Intelligent body-in-white connection point distribution method, electronic device, and storage medium
By combining deep learning algorithms with a rule engine, the problems of cumbersome and inaccurate traditional body-in-white connection point allocation schemes are solved, realizing automated and intelligent allocation of body-in-white connection points and improving allocation efficiency and accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NIO TECH ANHUI CO LTD
- Filing Date
- 2026-04-29
- Publication Date
- 2026-07-31
AI Technical Summary
Traditional body-in-white connection point allocation schemes rely on manual operation, which is cumbersome, time-consuming, and has limited accuracy, making it difficult to achieve automation and intelligence.
By combining deep learning algorithms with a rule engine, we can obtain simulation result data, perform cluster analysis and heuristic rule redistribution, and optimize with reinforcement learning algorithms to achieve intelligent allocation of connection points in a visual interactive interface.
The allocation cycle has been significantly shortened from several days to several hours, improving allocation accuracy and consistency, eliminating deviations caused by human factors, and enhancing manufacturing efficiency and quality.
Smart Images
Figure CN122491765A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent manufacturing technology, and in particular to a method for intelligent allocation of connection points in a body-in-white, an electronic device, and a storage medium. Background Technology
[0002] With the development of robotics technology, industrial robots have been widely applied in various aspects of industrial production and daily life, such as welding, painting, and material handling in automobile manufacturing. For spot welding operations in automobiles, to adapt to complex operating environments and reduce production costs, multiple robots working collaboratively at multiple workstations are required to complete designated tasks. Therefore, it is necessary to solve the problem of allocating body-in-white connection points (also known as weld points). Traditional body-in-white connection point allocation schemes typically rely on manual operation by simulation engineers, based on experience and trial and error, which suffers from problems such as cumbersome operation, excessive time consumption, and limited accuracy. Summary of the Invention
[0003] This application aims to solve the above-mentioned technical problems, namely, the intelligent allocation method, electronic device and storage medium for body-in-white connection points proposed in this application, which can solve the problem of automation and intelligence of connection point allocation in the body-in-white manufacturing process.
[0004] In a first aspect, this application provides a method for intelligent allocation of body-in-white connection points, comprising:
[0005] Acquire simulation result data, which is used to characterize the reachability of the connection point between the robot and the body-in-white;
[0006] Based on the simulation results data, an initial allocation scheme is determined, cluster analysis is performed on the initial allocation scheme, and a redistribution is carried out based on heuristic rules to obtain an adjusted initial allocation scheme.
[0007] The adjusted initial allocation scheme is optimized based on a reinforcement learning algorithm to obtain the final connection point allocation scheme.
[0008] The allocation scheme is used to characterize the allocation relationship between the connection point and the robot.
[0009] In some technical solutions, obtaining simulation result data includes: taking the 3D model of the vehicle body and the corresponding white body connection point data as input data, and outputting the reachability of each robot to all connection points in the online simulation environment to form the simulation result data.
[0010] In some technical solutions, determining the initial allocation scheme based on the simulation result data includes:
[0011] Constraint features corresponding to connection points in the simulation result data are extracted based on historical vehicle model data;
[0012] Calculate the connection relationship score from each connection point to the robot based on the constraint features;
[0013] Based on the connection score, a suitable robot is matched for each connection point to obtain the initial allocation scheme.
[0014] In some technical solutions, the step of performing cluster analysis on the initial allocation scheme and then redistributing it based on heuristic rules to obtain an adjusted initial allocation scheme includes:
[0015] Based on the initial allocation scheme, the maximum spanning tree of each robot reachable point is obtained, and the maximum spanning tree is pruned to obtain the pruning point;
[0016] Based on heuristic rules, the bounding box algorithm is used to redistribute the pruned points to obtain the adjusted initial allocation scheme.
[0017] In some technical solutions, optimizing the adjusted initial allocation scheme based on a reinforcement learning algorithm to obtain the final connection point allocation scheme includes:
[0018] Define the state space and the action space; the state space consists of the states assigned to the connection points, and the action space consists of the assignment decisions from each connection point to the robot.
[0019] Define a reward function; where the reward function takes into account the space occupancy of the connection point allocation scheme and the spatial overlap between connection points;
[0020] A strategy optimization algorithm is used to learn the optimal allocation strategy to obtain the final connection point allocation scheme.
[0021] In some technical solutions, the method further includes: obtaining a three-dimensional body-in-white point model based on the final connection point allocation scheme, and displaying the three-dimensional body-in-white point model based on a visual interactive interface.
[0022] In some technical solutions, the method further includes: obtaining connection point reallocation instructions based on the visual interactive interface to update the three-dimensional body-in-white point model.
[0023] In some technical solutions, the method further includes: obtaining data export instructions based on the visual interactive interface to export the final connection point allocation scheme.
[0024] In a second aspect, this application provides an electronic device including at least one processor;
[0025] And, a memory communicatively connected to the at least one processor;
[0026] The memory stores a computer program, which, when executed by the at least one processor, implements the intelligent allocation method for body-in-white connection points as described in any of the above technical solutions.
[0027] In a third aspect, this application provides a computer-readable storage medium storing a plurality of program codes adapted to be loaded and run by a processor to perform the intelligent allocation method for body-in-white connection points as described in any of the above technical solutions.
[0028] The above-mentioned technical solutions of this application have at least one or more of the following beneficial effects: The intelligent allocation solution for body-in-white connection points provided by this application solves the problem of automation and intelligence in connection point allocation, eliminates the cumbersome operation and subjective dependence of traditional manual allocation; significantly shortens the allocation cycle, compressing the allocation work of several days into several hours; improves the accuracy and consistency of allocation, and avoids allocation deviations caused by human factors; realizes the global optimal solution search for multi-dimensional constraints (accessibility, cycle balance, process feasibility); and provides a visual interactive interface to facilitate manual fine-tuning and solution comparison, ultimately comprehensively improving the efficiency and quality level of body-in-white manufacturing. Attached Figure Description
[0029] The preferred embodiments of the present invention are described below with reference to the accompanying drawings, in which:
[0030] Figure 1 This is a flowchart illustrating the steps of an intelligent allocation method for body-in-white connection points provided in the application.
[0031] Figure 2 This is a flowchart illustrating the implementation steps of a method for adjusting an initial allocation scheme provided in this application;
[0032] Figure 3 This is a schematic diagram of the structure of an intelligent allocation system for body-in-white connection points according to an embodiment of this application;
[0033] Figure 4 This is a schematic diagram of the main structure of an electronic device according to an embodiment of this application. Detailed Implementation
[0034] Some embodiments of this application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of this application and are not intended to limit the scope of protection of this application.
[0035] In the description of this application, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, and memory, and can also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.
[0036] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.
[0037] In automotive intelligent assembly applications, connection points are the welds, adhesives, and studs that tightly connect hundreds of parts on a car body. A body-in-white typically has thousands of connection points, and the production line has hundreds of robots. The process of assigning each connection point to a specific workstation and robot in the workshop is called connection point allocation. The result of this allocation directly impacts overall vehicle quality, production efficiency, and production line costs. While some research has attempted to optimize traditional body-in-white connection point allocation schemes using methods such as genetic algorithms and dynamic windowing, and for example, multi-station welding robot coordinated motion planning methods that optimize production efficiency by generating welding taboo lists, these optimization methods still haven't adequately addressed the multi-dimensional constraint balance issues in the allocation process.
[0038] To this end, this application proposes a complete solution that deeply integrates deep learning algorithms with rule engines and human-computer interaction to optimize the connection point allocation scheme of the body-in-white.
[0039] like Figure 1The diagram shown is a flowchart of an intelligent allocation method for body-in-white connection points provided in this application. The allocation scheme mentioned in this method refers to a scheme used to characterize the allocation relationship between the connection point and the robot. The intelligent allocation method for body-in-white connection points provided in this application mainly includes the following steps S101 to S103.
[0040] Step S101: Obtain simulation result data;
[0041] The simulation results data can be used to characterize the accessibility of the connection point between the robot and the body-in-white. For example, accessibility can include unreachable, reachable, and reachable with interference.
[0042] In one embodiment, step S101 may specifically include: taking the 3D model of the vehicle body and the corresponding white body connection point data as input data, and outputting the reachability of each robot to all connection points in the online simulation environment to form the simulation result data.
[0043] The line simulation environment is an automated simulation module obtained through secondary development of PDPS software, capable of automating the processing from CAD models to the simulation environment. The inputs to this module are the 3D model of the vehicle body, the connection point data of the body-in-white, and simulation environment parameters. The output is the reachability status of each robot to all connection points within the simulation environment. It should be understood that the secondary development includes solidifying repetitive manual software operations and simulation processes into standardized, automated rule scripts. During line simulation, engineers no longer need to remember complex software click steps; a single click can trigger the complex simulation process to obtain the reachability status of each robot to all connection points.
[0044] Taking 293 connection points and 26 robots as an example, obtaining the simulation result data through manual operation using existing PDPS software requires thousands of manual clicks and takes about 5 days. However, the simulation process implemented by the automatic simulation module provided in this application only requires about 4 manual clicks and takes about 5 hours.
[0045] Step S102: Determine the initial allocation scheme based on the simulation result data, perform cluster analysis on the initial allocation scheme, and redistribute the data based on heuristic rules to obtain the adjusted initial allocation scheme;
[0046] In this embodiment of the application, determining the initial allocation scheme based on the simulation result data may specifically include: extracting constraint features corresponding to the connection points in the simulation result data based on historical vehicle model data, calculating the connection relationship score from each connection point to the robot based on the constraint features, and matching a suitable robot for each connection point according to the connection relationship score to obtain the initial allocation scheme.
[0047] The historical vehicle model data can be historical process point data (such as point type and location coordinates) and equipment data (such as equipment type and maximum point-marking capacity). The constraint features include production factor features and the weights of each feature. The production factor features can be understood as elements that affect the process points, and the weights can be understood as representing the degree of influence of each production factor on the process points. For example, production factor features may include point type, point location coordinates, point normal features, equipment type, maximum point-marking capacity of the equipment, collision simulation information of each point on the equipment, and the dispersion of the point. Weights corresponding to each production factor feature can be set according to actual needs. In this step, the production factor features and weights corresponding to each of the hundreds of connection points in the simulation result data can be obtained based on the historical vehicle model data. The connection relationship score of each connection point is calculated based on the production factor features and weights. Finally, the robot matching each connection point is determined by obtaining the highest score. For example, if the i-th production factor characteristic is represented by Si and its weight is represented by λi, then the connection score can be expressed as: score = λ1*S1 + λ2*S2 + ... + λi*Si.
[0048] In practical applications, a digital business model can be pre-built based on historical vehicle model data. In this step, the simulation result data can be input into the digital business model to output the initial allocation scheme. Specifically, the digital business model is configured to calculate a connection relationship score from each connection point to the robot based on constraint features, and then match a suitable robot to each connection point according to the connection relationship score to obtain the initial allocation scheme.
[0049] It should be understood that in this step S102, the initial allocation scheme can also be determined by manually allocating the simulation result data.
[0050] In some embodiments, the step of performing cluster analysis on the initial allocation scheme and then redistributing it based on heuristic rules to obtain an adjusted initial allocation scheme can be carried out using... Figure 2 The method and steps shown are as follows: Figure 2 The diagram may specifically include steps 1021 and 1022:
[0051] Step 1021: Obtain the maximum spanning tree of each robot reachable point based on the initial allocation scheme, and perform a pruning operation on the maximum spanning tree to obtain the pruning point;
[0052] Specifically, a K-nearest neighbor (KNN) graph can be constructed by first finding the K nearest neighbors of each connection point in the initial allocation scheme using the KNN algorithm. Then, a maximum spanning tree algorithm is applied to the KNN graph to generate the maximum spanning tree for each robot-reachable point. Finally, the maximum spanning tree is pruned to obtain the pruned points. In the KNN graph, the edges represent the proximity relationship between the connection point and the robot; it should be understood that the robot-reachable points can be determined based on this proximity relationship.
[0053] Step 1022: Based on heuristic rules, the pruning points are redistributed using the bounding box algorithm to obtain the adjusted initial allocation scheme.
[0054] Specifically, the volume of the AABB (axisymmetric bounding box) is calculated for each pruning point, and the reachable points of the robot are further filtered by minimizing the bounding box volume. It should be understood that the adjusted initial allocation scheme refers to the allocation scheme obtained after redistributing the pruning points based on the initial allocation scheme.
[0055] Step S103: Optimize the adjusted initial allocation scheme based on the reinforcement learning algorithm to obtain the final connection point allocation scheme.
[0056] In this embodiment of the application, the process of optimizing the adjusted initial allocation scheme based on a reinforcement learning algorithm includes:
[0057] 1) Define the state space and action space;
[0058] The state space consists of multiple connection point allocation states, represented as multiple vectors. Each vector represents all the connection points assigned to a robot. For example, the connection point allocation state can be represented by the vector R2={5,6,7,8}, where R2 represents the robot, and 5, 6, 7, and 8 in the vector represent different connection points. The overall connection point allocation state represents that the connection points numbered 5, 6, 7, and 8 are assigned to the robot R2.
[0059] The action space consists of the allocation decisions from each connection point to the robot, defining the executable operations under each connection point's allocation state. For example, actions can include splitting decisions to perform swaps and allocation decisions to perform transfers. For instance, if the connection point allocation states are R1={1,2,3,7}, R2={4,5,6,8}, after performing a swap action, the states are updated to R1={1,2,3,4}, R2={5,6,7,8}. In practical applications, action masks can be designed to filter out illegal actions, ensuring that decisions always conform to task constraints.
[0060] It should be understood that reinforcement learning algorithms also define environmental constraints; the environment maintains the legality constraints of actions, for example, the defined environmental constraints are as follows: each connection point can only be assigned to one robot; the robot must satisfy the constraint assignment if the connection point is reachable, reachable (insufficient axis margin), or reachable but has interference; the load of each robot (such as the number of connection points) cannot exceed a preset threshold.
[0061] 2) Define the reward function; the reward function should at least consider the uniformity of distribution, the balance of cycle time, and the feasibility of the process.
[0062] The goal of reinforcement learning is to make each robot occupy less space and reduce spatial overlap between robots, thereby improving resource utilization and allocation effectiveness. Therefore, the design of the reward function mainly considers the spatial occupation of the connection point allocation scheme and the spatial overlap between connection points. For example, the reward function can be constructed based on the sum of the AABB bounding box volume and the AABB bounding box intersection volume.
[0063] During the reinforcement learning phase, the action execution process is as follows: based on the current connection point allocation state, select an action from the set of legal actions to execute, update the connection point allocation state, then generate an immediate reward based on the updated connection point allocation state and the legality of the action, and finally proceed to the next round of decision-making based on the immediate reward and the new state.
[0064] 3) The optimal allocation strategy is learned by using a strategy optimization algorithm to obtain the final connection point allocation scheme.
[0065] For example, a proximal policy optimization (PPO) algorithm can be used to optimize the policy and obtain the final connection point allocation scheme.
[0066] Furthermore, the intelligent allocation method for body-in-white connection points provided in this application also provides human-computer interaction functionality. Accordingly, based on the above steps S101 to S103, the method may further include at least one of the following steps S104-S106:
[0067] Step S104: Obtain the three-dimensional body-in-white point model based on the final connection point allocation scheme, and display the three-dimensional body-in-white point model based on the visual interactive interface.
[0068] The three-dimensional white body point model can be understood as a three-dimensional model obtained by integrating a connection point allocation scheme on the basis of the original white body 3D digital model.
[0069] Step S105: Obtain connection point reallocation instructions based on the visual interactive interface to update the three-dimensional body-in-white point model.
[0070] In practical applications, when a user drags a connection point in the 3D body-in-white point model displayed on the visual interactive interface, a connection point reallocation instruction can be obtained based on the visual interactive interface. The connection point reallocation instruction is used to represent the re-establishment of the allocation relationship between the connection point and the robot after the drag operation, and then the 3D body-in-white point model displayed on the visual interactive interface is updated based on the connection point reallocation instruction.
[0071] Step S106: Obtain data export instructions based on the visual interactive interface to export the final connection point allocation scheme.
[0072] In practical applications, when a user performs a data export operation on the visual interactive interface, a data export instruction can be obtained based on the visual interactive interface. The data export instruction is used to characterize the connection point allocation scheme corresponding to the three-dimensional white body segment model displayed in the current visual interactive interface.
[0073] like Figure 3 The diagram shown illustrates the structural composition of an intelligent allocation system for body-in-white connection points provided in this application. The system architecture comprises three layers: a bottom layer (rule engine layer) responsible for basic data processing and initial allocation; a middle layer (AI optimization layer), which can employ reinforcement learning algorithms for intelligent optimization; and a top layer (human-computer interaction layer), providing a visual user interface. Figure 3 As shown, the system provided in this embodiment includes a rule allocation module 301, an intelligent optimization module 302, and a human-computer interaction module 303. The functional configurations of each module are as follows:
[0074] The rule allocation module 301 is configured to determine an initial allocation scheme based on simulation result data, perform cluster analysis on the initial allocation scheme, and perform re-allocation based on heuristic rules to obtain an adjusted initial allocation scheme.
[0075] In practical applications, the rule allocation module can be connected to the automatic simulation module to obtain simulation result data. The automatic simulation module is described in the method embodiments.
[0076] The intelligent optimization module 302 is configured to optimize the adjusted initial allocation scheme based on a reinforcement learning algorithm to obtain the final connection point allocation scheme.
[0077] The human-computer interaction module 303 is configured to display a three-dimensional white body segment model based on a visual interactive interface; wherein the three-dimensional white body segment model is obtained according to the final connection point allocation scheme.
[0078] In practical applications, the human-computer interaction module is further configured to acquire user operations and update the 3D body-in-white point model based on these operations, or to export the final connection point allocation scheme based on user operations. These user operations include dragging and dropping connection points and exporting data.
[0079] It should be understood that the above system can be used to implement the above-described intelligent allocation method for body-in-white connection points. The technical principles, technical problems solved, and technical effects of the two are similar. Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the system can be referred to the content described in the method embodiments, and will not be repeated here.
[0080] Based on the performance of the intelligent body-in-white connection point solution provided in this application in practical applications, the allocation task that originally required 5 days of manual operation can now be completed in just 5 hours. The allocation accuracy has been improved from 85% to 95% by manual operation. The color blocks of the allocation results displayed based on the 3D model are more concentrated, and the convergence has been significantly improved. At the same time, this solution allows engineers to make manual fine adjustments by dragging and dropping, and can view the statistical indicators of allocation quality in real time, greatly improving the user experience and operational efficiency.
[0081] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effect of this application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders. These adjusted solutions are equivalent to the technical solutions described in this application and therefore will also fall within the protection scope of this application.
[0082] Those skilled in the art will understand that all or part of the processes in the method of the above-described embodiment can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.
[0083] Another aspect of this application provides a computer-readable storage medium.
[0084] In one embodiment of a computer-readable storage medium according to this application, the computer-readable storage medium can be configured to store a program that performs the intelligent allocation method for body-in-white connection points according to the above-described method embodiments. This program can be loaded and run by a processor to implement the intelligent allocation method for body-in-white connection points. For ease of explanation, only the parts related to the embodiments of this application are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of this application. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of this application, the computer-readable storage medium is a non-transitory computer-readable storage medium.
[0085] Another aspect of this application provides an electronic device.
[0086] In one embodiment of an electronic device according to this application, the electronic device may include at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program, which, when executed by the at least one processor, implements the intelligent allocation method for body-in-white connection points described in any of the above embodiments. The electronic device described in this application may be, but is not limited to, a mobile phone, tablet computer, handheld computer, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), etc., and this application does not limit this to any particular type. See appendix. Figure 4 , Figure 4 The example shows a memory 401 and a processor 402 connected via a bus communication connection.
[0087] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.
Claims
1. A body-in-white connection point intelligent allocation method, characterized in that, include: Acquire simulation result data, which is used to characterize the reachability of the connection point between the robot and the body-in-white; Based on the simulation results data, an initial allocation scheme is determined, cluster analysis is performed on the initial allocation scheme, and a redistribution is carried out based on heuristic rules to obtain an adjusted initial allocation scheme. The adjusted initial allocation scheme is optimized based on a reinforcement learning algorithm to obtain the final connection point allocation scheme. The allocation scheme is used to characterize the allocation relationship between the connection point and the robot.
2. The body-in-white connection point intelligent assignment method according to claim 1, wherein, The process of obtaining simulation result data includes: taking the 3D model of the vehicle body and the corresponding white body connection point data as input data, and outputting the reachability of each robot to all connection points in the online simulation environment to form the simulation result data.
3. The intelligent allocation method for body-in-white connection points according to claim 1, characterized in that, The process of determining the initial allocation scheme based on the simulation results data includes: Constraint features corresponding to connection points in the simulation result data are extracted based on historical vehicle model data; Calculate the connection relationship score from each connection point to the robot based on the constraint features; Based on the connection score, a suitable robot is matched for each connection point to obtain the initial allocation scheme.
4. The intelligent allocation method for body-in-white connection points according to claim 1, characterized in that, The step of performing cluster analysis on the initial allocation scheme and then redistributing it based on heuristic rules to obtain an adjusted initial allocation scheme includes: Based on the initial allocation scheme, the maximum spanning tree of each robot reachable point is obtained, and the maximum spanning tree is pruned to obtain the pruning point; Based on heuristic rules, the bounding box algorithm is used to redistribute the pruned points to obtain the adjusted initial allocation scheme.
5. The intelligent allocation method for body-in-white connection points according to claim 1, characterized in that, The optimization of the adjusted initial allocation scheme based on the reinforcement learning algorithm to obtain the final connection point allocation scheme includes: Define the state space and the action space; the state space consists of the states assigned to the connection points, and the action space consists of the assignment decisions from each connection point to the robot. Define a reward function; where the reward function takes into account the space occupancy of the connection point allocation scheme and the spatial overlap between connection points; A strategy optimization algorithm is used to learn the optimal allocation strategy to obtain the final connection point allocation scheme.
6. The intelligent allocation method for body-in-white connection points according to claim 1, characterized in that, The method further includes: obtaining a three-dimensional body-in-white point model based on the final connection point allocation scheme, and displaying the three-dimensional body-in-white point model based on a visual interactive interface.
7. The intelligent allocation method for body-in-white connection points according to claim 6, characterized in that, The method further includes: obtaining connection point reallocation instructions based on the visual interactive interface to update the three-dimensional body-in-white point model.
8. The intelligent allocation method for body-in-white connection points according to claim 6, characterized in that, The method further includes: obtaining data export instructions based on the visual interactive interface to export the final connection point allocation scheme.
9. An electronic device, characterized in that, Includes at least one processor; And, a memory communicatively connected to the at least one processor; The memory stores a computer program, which, when executed by the at least one processor, implements the intelligent allocation method for body-in-white connection points as described in any one of claims 1 to 8.
10. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the intelligent allocation method for body-in-white connection points as described in any one of claims 1 to 8.