Industrial digital genealogy system and industrial digital genealogy generation method

Abstract

The present application provides an industrial digital family tree system and a method for generating an industrial digital family tree. The method includes: establishing a digital twin product and a digital twin space based on physical interaction information; generating a rich geometric representation corresponding to the product, a rich feature representation corresponding to the product, an environmental configuration corresponding to the scene, and an equipment configuration corresponding to the scene based on the physical interaction information; generating a digital family tree of production objects corresponding to the production objects based on the digital twin product, the rich geometric representation, and the rich feature representation; generating a digital family tree of production spaces corresponding to the production space based on the digital twin space, the environmental configuration, and the equipment configuration; establishing a target digital family tree based on the above digital family tree, which can combine the diverse random combinations of different parts and assemblies in the production objects in the diversified production spaces to generate a large amount of three-dimensional digital scene data for the industrial embodied intelligent world model to learn and train in the digital family tree, thereby improving the adaptability and generalization of the model.

Description

Technical Field

[0001] The present application relates to the field of intelligent manufacturing technology, and in particular to an industrial digital genealogy system and a method for generating an industrial digital genealogy. Background Art

[0002] With the rapid development of large-scale model technology, general-purpose large-scale models have achieved remarkable application results in many fields, especially in natural language processing and computer vision. However, these large-scale models are typically disembodied, existing in the digital realm and unable to directly drive physical devices for embodied perception and intelligent operation. The manufacturing industry has also entered the era of large-scale models. Compared to the disembodied intelligence of general-purpose large-scale models, the manufacturing industry has a large number of physical production equipment that requires control. Therefore, industrial embodied intelligence is needed to exert influence in the physical world by controlling physical terminal devices.

[0003] Related technologies introduce world models into the industrial sector, building virtual environment simulators to train intelligent agents and thus achieve embodied industrial control. World models leverage the learning of physical laws, such as object dynamics and spatial relationships, to create abstract representations of the external world. This provides prior knowledge for embodied industrial intelligence, helping embodied agents perform intelligent perception, planning, and decision-making in the physical world.

[0004] However, existing technologies lack sufficient trainable data and scenarios and cannot be applied to the training of industrial embodied intelligent world models. Summary of the Invention

[0005] This application provides an industrial digital genealogy system and a method for generating an industrial digital genealogy to solve the technical problem that the existing technology lacks sufficient trainable data and scenarios and cannot be applied to the training of industrial embodied intelligent world models.

[0006] In a first aspect, the present application provides a method for generating an industrial digital family tree, comprising: obtaining physical interaction information; establishing a digital twin product and a digital twin space based on the physical interaction information; generating a rich geometric representation corresponding to the product, a rich feature representation corresponding to the product, an environmental configuration corresponding to the scene, and an equipment configuration corresponding to the scene based on the physical interaction information; generating a production object digital family tree corresponding to the production object based on the digital twin product, the rich geometric representation, and the rich feature representation; generating a production space digital family tree corresponding to the production space based on the digital twin space, the environmental configuration, and the equipment configuration; establishing a target digital family tree based on the production object digital family tree and the production space digital family tree, wherein the target digital family tree is used for training an industrial embodied intelligent world model.

[0007] The present application provides a method for generating an industrial digital family tree. Digital family tree is a new concept proposed in this application, which provides new possibilities for the construction of an industrial embodied intelligent world model from two perspectives. Specifically, from the two perspectives of production objects and production space, digital twin technology and generation technology are combined to generate a series of tree-like family trees from parts to assemblies and then to products, as well as a variety of digital production spaces in the entire life cycle of intelligent manufacturing products based on the collected physical interaction information, and then construct a production object digital family tree corresponding to the production object and a production space digital family tree corresponding to the production space. Through the production object digital family tree corresponding to the production object and the production space digital family tree corresponding to the production space, a large amount of three-dimensional digital scene data can be generated by combining the diverse random combinations of different parts and assemblies in the production objects in the diversified production space for the industrial embodied intelligent world model to learn and train in the digital family tree, thereby improving the adaptability and generalization of the model.

[0008] Optionally, the physical interaction information includes genetic coding information, multimodal information, production equipment information and environmental parameter information of the product or part; accordingly, generating a rich geometric representation corresponding to the product, a rich feature representation corresponding to the product and an environmental configuration corresponding to the scene based on the physical interaction information includes: generating a rich geometric representation corresponding to the product based on the genetic coding information, wherein the genetic coding information includes at least one of shape, size, material, type, purpose, and assembly relationship, and the rich geometric representation includes at least one of boundary representation, modeling sequence, network entity, polygon, point cloud and voxel; generating a rich feature representation corresponding to the product based on the multimodal information, wherein the multimodal information includes at least one of voice, text and image; generating an equipment configuration corresponding to the scene based on the production equipment information; generating an environmental configuration corresponding to the scene based on the environmental parameter information.

[0009] Here, this application proposes an information mechanism for the gene (Deoxyribonucleic Acid, DNA) encoding of a digital family tree. By designing DNA encoding to constrain the phenotype of parts generated in the family tree, it ensures that it meets the performance requirements of industrial production while being interpretable. Combined with multimodal information such as voice, text or images, it can automatically generate a three-dimensional (3D) model that meets engineering needs. In terms of production space, this application realizes the construction of a digital twin scene by configuring scene elements, and realizes the equipment configuration and environment configuration in the scene elements through production equipment information and environmental parameter information. Through the construction of the above series of scene elements and 3D models, sufficient training data and a precise simulation environment are provided for the highly adaptive capabilities of industrial intelligent bodies, further enriching the trainable data and scenes, and improving the training effect of the industrial embodied intelligent world model.

[0010] Optionally, the physical interaction information includes first target detection information of the part and second target detection information of the scene; accordingly, establishing a digital twin product and a digital twin space based on the physical interaction information includes: performing approximate matching in a preset part asset library based on the first target detection information, and determining the feature vector corresponding to the first target detection information based on the approximate matching result; performing matching processing of similarity measurement in a predefined part library based on the feature vector, and determining the digital twin product corresponding to the first target detection information based on the matching processing result of the similarity measurement; and establishing a digital twin space based on the second target detection information.

[0011] Among them, this application extracts data from the physical world and generates digital twins, providing a digital foundation for subsequent genealogy generation and intelligent agent learning. Specifically, the target detection algorithm can complete the target detection of each part in the red, green and blue color model (RGB Color Model, RGB) image of the physical world, identify and classify each part in the image, and use approximate matching and precise matching methods of similarity measurement to identify and detect the parts that are most similar to the parts as digital entities in the digital twin scene, as part of the entire scene, and based on the recognition results, determine the shortcomings of the digital twin space, data twin products and digital twin space, so that the simulation is closer to real production conditions, thereby improving the reliability and accuracy of the simulation reinforcement learning process, further improving the training effect of the industrial embodied intelligent world model, and improving the reasoning accuracy of the model.

[0012] Optionally, generating a digital family tree of production objects corresponding to the production objects based on the digital twin product, the rich geometric representation and the rich feature representation includes: obtaining a preset first family tree structure, wherein the preset first family tree structure is a first tree structure, the first tree structure includes multiple first-level tree nodes, and the first level includes product level, assembly level and part level; performing node filling processing on the first family tree structure according to the digital twin product, the rich geometric representation and the rich feature representation to obtain the digital family tree of production objects corresponding to the production objects.

[0013] Here, this application establishes the first family tree structure from the perspective of production objects. From the perspective of production objects, a series of tree-like family trees can be generated from parts to assemblies and then to products. Based on this digital family tree structure, 3D parts are not only stored as independent geometric representations, but also placed in the family tree structure to reflect the generation relationship between parts, as well as their hierarchical relationship with downstream assemblies and final products. Through this organizational method, it is possible to clearly express how different needs derive diverse part designs and how a complete product system is formed through assembly relationships, thereby enriching the trainable data and improving the training effect of the industrial embodied intelligent world model.

[0014] Optionally, generating a production space digital family tree corresponding to the production space based on the digital twin space, the environment configuration and the equipment configuration includes: obtaining a plurality of preset types of production scenes, wherein the preset types are determined based on a plurality of production equipment, production environment and production personnel; obtaining a second family tree structure corresponding to each of the preset types of production scenes; performing node filling processing on the second family tree structure according to the digital twin space, the environment configuration and the equipment configuration to obtain a production space digital family tree corresponding to the production space.

[0015] This application establishes a second family tree structure from the perspective of production scenarios. The family tree layer constructs a variety of 3D digital scenes through the methods of the generation layer, providing a rich training environment for subsequent intelligent agent learning. Different types of production scenarios are systematically classified, each with different production equipment, production environment, and production personnel. Intelligent agents of the industrial embodied intelligent world model can conduct simulation learning in these scenarios. Through industrial family tree 3D scene training, the adaptability of intelligent equipment such as industrial robots and automated production systems can be improved.

[0016] Optionally, after establishing a target digital family tree based on the production object digital family tree and the production space digital family tree, the method further includes: obtaining an original industrial embodied intelligent world model; and training the original industrial embodied intelligent world model based on the target digital family tree to obtain a target industrial embodied intelligent world model.

[0017] Among them, the digital genealogy created by this application records the evolution of parts data from multi-model parts to multi-performance products. Combined with its various production scenarios, it not only describes the mapping relationship between different part characteristics and different product performances, but also traces the changes in the product during its life cycle, ensuring the continuity and consistency of the production process from parts to products. It also includes scene-level digital spaces for different tasks in each production and manufacturing stage. The training of the industrial embodied intelligent world model based on the digital genealogy can enable the industrial embodied intelligent world model to manipulate different models of physical equipment to learn and train in a rich and diverse digital space, further improving the adaptability and generalization of the industrial embodied intelligent world model, thereby realizing interaction and feedback in the industrial physical environment.

[0018] Optionally, the target industrial embodied intelligent world model is used to execute at least one of the full life cycle applications of industrial products, and the full life cycle applications of industrial products include: model simulation design based on digital genealogy; product design based on genetic coding constraints; flexible sorting based on digital genealogy; product assembly guidance with reference to genetic coding; genealogy-driven adaptive scenario understanding; genetic coding similarity-driven process generation; genealogy-based predictive operation and maintenance of parts; and operation and maintenance guidance based on genetic coding similarity.

[0019] Here, this application can train an embodied intelligent world model of the target industry with excellent results based on the rich product and scenario data in the digital map, and then realize practical applications such as intelligent design, manufacturing optimization, and predictive maintenance, thereby improving the performance of intelligent systems in flexible and dynamic environments. In the field of intelligent manufacturing, it improves the automation and intelligence of intelligent manufacturing of industrial parts.

[0020] In a second aspect, the present application provides a device for generating an industrial digital family tree, comprising: an acquisition module for acquiring physical interaction information; a twin module for establishing a digital twin product and a digital twin space based on the physical interaction information; a generation module for generating a rich geometric representation corresponding to the product, a rich feature representation corresponding to the product, an environmental configuration corresponding to the scene, and an equipment configuration corresponding to the scene based on the physical interaction information; a first family tree module for generating a production object digital family tree corresponding to the production object based on the digital twin product, the rich geometric representation, and the rich feature representation; a second family tree module for generating a production space digital family tree corresponding to the production space based on the digital twin space, the environmental configuration, and the equipment configuration; an establishment module for establishing a target digital family tree based on the production object digital family tree and the production space digital family tree, wherein the target digital family tree is used for training the industrial embodied intelligent world model.

[0021] Optionally, the physical interaction information includes genetic coding information, multimodal information, production equipment information and environmental parameter information of the product or part; accordingly, the generation module is specifically used to: generate a rich geometric representation corresponding to the product based on the genetic coding information, wherein the genetic coding information includes at least one of shape, size, material, type, purpose, and assembly relationship, and the rich geometric representation includes at least one of boundary representation, modeling sequence, network entity, polygon, point cloud and voxel; generate a rich feature representation corresponding to the product based on the multimodal information, wherein the multimodal information includes at least one of voice, text and image; generate a device configuration corresponding to the scene based on the production equipment information; generate an environmental configuration corresponding to the scene based on the environmental parameter information.

[0022] Optionally, the physical interaction information includes first target detection information of the part and second target detection information of the scene; accordingly, the twin module is specifically used to: perform approximate matching in a preset parts asset library based on the first target detection information, and determine the feature vector corresponding to the first target detection information based on the approximate matching result; perform matching processing of similarity measurement in a predefined parts library based on the feature vector, and determine the digital twin product corresponding to the first target detection information based on the matching processing result of the similarity measurement; and establish a digital twin space based on the second target detection information.

[0023] Optionally, the first genealogy module is specifically used to: obtain a preset first genealogy structure, wherein the preset first genealogy structure is a first tree structure, the first tree structure includes multiple first-level tree nodes, and the first level includes product level, assembly level and part level; according to the digital twin product, the rich geometric representation and the rich feature representation, the first genealogy structure is node-filled to obtain a digital genealogy of the production object corresponding to the production object.

[0024] Optionally, the second genealogy module is specifically used to: obtain multiple preset types of production scenarios, wherein the preset types are determined based on multiple production equipment, production environment, and production personnel; obtain a second genealogy structure corresponding to each of the preset types of production scenarios; and perform node filling processing on the second genealogy structure according to the digital twin space, the environment configuration, and the equipment configuration to obtain a production space digital genealogy corresponding to the production space.

[0025] Optionally, after the establishment module is used to establish a target digital family tree based on the production object digital family tree and the production space digital family tree, the above-mentioned device also includes a training module for: obtaining an original industrial embodied intelligent world model; and training the original industrial embodied intelligent world model based on the target digital family tree to obtain a target industrial embodied intelligent world model.

[0026] Optionally, the target industrial embodied intelligent world model is used to execute at least one of the full life cycle applications of industrial products, and the full life cycle applications of industrial products include: model simulation design based on digital genealogy; product design based on genetic coding constraints; flexible sorting based on digital genealogy; product assembly guidance with reference to genetic coding; genealogy-driven adaptive scenario understanding; genetic coding similarity-driven process generation; genealogy-based predictive operation and maintenance of parts; and operation and maintenance guidance based on genetic coding similarity.

[0027] In a third aspect, the present application provides an industrial digital genealogy system, comprising: a memory, a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor executes the first aspect above and / or various possible implementations of the first aspect.

[0028] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementations of the first aspect.

[0029] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementations of the first aspect.

[0030] The industrial digital genealogy system and the method for generating an industrial digital genealogy provided in this application provide new possibilities for the construction of an industrial embodied intelligent world model from two perspectives. Specifically, from the two perspectives of production objects and production space, respectively, by combining digital twin technology and generation technology, a series of tree-like genealogies from parts to assemblies to products and a diverse digital production space in the entire life cycle of intelligent manufacturing products are generated based on the collected physical interaction information, and then a production object digital genealogy corresponding to the production object and a production space digital genealogy corresponding to the production space are constructed. Through the production object digital genealogy corresponding to the production object and the production space digital genealogy corresponding to the production space, a large amount of three-dimensional digital scene data can be generated by combining diverse random combinations of different parts and assemblies in the production objects in diversified production spaces for the industrial embodied intelligent world model to learn and train in the digital genealogy, thereby improving the adaptability and generalization of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0032] Figure 1aA physical comparison diagram of a digital family tree, digital twins, and digital cousins ​​provided in an embodiment of the present application;

[0033] Figure 1b A conceptual comparison diagram of a digital family tree, digital twins, and digital cousins ​​provided in an embodiment of the present application;

[0034] Figure 2 A schematic diagram of the system architecture for generating an industrial digital family tree provided in an embodiment of the present application;

[0035] Figure 3 A flowchart of a method for generating an industrial digital family tree provided in an embodiment of the present application;

[0036] Figure 4 A schematic diagram of the structure of a digital family tree of production objects provided in an embodiment of the present application;

[0037] Figure 5 A schematic diagram of the structure of a production space digital family tree provided in an embodiment of the present application;

[0038] Figure 6 A schematic diagram of a digital genealogy system architecture provided in an embodiment of the present application;

[0039] Figure 7 A schematic diagram of the steps of a method for constructing a digital family tree provided in an embodiment of the present application;

[0040] Figure 8 A schematic diagram of the structure of a device for generating an industrial digital family tree provided in an embodiment of the present application;

[0041] Figure 9 A schematic diagram of the structure of an industrial digital genealogy system provided in an embodiment of the present application.

[0042] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0043] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0044] First, let’s explain the terms involved in this application:

[0045] Digital twins, also known as digital twins, make full use of physical models, sensors, operation history and other data to complete simulation and mapping in virtual space, thereby reflecting the entire life cycle process of the corresponding entity or system.

[0046] A digital cousin is a digital entity that corresponds to a physical entity. Unlike a digital twin, a digital cousin does not completely simulate the physical entity in the real world, but instead exhibits similar geometric shapes and semantic features.

[0047] Digital genealogy is a new concept proposed in the embodiments of this application, and it has two perspectives: production object and production space. The digital genealogy from the perspective of production objects reflects the mapping system of the blood relationship between multiple physical entities in the product genealogy. It focuses on the similarities between parts and the evolution trend from parts to products; the digital genealogy from the perspective of production space reflects the multiple parallel digital worlds parallel to the physical world, and can display the manufacturing process of different production links through the spatial dimension. Unlike digital twins and cousins, digital genealogy focuses on the genealogical relationship, common characteristics and change process between digital entities, rather than the digital mapping of a single entity or its approximate entities.

[0048] World model: By creating an abstract representation of the external world, it helps embodied agents perform intelligent perception, planning, and decision-making in the physical world.

[0049] World models have been a research hotspot in recent years. By creating abstract representations of the external world, they help embodied agents perform intelligent perception, planning, and decision-making in the physical world. Combining embodied intelligence with world models, industrial embodied intelligence world models can control physical devices to achieve a deep integration of perception, decision-making, and execution in the industrial world. For example, in flexible manufacturing environments, the diversity and complexity of production tasks require intelligent systems to effectively respond to various changes, such as different product types, process flows, and diverse production environments. Industrial embodied intelligence world models must learn from large amounts of data to enable interaction and feedback in the industrial physical environment, and possess adaptability and generalization to multiple product models and production scenarios.

[0050] However, a core challenge for industrial embodied intelligence world models is the lack of sufficient training data and scenarios. Existing general scenarios cannot be directly applied to the training of industrial embodied intelligence world models. This is because the diversity, complexity, and physical interaction requirements of flexible industrial production environments all require a more diverse and finely labeled data set. This data must not only cover all aspects of product design, manufacturing, and assembly, but also requires perception and operation data from real-world scenarios so that the model can learn more precise operational strategies and feedback mechanisms.

[0051] In order to solve the above problems, the embodiments of the present application provide an industrial digital genealogy system and a method for generating an industrial digital genealogy. The method proposes the concept of digital genealogy, and provides new possibilities for the construction of industrial embodied intelligent world models from two perspectives. In diversified production spaces, the method combines the diverse random combinations of different parts and assemblies in the production objects to generate a large amount of three-dimensional digital scene data for the industrial embodied intelligent world model to learn and train in the digital genealogy.

[0052] Optionally, in response to the challenge of insufficient data in constructing an industrial embodied intelligent world model, the embodiment of the present application proposes an innovative concept - digital genealogy, which provides new possibilities for the construction of an industrial embodied intelligent world model from two perspectives. From the perspective of production objects, a series of tree-like genealogies from parts to assemblies to products can be generated, and the digital genealogy DNA gene mechanism is defined. By designing DNA coding to constrain the phenotype of the parts generated in the genealogy, it is ensured that it meets the performance requirements of industrial production while being interpretable; from the perspective of production space, a variety of digital production spaces in the entire life cycle of intelligent manufacturing products can be generated, including diversified scenarios of different equipment and environmental configurations in warehousing, manufacturing, and operation and maintenance scenarios. Combining the above two perspectives, a large amount of three-dimensional digital scene data can be generated in a diversified production space by combining the diverse random combinations of different parts and assemblies in the production objects for the industrial embodied intelligent world model to learn and train in the digital genealogy, thereby improving the adaptability and generalization of the model.

[0053] The digital family tree not only describes the mapping relationship between the characteristics of different parts and the performance of different products, but also traces the changes in the product life cycle, ensuring the continuity and consistency of the production process from parts to products. It also includes scene-level digital spaces for different tasks in each production and manufacturing stage, allowing embodied world models to manipulate different types of physical equipment to learn and train in a rich and diverse digital space. Figure 1a A physical comparison diagram of a digital family tree, digital twins, and digital cousins ​​provided in an embodiment of the present application; Figure 1b A conceptual comparison diagram of a digital family tree, digital twins, and digital cousins ​​provided in an embodiment of the present application is shown in FIG. Figure 1a and Figure 1b As shown, there are certain similarities between digital family trees and digital twins and digital cousins, and digital family trees have richer information. It is understandable that Figure 1a 、 Figure 1b as well as Figure 1a 、 Figure 1b The entities in the figure are for illustration only and do not affect the scope of protection of the embodiments of the present application.

[0054] Optional, Figure 2This is a schematic diagram of the system architecture for generating an industrial digital genealogy provided in an embodiment of the present application. Figure 2 In the above architecture, the above architecture includes at least one of a data acquisition device 201, a processing device 202 and a display device 203.

[0055] It is understood that the structure illustrated in the embodiments of this application does not constitute a specific limitation on the system architecture for generating industrial digital genealogies. In other feasible implementations of this application, the above architecture may include more or fewer components than shown, or may combine or split certain components, or have different component arrangements. The specific configuration can be determined based on the actual application scenario and is not limited here. Figure 2 The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0056] In a specific implementation process, the data acquisition device 201 may include an input / output interface and may also include a communication interface. The data acquisition device 201 may be connected to the processing device via the input / output interface or the communication interface.

[0057] The processing device 202 can provide new possibilities for the construction of the industrial embodied intelligent world model from two perspectives. It can combine the diverse random combinations of different parts and assemblies in the production objects in the diversified production space to generate a large amount of three-dimensional digital scene data for the industrial embodied intelligent world model to learn and train in the digital genealogy.

[0058] The display device 203 may also be a touch screen display or a screen of a terminal device, which is used to receive user instructions while displaying the above content to achieve interaction with the user.

[0059] It should be understood that the above-mentioned processing device can be implemented by a processor reading instructions in a memory and executing the instructions, or it can be implemented by a chip circuit.

[0060] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0061] The technical solution of this application is described in detail below with reference to specific embodiments:

[0062] Optionally, Figure 3 A flow chart of a method for generating an industrial digital genealogy provided in an embodiment of the present application. The execution subject of the embodiment of the present application may be Figure 2The specific execution subject of the processing device 202 can be determined according to the actual application scenario. Figure 3 As shown, the method includes the following steps:

[0063] S301: Acquire physical interaction information.

[0064] Optionally, based on Figure 2 The data acquisition device 201 obtains physical interaction information.

[0065] Alternatively, at the interaction level of the industrial embodied intelligent world model, three core elements—people, terminal devices, and materials—form the physical carriers of actual industrial production and manufacturing activities. At the human level, the physical world involves different roles, such as skilled workers, designers, and experimenters. Physical interaction information can be obtained through interaction with terminal devices at the human level. At the terminal device level, the physical world encompasses industrial automation equipment such as robots and machine tools, through which physical interaction information can be obtained. At the material level, the physical world involves raw materials, parts, and products. Through data collection and modeling, information from the physical world layer can be mapped to the digital world, providing a data source for digital twins and digital family trees.

[0066] Optionally, physical interaction information includes genetically encoded information about the product or part. Drawing on the concept of genes in the biological world, this embodiment defines the genes of industrial parts from different dimensions, corresponding to different phenotypes of industrial parts. This defines a digital genealogy DNA gene mechanism, and by designing DNA encoding to constrain the phenotypes of parts generated in the genealogy, ensures that they meet industrial production performance requirements while remaining interpretable.

[0067] In the concept of the digital genealogy of industrial parts, the basic attributes of parts can be mapped to similar elements in biological DNA. DNA defines the basic characteristics that determine the phenotype of a part, including shape, size, material, type, purpose, and fitting relationship. Specifically, these attributes are identified as key elements in the digital genealogy of industrial parts, as shown below:

[0068] Shape: The shape of a part is similar to the appearance of an organism. Different parts have different shapes, such as plate-shaped, T-shaped, block-shaped, etc.

[0069] Size: The dimensions of a part, including length, width, and height, are analogous to physical characteristics such as height and weight of an organism. Industrial parts are categorized by size into large, medium, and small.

[0070] Material: The material composition of a part, such as metal, plastic, or rubber, corresponds to the concept of skin color in biological DNA and reflects the inherent properties of the part.

[0071] Type: The classification of a part, meaning the specific category or lineage it belongs to, such as a gear, pipe, or bolt. Similar to species classification in biological classification, this DNA defines the type and structure of the part.

[0072] Purpose: The intended function or role of a part in a system, similar to a human occupation. This attribute determines the part's contribution to the overall system, such as transmission, fastening, clamping, and other functions.

[0073] Assembly relationships: This DNA is a unique property of a part, with no direct correspondence to biological entities. It describes the assembly relationship between a part and other parts in the system, specifically how they fit together and interact. Assembly relationships determine the compatibility and performance of parts within the overall assembly, including press fits, threaded connections, and clamped fits.

[0074] Together, these elements constitute the DNA of industrial parts, providing a comprehensive perspective on their characteristics, functions, and evolution within manufacturing systems. Just as biological DNA encapsulates the genetic information required for an organism's development and adaptation, the DNA of industrial parts enables the tracking of their historical evolution, modifications, and future potential, supporting optimization and customization in modern manufacturing. Furthermore, this DNA can further facilitate the generation of industrial parts under diverse constraints.

[0075] It is understandable that the DNA coding of the parts here is only schematic. In actual application, the DNA coding of the parts can be set according to the specific usage.

[0076] S302: Establish digital twin products and digital twin spaces based on physical interaction information.

[0077] Optionally, the physical interaction information includes first target detection information of the part and second target detection information of the scene; accordingly, based on the physical interaction information, a digital twin product and a digital twin space are established, including: performing approximate matching in a preset parts asset library based on the first target detection information, and determining the feature vector corresponding to the first target detection information based on the approximate matching result; performing matching processing of similarity measurement in a predefined parts library based on the feature vector, and determining the digital twin product corresponding to the first target detection information based on the matching processing result of the similarity measurement; and establishing a digital twin space based on the second target detection information.

[0078] In one possible implementation, the process of constructing a digital family tree 3D scene typically begins with perception of the physical world, typically achieved through visual sensors and visual perception algorithms. For example, object detection algorithms can be used to detect and classify parts in an RGB image of the physical world. Once the parts are identified, approximate matching is performed within a parts library based on their category, searching for identical or similar parts. This matching process aims to find the closest part matches based on their DNA, such as geometric configuration, material properties, or functional characteristics. These features are then used to create a feature vector, a numerical representation of the part's essential properties. Next, the system searches a parts library containing a large number of predefined parts for parts with similar feature vectors. This is typically done using similarity metrics such as cosine similarity and Euclidean distance. Parts are then ranked according to their similarity scores and the most suitable candidate parts are selected. Ultimately, the part in the parts library that is most similar to the detected part is identified as a digital entity in the digital twin scene, forming part of the overall scene.

[0079] Among them, the embodiment of the present application extracts data from the physical world and generates a digital twin, providing a digital foundation for subsequent genealogy generation and intelligent agent learning. Specifically, the target detection algorithm can be used to complete the target detection of each part in the RGB image of the physical world, identify and classify each part in the image, and adopt an approximate matching and a precise matching method of similarity measurement to identify and detect the parts that are most similar to the parts as digital entities in the digital twin scene, as part of the entire scene, and based on the recognition results, determine the shortcomings of the digital twin space, data twin products and digital twin space, so that the simulation is closer to the real production conditions, thereby improving the reliability and accuracy of the simulation reinforcement learning process, further improving the training effect of the industrial embodied intelligent world model, and improving the reasoning accuracy of the model.

[0080] S303: Generate a rich geometric representation corresponding to the product, a rich feature representation corresponding to the product, an environment configuration corresponding to the scene, and a device configuration corresponding to the scene based on the physical interaction information.

[0081] Optionally, the physical interaction information includes genetic coding information, multimodal information, production equipment information, and environmental parameter information of the product or part; accordingly, generating a rich geometric representation corresponding to the product, a rich feature representation corresponding to the product, and an environmental configuration corresponding to the scene based on the physical interaction information includes:

[0082] Generate a rich geometric representation of the product based on genetic encoding information; generate a rich feature representation of the product based on multimodal information; generate a device configuration for the scenario based on production equipment information; and generate an environmental configuration for the scenario based on environmental parameter information.

[0083] The genetic coding information includes at least one of shape, size, material, type, purpose, and assembly relationship.

[0084] The rich geometry representation includes at least one of a boundary representation, a modeling sequence, a network entity, a polygon, a point cloud, and a voxel.

[0085] The multimodal information includes at least one of voice, text and image.

[0086] In one possible implementation, the production object is intelligently generated as follows:

[0087] During the digital twin modeling process described above, if the parts asset library does not match the same or similar parts, the system will use generative artificial intelligence methods to generate similar industrial parts. Due to the high requirements of industrial scenarios for the credibility of generated content, this method should be able to generate new parts based on given DNA constraints, rather than over-exerting creativity and distorting the generated parts. According to the definition of digital family part DNA in [1], the basic properties of DNA such as shape, size, and material can be used to guide the generation of new parts in a variety of ways. By specifying these DNA parameters, it can be ensured that the generated parts are both diverse and meet industrial requirements as much as possible.

[0088] During the generation process, DNA editing can be used to customize parts for specific designs. DNA-edited parts retain their unmodified DNA properties, allowing the newly generated part to inherit most of the original's characteristics while also possessing some unique, customized features. This intelligent generation method enables efficient batch generation of new parts that are interpretable from an industrial perspective, expanding the digital family part asset library and enabling the construction of digital family 3D scenes.

[0089] In one possible implementation, the production space is intelligently generated as follows:

[0090] Once parts are matched or generated, they can be imported into the Digital Family Tree 3D scene. As a more scalable digital world corresponding to the physical world, multiple parts from the family tree can be placed within it and arranged in various combinations. The Digital Family Tree 3D scene not only reflects the current state and configuration of the physical world but also records and predicts its changes over time, including the addition of new parts and changes to existing parts during the manufacturing process. This will enable the embodied intelligent world model to have greater generalization and adaptability.

[0091] After matching or generating parts, they are imported into a digital family 3D scene and placed within the 3D scene space while satisfying physical constraints. Domain randomization parameters can then be set within the digital family 3D scene. For example, environmental parameters can be modified to enhance the diversity of the synthesized data, thereby improving the robustness of the embodied intelligence world model in diverse environments. By creating diverse and realistic scenes, various conditions and challenges encountered in real-world manufacturing environments can be simulated. Specifically, domain randomization parameters within the digital family scene primarily relate to the environment, such as lighting conditions, spatial relationships between objects, object poses, and background. For example, lighting intensity and angle can be randomly adjusted to simulate varying lighting conditions on a factory floor. The spatial relationships and poses between parts in the scene can also be randomized, including changing their position, rotation, and relative spatial relationships. Furthermore, the background of the object workspace can be configured. For example, the material of the workbench can be changed to different backgrounds, such as metal or plastic, and different scales of wear can be added. This domain randomization generates more diverse synthetic data for training embodied intelligence world models. Domain randomization helps improve the generalization capabilities of models, ensuring they perform well in diverse scenarios and adapt to unpredictable conditions in real-world applications. Therefore, the Digital Genealogy framework becomes a powerful tool for creating versatile training environments that can simulate complex manufacturing processes and improve the performance of intelligent systems in flexible and dynamic environments.

[0092] Here, the embodiment of the present application proposes an information mechanism of DNA coding for digital genealogies. By designing DNA coding to constrain the phenotypes of parts generated in the genealogy, it ensures that they meet the performance requirements of industrial production while being interpretable. Combined with multimodal information such as voice, text or images, it can automatically generate 3D models that meet engineering needs. In terms of production space, the embodiment of the present application realizes the construction of digital twin scenes by configuring scene elements, and realizes the equipment configuration and environment configuration in the scene elements through production equipment information and environmental parameter information. Through the construction of the above series of scene elements and 3D models, sufficient training materials and accurate simulation environments are provided for the high adaptability of industrial intelligent bodies, further enriching the trainable data and scenes, and improving the training effect of the industrial embodied intelligent world model.

[0093] S304: Generate a digital family tree of production objects corresponding to the production objects based on the digital twin product, the rich geometry representation, and the rich feature representation.

[0094] Optionally, generating a digital family tree of production objects corresponding to the production objects based on the digital twin product, the rich geometry representation, and the rich feature representation includes:

[0095] Obtain a preset first family tree structure, wherein the preset first family tree structure is a first tree structure, the first tree structure includes multiple first-level tree nodes, and the first level includes product level, assembly level and part level; according to the digital twin product, rich geometry representation and rich feature representation, perform node filling processing on the first family tree structure to obtain a digital family tree of the production object corresponding to the production object.

[0096] Demonstratively, Figure 4 A schematic diagram of the structure of a digital genealogy of production objects provided in an embodiment of the present application is shown as follows: Figure 4 The figure below illustrates a digital family tree from the perspective of production objects. Regarding production objects, the previously generated 3D parts are not only stored as independent geometric representations but also organized into a family tree structure to reflect the generational relationships between parts and their hierarchical connections to downstream assemblies and the final product. This organizational approach clearly demonstrates how diverse part designs are derived from different requirements and how assembly relationships form a complete product system.

[0097] Here, the embodiment of the present application establishes a first family tree structure from the perspective of production objects. From the perspective of production objects, a series of tree-like family trees can be generated from parts to assemblies and then to products. Based on this digital family tree structure, 3D parts are not only stored as independent geometric representations, but also placed in the family tree structure to reflect the generation relationship between parts, as well as their hierarchical relationship with downstream assemblies and final products. Through this organizational method, it is possible to clearly express how different needs derive diverse part designs and how a complete product system is formed through assembly relationships, thereby enriching the trainable data and improving the training effect of the industrial embodied intelligent world model.

[0098] S305: Generate a production space digital genealogy corresponding to the production space based on the digital twin space, environment configuration, and equipment configuration.

[0099] Optionally, generating a digital genealogy of the production space corresponding to the production space based on the digital twin space, environmental configuration and equipment configuration includes: obtaining a plurality of preset types of production scenes, wherein the preset types are determined based on multiple production equipment, production environment and production personnel; obtaining a second genealogy structure corresponding to each preset type of production scene; performing node filling processing on the second genealogy structure according to the digital twin space, environmental configuration and equipment configuration to obtain a digital genealogy of the production space corresponding to the production space.

[0100] Demonstratively, Figure 5 A schematic diagram of the structure of a production space digital family tree provided in an embodiment of the present application is shown as follows: Figure 5As shown in the figure, a digital genealogy from the perspective of production space is presented. In terms of production space, a variety of 3D digital scenes are constructed to provide a rich training environment for subsequent intelligent agent learning. Different types of production scenes are systematically classified, each with different production equipment, production environment and production personnel. Intelligent agents can perform simulation learning in these scenes. Through industrial genealogy 3D scene training, the adaptability of intelligent equipment such as industrial robots and automated production systems can be improved. It is understandable that Figure 4 、 Figure 5 And the embodiments of this application Figure 6 This is for illustration only and does not affect the scope of protection of the embodiments of the present application.

[0101] The embodiment of this application establishes a second family tree structure from the perspective of production scenarios. The family tree layer constructs a variety of 3D digital scenes through the methods of the generation layer, providing a rich training environment for subsequent intelligent agent learning. Different types of production scenarios are systematically classified, each with different production equipment, production environment, and production personnel. Intelligent agents of the industrial embodied intelligent world model can conduct simulation learning in these scenarios. Through industrial family tree 3D scene training, the adaptability of intelligent equipment such as industrial robots and automated production systems can be improved.

[0102] S306: Establish a target digital family tree based on the production object digital family tree and the production space digital family tree.

[0103] Among them, the target digital family tree is used to train the industrial embodied intelligent world model.

[0104] An embodiment of the present application provides a method for generating an industrial digital family tree. The digital family tree is a new concept proposed in the embodiment of the present application, which provides new possibilities for the construction of an industrial embodied intelligent world model from two perspectives. Specifically, from the two perspectives of production objects and production space, combined with digital twin technology and generation technology, a series of tree-like family trees from parts to assemblies and then to products and a diverse digital production space in the entire life cycle of intelligent manufacturing products are generated based on the collected physical interaction information, and then a production object digital family tree corresponding to the production object and a production space digital family tree corresponding to the production space are constructed. Through the production object digital family tree corresponding to the production object and the production space digital family tree corresponding to the production space, a large amount of three-dimensional digital scene data can be generated by combining diverse random combinations of different parts and assemblies in the production objects in diversified production spaces for the industrial embodied intelligent world model to learn and train in the digital family tree, thereby improving the adaptability and generalization of the model.

[0105] Optionally, after establishing the target digital genealogy based on the production object digital genealogy and the production space digital genealogy, it also includes: obtaining the original industrial embodied intelligent world model; training the original industrial embodied intelligent world model based on the target digital genealogy to obtain the target industrial embodied intelligent world model.

[0106] Among them, the digital genealogy created by the embodiment of the present application records the evolution of part data from multi-model parts to multi-performance products. Combined with its various production scenarios, it not only describes the mapping relationship between different part characteristics and different product performances, but also traces the changes in the product during its life cycle, ensuring the continuity and consistency of the production process from parts to products. It also includes scene-level digital spaces for different tasks in each production and manufacturing stage. The training of the industrial embodied intelligent world model based on the digital genealogy can enable the industrial embodied intelligent world model to manipulate different models of physical equipment for learning and training in a rich and diverse digital space, further improving the adaptability and generalization of the industrial embodied intelligent world model, thereby realizing interaction and feedback in the industrial physical environment.

[0107] Optionally, the target industrial embodied intelligent world model is used to execute at least one of the full life cycle applications of industrial products, which include: model simulation design based on digital genealogy; product design based on genetic coding constraints; flexible sorting based on digital genealogy; product assembly guidance with reference to genetic coding; genealogy-driven adaptive scenario understanding; genetic coding similarity-driven process generation; genealogy-based predictive operation and maintenance of parts; and operation and maintenance guidance based on genetic coding similarity.

[0108] Here, the embodiment of the present application can train an embodied intelligent world model of the target industry with excellent results based on the rich product and scenario data in the digital map, and then realize practical applications such as intelligent design, manufacturing optimization, and predictive maintenance, thereby improving the performance of intelligent systems in flexible and dynamic environments, and in the field of intelligent manufacturing, improving the automation and intelligence of intelligent manufacturing of industrial parts.

[0109] Optionally, Figure 6 A schematic diagram of a digital genealogy system architecture provided in an embodiment of the present application. The digital genealogy system may be an industrial digital genealogy system in an embodiment of the present application, or may be implemented based on an industrial digital genealogy system, such as Figure 6 As shown in the figure, the architecture of the digital genealogy includes the physical world layer, the digital genealogy layer, the intelligent interaction layer and the typical application layer. Among them, the digital genealogy layer includes three sublayers: the twin layer, the generation layer and the digital genealogy.

[0110] The physical world layer is the real-world foundation of the digital family tree. It encompasses three core elements: people, devices, and materials, forming the physical vehicle for actual industrial production and manufacturing activities. The data and structures at this layer are not only the direct objects of interaction for industrial agents but also the true source of digital twins and agent learning, providing industrial agents with rich information about physical interactions. At the human level, the physical world encompasses diverse roles such as skilled workers, designers, and experimenters; at the device level, it encompasses industrial automation equipment such as robots and machine tools; and at the material level, it encompasses raw materials, parts, and products. Through data collection and modeling, information from the physical world layer can be mapped to the digital world, thereby forming a digital twin and digital family tree.

[0111] The twin layer is a precursor to building a digital family tree. It extracts data from the physical world and generates digital twins, providing a digital foundation for subsequent family tree generation and agent learning. At this layer, industrial systems map production factors from the physical world into the digital space through methods such as 3D modeling and data collection. Regarding production objects, the twin layer focuses on the digital transformation of specific products. Through 3D modeling, structural scanning, and material analysis, physical products are transformed into 3D models accompanied by detailed feature data. This data, including product geometry, assembly methods, and process parameters, provides the foundation for subsequent agent training. Regarding the production space, the twin layer digitally maps elements such as the production environment, manufacturing processes, and human interaction. This encompasses manufacturing scenarios such as automated production lines, smart workshops, and robotic workstations. Combined with sensor data, it dynamically reflects the operating status of the actual industrial environment. Environmental twin data integrates parameters such as workshop temperature, humidity, light, and energy consumption, making simulations more realistic, thereby improving the reliability and accuracy of the simulation-based reinforcement learning process.

[0112] The digital family tree generation layer is the core component of intelligent modeling for large industrial models, encompassing both product and scenario family tree generation. This layer utilizes multimodal data fusion and deep learning to construct a digital family tree rich in features and geometric information. Regarding production objects, the system automatically generates a 3D model that meets engineering requirements based on the input "DNA data" (the genetic code of a product or component, including structural parameters, functional characteristics, and manufacturing processes) combined with multimodal information such as text, images, and audio. This model can utilize various geometric representations, including boundary representation (B-rep), modeling sequences, meshes, polygons, point clouds, and voxels. Regarding production spaces, the generation layer constructs digital twin scenarios by configuring scenario elements. By selecting different environmental parameters (such as temperature, humidity, and lighting) and different production equipment, the generation layer configures the entire production scenario based on the given input parameters, enabling simulated production performance under a variety of working conditions. By constructing a series of family tree scenarios, the highly adaptive capabilities of industrial agents are provided with sufficient training data and a precise simulation environment.

[0113] The digital family tree sublayer, based on the generated 3D models, further constructs a family tree structure for products and scenarios, establishing product and scenario families. Regarding production objects, the generated 3D parts are not only stored as independent geometric representations but also placed into a family tree structure to reflect the generational relationships between parts and their hierarchical connections with downstream assemblies and the final product. This organizational approach clearly demonstrates how diverse part designs are derived from different requirements and how assembly relationships form a complete product system. Regarding production spaces, the digital family tree sublayer constructs diverse 3D digital scenes using methods from the generation layer, providing a rich training environment for subsequent intelligent agent learning. Different types of production scenarios are systematically categorized, each with distinct production equipment, production environments, and production personnel. Intelligent agents can conduct simulated learning in these scenarios. Through 3D scenario training within the industrial family tree, the adaptability of intelligent devices such as industrial robots and automated production systems is improved.

[0114] The intelligent interaction layer is a key step in transitioning from agent learning to practical industrial application. During the interaction process, the industrial embodied intelligence model uses data from the genealogy of production objects and production spaces to learn. The trained agent can efficiently interact with humans, terminal devices, and materials, enabling the digital genealogy to function in real-world production environments. In the interaction layer, human operators communicate with the industrial embodied intelligence model through natural language, commands, and other interactive methods, making adjustments as necessary. As the intelligent core, the industrial embodied intelligence model intelligently operates terminal devices, enabling intelligent production. While executing tasks, the industrial embodied intelligence model continuously coordinates and manages production materials.

[0115] The typical application layer is the practical implementation stage of the industrial large-scale model. Relying on the aforementioned layers, it enables practical applications such as intelligent design, manufacturing optimization, and predictive maintenance. During the design phase, based on historical product data, process parameters, and production experience of similar products within the family tree, efficient and reliable design solutions are automatically generated, enabling digital family tree-driven simulation design and reducing design time. During the manufacturing phase, the application layer implements family tree-based production process simulation, optimizing production processes within virtual digital family tree scenarios and improving the model's generalization capabilities. Simultaneously, the intelligent agent can generate processing plans or operating methods based on the similarities between the manufacturing-related DNA of parts, enabling the large-scale model to demonstrate excellent flexibility in a flexible manufacturing environment. During the operation and maintenance phase, the part family tree can be used to perform predictive operation and maintenance on parts. By analyzing DNA information such as part material and shape and combining it with the part's operating status data, potential faults can be detected in advance, improving equipment reliability.

[0116] In one possible implementation, Figure 7 A schematic diagram of the steps of a method for constructing a digital family tree provided in an embodiment of the present application, combined with Figure 7 , the embodiments of the present application can achieve the following functions:

[0117] Two perspectives provide new possibilities for constructing an industrial embodied intelligent world model. From the production object perspective, a tree-like family tree can be generated, spanning from parts to assemblies to products. A digital family tree DNA gene mechanism is defined, and by designing DNA encoding to constrain the phenotypes of parts generated in the family tree, it ensures that they meet industrial production performance requirements while also being interpretable. From the production space perspective, a diverse digital production space can be generated for the entire life cycle of intelligent manufacturing products, including diverse scenarios with different equipment and environmental configurations in warehousing, manufacturing, and operation and maintenance scenarios. Combining these two perspectives, a large amount of three-dimensional digital scene data can be generated within diverse production spaces by combining the diverse random combinations of different parts and assemblies within production objects. This data can then be used by the industrial embodied intelligent world model to learn and train within the digital family tree, improving the model's adaptability and generalization.

[0118] The digital family tree not only describes the mapping relationship between the characteristics of different parts and the performance of different products, but also traces the changes in the product during its life cycle, ensuring the continuity and consistency of the production process from parts to products. It also includes scene-level digital spaces for different tasks in each production and manufacturing stage, which can be used by embodied world models to manipulate different types of physical equipment for learning and training in a rich and diverse digital space.

[0119] Figure 8 A schematic diagram of a device for generating an industrial digital family tree provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the apparatus of the embodiment of the present application includes: an acquisition module 801, a twin module 802, a generation module 803, a first family tree module 804, a second family tree module 805 and an establishment module 806. The generation device of the industrial digital family tree here can be the above-mentioned processing device itself, or a chip or integrated circuit that realizes the function of the processing device. It should be noted here that the division of the acquisition module 801, the twin module 802, the generation module 803, the first family tree module 804, the second family tree module 805 and the establishment module 806 is only a division of logical functions. Physically, the two can be integrated or independent.

[0120] Among them, the acquisition module is used to obtain physical interaction information; the twin module is used to establish digital twin products and digital twin spaces based on the physical interaction information; the generation module is used to generate rich geometric representations corresponding to the products, rich feature representations corresponding to the products, and environmental configurations and equipment configurations corresponding to the scenes based on the physical interaction information; the first family tree module is used to generate a digital family tree of production objects corresponding to the production objects based on the digital twin products, rich geometric representations and rich feature representations; the second family tree module is used to generate a digital family tree of production spaces corresponding to the production spaces based on the digital twin spaces, environmental configurations and equipment configurations; the establishment module is used to establish a target digital family tree based on the digital family tree of production objects and the digital family tree of production spaces, wherein the target digital family tree is used for training the industrial embodied intelligent world model.

[0121] Optionally, the physical interaction information includes genetic coding information, multimodal information, production equipment information and environmental parameter information of the product or part; accordingly, the generation module is specifically used to: generate a rich geometric representation corresponding to the product based on the genetic coding information, wherein the genetic coding information includes at least one of shape, size, material, type, purpose, and assembly relationship, and the rich geometric representation includes at least one of boundary representation, modeling sequence, network entity, polygon, point cloud and voxel; generate a rich feature representation corresponding to the product based on the multimodal information, wherein the multimodal information includes at least one of voice, text and image; generate a device configuration corresponding to the scene based on the production equipment information; generate an environmental configuration corresponding to the scene based on the environmental parameter information.

[0122] Optionally, the physical interaction information includes first target detection information of the part and second target detection information of the scene; accordingly, the twin module is specifically used to: perform approximate matching in a preset part asset library based on the first target detection information, and determine the feature vector corresponding to the first target detection information based on the approximate matching result; perform matching processing of similarity measurement in a predefined parts library based on the feature vector, and determine the digital twin product corresponding to the first target detection information based on the matching processing result of the similarity measurement; and establish a digital twin space based on the second target detection information.

[0123] Optionally, the first genealogy module is specifically used to: obtain a preset first genealogy structure, wherein the preset first genealogy structure is a first tree structure, the first tree structure includes multiple first-level tree nodes, and the first level includes product level, assembly level and part level; according to the digital twin product, rich geometry representation and rich feature representation, the first genealogy structure is node-filled to obtain a digital genealogy of the production object corresponding to the production object.

[0124] Optionally, the second genealogy module is specifically used to: obtain multiple preset types of production scenarios, where the preset types are determined based on multiple production equipment, production environment, and production personnel; obtain the second genealogy structure corresponding to each preset type of production scenario; and perform node filling processing on the second genealogy structure according to the digital twin space, environment configuration, and equipment configuration to obtain a production space digital genealogy corresponding to the production space.

[0125] Optionally, after the establishment module is used to establish the target digital family tree based on the production object digital family tree and the production space digital family tree, the above-mentioned device also includes a training module for: obtaining the original industrial embodied intelligent world model; training the original industrial embodied intelligent world model based on the target digital family tree to obtain the target industrial embodied intelligent world model.

[0126] Optionally, the target industrial embodied intelligent world model is used to execute at least one of the full life cycle applications of industrial products, which include: model simulation design based on digital genealogy; product design based on genetic coding constraints; flexible sorting based on digital genealogy; product assembly guidance with reference to genetic coding; genealogy-driven adaptive scenario understanding; genetic coding similarity-driven process generation; genealogy-based predictive operation and maintenance of parts; and operation and maintenance guidance based on genetic coding similarity.

[0127] refer to Figure 9 , which shows a schematic diagram of the structure of an industrial digital genealogy system 900 suitable for implementing embodiments of the present disclosure. The industrial digital genealogy system 900 can be a terminal device or a server. Terminal devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 9 The industrial digital genealogy system shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0128] like Figure 9 As shown, industrial digital genealogy system 900 may include a processing device (e.g., a central processing unit, graphics processing unit, etc.) 901, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 902 or programs loaded from storage device 908 into random access memory (RAM) 903. RAM 903 also stores various programs and data required for the operation of industrial digital genealogy system 900. Processing device 901, ROM 902, and RAM 903 are interconnected via bus 904. An input / output (I / O) interface 905 is also connected to bus 904.

[0129] Typically, the following devices can be connected to the I / O interface 905: input devices 906 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 908 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 909. The communication devices 909 can allow the industrial digital genealogy system 900 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 9 The industrial digital genealogy system 900 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0130] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the processing device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0131] It should be noted that the computer-readable medium described above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable storage media may include, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wire, optical cable, RF (radio frequency), or any suitable combination thereof.

[0132] The computer-readable medium may be included in the industrial digital genealogy system; or it may exist independently without being incorporated into the industrial digital genealogy system.

[0133] The computer-readable medium carries one or more programs. When the one or more programs are executed by the industrial digital genealogy system, the industrial digital genealogy system executes the method shown in the above embodiment.

[0134] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0137] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0138] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0139] The industrial digital genealogy system of the embodiment of the present application can be used to implement the technical solutions in the above-mentioned method embodiments of the present application. Its implementation principles and technical effects are similar and will not be repeated here.

[0140] An embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement any of the above-mentioned methods for generating industrial digital genealogies.

[0141] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, is used to implement any of the above-mentioned methods for generating an industrial digital family tree.

[0142] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0143] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0144] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0145] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for generating an industrial digital family tree, characterized in that: include: Obtain physical interaction information; Establishing a digital twin product and a digital twin space based on the physical interaction information; The physical interaction information includes genetic coding information, multimodal information, production equipment information and environmental parameter information of the product or part; Generating, based on the physical interaction information, a rich geometric representation corresponding to the product, a rich feature representation corresponding to the product, an environmental configuration corresponding to the scene, and an equipment configuration corresponding to the scene, including: generating, based on the genetic coding information, a rich geometric representation corresponding to the product, wherein the genetic coding information includes at least one of shape, size, material, type, purpose, and assembly relationship, and the rich geometric representation includes at least one of boundary representation, modeling sequence, network entity, polygon, point cloud, and voxel; generating, based on the multimodal information, a rich feature representation corresponding to the product, wherein the multimodal information includes at least one of voice, text, and image; generating, based on the production equipment information, an equipment configuration corresponding to the scene; and generating, based on the environmental parameter information, an environmental configuration corresponding to the scene; Generating a production object digital family tree corresponding to the production object according to the digital twin product, the rich geometric representation, and the rich feature representation, including: obtaining a preset first family tree structure, wherein the preset first family tree structure is a first tree structure, the first tree structure including a plurality of first-level tree nodes, the first level including a product level, an assembly level, and a part level; performing node filling processing on the first family tree structure according to the digital twin product, the rich geometric representation, and the rich feature representation to obtain a production object digital family tree corresponding to the production object; Generating a production space digital family tree corresponding to the production space according to the digital twin space, the environment configuration, and the equipment configuration, including: obtaining a plurality of preset types of production scenarios, wherein the preset types are determined based on a plurality of production equipment, production environment, and production personnel; obtaining a second family tree structure corresponding to each of the preset types of production scenarios; performing node filling processing on the second family tree structure according to the digital twin space, the environment configuration, and the equipment configuration to obtain a production space digital family tree corresponding to the production space; A target digital family tree is established based on the production object digital family tree and the production space digital family tree, wherein the target digital family tree is used for training the industrial embodied intelligent world model.

2. The method according to claim 1, characterized in that The physical interaction information includes first target detection information of the part and second target detection information of the scene; Accordingly, the establishment of a digital twin product and a digital twin space based on the physical interaction information includes: performing an approximate match in a preset parts asset library based on the first target detection information, and determining a feature vector corresponding to the first target detection information based on the approximate matching result; Performing a matching process of similarity measurement in a predefined parts library based on the feature vector, so as to determine a digital twin product corresponding to the first target detection information based on a matching process result of the similarity measurement; A digital twin space is established based on the second target detection information.

3. The method according to claim 1, characterized in that After establishing a target digital family tree based on the production object digital family tree and the production space digital family tree, the method further includes: Obtaining original industrial embodied intelligence world models; The original industrial embodied intelligent world model is trained according to the target digital family tree to obtain a target industrial embodied intelligent world model.

4. The method according to claim 3, characterized in that The target industrial embodied intelligent world model is used to execute at least one of the industrial product full life cycle applications, wherein the industrial product full life cycle applications include: Model simulation design based on digital genealogy; Product design based on genetically encoded constraints; Flexible sorting based on digital genealogy; Product assembly instructions encoded with reference genes; Genealogy-driven adaptive scene understanding; process generation driven by genetic coding similarity; Genealogy-based predictive maintenance of parts; Operation and maintenance guidance based on genetic coding similarity.

5. An industrial digital genealogy system, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 4 when executed by a processor.

7. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 4 when executed by a processor.

Images