A general servo drive method and system based on artificial intelligence

Abstract

A general servo drive method and system based on artificial intelligence provided by the present invention relate to the technical field of general servo drive. The method includes obtaining a three-dimensional image of a device to be cut, a three-dimensional image of a target device, and servo drive device information; determining multiple sets of preliminary operation plans using an image processing model based on the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the servo drive device information; generating a simulated operation video for each set of preliminary operation plans using a generative adversarial network based on the three-dimensional image of the device to be cut and the multiple sets of preliminary operation plans; determining a target operation plan based on the simulated operation videos of each set of preliminary operation plans; and controlling the servo drive device to perform servo drive based on the target operation plan. This method can quickly determine the optimal operation plan for cutting and processing devices.

Description

Technical Field

[0001] The present invention relates to the technical field of servo device control, and particularly to a general servo drive method and system based on artificial intelligence. Background Art

[0002] Servo drive systems have important application values in cutting device operations. By precisely controlling mechanical movements, they can achieve high-precision and high-efficiency operations. Traditional device cutting operations usually rely on fixed solutions for execution and lack the ability to dynamically adjust according to the specific characteristics of the device to be cut. In addition, the selection and adjustment of operation plans overly rely on the experience of operators, which is prone to human errors. In some complex and high-precision tasks, determining and selecting operation plans often takes a long time, resulting in low efficiency.

[0003] Therefore, how to quickly determine the optimal operation plan for cutting and processing devices is an urgent problem to be solved currently. Summary of the Invention

[0004] The main technical problem to be solved by the present invention is how to quickly determine the optimal operation plan for cutting and processing devices.

[0005] According to a first aspect, the present invention provides a general servo drive method based on artificial intelligence, including: obtaining three-dimensional images of a device to be cut, three-dimensional images of target devices, and servo drive device information; determining multiple sets of preliminary operation plans using an image processing model based on the three-dimensional images of the device to be cut, the three-dimensional images of the target devices, and the servo drive device information; generating a simulated operation video for each set of preliminary operation plans using a generative adversarial network based on the three-dimensional images of the device to be cut and the multiple sets of preliminary operation plans; determining a target operation plan based on the simulated operation videos of each set of preliminary operation plans; and controlling the servo drive device to perform servo drive based on the target operation plan.

[0006] In a possible implementation, determining the target operation plan based on the simulation operation videos of each set of preliminary selection operation plans includes: processing the simulation operation videos of each set of preliminary selection operation plans based on an information processing model to determine the simulation operation information of each set of preliminary selection operation plans; determining multiple sets of preferred operation plans, the similarity between different preferred operation plans, and the information of multiple excellent operation steps of the preliminary selection operation plans based on the simulation operation information of each set of preliminary selection operation plans; constructing a knowledge graph, where the knowledge graph includes multiple preferred operation plan nodes and multiple edges between the multiple preferred operation plan nodes, and the node features of the multiple preferred operation plan nodes include the simulation operation videos of the preferred operation plans and the information of multiple excellent operation steps of the preliminary selection operation plans, and the edges between different preferred operation plan nodes represent the similarity between different preferred operation plans; and determining the target operation plan based on processing the knowledge graph by a graph convolutional network.

[0007] In a possible implementation, the image processing model is a deep neural network model.

[0008] In a possible implementation, the information processing model is a Transformer model.

[0009] According to a second aspect, the present invention provides a general servo drive system based on artificial intelligence, including:

[0010] An acquisition module, configured to acquire a three-dimensional image of a device to be cut, a three-dimensional image of a target device, and servo drive device information;

[0011] A preliminary selection plan generation module, configured to determine multiple sets of preliminary selection operation plans based on the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the servo drive device information by using an image processing model;

[0012] A simulation operation generation module, configured to generate a simulation operation video of each set of preliminary selection operation plans based on the three-dimensional image of the device to be cut and the multiple sets of preliminary selection operation plans by using a generative adversarial network;

[0013] A target plan determination module, configured to determine a target operation plan based on the simulation operation videos of each set of preliminary selection operation plans;

[0014] A control module, configured to control the servo drive device to perform servo drive based on the target operation plan.

[0015] In a possible implementation, the target solution determination module is further configured to: process the simulation operation videos of each set of preliminary selection operation solutions based on an information processing model to determine the simulation operation information of each set of preliminary selection operation solutions; determine multiple sets of preferred operation solutions, the similarity between different preferred operation solutions, and the multiple excellent operation step information of the preliminary selection operation solutions based on the simulation operation information of each set of preliminary selection operation solutions; construct a knowledge graph, where the knowledge graph includes multiple preferred operation solution nodes and multiple edges between the multiple preferred operation solution nodes, and the node features of the multiple preferred operation solution nodes include the simulation operation videos of the preferred operation solutions and the multiple excellent operation step information of the preliminary selection operation solutions, and the edges between different preferred operation solution nodes represent the similarity between different preferred operation solutions; process the knowledge graph based on a graph convolutional network to determine the target operation solution.

[0016] In a possible implementation, the image processing model is a deep neural network model.

[0017] In a possible implementation, the information processing model is a Transformer model.

[0018] According to a third aspect, an embodiment of the present invention provides an electronic device, including: a processor; a memory; and a computer program; wherein, the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above, and the method includes: obtaining a three-dimensional image of a device to be cut, a three-dimensional image of a target device, and servo drive device information; determining multiple sets of preliminary selection operation solutions using an image processing model based on the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the servo drive device information; generating a simulation operation video for each set of preliminary selection operation solutions using a generative adversarial network based on the three-dimensional image of the device to be cut and the multiple sets of preliminary selection operation solutions; determining a target operation solution based on the simulation operation video of each set of preliminary selection operation solutions; and controlling the servo drive device to perform servo drive based on the target operation solution.

[0019] According to a fourth aspect, the present embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the aforementioned general servo drive method based on artificial intelligence. The method includes: obtaining three-dimensional images of a device to be cut, three-dimensional images of a target device, and servo drive device information; based on the three-dimensional images of the device to be cut, the three-dimensional images of the target device, and the servo drive device information, using an image processing model to determine multiple sets of preliminary operation plans; based on the three-dimensional images of the device to be cut and the multiple sets of preliminary operation plans, using a generative adversarial network to generate simulated operation videos for each set of preliminary operation plans; determining a target operation plan based on the simulated operation videos of each set of preliminary operation plans; and controlling the servo drive device to perform servo drive based on the target operation plan.

[0020] A general servo drive method and system based on artificial intelligence provided by the present invention. The method includes obtaining three-dimensional images of a device to be cut, three-dimensional images of a target device, and servo drive device information; based on the three-dimensional images of the device to be cut, the three-dimensional images of the target device, and the servo drive device information, using an image processing model to determine multiple sets of preliminary operation plans; based on the three-dimensional images of the device to be cut and the multiple sets of preliminary operation plans, using a generative adversarial network to generate simulated operation videos for each set of preliminary operation plans; determining a target operation plan based on the simulated operation videos of each set of preliminary operation plans; and controlling the servo drive device to perform servo drive based on the target operation plan. This method can quickly determine the optimal operation plan for cutting and processing devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of an application scenario of a general servo drive method based on artificial intelligence provided by an embodiment of the present invention;

[0022] Figure 2 It is a schematic flowchart of a general servo drive method based on artificial intelligence provided by an embodiment of the present invention;

[0023] Figure 3 It is a schematic flowchart of determining a target operation plan provided by an embodiment of the present invention;

[0024] Figure 4 It is a schematic diagram of a general servo drive system based on artificial intelligence provided by an embodiment of the present invention;

[0025] Figure 5 It is a schematic diagram of an electronic device provided by an embodiment of the present invention;

[0026] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] The present invention will be further described in detail below in conjunction with the specific embodiments and the accompanying drawings. Similar elements in different embodiments are labeled with related similar element numbers. In the following embodiments, many detailed descriptions are provided to enable a better understanding of the present invention. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, or methods. In some cases, some operations related to the present invention are not shown or described in the specification to avoid overshadowing the core part of the present invention. For those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the description in the specification and the general technical knowledge in the art.

[0028] Figure 1 It is a schematic diagram of an application scenario of a general servo drive method based on artificial intelligence provided by an embodiment of the present invention. Figure 1 The application scenario of the general servo drive method based on artificial intelligence may include a server 11, a network 12, a terminal 13, and a storage device 14.

[0029] In some embodiments, the server 11 may be a single server or a server group. The server 11 can access the information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 may be used to execute Figure 2 the general servo drive method based on artificial intelligence shown in

[0030] The network 12 can facilitate the exchange of information and / or data. In some embodiments, the network 12 can be any form of wired or wireless network, or any combination thereof.

[0031] The terminal 13 may refer to one or more terminal devices used by the user. In some embodiments, the terminal 13 may include one or more combinations of mobile devices, tablet computers, laptop computers, etc.

[0032] The storage device 14 can store data and / or instructions. For example, the storage device 14 can store data instructions of the general servo drive method based on artificial intelligence.

[0033] In an embodiment of the present invention, there is provided a general servo drive method based on artificial intelligence as shown in Figure 2 The general servo drive method based on artificial intelligence includes steps S1 to S5:

[0034] Step S1, obtaining a three-dimensional image of the device to be cut, a three-dimensional image of the target device, and servo drive device information;

[0035] The three-dimensional image of the device to be cut refers to the digital model of the device to be cut generated by three-dimensional scanning technology, which can be used to describe the geometric shape, dimensions and other information of the device to be cut. The three-dimensional image of the device to be cut is usually obtained using a three-dimensional scanner or a depth camera. For example, an accurate three-dimensional contour can be generated by a laser scanner.

[0036] The target device refers to the device model that achieves the expected shape and dimensions after the operation of the device to be cut is completed.

[0037] The three-dimensional image of the target device refers to the digital model of the target device drawn by computer-aided design (CAD) software, which can be used to describe the ideal shape, dimensions and other information expected to be achieved after the operation of the device to be cut is completed.

[0038] The information of the servo drive device refers to the key parameters related to the servo drive device, which can be used to describe the performance and operating status of the device. For example, the information of the servo drive device may include the motion range, accuracy, speed and load capacity. The information of the servo drive device is usually directly read through the device interface or the control system. For example, real-time data can be obtained through a PLC (programmable logic controller) or host computer software.

[0039] Step S2, based on the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the information of the servo drive device, use an image processing model to determine multiple sets of preliminary operation plans;

[0040] The image processing model is a deep neural network model. The input of the image processing model is the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the information of the servo drive device. The output of the image processing model is multiple sets of preliminary operation plans.

[0041] Multiple sets of preliminary operation plans are a set of multiple simulated operation plans generated by the deep neural network model.

[0042] The deep neural network model is a machine learning model that simulates the structure of human brain neurons, including Deep Neural Networks (DNN). The deep neural network can include multiple processing layers, each processing layer consists of multiple neurons, and each neuron performs a matrix transformation on the data. Advanced features can be extracted from the input data through multiple non-linear transformations. The deep neural network can process complex multi-dimensional data, such as images, texts, etc., and learn the potential laws in the data through training. The deep neural network extracts the geometric features in the image and combines the fully connected layer to analyze the constraint conditions of the servo drive device, so as to generate multiple sets of preliminary operation plans. The advantage of the deep neural network is that it can automatically learn the complex relationships in the data and comprehensively analyze the geometric shape, operation accuracy and equipment limitations, so as to provide diverse feasible solutions for subsequent optimization.

[0043] Step S3: Based on the three-dimensional image of the device to be cut and the multiple sets of preliminary operation plans, use a generative adversarial network to generate a simulated operation video for each set of preliminary operation plans.

[0044] The simulated operation video for each set of preliminary operation plans is a simulated video of a virtual operation process generated by a generative adversarial network (GAN). The simulated operation video for each set of preliminary operation plans is continuous time-series data, which can record the dynamic changes of tool movement, operation steps, and effects during the operation.

[0045] The input of the generative adversarial network is the three-dimensional image of the device to be cut and multiple sets of preliminary operation plans, and the output of the generative adversarial network is the simulated operation video for each set of preliminary operation plans. The generative adversarial network is a way of implementing artificial intelligence.

[0046] The generative adversarial network (GAN) includes a generator and a discriminator. The generator is responsible for generating simulated data, and the discriminator is used to distinguish between the generated data and the real data. The two compete with each other and make progress together, and generate high-quality data through adversarial training. The generator of the generative adversarial network generates a simulated operation video for each set of plans based on the three-dimensional image of the device to be cut and multiple sets of preliminary operation plans, and the discriminator evaluates the authenticity of the simulated operation video for each set of plans to ensure that it is highly consistent with the actual operation process.

[0047] The three-dimensional image of the device to be cut is an accurate description of the shape and structure of the object, containing all the geometric information of the device to be cut. This information is crucial for predicting the interaction between the tool and the material during the cutting process. The generator can ensure that the cutting path, tool movement, and other details in the generated simulated video comply with the actual physical constraints based on the three-dimensional image of the device to be cut.

[0048] Each set of preliminary operation plans provides specific cutting parameters and steps, such as cutting speed, feed rate, tool path, etc. This information provides clear operation instructions for the generator, making the generated simulated video more specific and targeted.

[0049] Different preliminary operation plans represent different operation strategies, ensuring that the generated simulated videos cover a variety of possible situations, increasing the diversity and coverage of the results.

[0050] Step S4: Determine the target operation plan based on the simulated operation video for each set of preliminary operation plans.

[0051] In some embodiments Figure 3 is a schematic flowchart of a process for determining a target operation plan provided by an embodiment of the present invention. The determining the target operation plan includes steps S21 to S24:

[0052] Step S21: Process the simulation operation videos of each set of preliminary operation plans based on the information processing model to determine the simulation operation information of each set of preliminary operation plans;

[0053] The simulation operation information of each set of preliminary operation plans is the information determined after the information processing model analyzes the simulation operation videos.

[0054] The simulation operation information of each set of preliminary operation plans includes information such as the number of operations, the operation score of each step, the operation time, the material utilization rate, the energy consumption, the tool wear degree, and the error rate.

[0055] The simulation operation information of each set of preliminary operation plans can comprehensively describe the operation effects and performance of each set of preliminary operation plans. For example, the operation score can evaluate the quality of each cutting step. The higher the operation score, the better the accuracy, stability, and effect of the operation step. The number of operations and the operation time are used to calculate the efficiency of the plan. The energy consumption and the tool wear degree are used to evaluate the energy conservation and sustainability. The error rate can measure the operation accuracy. By analyzing the simulation operation information of each set of preliminary operation plans, excellent operation steps can be identified and the optimal operation plan can be determined.

[0056] The information processing model is the Transformer model. The input of the information processing model is each set of preliminary operation plans, and the output of the information processing model is the simulation operation information of each set of preliminary operation plans. The Transformer model is an implementation method of artificial intelligence.

[0057] The Transformer model is a deep learning model based on the self-attention mechanism and is good at processing sequence data such as simulation operation videos. Through the self-attention mechanism, the Transformer model can capture the global dependencies between video frames, such as the continuity of the tool movement trajectory and the dynamic changes in the operation area. In addition, the Transformer model can combine visual features and temporal information and can generate comprehensive simulation operation information, such as data on the number of operations, operation scores, and material utilization rates.

[0058] In some embodiments, the information processing model includes a video feature extraction layer, an operation parameter analysis layer, and a comprehensive evaluation layer. The video feature extraction layer, the operation parameter analysis layer, and the comprehensive evaluation layer all include a Transformer structure. The input of the video feature extraction layer is the simulated operation video of each set of preliminary operation plans, and the output of the video feature extraction layer is the key operation steps, the tool movement trajectory, and the operation process stability index. The input of the operation parameter analysis layer is the key operation steps and the tool movement trajectory, and the output of the operation parameter analysis layer is the number of operations, the operation score of each step, the operation time, the material utilization rate, the energy consumption, the tool wear degree, and the error rate. The input of the comprehensive evaluation layer is the number of operations, the operation score of each step, the operation time, the material utilization rate, the energy consumption, the tool wear degree, the error rate, and the operation process stability index, and the output of the comprehensive evaluation layer is the simulated operation information of each set of preliminary operation plans.

[0059] The video feature extraction layer can extract key features from the simulated operation video, including the movement trajectory of the tool, the key operation steps, and the operation process stability index. By analyzing the key operation steps and the tool movement trajectory, the operation parameter analysis layer can calculate parameters such as the number of operations, the operation score of each step, the operation time, the material utilization rate, the energy consumption, the tool wear degree, and the error rate. By combining the operation parameters and the operation process stability index, the comprehensive evaluation layer can generate the simulated operation information of each set of preliminary operation plans. This hierarchical design not only improves the accuracy and efficiency of the system but also enhances the interpretability of the model.

[0060] By decomposing the task into multiple steps and performing refined processing based on the results of the previous step in each step, the accuracy of the information can be gradually improved. This hierarchical processing method can enhance the accuracy of the final output data because each layer can focus on optimizing the accuracy of its specific task, thereby improving the stability and reliability of the entire model.

[0061] Step S22, determining multiple sets of optimal operation plans, the similarity between different optimal operation plans, and the information of multiple excellent operation steps of the preliminary operation plan based on the simulated operation information of each set of preliminary operation plans;

[0062] In some embodiments, a deep neural network model can be used to determine multiple sets of optimal operation plans, the similarity between different optimal operation plans, and the information of multiple excellent operation steps of the preliminary operation plan. The input of the deep neural network model is the simulated operation information of each set of preliminary operation plans, and the output of the deep neural network model is multiple sets of optimal operation plans, the similarity between different optimal operation plans, and the information of multiple excellent operation steps of the preliminary operation plan.

[0063] Multiple sets of optimal operation plans refer to a set of plans selected from the initially selected operation plans, which perform excellently in multiple evaluation dimensions and have their respective advantages.

[0064] The similarity between different optimal operation plans is a parameter used to quantify the similarity degree of multiple sets of optimal operation plans in key features.

[0065] The information of multiple excellent operation steps of the initially selected operation plan is a set of excellent operation steps extracted from the initially selected operation plan.

[0066] Step S23, construct a knowledge graph, the knowledge graph includes multiple optimal operation plan nodes and multiple edges between the multiple optimal operation plan nodes, the node features of the multiple optimal operation plan nodes include the simulation operation video of the optimal operation plan and the information of multiple excellent operation steps of the initially selected operation plan, and the edges between different optimal operation plan nodes represent the similarity between different optimal operation plans;

[0067] A knowledge graph is a structured data representation method, which is composed of multiple nodes and the edges between the nodes, and can be used to express the relationships between different entities. In some embodiments, the knowledge graph is used to represent the similarity and relevance between different optimal operation plans. Each optimal operation plan node represents an optimal operation plan, such as Plan A, Plan B, Plan C, etc. The node features include the simulation operation video of the plan and the information of multiple excellent operation steps of the initially selected operation plan. The edges connect different optimal operation plan nodes, indicating the similarity between these plans.

[0068] Step S24, process the knowledge graph based on a graph convolutional network to determine the target operation plan.

[0069] The target operation plan is the operation plan determined from multiple sets of optimal operation plans that is most suitable for the current operation requirements. The target operation plan is generated through analysis by a graph convolutional network (GCN) based on the optimal operation plan nodes and their relationships in the knowledge graph. The target operation plan is one of the multiple optimal operation plans. The target operation plan can be used to optimize the operation process, reduce human intervention, and adapt to dynamic requirements. The input of the graph convolutional network is the knowledge graph, and the output of the graph convolutional network is the target operation plan.

[0070] Each node (optimal operation plan node) contains the behavioral features (simulation operation video, information of multiple excellent operation steps of the initially selected operation plan) of the operation plan under specific conditions, and the edges represent the similarity scores between the optimal operation plans.

[0071] Since the excellent operation step information performs excellently, by using the excellent operation step information as the node features, the graph neural network model can understand which operation details are crucial for achieving high-quality cutting.

[0072] The simulation operation video shows the expected operation effects under different conditions. The simulation operation video contains rich visual information, such as particle movement trajectories, separation effects, etc. The simulation operation video can intuitively reflect the effects of the operation plan, enabling the model to more comprehensively understand the actual performance of different operation plans. Compared with static images or simple numerical parameters, video data can capture the dynamic characteristics that change over time during the operation process. This is especially important for evaluating complex operation processes because many key operation details can only be accurately identified during the dynamic process.

[0073] By organizing different primary operation plans into a graph structure, the complex relationships between various plans can be better captured. For example, which plans have similar operation steps or effects, and which plans have significant differences, so that the graph convolutional network can better determine the target operation plan. The Graph Convolutional Network (GCN) is a deep learning model used to process knowledge graphs. The graph convolutional network can utilize the node features and edge features in the knowledge graph to learn the complex relationships between operation plans. In this way, the graph convolutional network can comprehensively consider the characteristics of each preferred operation plan and their similarities, and thus recommend the most suitable and optimal target operation plan.

[0074] Step S5, controlling the servo drive device to perform servo drive based on the target operation plan.

[0075] After determining the target operation plan, the servo drive device is controlled to operate on the device to be cut based on the target operation plan.

[0076] Based on the same inventive concept, Figure 4 The following is a schematic diagram of a general servo drive system based on artificial intelligence provided by an embodiment of the present invention. The general servo drive system based on artificial intelligence includes:

[0077] An acquisition module 41, configured to acquire a three-dimensional image of the device to be cut, a three-dimensional image of the target device, and servo drive device information;

[0078] A primary selection plan generation module 42, configured to determine multiple sets of primary operation plans using an image processing model based on the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the servo drive device information;

[0079] A simulation operation generation module 43, configured to generate a simulation operation video for each set of primary operation plans using a generative adversarial network based on the three-dimensional image of the device to be cut and the multiple sets of primary operation plans;

[0080] A target solution determination module 44, configured to determine a target operation solution based on the simulation operation videos of each set of preliminary operation solutions;

[0081] A control module 45, configured to control a servo drive device to perform servo drive based on the target operation solution.

[0082] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, as Figure 5 shown, including:

[0083] Including: a processor 51; a memory 52; and a computer program; wherein, the computer program is stored in the memory 52 and is configured to be executed by the processor 51 to implement the general servo drive method based on artificial intelligence provided above. The method includes: acquiring three-dimensional images of a device to be cut, three-dimensional images of a target device, and servo drive device information; based on the three-dimensional images of the device to be cut, the three-dimensional images of the target device, and the servo drive device information, using an image processing model to determine multiple sets of preliminary operation solutions; based on the three-dimensional images of the device to be cut and the multiple sets of preliminary operation solutions, using a generative adversarial network to generate simulation operation videos of each set of preliminary operation solutions; determining a target operation solution based on the simulation operation videos of each set of preliminary operation solutions; and controlling a servo drive device to perform servo drive based on the target operation solution.

[0084] Based on the same inventive concept, this embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor 51, it implements the general servo drive method based on artificial intelligence provided above. The method includes: acquiring a screen recording running video and data transmission description text of a user-preferred software; acquiring three-dimensional images of a device to be cut, three-dimensional images of a target device, and servo drive device information; based on the three-dimensional images of the device to be cut, the three-dimensional images of the target device, and the servo drive device information, using an image processing model to determine multiple sets of preliminary operation solutions; based on the three-dimensional images of the device to be cut and the multiple sets of preliminary operation solutions, using a generative adversarial network to generate simulation operation videos of each set of preliminary operation solutions; determining a target operation solution based on the simulation operation videos of each set of preliminary operation solutions; and controlling a servo drive device to perform servo drive based on the target operation solution.

[0085] The general servo drive method based on artificial intelligence provided by the embodiments of the present application can be applied to electronic devices such as terminal devices (such as mobile phones), tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smart watches, smart glasses, or smart helmets, etc.), augmented reality (AR) / virtual reality (VR) devices, smart home devices, in-vehicle computers, etc. The embodiments of the present application do not impose any restrictions on this.

[0086] Taking the mobile phone 100 as an example of the above-mentioned electronic device, Figure 6 The structural schematic diagram of the mobile phone 100 is shown.

[0087] As Figure 6 shown, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone interface 170D, a sensor module 180, a key 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0088] The processing module 110 may include one or more processing units. For example, the processing module 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0089] The processing module 110 can be used to: obtain the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the servo drive device information; determine multiple sets of preliminary operation plans using an image processing model based on the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the servo drive device information; generate a simulated operation video for each set of preliminary operation plans using a generative adversarial network based on the three-dimensional image of the device to be cut and the multiple sets of preliminary operation plans; determine the target operation plan based on the simulated operation video of each set of preliminary operation plans; and control the servo drive device to perform servo drive based on the target operation plan.

[0090] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

[0091] Meanwhile, this specification uses specific terms to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0092] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numbers and letters, or the use of other names in this specification are not used to limit the order of the processes and methods in this specification. Although some currently considered useful invention embodiments are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0093] Similarly, it should be noted that, in order to simplify the description disclosed in this specification and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, sometimes multiple features are incorporated into one embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are less than all the features of the individual embodiments disclosed above.

[0094] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A general servo driving method based on artificial intelligence, characterized in that: include: Obtaining a three-dimensional image of the device to be cut, a three-dimensional image of the target device, and information of a servo drive device; Based on the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the information of the servo drive device, a plurality of sets of preliminary operation schemes are determined using an image processing model; Based on the three-dimensional image of the device to be cut and the multiple sets of preliminary operation schemes, using a generative adversarial network to generate a simulated operation video of each set of preliminary operation schemes; Determining the target operation scheme based on the simulated operation video of each set of the preliminary operation schemes, wherein determining the target operation scheme based on the simulated operation video of each set of the preliminary operation schemes comprises: Processing the simulated operation video of each set of preliminary operation schemes based on the information processing model to determine the simulated operation information of each set of preliminary operation schemes; Determine multiple sets of preferred operation schemes, similarities between different preferred operation schemes, and multiple excellent operation step information of the preliminary operation schemes based on the simulated operation information of each set of preliminary operation schemes; Constructing a knowledge graph, wherein the knowledge graph includes a plurality of preferred operation solution nodes and a plurality of edges between the plurality of preferred operation solution nodes, wherein the node features of the plurality of preferred operation solution nodes include a simulated operation video of the preferred operation solution and a plurality of excellent operation step information of the preliminary operation solution, and the edges between different preferred operation solution nodes represent the similarity between the different preferred operation solutions; Processing the knowledge graph based on a graph convolutional network to determine a target operation plan; The servo drive device is controlled to perform servo drive based on the target operation scheme.

2. The universal servo driving method based on artificial intelligence as claimed in claim 1, characterized in that: The image processing model is a deep neural network model.

3. The universal servo driving method based on artificial intelligence as claimed in claim 1, characterized in that: The information processing model is a Transformer model.

4. A universal servo drive system based on artificial intelligence, characterized in that: include: An acquisition module, used to acquire a three-dimensional image of a device to be cut, a three-dimensional image of a target device, and information of a servo drive device; A preliminary selection scheme generating module, used to determine a plurality of preliminary selection operation schemes using an image processing model based on the three-dimensional image of the device to be cut, the three-dimensional image of the target device, and the information of the servo drive device; A simulation operation generation module, used to generate a simulation operation video of each set of preliminary operation schemes using a generative adversarial network based on the three-dimensional image of the device to be cut and the multiple sets of preliminary operation schemes; A target solution determination module is used to determine a target operation solution based on the simulated operation video of each set of preliminary operation solutions, and the target solution determination module is also used to: Processing the simulated operation video of each set of preliminary operation schemes based on the information processing model to determine the simulated operation information of each set of preliminary operation schemes; Determine multiple sets of preferred operation schemes, similarities between different preferred operation schemes, and multiple excellent operation step information of the preliminary operation schemes based on the simulated operation information of each set of preliminary operation schemes; Constructing a knowledge graph, wherein the knowledge graph includes a plurality of preferred operation solution nodes and a plurality of edges between the plurality of preferred operation solution nodes, wherein the node features of the plurality of preferred operation solution nodes include a simulated operation video of the preferred operation solution and a plurality of excellent operation step information of the preliminary operation solution, and the edges between different preferred operation solution nodes represent the similarity between the different preferred operation solutions; Processing the knowledge graph based on a graph convolutional network to determine a target operation plan; The control module is used to control the servo drive device to perform servo drive based on the target operation scheme.

5. The universal servo drive system based on artificial intelligence as claimed in claim 4, characterized in that: The image processing model is a deep neural network model.

6. The universal servo drive system based on artificial intelligence as claimed in claim 4, characterized in that: The information processing model is a Transformer model.

7. An electronic device, characterized in that: include: processor; Memory; And a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the general servo drive method based on artificial intelligence as described in any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the universal servo drive method based on artificial intelligence as described in any one of claims 1 to 3 is implemented.

Images