameters of the process area corresponding to each process type and the process type-cost mapping relationship, the process cost of surface treatment of parts according to each process type is obtained.

4. The method according to claim 1, characterized in that, Determining the target bounding box of the region occupied by the component in the image includes: The image and preset prompts are input into a pre-trained open vocabulary detection model to obtain multiple candidate bounding boxes and the confidence score of each candidate bounding box output by the open vocabulary detection model; the prompts are used to guide the open vocabulary detection model to analyze and infer the region occupied by the component in the image; The target bounding box is determined from each of the candidate bounding boxes based on the confidence level of each candidate bounding box.

5. The method according to claim 4, characterized in that, The constraints on the open vocabulary detection model include at least one of the following: The bounding box confidence threshold is used to constrain the range of confidence values ​​for the candidate bounding boxes output by the open vocabulary detection model. The text matching degree threshold is used to constrain the range of text matching degree values ​​of the candidate bounding boxes output by the open vocabulary detection model. The text matching degree is used to quantify the degree of association between the image region marked by the candidate bounding box and the prompt word.

6. The method according to claim 4, characterized in that, The method further includes: If the confidence scores of each candidate bounding box are less than a preset confidence threshold, a prompt message is generated to indicate that the image does not support surface processing cost determination.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: In response to a cost information access operation triggered by a user account, an access response is generated based on the access permissions of the user account, at least according to the surface treatment cost. The response information is pushed to the terminal corresponding to the user account so that the access response information is displayed on the terminal.

8. A device for determining the cost of surface treatment of parts, characterized in that, The device includes: A multi-dimensional information acquisition module is used to acquire images of components, component types, reference scale information, and the process type for surface treatment of the components; the reference scale information represents the mapping relationship between the pixel size of the image and the actual physical size; The component detection module is used to determine the target bounding box that marks the area occupied by the component in the image; The region parameter determination module is used to determine the region parameters of the process area for surface treatment in the component based on the target bounding box, the component type, and the reference scale information. The process cost determination module is used to obtain the process cost of surface treatment of the component based on the region parameters.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images