Intelligent recommendation method and system based on shared robot

Abstract

The invention belongs to the field of intelligent manufacturing, and provides an intelligent recommendation method and system based on a shared robot, and the method comprises the steps: receiving a picture and a processing demand provided by a user; determining the processing attribute of the target workpiece according to the picture; determining a processing sub-task according to the processing attribute; determining an optimal shared robot combination according to the processing subtasks and the processing requirements; and displaying the optimal shared robot combination to the user.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent manufacturing, and specifically relates to an intelligent recommendation method and system based on a shared robot. Background Art

[0002] Smart manufacturing and automation technology have become the core driving force of modern industry. In this context, shared robots, as a flexible and efficient production tool, are gradually replacing traditional single-purpose industrial robots. Shared robots can dynamically allocate and collaborate to complete a variety of tasks according to actual needs. They have the characteristics of high resource utilization and strong adaptability, and are particularly suitable for complex and diverse production environments.

[0003] In traditional industrial scenarios, robots are usually fixed for certain specific tasks, such as cutting, welding, grinding, etc. However, some robots are idle when the task volume is low, while other tasks may be hindered by the lack of suitable robots. Traditional robots are difficult to adapt to complex and diverse task requirements, especially when production tasks involve multiple different processes, which usually require the support of multiple dedicated equipment, increasing costs and management complexity. When production needs change (such as urgent orders or product design changes), it is difficult to quickly adjust the existing robot allocation plan, resulting in production delays and reduced efficiency.

[0004] To solve these problems, shared robot systems have emerged. Through intelligent resource scheduling and task optimization, shared robots can flexibly allocate tasks according to production needs and dynamically adjust robot combinations, thereby significantly improving resource utilization and production efficiency. However, there is no specific technical solution for how to recommend the allocation of shared robots in the prior art. Summary of the invention

[0005] In order to solve the problems in the prior art, the present invention provides an intelligent recommendation method based on shared robots, which includes the following steps: receiving pictures and processing requirements provided by users; determining processing attributes of a target workpiece based on the pictures; determining processing subtasks based on the processing attributes; determining an optimal shared robot combination based on the processing subtasks and the processing requirements; and displaying the optimal shared robot combination to users.

[0006] Another aspect of the present invention further provides an intelligent recommendation system based on a shared robot, the system comprising the following modules:

[0007] Receiving module, used to receive pictures and processing requirements provided by users;

[0008] A determination module, used to determine the processing attributes of the target workpiece according to the image;

[0009] A splitting module, used for determining processing subtasks according to the processing attributes;

[0010] A combination module, used to determine the optimal shared robot combination according to the processing subtasks and the processing requirements;

[0011] A display module is used to display the optimal shared robot combination to the user.

[0012] The intelligent recommendation method based on shared robots proposed in the present invention performs intelligent analysis on the processing requirements and workpiece information provided by users, combines the shared robot database, and dynamically recommends the optimal robot combination, which has the following significant beneficial effects:

[0013] The present invention can dynamically allocate robot resources according to task requirements, avoiding the problem of idle or overloaded resources in the traditional fixed allocation mode. It supports multiple robots to work together, decomposes complex tasks into subtasks and allocates them reasonably, and improves the overall resource utilization and task completion efficiency of the system.

[0014] Intelligent algorithms are used to optimize task allocation to ensure that all tasks are completed in the shortest possible time while meeting processing accuracy and cost constraints. Multiple robots can perform different parts of tasks in parallel, such as multiple cutting robots processing different areas at the same time, which can significantly shorten the time it takes to complete a single task.

[0015] In task allocation and robot combination optimization, the balance between processing time and cost is fully considered. Users can customize the weight of time and cost and choose the recommended solution with efficiency priority or cost priority. Reduce the dependence on high-performance stand-alone equipment, complete difficult tasks through the collaboration of ordinary robots, and reduce equipment investment and operating costs.

[0016] The task allocation scheme is intuitively displayed through a visual interface, including task division, robot configuration, completion time and cost distribution, which is convenient for users to understand and make decisions. It provides user interaction functions, allowing users to adjust the recommended scheme and calculate the updated results in real time, enhancing the flexibility and applicability of the system.

[0017] In summary, the present invention realizes efficient configuration and flexible adaptation of production resources through an intelligent, visual and interactive robot recommendation system, provides important technical support for modern industrial intelligent manufacturing, and significantly improves processing efficiency, resource utilization and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0020] Below, the invention is preferably described in conjunction with the accompanying drawings and specific implementation methods.

[0021] This embodiment solves the above problem through the following steps:

[0022] In one embodiment, reference Figure 1 The present invention provides an intelligent recommendation method based on shared robots, which intelligently identifies user needs by analyzing the input information provided by users, and dynamically selects suitable robot combinations and supporting equipment from the shared robot database to complete specified tasks, while optimizing processing time, cost and resource utilization efficiency, providing users with visual processing plans and feedback adjustment mechanisms, and realizing intelligent and customized robot service recommendations.

[0023] Receive pictures and processing requirements provided by users. By obtaining relevant pictures uploaded by users and clear descriptions of processing requirements, data support is provided for subsequent intelligent analysis and determination of the optimal shared robot combination.

[0024] First, users need to provide a full-view picture of the workpiece, showing the overall shape, size and structural features of the target workpiece, for preliminary identification of the workpiece type and geometric characteristics. Provide a front view, top view and side view to reflect the complete form of the workpiece. Ensure that the picture is clear, such as a resolution of no less than 300dpi, and avoid background interference.

[0025] The full picture of the workpiece can be used to extract the basic geometric parameters of the workpiece (such as length, width, height), determine the type of workpiece (such as plate, pipe, complex special-shaped parts, etc.), and provide a basis for robot task planning.

[0026] It is also necessary to provide close-up photos of the workpiece details, and take close-up photos of the areas that need to be processed or treated (such as holes, welding points, edges, and notches) to show the local characteristics. Provide high-definition close-up photos for each key processing part to ensure that the local details are clearly visible. If there are multiple processing areas, they should be photographed and marked separately.

[0027] Close-up images of workpiece details can be used to accurately identify processing requirements in key areas (such as hole diameter, edge characteristics, and weld point locations) and determine whether robots with specific functions are needed (such as drilling robots and grinding robots).

[0028] You can also provide material attribute identification images to provide material information of the target workpiece, including material type, physical properties and possible surface treatment layers. If there is a material identification on the workpiece, you need to provide an identification image (such as a metal nameplate, plastic code). For composite materials, provide an image or description of the layered structure.

[0029] Provide material property identification images to determine material processing properties (such as hardness, toughness, thermal sensitivity). Help recommend processing tools and robots (such as laser cutting robots, welding robots) that are suitable for the material.

[0030] You can also provide pictures of the target product to show the final shape of the workpiece after processing, reflecting the appearance and functional characteristics of the target workpiece. Provide front, back and side views of the target product to show the effect to be achieved after processing. If surface treatment is involved, provide pictures of the surface effect of the finished product (such as polishing, spraying).

[0031] The target product image can be used to compare the shape changes of the workpiece before and after processing, clarify the processing steps and precision requirements, and optimize the recommended processing plan and process.

[0032] You can also provide pictures of the processing scene, provide pictures of the actual processing scene where the workpiece is located, including the existing equipment layout, space environment and other conditions. Take pictures of the workbench or fixture where the workpiece is located, as well as wide-angle photos of the surrounding space. Show the use status of the on-site equipment and related auxiliary facilities.

[0033] The processing scene pictures can be used to confirm the site limitations (such as space height, processing range) and recommend robots suitable for the site conditions (such as size, load capacity, range of motion).

[0034] The processing requirements that users need to provide include:

[0035] Processing type, specify the specific type of processing task, including one or more of the following:

[0036] Cutting: The method by which material removal is required (laser cutting, plasma cutting, etc.).

[0037] Welding: The parts of the workpiece that need to be welded and the strength requirements.

[0038] Drilling: hole size, location and number.

[0039] Grinding and polishing: roughness requirements for surface treatment.

[0040] Assembly: The way parts are joined or assembled.

[0041] Spraying: surface coating type and uniformity requirements.

[0042] Processing accuracy, clarify the processing accuracy parameters, including:

[0043] Geometric tolerances (such as flatness, perpendicularity).

[0044] Dimensional tolerances (e.g. aperture deviation, edge dimensions).

[0045] Surface roughness (such as Ra value).

[0046] Processing efficiency, clearly specify the requirements for processing speed or production efficiency, for example:

[0047] Processing time limit (such as a single workpiece needs to be completed within a certain time).

[0048] Daily production target.

[0049] Processing cost, propose a budget or constraints for processing cost, including robot resource usage fees and energy consumption limits.

[0050] Environmental adaptation, requirements for the working environment, such as:

[0051] Whether high temperature, high humidity, dust or other special conditions are involved.

[0052] Whether it is necessary to meet additional requirements such as low noise and environmental protection.

[0053] Determine the processing properties of the target workpiece based on the image. Through intelligent analysis and feature extraction of the images uploaded by users, we can fully understand the physical properties, geometric properties and potential processing requirements of the target workpiece, providing a basis for subsequent task decomposition and robot matching.

[0054] Before analyzing the image, the following processing is performed on the image uploaded by the user to ensure accurate information extraction, including:

[0055] Image cleaning: Remove background noise and interference from non-target objects and focus on the target artifact area.

[0056] Multi-angle fusion: Align and fuse artifact images from different perspectives to generate a complete 3D model.

[0057] Image Enhancement: Improves picture contrast and resolution to ensure details are clearly visible.

[0058] Extract the geometric characteristics of the target workpiece from the image, including overall shape and key dimensions:

[0059] Extract the overall shape, use image segmentation algorithms (such as U-Net) to separate the main part of the workpiece, and determine the basic shape of the workpiece (such as plates, bars, cylinders, and complex special-shaped parts).

[0060] Extract key dimensions, use edge detection algorithms (such as Canny edge detection) to extract the workpiece contour, and calculate key parameters such as length, width, and height. Detect the position, size, and shape of special geometric features (such as holes, grooves, and edge chamfers).

[0061] Combine the material information and texture features reflected in the picture to determine the material properties of the workpiece:

[0062] Use deep learning models (such as ResNet) to analyze the texture pattern of the workpiece surface to determine whether it is metal, plastic, composite material or other special materials.

[0063] Detect surface gloss, roughness, coating or protective layer. Determine whether further surface treatment (such as polishing, spraying) is required.

[0064] If the image contains material identification information (such as nameplate, code), extract the corresponding material type (such as aluminum alloy, stainless steel, ABS plastic) and its physical properties.

[0065] By analyzing the local area of ​​the picture, determine the area that needs to be processed:

[0066] Use object detection algorithms (such as YOLO) to automatically identify critical processing areas (such as holes, welds, cut edges).

[0067] Detailed feature analysis of the processing area, such as:

[0068] Holes: diameter, depth, location.

[0069] Welding point: welding path, weld length.

[0070] Edge: chamfer angle, cutting accuracy requirements.

[0071] Based on the image analysis results and combined with the industry knowledge base, the processing requirements of the target workpiece are inferred:

[0072] Determine the required processing tasks (such as cutting, welding, drilling, assembly, spraying) based on the characteristics of the workpiece.

[0073] Infer dimensional tolerances, geometric tolerances, and surface finish requirements based on the workpiece characteristics and textures shown in the images.

[0074] If the image contains the reference form of the target product, the functional requirements that the workpiece needs to meet (such as sealing, wear resistance) can be further inferred.

[0075] Through comprehensive analysis of the image, the following processing attributes are extracted and output:

[0076] Geometric properties: including workpiece shape, size, hole location and other features.

[0077] Material properties: including material type, surface state, and physical properties.

[0078] Processing area attributes: including the characteristics and requirements of key parts.

[0079] Processing requirements: including processing task type, processing accuracy and functional goals.

[0080] The above processing attributes provide comprehensive data support for the subsequent task decomposition and optimization recommendation of shared robot combinations, ensuring that the recommended solutions can accurately meet the actual processing requirements of the workpiece.

[0081] Determining the processing subtasks based on the processing attributes specifically refers to breaking down the overall processing task into multiple executable subtasks by analyzing the geometric characteristics, material characteristics, key processing areas, and processing requirements of the target workpiece. These subtasks clarify the goals, scope, and requirements of each processing step, providing a basis for subsequent robot division of labor and resource optimization.

[0082] Specifically, the cutting subtask is determined first.

[0083] According to the geometric characteristics of the target workpiece, such as the overall shape and size requirements, it is determined whether the shape or edge processing needs to be completed by cutting. For example, when the design drawing of the workpiece shows a complex contour or irregular shape, by analyzing the difference between the outer contour of the workpiece in the picture and the design target, it is determined that a cutting operation is required. In addition, when the material characteristics indicate that the workpiece is metal or composite material and has a thick edge, laser cutting or water jet cutting is preferred.

[0084] For example, if a user uploads a picture showing a metal sheet and the goal is to process a workpiece with a complex curved contour, the image analysis shows that the sheet is currently rectangular and made of stainless steel. Based on the processing attributes (complex curved contour, stainless steel material, thickness 5mm), the cutting subtask can be determined and the laser cutting robot is recommended to complete it.

[0085] Then determine the welding subtask.

[0086] Based on the material properties of the workpiece and the location of the critical processing area, it is determined whether welding is required to achieve the splicing or connection of the workpiece. When the processing attributes show that the workpiece consists of multiple parts and needs to maintain the overall structural integrity under high strength, the welding subtask can be determined. In addition, the welding demand also depends on the length of the seam, the number of welding points, and the welding characteristics of the material (such as the ease of welding of metal alloys).

[0087] For example, a user provides a set of pictures of a steel frame, and the goal is to weld the separated steel pipes to form an overall structure. Analysis of the pictures shows that the joints are located at the nodes of the frame, and the material properties indicate that the steel is suitable for arc welding. Based on the processing properties (steel, node location, welding strength requirements), the welding subtasks can be determined and the arc welding robot can be recommended to complete them.

[0088] Then determine the grinding and polishing subtasks.

[0089] According to the roughness requirements of the workpiece surface and the characteristics of the local processing area, it is determined whether the surface quality needs to be improved by grinding or polishing. For example, when the joint after welding needs to be deburred or smoothed, or the surface needs to achieve a mirror finish, the grinding and polishing subtasks can be determined. Material properties (such as the hardness of metals or the scratch resistance of plastic surfaces) will also affect the selection of grinding tools.

[0090] For example, a user uploads a picture of a metal bracket, and the goal is to make the bracket surface smooth. Analysis of the picture shows that there is an obvious weld in the welding area, and the surface roughness is higher than the design requirement (Ra>2.0). According to the processing attributes (weld area, metal material, smooth appearance requirements), the grinding and polishing subtasks can be determined, and the use of an automatic grinding robot is recommended.

[0091] Then determine the drilling subtask

[0092] According to the geometric characteristics and functional requirements of the target workpiece, it is determined whether it is necessary to provide the workpiece with connection or assembly functions through drilling. For example, when the processing attributes show that the workpiece needs to be bolted, and the precise hole position, quantity and size (such as diameter and depth) are marked in the design drawing, the drilling subtask can be determined. Material properties will also affect the choice of drilling method (such as plastics are suitable for mechanical drilling, hard metals may require laser drilling).

[0093] For example, a user uploads a picture of a plastic board, and the goal is to drill multiple mounting holes with a diameter of 10 mm on the board. After analyzing the picture and processing requirements, it is found that the hole positions and quantity are clear, and the material is ABS plastic. Based on the processing properties (hole diameter, hole position, plastic material), the drilling subtask can be determined, and the use of a mechanical drilling robot is recommended.

[0094] Then determine the assembly subtasks.

[0095] Based on the geometric characteristics of the workpiece and the overall requirements of the product design, determine whether it is necessary to complete the connection of multiple parts through assembly. When the processing attributes show that the workpiece consists of multiple parts and needs to be assembled into a whole, or the target product picture shows the assembled finished product form, the assembly subtask can be determined. The assembly method also depends on the functional requirements (such as fixed connection, flexible disassembly).

[0096] For example, if a user provides multiple pictures of electronic product housing parts, the goal is to assemble these parts into a complete housing structure. By analyzing the pictures, it is found that the slot design of each part is clear and the assembly method is snap-on connection. Based on the processing attributes (slot structure, assembly method), the assembly subtask can be determined and the flexible assembly robot can be recommended to complete it.

[0097] Then determine the surface treatment subtasks.

[0098] Determine whether surface treatment (such as coating, anti-corrosion or spraying) is required based on the surface condition and design requirements of the workpiece. When the processing attributes show that the target product requires a uniform coating, a specific color or a protective function, the surface treatment subtask can be determined. Material properties (such as anti-corrosion coating for metals and aesthetic spraying for plastics) determine the choice of spraying materials and methods.

[0099] For example, a user provides a picture of a steel pipe, and the goal is to spray an anti-rust coating. Analysis of the picture shows that the surface of the steel pipe is exposed and rough, and a uniform anti-corrosion coating needs to be sprayed to meet outdoor use requirements. Based on the processing properties (steel pipe material, coating uniformity requirements), the surface treatment subtask can be determined, and it is recommended to use a multi-axis spray robot to complete it.

[0100] Finally, determine the inspection and quality control subtasks.

[0101] Based on the geometric characteristics, functional requirements and surface quality requirements of the workpiece after processing, it is determined whether it is necessary to confirm whether the workpiece meets the design standards through inspection. When the processing attributes show that precise dimensional tolerances, surface defects or specific mechanical properties are required, the inspection and quality control subtasks can be determined. The inspection method depends on the specific needs (such as visual inspection, dimensional measurement, ultrasonic non-destructive testing).

[0102] For example, if a user uploads a picture of a precision part, the goal is to confirm whether the hole position and size meet the design tolerance. Analyzing the picture and design requirements, it is found that the hole position must be accurate to ±0.1mm and there must be no scratches on the surface. Based on the processing properties (hole tolerance, surface defect requirements), the inspection and quality control subtasks can be determined, and the use of visual inspection robots and three-dimensional coordinate measuring machines is recommended.

[0103] An optimal shared robot combination is determined according to the processing subtasks and the processing requirements.

[0104] After the client uploads the image on the web page or mobile terminal, it is hoped that the recommendation of the shared robot combination can be obtained quickly. In order to quickly obtain the optimal shared robot combination, the present invention is implemented by the following steps:

[0105] Decompose the processing task into multiple subtasks T = {t1, t2…t n}, where n represents the total number of tasks, t nIndicates the nth task, such as cutting, welding, grinding, etc.

[0106] Each subtask t i include:

[0107] Task type: processing type (such as cutting, welding).

[0108] Time limit limit (t i ): Subtasks need to be completed within the specified time.

[0109] Cost Limit limit (t i ): The upper limit of the task execution budget.

[0110] Accuracy requirement limit (t i ): The processing accuracy requirements that the task needs to meet.

[0111] Robot set R = {r1, r2…r m}, where m represents the total number of robots, r m Represents the mth robot, each robot rj includes:

[0112] Function f j : The types of tasks supported by the robot (such as cutting, welding).

[0113] Performance pj: processing accuracy, speed, etc. of the robot's tasks.

[0114] Time efficiency j : Time to complete the task.

[0115] Cost cj: The cost of the robot performing the task.

[0116] Available states j : Whether it is currently available (1 means available, 0 means unavailable).

[0117] Define the allocation matrix X = {x ij}, indicating robot r j Is it assigned to task t? i :

[0118]

[0119] The goal is to minimize the total time and total cost of the task while satisfying all task requirements:

[0120]

[0121] Among them, α and β are the weight coefficients of time and cost respectively. They can be set by the user in the user interface. If the user pays more attention to the completion time of the task, α can be set to a larger value, and if the user pays more attention to cost saving, β can be set to a larger value.

[0122] Each task must be assigned at least one robot that meets the functional requirements:

[0123]

[0124] Robot j Subtask t must be supported i Features:

[0125]

[0126] The total robot time allocated to a task must not exceed the task limit:

[0127]

[0128] The total cost of the robots assigned to a task must not exceed the cost limit:

[0129]

[0130] Robot j The machining accuracy must meet the task t i Requirements:

[0131] p j ≥p limit (t i ),if x ij =1

[0132] Only robots that are currently available can be selected:

[0133]

[0134] Determining the optimal shared robot combination

[0135] Several initial combinations are randomly generated, and each solution is an assignment matrix X that satisfies the constraints, ensuring that at least one robot is assigned to each task (task completion constraint), the robot function must match the task requirements (function matching constraint), and the robot available state is 1.

[0136] For the initial combination, the robot cost c j or time t j Sort in ascending order (tasks with tighter constraints are assigned first), and assign robots that meet the requirements to each task in turn to ensure the basic feasibility of the solution.

[0137] Calculate each combination X i Target value

[0138]

[0139] Use genetic algorithms to perform genetic mutations on several initial combinations and determine the current optimal combination X based on the target value * .

[0140] Replace a task i Robots:

[0141] x ij →0,x ik →1,j≠k

[0142] Ensure that the replacement task t i The functional requirements are still met. The objective function value does not increase after replacement.

[0143] For each task, introduce multiple robots and analyze the changes in the objective function:

[0144] x ij ,x ik =1,j≠k

[0145] If the objective function value decreases and satisfies the constraints, keep this adjustment. In the adjusted result, one task may correspond to multiple robots, and multiple robots can perform different parts of the task in parallel. For example, in a cutting task, different robots process different workpiece areas at the same time, greatly reducing the total task time caused by single-machine operation. By assigning multiple robots to complete a single task, resource utilization can be optimized, task execution quality can be improved, and higher flexibility and adaptability can be provided for complex production environments.

[0146] The optimal shared robot combination is presented to the user. Specifically, the optimization results are presented intuitively in a variety of ways, so that the user can clearly understand the assigned robot combination, task division, processing flow and its advantages, and the user is allowed to verify or adjust the recommended solution.

[0147] Clearly list the assignment relationship between each task and the corresponding robot, including:

[0148] Task number: such as t1 (cutting task), t2 (welding task).

[0149] Assign robots: such as r1 (cutting robot), r2 (welding robot).

[0150] For each task, the following details are shown:

[0151] Task type: such as cutting, welding, polishing.

[0152] Execute Robot: Displays the robot model and performance parameters (such as speed, accuracy, and load capacity).

[0153] Completion Time: The estimated completion time for each task.

[0154] Execution cost: The robot running cost for each task and the total cost distribution.

[0155] Comprehensively display the performance indicators of the entire shared robot system:

[0156] Total Task Time: The total time required to complete all tasks.

[0157] Total Task Cost: The cumulative cost to complete all tasks.

[0158] Resource utilization: Displays the workload ratio of each robot to avoid resource waste.

[0159] Furthermore, the task allocation and collaboration process between robots can be displayed through a task flow chart:

[0160] Nodes represent tasks (such as cutting and welding), and edges represent the sequential relationship between tasks.

[0161] Each node is marked with the corresponding robot number and estimated completion time.

[0162] Furthermore, it is possible to generate dynamic visualization of robot task execution in combination with the actual factory layout:

[0163] Mark the robot's location and task execution path in a two-dimensional plane.

[0164] Use different colors and line types to distinguish robots and their task flows.

[0165] Furthermore, the task execution process can be displayed through 3D animation:

[0166] Show how robots complete tasks in a simulated environment, including task division, collaboration, and execution process.

[0167] For example:

[0168] The cutting robot cuts the metal sheet along a preset path.

[0169] The welding robot automatically welds the connection parts.

[0170] Furthermore, an interactive interface is provided to allow users to adjust robot allocation based on the displayed results:

[0171] Users can manually change the assignment relationship between tasks and robots.

[0172] The system calculates the adjusted time, cost and performance indicators in real time, and dynamically updates the displayed results.

[0173] Furthermore, it provides a virtual simulation function for task execution, simulating the working conditions of the robot in the actual environment and verifying the feasibility and effectiveness of the assignment:

[0174] Users can observe the robots moving, processing, and collaborating in a virtual environment.

[0175] Highlight the time nodes and key steps for task completion.

[0176] Through these methods, showing users the optimal shared robot combination not only helps them intuitively understand the optimization results, but also provides a reliable basis for actual production deployment.

[0177] On the other hand, the present invention also provides an intelligent recommendation system based on a shared robot, comprising:

[0178] Receiving module, used to receive pictures and processing requirements provided by users;

[0179] A determination module, used to determine the processing attributes of the target workpiece according to the image;

[0180] A splitting module, used for determining processing subtasks according to the processing attributes;

[0181] A combination module, used to determine the optimal shared robot combination according to the processing subtasks and the processing requirements;

[0182] A display module is used to display the optimal shared robot combination to the user.

[0183] The prior art mentioned in the above background technology section and specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters.

Claims

1. An intelligent recommendation method based on a shared robot, characterized in that: The method comprises the following steps: Receive pictures and processing requirements provided by users; determining a processing attribute of a target workpiece according to the image; Determining a processing subtask according to the processing attribute; Determine the optimal shared robot combination according to the processing subtasks and the processing requirements; The optimal shared robot combination is displayed to the user.

2. The intelligent recommendation method based on a shared robot according to claim 1, characterized in that: The pictures provided by the user include: overall pictures of the workpiece, close-up pictures of the workpiece details, pictures of material attribute identification, pictures of the target product, and pictures of the processing scene.

3. The intelligent recommendation method based on a shared robot according to claim 1, characterized in that: The processing requirements include: processing type, processing efficiency, processing time limit, daily production volume, processing cost, and environmental adaptation.

4. The intelligent recommendation method based on a shared robot according to claim 1, characterized in that: The processing subtasks include: cutting subtask, welding subtask, grinding and polishing subtask, drilling subtask, assembly subtask, surface treatment subtask, and detection and quality control subtask.

5. The intelligent recommendation method based on a shared robot according to claim 1, characterized in that: Determining the optimal shared robot combination according to the processing subtasks and the processing requirements includes: Decompose the processing task into multiple subtasks; Robot collection; Each robot includes: function, performance, time efficiency, cost, and availability; Define the assignment matrix, indicating whether the robot is assigned to a task: The goal is to minimize the total time and total cost of the task while satisfying all task requirements; Each task must be assigned at least one robot that meets the functional requirements; The robot must support the functionality of the subtasks; The total robot time allocated to a task must not exceed the task limit; The total cost of the robots assigned to a task must not exceed the cost limit; The robot's machining accuracy must meet the requirements of the task; Only robots that are currently available can be selected; When determining the optimal shared robot combination, several initial combinations are randomly generated. Each solution is an allocation matrix that satisfies the constraints, ensuring that at least one robot is assigned to each task, the robot function must match the task requirements, and the robot availability status is 1; Sort the initial combinations in ascending order of robot cost or time, and assign robots that meet the requirements to each task in turn; Calculate the target value for each combination; Use genetic algorithms to perform genetic mutations on the initial combination and determine the current optimal combination based on the target value; Replace the robot for a certain task with the current optimal combination; Ensure that the task still meets the functional requirements after replacement and the objective function value does not increase after replacement; For each task, multiple robots are introduced and the objective function changes are analyzed; If the objective function value decreases and the constraints are satisfied, keep the adjustment.

6. An intelligent recommendation system based on a shared robot, characterized in that: The system includes the following modules: Receiving module, used to receive pictures and processing requirements provided by users; A determination module, used to determine the processing attributes of the target workpiece according to the image; A splitting module, used for determining processing subtasks according to the processing attributes; A combination module, used to determine the optimal shared robot combination according to the processing subtasks and the processing requirements; A display module is used to display the optimal shared robot combination to the user.

7. The intelligent recommendation system based on a shared robot according to claim 6, characterized in that: The pictures provided by the user include: overall pictures of the workpiece, close-up pictures of the workpiece details, pictures of material attribute identification, pictures of the target product, and pictures of the processing scene.

8. The intelligent recommendation system based on a shared robot according to claim 6, characterized in that: The processing requirements include: processing type, processing efficiency, processing time limit, daily production volume, processing cost, and environmental adaptation.

9. The intelligent recommendation system based on a shared robot according to claim 6, characterized in that: The processing subtasks include: cutting subtask, welding subtask, grinding and polishing subtask, drilling subtask, assembly subtask, surface treatment subtask, and detection and quality control subtask.

10. The intelligent recommendation system based on a shared robot according to claim 6, characterized in that: Determining the optimal shared robot combination according to the processing subtasks and the processing requirements includes: Decompose the processing task into multiple subtasks; Robot collection; Each robot includes: function, performance, time efficiency, cost, and availability; Define the assignment matrix, indicating whether the robot is assigned to a task: The goal is to minimize the total time and total cost of the task while satisfying all task requirements; Each task must be assigned at least one robot that meets the functional requirements; The robot must support the functionality of the subtasks; The total robot time allocated to a task must not exceed the task limit; The total cost of the robots assigned to a task must not exceed the cost limit; The robot's machining accuracy must meet the requirements of the task; Only robots that are currently available can be selected; When determining the optimal shared robot combination, several initial combinations are randomly generated. Each solution is an allocation matrix that satisfies the constraints, ensuring that at least one robot is assigned to each task, the robot function must match the task requirements, and the robot availability status is 1; Sort the initial combinations in ascending order of robot cost or time, and assign robots that meet the requirements to each task in turn; Calculate the target value for each combination; Use genetic algorithms to perform genetic mutations on the initial combination and determine the current optimal combination based on the target value; Replace the robot for a certain task with the current optimal combination; Ensure that the task still meets the functional requirements after replacement and the objective function value does not increase after replacement; For each task, multiple robots are introduced and the objective function changes are analyzed; If the objective function value decreases and the constraints are satisfied, keep the adjustment.

Images