Business data management method, system and cloud platform based on process industry digital factory

Abstract

The embodiments of the present application provide a business data management method, system and cloud platform based on a process industry digital factory. First, multiple standard production process data and the operation configuration data of the target digital factory production line are obtained from the process industry digital factory. Subsequently, the operation drive instruction data of the standard space collaborative operation node is extracted from the standard production process data, and the basic operation data of the basic space collaborative operation node is extracted from the production line operation configuration data, thereby mapping the predefined production operation data in the standard production process to the configuration of the target production line, and generating multiple reference production line optimization data. Finally, based on the characterization vector of the target production line in the configuration data as a restriction basis, combined with the reference optimization data, the activation data of the target production line is generated, and through intelligent analysis and optimization, the precise control and efficient management of the production process of the home furnishing industry are realized, which significantly improves the production efficiency and product quality.

Description

Technical Field

[0001] The present invention relates to the field of digital factories and artificial intelligence technologies, and in particular to a business data management method, system and cloud platform based on a digital factory in a process industry. Background Art

[0002] In the home furnishing industry, as consumers' demands for quality and personalization of home furnishing products continue to increase, the traditional home furnishing manufacturing model faces severe challenges. In order to meet these challenges, the home furnishing industry is accelerating its transformation to digitalization and intelligence, and the concept of process industry digital factories is gradually being applied in the field of home furnishing manufacturing. However, although digital factory technology has brought many conveniences to home furnishing production, in actual operation, how to efficiently manage and utilize business data to optimize production processes, improve production efficiency and product quality is still an important issue facing the home furnishing industry.

[0003] Traditional home furnishing production management methods often rely on manual experience and paper records, lacking precise control of production processes and data analysis. This management method may be competent when dealing with simple and repetitive production tasks, but it is powerless when faced with complex and changing production environments and personalized consumer needs. Especially in the home furnishing manufacturing process, there are a large number of spatial collaborative operation nodes, such as material transfer between equipment, precise positioning and assembly of components, etc. The operating efficiency and accuracy of these nodes directly affect the operating efficiency and product quality of the entire production line. Summary of the invention

[0004] In order to at least overcome the above-mentioned deficiencies in the prior art, the purpose of the embodiments of the present application is to provide a business data management method, system and cloud platform based on a process industry digital factory.

[0005] According to one aspect of the present application, a business data management method based on a process industry digital factory is provided, the method comprising: obtaining X standard production process data and production line operation configuration data of a target digital factory production line from the process industry digital factory; X is a positive integer, and each standard production process data contains predefined production operation data; from the X standard production process data, extracting operation drive instruction data associated with each of X groups of standard space collaborative operation nodes, and extracting basic operation data corresponding to the basic space collaborative operation nodes of the target digital factory production line from the production line operation configuration data; one standard production process data corresponds to a group of operation drive instruction data of standard space collaborative operation nodes; based on the operation drive instruction data associated with each of the X groups of standard space collaborative operation nodes and the basic operation data corresponding to the basic space collaborative operation nodes, mapping the predefined production operation data associated with each of the X standard production process data to the production line operation configuration data, and generating X reference production line optimization data of the target digital factory production line; using the characterization vector of the target digital factory production line in the production line operation configuration data as a restriction basis, based on the X reference production line optimization data, generating the target production line activation data of the target digital factory production line.

[0006] According to one aspect of an embodiment of the present application, a business data management system based on a process industry digital factory is provided, including a cloud platform and a process industry digital factory communicated with the cloud platform; the cloud platform is specifically used to: obtain X standard production process data and production line operation configuration data of a target digital factory production line from the process industry digital factory; X is a positive integer, and each standard production process data contains predefined production operation data; from the X standard production process data, extract X groups of operation drive instruction data associated with each of the standard space collaborative operation nodes, and from the production line operation configuration data, extract the basic space collaborative operation nodes corresponding to the target digital factory production line. The method comprises the steps of: mapping the predefined production operation data associated with each of the X sets of standard space collaborative operation nodes to the production line operation configuration data based on the operation drive instruction data associated with each of the X sets of standard space collaborative operation nodes and the basic operation data corresponding to the basic space collaborative operation nodes, and generating X reference production line optimization data of the target digital factory production line; and generating target production line activation data of the target digital factory production line based on the X reference production line optimization data, taking the characterization vector of the target digital factory production line in the production line operation configuration data as a restriction basis.

[0007] According to one aspect of an embodiment of the present application, a cloud platform is provided, which includes a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions, and the machine-executable instructions are loaded and executed by the processor to implement the methods provided in the various optional implementations described above.

[0008] According to one aspect of the embodiments of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above various optional implementations.

[0009] In the technical solutions provided in some embodiments of the present application, the embodiments of the present application achieve accurate management and optimization of the production process by acquiring standard production process data and operation configuration data of the target digital factory production line from the process industry digital factory. Specifically, the operation drive instruction data of the standard space collaborative operation node and the basic operation data of the basic space collaborative operation node are extracted, and these data are integrated into the configuration of the target digital factory production line through mapping operations, and multiple reference production line optimization data are generated. Finally, based on the characterization vector of the target digital factory production line, the present invention generates the target production line activation data. By integrating and optimizing the standard production process data, a more efficient production line configuration scheme can be generated, and redundant operations and waiting time in the production process can be reduced, thereby improving the overall production efficiency. In addition, the spatial collaborative operation nodes on the production line can be accurately analyzed, and resource allocation can be performed based on the operation requirements of these spatial collaborative operation nodes to ensure efficient use of resources and avoid resource waste. By mapping the standard production process data to the target production line configuration, the consistency and standardization of the production operation can be ensured, thereby reducing the quality risk in the production process and improving product quality. The target production line activation data generated thereby has a high degree of flexibility and adjustability, and can be quickly adjusted according to changes in market demand and production environment to meet diverse production needs. By optimizing production processes and resource allocation, it helps to reduce energy consumption, material consumption and labor costs in the production process, thereby reducing overall operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be extracted in combination with these drawings without creative work.

[0011] Figure 1 A flowchart of a business data management method based on a process industry digital factory provided in an embodiment of the present application;

[0012] Figure 2 A schematic block diagram of the architecture of the cloud platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] The following description is intended to enable one of ordinary skill in the art to implement and combine the present application, and the description is provided in the context of a specific application scenario and its requirements. It will be apparent to one of ordinary skill in the art that various changes may be made to the disclosed embodiments, and that the general principles defined in the present application may be applied to other embodiments and application scenarios without departing from the principles and scope of the present application. Therefore, the present application is not limited to the described embodiments, but should be given the broadest scope consistent with the claims.

[0014] Figure 1 This is a flow chart of a business data management method based on a process industry digital factory provided by an embodiment of the present application. The business data management method based on a process industry digital factory is introduced in detail below.

[0015] Step S110, obtaining X standard production process data and production line operation configuration data of the target digital factory production line from the process industry digital factory. X is a positive integer, and each standard production process data contains predefined production operation data.

[0016] Specifically, the process industry digital factory refers to an industrial production environment that integrates digitalization, automation and intelligent technologies, covering the entire process from raw material supply, production and processing to finished product output. The digital factory achieves precise control and optimization of the production process through virtual simulation, data analysis and other means.

[0017] The standard production process data is production operation process data that has been verified and standardized in the process industry, including detailed operation specifications, parameter settings, etc. of each step in the production process, which is used to ensure the consistency and efficiency of production. The target digital factory production line refers to a specific production line that needs to be optimized and configured, located in the target digital factory. This target digital factory production line may be in operation or about to be put into operation, and its performance and production efficiency need to be improved.

[0018] The production line operation configuration data is data describing the current operation status and configuration information of the target digital factory production line, including equipment layout, equipment parameters, material flow path, etc. These production line operation configuration data are the basis for optimizing the production line.

[0019] For example, in this embodiment, in the furniture industry, multiple furniture manufacturing digital factories are set up, and this digital factory covers all links from raw material processing to final furniture assembly. Assuming that X is 3, it means that the server needs to obtain 3 standard production process data and the production line operation configuration data of the target digital factory production line (for example, a production line specializing in the production of a certain type of wooden furniture) from the process industry digital factory.

[0020] For the first standard production process data, it can be about the preliminary processing process of wood. The predefined production operation data includes the cutting size of wood (for example, cutting logs into boards of different lengths and widths, such as boards with a length of 2 meters and a width of 0.5 meters for making tabletops), cutting angles (such as 45-degree cutting for special-shaped furniture parts), cutting speed (parameters such as how many meters are cut per minute, which will affect production efficiency and cutting accuracy), etc. At the same time, this process data may also include operational data for drying wood, such as drying temperature (50 degrees Celsius), drying time (24 hours), etc., all of which are to ensure that the quality of wood is suitable for subsequent processing.

[0021] The second standard production process data may be about the processing process of furniture parts. The predefined production operation data includes the operation information of sanding the cut wood board, such as the sandpaper type used (200-grit sandpaper is used for preliminary sanding, 800-grit sandpaper is used for fine sanding), sanding pressure (in Newtons, different parts may require different sanding pressures to ensure the flatness of the surface), sanding direction (along the wood grain or a specific shape direction), etc. In addition, it may also include the operation data of drilling holes in the wood board, such as the diameter of the hole (5 mm for installing screws), the depth of the hole (10 mm), the spacing of the holes (determined according to the furniture design requirements), etc.

[0022] The third standard production process data is about the assembly process of furniture. The predefined production operation data includes the type of connectors used (such as metal screws, mortise and tenon structures, etc.), the order of assembly (first assemble the frame, then install drawers and other components), the torque requirements of each connector (the force with which the screws are tightened to ensure the stability of the furniture structure), etc.

[0023] The production line operation configuration data of the target digital factory production line contains relevant information about the production line equipment. For example, the model of the cutting equipment in the production line (a certain brand of high-precision CNC cutting saw), the maximum cutting capacity of the cutting equipment (the maximum wood thickness and width that can be cut), the type of grinding equipment (the model and functional parameters of the automatic sanding machine), the type of fixture on the assembly workbench (used to fix furniture parts for assembly), etc. At the same time, it also includes the layout information of the production line, such as the position relationship of each equipment on the production line (cutting equipment at the front end of the production line, grinding equipment in the middle, assembly equipment at the end, etc.), which helps to determine the flow path of materials on the production line. The server interacts with the database system of the digital factory to accurately obtain these standard production process data and production line operation configuration data, and prepare for subsequent optimization operations.

[0024] Step S120, extracting operation drive instruction data associated with each of the X groups of standard space collaborative operation nodes from the X standard production process data, and extracting basic operation data corresponding to the basic space collaborative operation nodes of the target digital factory production line from the production line operation configuration data. One standard production process data corresponds to a group of operation drive instruction data of the standard space collaborative operation nodes.

[0025] In detail, the standard space collaborative operation node is a node responsible for specific space collaborative operations (such as material transfer between equipment, equipment position adjustment, etc.) in the production process. Each standard space collaborative operation node is associated with a set of operation drive instruction data to guide it to complete the collaborative operation. The operation drive instruction data is the data that controls the standard space collaborative operation node to perform specific operations, including position adjustment, posture adjustment, operation state parameters, etc., which directly determines the operation behavior and effect of the node.

[0026] The basic space collaborative operation node is a node responsible for basic space collaborative operation on the target digital factory production line. These basic space collaborative operation nodes are the basis for the normal operation of the production line, and their operation data (such as equipment position, equipment parameters, etc.) are the key to optimizing the production line. The basic operation data is data that describes the current operation status of the basic space collaborative operation node, including position adjustment arrays, operation status parameters, etc., reflecting the current configuration and operation status of the production line.

[0027] For example, in this embodiment, the example of the home furnishing industry is continued to be used for explanation. After acquiring the above three standard production process data and the target production line operation configuration data, the server starts to further extract data.

[0028] For the first standard production process (wood pre-processing process), the operation drive instruction data associated with a set of standard spatial collaborative operation nodes may be as follows. The operation drive instruction data includes a position adjustment array, a posture adjustment array, and an operation state parameter. Taking wood cutting equipment as an example, the position adjustment array may involve the initial position of the cutting tool relative to the wood, such as the coordinates on the x, y, and z axes (x = 0, y = 0, z = 0 means that the tool is located at the starting cutting point of the wood). This position will be dynamically adjusted according to the size of the wood and the cutting requirements. The posture adjustment array is related to the angle of the tool, such as the angle between the tool and the surface of the wood (when cutting wood at a 45-degree angle, the tool needs to be adjusted to the corresponding angle). The operation state parameters include the rotation speed of the cutting tool (such as 3000 revolutions per minute), the feed speed of the tool (how many millimeters per second), etc.

[0029] For the second standard production process (furniture parts processing process), the operation drive instruction data associated with the standard space collaborative operation node also includes these contents. For example, in the process of sanding the wooden board, the position adjustment array indicates the contact position between the sandpaper and the wooden board, the attitude adjustment array reflects the contact angle between the sandpaper and the wooden board (to ensure uniform sanding), and the operation state parameters include the movement speed of the sandpaper (the distance moved on the wooden board per minute), the sanding pressure value (set according to the material of the wooden board and the required sanding effect), etc. In the drilling operation, the position adjustment array determines the starting position of the drilling drill on the wooden board, the attitude adjustment array ensures that the drill is perpendicular to the surface of the wooden board, and the operation state parameters include the drill speed (such as 1500 revolutions per minute), the depth control parameters of the drilling, etc.

[0030] For the third standard production process (furniture assembly process), when using connectors to assemble furniture components, the position adjustment array involves the position coordinates of the connector installation, and the posture adjustment array takes into account the installation angle of the connector (such as the direction in which the screw is screwed in must be perpendicular to the surface of the component). The operating status parameters include the torque value of the screw tightening (such as 20 Newton meters), the sequential control parameters of the connector installation, etc.

[0031] The basic operation data corresponding to the basic spatial collaborative operation node extracted from the production line operation configuration data of the target digital factory production line. For example, for the cutting equipment in the production line, the position adjustment array in the basic operation data represents the fixed position coordinates of the equipment in the production workshop (such as x = 10 meters, y = 5 meters, z = 0 meters), and the operation status parameters include the maximum power of the equipment (5 kilowatts), the default operation mode of the equipment (such as continuous operation mode or intermittent operation mode), etc. For the grinding equipment, the position adjustment array is its layout position on the production line, and the operation status parameters include the start time of the equipment (start at 8 o'clock in the morning), the maintenance cycle of the equipment (maintenance every 100 hours of operation), etc. The position adjustment array in the basic operation data of the assembly workbench determines its specific position at the end of the production line, and the operation status parameters include the number of parts that the workbench can accommodate (a maximum of 5 sets of furniture parts can be placed for assembly at a time), etc.

[0032] Step S130, based on the operation drive instruction data associated with each of the X groups of standard space collaborative operation nodes and the basic operation data corresponding to the basic space collaborative operation nodes, the predefined production operation data associated with each of the X standard production process data are mapped to the production line operation configuration data to generate X reference production line optimization data of the target digital factory production line.

[0033] In detail, the reference production line optimization data is based on standard production process data and the current configuration of the target digital factory production line. The data generated through mapping and optimization includes optimized production operation parameters and configuration information, which is used to guide the actual operation of the production line.

[0034] For example, in this embodiment, first, from the three groups of standard space collaborative operation nodes, the standard mapping operation nodes corresponding to each group of standard space collaborative operation nodes are obtained. Assume that the standard mapping operation nodes here are all the first group of standard space collaborative operation nodes, that is, extracted from the earliest enabled standard production process data (timber pre-processing process).

[0035] The determination of the operation mapping parameter data is described in detail by taking the wood cutting operation and the cutting equipment in the target production line as an example. For the position adjustment array in the operation drive instruction data, the position adjustment array of the cutting tool in the wood cutting process (assuming that the initial position is x = 0, y = 0, z = 0) and the position adjustment array of the standard mapping operation node (the initial position of the cutting tool in the first set of standard production processes) are deviated to generate the position offset array corresponding to each set of standard space collaborative operation nodes. For example, if the initial position of the standard mapping operation node is x = -1, y = 0, z = 0, then the position offset array is (1, 0, 0), indicating an offset of 1 unit in the x-axis direction.

[0036] The operating state parameters in the wood cutting process (such as the tool speed of 3000 revolutions per minute) and the operating state parameters of the standard mapping operation nodes (assuming 2800 revolutions per minute) are deviated to generate the operating state offset parameters corresponding to each group of standard space collaborative operation nodes, which is 200 revolutions per minute in this case.

[0037] Then, the operation state offset parameters, position offset array and posture adjustment array corresponding to each group of standard space cooperative operation nodes are output as operation mapping parameter data corresponding to each group of standard space cooperative operation nodes.

[0038] Based on these operation mapping parameter data, the basic operation data corresponding to the basic space collaborative operation node is optimized. For the cutting equipment, taking the position adjustment array as an example, the position offset array (1, 0, 0) corresponding to the wood cutting process and the position adjustment array (x = 10 meters, y = 5 meters, z = 0 meters) corresponding to the basic space collaborative operation node (cutting equipment) are fused and calculated. Assuming that the fusion calculation is a simple addition, the optimized position adjustment array generated for the target digital factory production line may be (x = 11 meters, y = 5 meters, z = 0 meters). For the operation state parameters, the operation state offset parameters (200 revolutions per minute) corresponding to the wood cutting process and the operation state parameters (maximum power 5 kilowatts, here it is assumed to be related to the speed. According to the performance curve of the equipment, the power corresponding to the speed increase of 200 revolutions per minute is adjusted to 5.2 kilowatts) are fused and calculated to obtain the optimized operation state parameters. The posture adjustment array directly outputs the posture adjustment array corresponding to the wood cutting process as the optimized posture adjustment array. In this way, optimized operation data corresponding to a set of optimized spatial collaborative operation nodes of the target digital factory production line are generated.

[0039] According to the same method, similar operations are performed on the furniture component processing process and the furniture assembly process to generate another two sets of optimized operation data corresponding to the collaborative operation nodes of the optimized space.

[0040] Next, the spatial attention collaborative operation nodes in the cth group of optimized spatial collaborative operation nodes are extracted. For example, in the optimized spatial collaborative operation nodes of the furniture assembly process, the spatial attention collaborative operation node may be the operation node for determining the installation position of the connector, because this node is very critical to the accuracy of furniture assembly.

[0041] According to the radiation area of ​​this spatial attention collaborative operation node, the cth adaptation reference point is determined. Assuming that the radiation area of ​​this spatial attention collaborative operation node is a circular area with a radius of 0.5 meters and with the node as the center, the adaptation reference point may be set at the center of this circular area.

[0042] The relative position relationship between the adaptation reference point and the c-th group of optimized space collaborative operation nodes is used as the conversion basis, and the optimization operation data corresponding to the c-th group of optimized space collaborative operation nodes is dimensionally adapted. For example, the position adjustment array and the posture adjustment array corresponding to the c-th group of optimized space collaborative operation nodes are fused to generate a conversion array corresponding to the c-th group of optimized space collaborative operation nodes. Then, based on this conversion array, the operation state parameters corresponding to the c-th group of optimized space collaborative operation nodes are mapped to generate the initial mapping operation data of the c-th group of plane collaborative operation nodes of the target digital factory production line. Based on the relative position relationship between the adaptation reference point and the c-th group of optimized space collaborative operation nodes, the initial mapping operation data is updated to generate the mapping operation data of the c-th group of plane collaborative operation nodes of the target digital factory production line.

[0043] Finally, from each group of plane collaborative operation nodes of the target digital factory production line, the plane collaborative operation nodes reflecting the key operation areas for the target digital factory production line are screened out. For example, in the furniture manufacturing production line, for cutting equipment, the key operation area may be the plane collaborative operation node corresponding to the area where the tool contacts the wood; for grinding equipment, it is the plane collaborative operation node corresponding to the area where the sandpaper contacts the wood board; for assembly equipment, it is the plane collaborative operation node corresponding to the area where the connector is installed. Based on the plane collaborative operation nodes of these key operation areas extracted from each group of plane collaborative operation nodes, three reference production line optimization data for the target digital factory production line are determined. These reference production line optimization data contain the optimized operation data for the target production line, such as the optimized equipment position, operation parameters, etc., which can improve the efficiency of the production line and product quality.

[0044] Step S140 , taking the characterization vector of the target digital factory production line in the production line operation configuration data as a restriction basis and based on the X reference production line optimization data, generating target production line activation data for the target digital factory production line.

[0045] In detail, the characterization vector is a vector used to describe the key characteristics or states of the target digital factory production line in the production line operation configuration data, which can include multiple dimensions, such as production efficiency, energy consumption, equipment utilization, etc., for subsequent optimization and decision-making processes. The target production line activation data is the data that is finally generated and used to guide the actual operation of the target digital factory production line, including optimized equipment configuration, operating parameters, etc., which can improve the overall performance and efficiency of the production line.

[0046] For example, in this embodiment, first, the graph autoencoder is used to encode and represent the three reference production line optimization data, and the encoding representation vectors associated with the three reference production line optimization data are generated. The graph autoencoder can convert complex production line optimization data into a compact vector representation form, which is convenient for subsequent processing.

[0047] Then, the guided feature data including the characterization vector of the target digital factory production line in the production line operation configuration data is generated. For example, the characterization vector of the target production line may include the overall efficiency index of the production line (such as the number of furniture produced per hour), the product quality index (such as the qualified rate of the product), etc., which constitute part of the guided feature data.

[0048] Then, interference is added to the code representation vectors associated with the three reference production line optimization data to generate interference code representation vectors associated with the three reference production line optimization data. This is like introducing some small fluctuations or noise into the data to simulate the uncertainty factors in the actual production environment.

[0049] The self-focusing unit of the production line activation estimation network is used to perform a weighting operation on the interference code representation vectors associated with the three reference production line optimization data of the target digital factory production line, and generate weighted interference code representation vectors associated with the three reference production line optimization data of the target digital factory production line. The self-focusing unit can assign different weights to different interference code representation vectors according to the importance or relevance of the data, for example, a higher weight is assigned to the interference code representation vector corresponding to the optimization data closely related to product quality.

[0050] Then, the interactive focusing unit of the production line activation estimation network is used to remove interference from the weighted interference coding representation vectors associated with the three reference production line optimization data of the target digital factory production line based on the guided feature data, and generate interference-removed coding representation vectors associated with the three reference production line optimization data of the target digital factory production line. The interactive focusing unit removes interference factors that do not meet the overall requirements of the production line through interaction with the guided feature data, so that the coding representation vector more accurately reflects the actual needs of the production line.

[0051] Then, the timing unit of the production line activation estimation network is used to adjust the interference removal coding representation vectors associated with the three reference production line optimization data of the target digital factory production line based on the activation time associated with the three reference production line optimization data, and generate coding representation vectors associated with the three estimated production line optimization data of the target digital factory production line. The timing unit takes into account the sequence and time correlation of different optimization data in the production process and adjusts the coding representation vector to better meet the timing requirements of production.

[0052] Finally, the decoder is used to decode the coded representation vectors associated with the three estimated production line optimization data of the target digital factory production line, and generate the target production line activation data of the target digital factory production line. These target production line activation data contain information such as the final equipment settings and operating parameters of the production line, such as the final operating speed of the cutting equipment, the final grinding pressure of the grinding equipment, and the final assembly sequence of the assembly equipment. These data will be applied to the actual home furnishing production line to achieve efficient and high-quality home furnishing product production.

[0053] Based on the above steps, the embodiment of the present application realizes accurate management and optimization of the production process by acquiring standard production process data and operation configuration data of the target digital factory production line from the process industry digital factory. Specifically, the operation drive instruction data of the standard space collaborative operation node and the basic operation data of the basic space collaborative operation node are extracted, and these data are integrated into the configuration of the target digital factory production line through mapping operation, and multiple reference production line optimization data are generated. Finally, based on the characterization vector of the target digital factory production line, the present invention generates the target production line activation data. By integrating and optimizing the standard production process data, a more efficient production line configuration scheme can be generated, and redundant operations and waiting time in the production process can be reduced, thereby improving the overall production efficiency. In addition, the spatial collaborative operation nodes on the production line can be accurately analyzed, and resource allocation can be performed based on the operation requirements of these spatial collaborative operation nodes to ensure efficient use of resources and avoid waste of resources. By mapping the standard production process data to the target production line configuration, the consistency and standardization of the production operation can be ensured, thereby reducing the quality risk in the production process and improving product quality. The target production line activation data generated thereby has a high degree of flexibility and adjustability, and can be quickly adjusted according to changes in market demand and production environment to meet diverse production needs. By optimizing production processes and resource allocation, it helps to reduce energy consumption, material consumption and labor costs in the production process, thereby reducing overall operating costs.

[0054] In a possible implementation, step S130 includes:

[0055] Step S131, acquiring, from the X groups of standard space collaborative operation nodes, a standard mapping operation node corresponding to each group of standard space collaborative operation nodes;

[0056] Step S132, determining the operation mapping parameter data corresponding to each group of standard space collaborative operation nodes based on the operation driving instruction data of each group of standard space collaborative operation nodes and the operation driving instruction data of the corresponding standard mapping operation nodes;

[0057] Step S133, based on the operation mapping parameter data associated with each of the X groups of standard space collaborative operation nodes, the basic operation data corresponding to the basic space collaborative operation node is optimized to generate the optimized operation data associated with each of the X groups of optimized space collaborative operation nodes of the target digital factory production line. The optimized operation data of a group of optimized space collaborative operation nodes corresponds to the predefined production operation data in a standard production process data;

[0058] Step S134, extracting the spatial attention collaborative operation nodes in the cth group of optimized spatial collaborative operation nodes. c is a positive integer not greater than X;

[0059] Step S135, determining the cth adaptation reference point according to the radiation area of ​​the spatial attention collaborative operation node in the cth group of optimized spatial collaborative operation nodes;

[0060] Step S136, taking the relative position relationship between the c-th adaptation reference point and the c-th group of optimized spatial collaborative operation nodes as the conversion basis, performing dimension adaptation processing on the optimized operation data corresponding to the c-th group of optimized spatial collaborative operation nodes, and generating mapping operation data of the c-th group of plane collaborative operation nodes of the target digital factory production line;

[0061] Step S137, selecting, from each group of plane collaborative operation nodes of the target digital factory production line, plane collaborative operation nodes reflecting key operation areas for the target digital factory production line;

[0062] Step S138: determining X reference production line optimization data of the target digital factory production line based on the plane collaborative operation nodes extracted from each group of plane collaborative operation nodes.

[0063] In this embodiment, for the furniture production line, the server obtains each corresponding standard mapping operation node from X groups of standard space collaborative operation nodes. For example, when X = 3, there are three groups of standard space collaborative operation nodes, namely, wood pre-processing, furniture component processing, and furniture assembly. Taking the standard space collaborative operation node corresponding to the wood pre-processing process as an example, its corresponding standard mapping operation node may be obtained from the relevant operation node initially set in the entire furniture production process. This standard mapping operation node contains operation drive instruction data such as the initial position and initial rotation speed of the wood cutting tool that were initially set.

[0064] Next, the operation mapping parameter data is determined based on the operation drive instruction data of each group of standard space collaborative operation nodes and the operation drive instruction data of the corresponding standard mapping operation node. Still taking the wood pre-processing process as an example, the operation drive instruction data includes a position adjustment array, a posture adjustment array and an operation state parameter. For the position adjustment array, if the cutting tool position adjustment array in the standard space collaborative operation node is different from the tool position adjustment array in the standard mapping operation node, the position offset array is obtained by deviation operation. For example, the tool position of the standard space collaborative operation node is 1 meter on the x-axis, the tool position of the standard mapping operation node is 0.5 meters on the x-axis, and the position offset array is 0.5 meters. Similar operations are also performed on the operation state parameters, such as the tool speed in the standard space collaborative operation node is 3000 revolutions per minute, the tool speed of the standard mapping operation node is 2800 revolutions per minute, and the operation state offset parameter is 200 revolutions per minute. The operation state offset parameter, the position offset array and the posture adjustment array are collectively used as the operation mapping parameter data.

[0065] Then, the basic operation data corresponding to the basic space collaborative operation node is optimized according to the operation mapping parameter data associated with each of the X groups of standard space collaborative operation nodes. Taking the cutting equipment in the production line as an example, the basic operation data includes position adjustment array and operation state parameters. Assuming that the position offset array of the standard space collaborative operation node corresponding to the wood pre-processing process is 0.5 meters, the basic position adjustment array of the cutting equipment in the production line is x = 10 meters, and the optimized position adjustment array after fusion calculation becomes x = 10.5 meters. For the operation state parameter, if the operation state offset parameter is 200 revolutions per minute, the basic operation state parameter of the cutting equipment is 5 kilowatts of power (associated with the speed), and the power of the operation state parameter after optimization according to the equipment performance curve is adjusted to 5.2 kilowatts. The posture adjustment array directly adopts the posture adjustment array corresponding to the wood pre-processing process, thereby generating the optimized operation data of the optimized space collaborative operation node corresponding to the wood pre-processing process. The furniture component processing and furniture assembly processes are also operated in the same way to obtain their respective optimized operation data.

[0066] After that, the spatial attention collaborative operation nodes in the cth group of optimized spatial collaborative operation nodes are extracted. For example, in the optimized spatial collaborative operation nodes corresponding to the furniture assembly process, the operation node for determining the installation position of the connector is a spatial attention collaborative operation node, because it is crucial to the accuracy of furniture assembly.

[0067] The cth adaptation reference point is determined according to the radiation area of ​​the spatial attention collaborative operation node. For example, if the radiation area of ​​the spatial attention collaborative operation node is a circular area with a radius of 0.5 meters centered on it, the adaptation reference point can be set to the center position of the circular area.

[0068] The relative positional relationship between the c-th adaptation reference point and the c-th group of optimized spatial collaborative operation nodes is used as the conversion basis, and the optimization operation data corresponding to the c-th group of optimized spatial collaborative operation nodes are dimensionally adapted. For example, in the furniture assembly process, the position adjustment array and the posture adjustment array corresponding to the c-th group of optimized spatial collaborative operation nodes are fused to generate a conversion array, and then the operation state parameters are mapped based on the conversion array to obtain the initial mapping operation data of the c-th group of plane collaborative operation nodes, and then the initial mapping operation data is updated according to the relative positional relationship between the adaptation reference point and the c-th group of optimized spatial collaborative operation nodes to generate the mapping operation data of the c-th group of plane collaborative operation nodes.

[0069] Finally, the plane collaborative operation nodes reflecting the key operation areas of the target digital factory production line are selected from each group of plane collaborative operation nodes of the target digital factory production line. In the furniture manufacturing production line, for cutting equipment, the plane collaborative operation nodes corresponding to the contact area between the tool and the wood are the plane collaborative operation nodes of the key operation area; for grinding equipment, the plane collaborative operation nodes corresponding to the contact area between the sandpaper and the wood board are the plane collaborative operation nodes of the key operation area; for assembly equipment, the plane collaborative operation nodes corresponding to the connection installation area are the plane collaborative operation nodes of the key operation area. Based on these plane collaborative operation nodes extracted from each group of plane collaborative operation nodes, X reference production line optimization data of the target digital factory production line are determined. These data cover the operation-related information after optimization of each link of the production line, which can be used to improve the efficiency and quality of furniture production.

[0070] In a possible implementation, the operation drive instruction data includes a position adjustment array, a posture adjustment array and an operation state parameter. The operation state parameter is a specific parameter that describes the current operation state of the production equipment or operation node, such as equipment speed, temperature, pressure, etc. These parameters are crucial for controlling the production process and ensuring product quality. The position adjustment array is a set of data used to describe the position information of the production equipment or operation node in space. This set of data may contain multiple dimensions (such as x, y, z coordinates) to guide the precise positioning and movement of the equipment. The posture adjustment array is a set of data that describes the posture (such as angle, direction, etc.) of the production equipment or operation node in space. This set of data is crucial to ensure that the equipment performs the operation correctly.

[0071] Step S132 includes:

[0072] Step S1321, performing deviation operation on the position adjustment array of each group of standard space cooperative operation nodes and the position adjustment array of the corresponding standard mapping operation nodes to generate a position offset array corresponding to each group of standard space cooperative operation nodes;

[0073] Step S1322, performing deviation operation on the operation state parameters of each group of standard space collaborative operation nodes and the operation state parameters of the corresponding standard mapping operation nodes, to generate operation state offset parameters corresponding to each group of standard space collaborative operation nodes;

[0074] Step S1323: outputting the operation state offset parameters, position offset array and posture adjustment array corresponding to each group of standard space collaborative operation nodes as operation mapping parameter data corresponding to each group of standard space collaborative operation nodes.

[0075] In the furniture industry, for each process of furniture production, the operation drive instruction data includes a position adjustment array, a posture adjustment array, and an operation state parameter. When determining the operation mapping parameter data corresponding to each set of standard spatial collaborative operation nodes, take the wood cutting process in furniture production and the corresponding standard mapping operation node as an example. Assume that in the standard spatial collaborative operation node of the wood cutting process, the position adjustment array indicates the position information of the cutting tool relative to the wood, such as the coordinate values ​​on the x, y, and z axes are x = 2 meters, y = 1 meter, and z = 0.5 meters, respectively. This is the initial position of the tool determined according to the current placement and cutting plan of the wood. The corresponding standard mapping operation node (obtained from the initial setting or standard process) has a position adjustment array with coordinate values ​​on the x, y, and z axes of x = 1.8 meters, y = 1 meter, and z = 0.5 meters. The two position adjustment arrays are deviated, that is, the differences on the x, y, and z axes are calculated respectively to obtain the position offset array. In this example, the offset on the x axis is 2 - 1.8 = 0.2 meters, and there is no offset on the y and z axes, so the position offset array is x = 0.2 meters, y = 0 meters, and z = 0 meters.

[0076] In terms of operating state parameters, the operating state parameters of the standard spatial collaborative operating node of the wood cutting process set the speed of the cutting tool to 3500 revolutions per minute, which is determined based on factors such as the material of the wood and the cutting thickness. The corresponding standard mapping operating node's operating state parameters set the tool speed to 3200 revolutions per minute. By performing a deviation operation on these two operating state parameters, the operating state offset parameter is 3500 - 3200 = 300 revolutions per minute.

[0077] Then, the calculated operation state offset parameters, position offset array and posture adjustment array (the posture adjustment array, for example, involves the angle relationship between the tool and the wood surface. Assume that it has not changed in this example and the original posture adjustment array is maintained) corresponding to each set of standard space collaborative operation nodes are output as a whole as the operation mapping parameter data corresponding to each set of standard space collaborative operation nodes. For other processes in furniture production, such as grinding operations and punching operations in the furniture component processing process and connector installation operations in the furniture assembly process, the server will calculate in the same way according to the operation drive instruction data of the respective standard space collaborative operation nodes and the corresponding standard mapping operation nodes, thereby obtaining the corresponding operation mapping parameter data, which will be used for subsequent optimization of basic operation data and other operations to improve the overall performance and production efficiency of the furniture production line.

[0078] In a possible implementation, the standard mapping operation nodes associated with each of the X groups of standard space collaborative operation nodes are all the first group of standard space collaborative operation nodes, and the first group of standard space collaborative operation nodes are extracted from the earliest enabled standard production process data among the X standard production process data. The operation mapping parameter data includes an operation state offset parameter, a position offset array, and a posture adjustment array. The basic operation data includes a position adjustment array and an operation state parameter.

[0079] Step S131 includes: performing fusion calculation on the position offset array corresponding to the ath group of standard spatial collaborative operation nodes and the position adjustment array corresponding to the basic spatial collaborative operation nodes to generate the position adjustment array corresponding to the ath group of optimized spatial collaborative operation nodes of the target digital factory production line. a is a positive integer not greater than X.

[0080] The operation state offset parameters corresponding to the ath group of standard space collaborative operation nodes and the operation state parameters corresponding to the basic space collaborative operation nodes are fused and calculated to generate the operation state parameters corresponding to the ath group of optimized space collaborative operation nodes.

[0081] The posture adjustment array corresponding to the a-th group of standard space collaborative operation nodes is output as the posture adjustment array corresponding to the a-th group of optimized space collaborative operation nodes.

[0082] The position adjustment array, operation state parameters and posture adjustment array corresponding to the ath group of optimized space collaborative operation nodes of the target digital factory production line are output as optimized operation data corresponding to the ath group of optimized space collaborative operation nodes.

[0083] In this embodiment, it is assumed that X is 3, that is, there are 3 groups of standard production process data, corresponding to the wood pre-processing, furniture component processing, and furniture assembly processes respectively.

[0084] The first set of standard spatial collaborative operation nodes is extracted from the earliest enabled standard production process data (wood pre-processing process), and the standard mapping operation nodes associated with each of the X sets of standard spatial collaborative operation nodes are all the first set of standard spatial collaborative operation nodes. The operation mapping parameter data includes the operation state offset parameter, the position offset array and the posture adjustment array, and the basic operation data includes the position adjustment array and the operation state parameter.

[0085] For the ath group of standard spatial collaborative operation nodes (here, the first group corresponding to the wood pre-processing process, i.e., a = 1, is taken as an example), the server performs the following operations. In terms of position, it is assumed that the position offset array corresponding to the first group of standard spatial collaborative operation nodes is 0.5 meters on the x-axis (this is obtained by the deviation operation from the position adjustment array of the first group of standard mapping operation nodes), and the position adjustment array corresponding to the basic spatial collaborative operation node (such as the cutting equipment in the production line) is 10 meters on the x-axis. Through fusion calculation (here, it is assumed to be a simple addition), the position adjustment array corresponding to the first group of optimized spatial collaborative operation nodes of the target digital factory production line is generated to be 10.5 meters on the x-axis.

[0086] In terms of operating status parameters, the operating status offset parameter corresponding to the first group of standard space collaborative operation nodes is 200 revolutions per minute (for example, the offset of the cutting tool speed calculated previously), and the operating status parameter corresponding to the basic space collaborative operation node (cutting equipment) is power 5 kilowatts (assuming it is related to the speed and this is the initial setting of the equipment). After fusion calculation (calculation method determined according to the performance curve of the equipment, etc.), the operating status parameter corresponding to the first group of optimized space collaborative operation nodes may be adjusted to 5.2 kilowatts.

[0087] For the posture adjustment array, the posture adjustment array corresponding to the first group of standard spatial collaborative operation nodes is directly output as the posture adjustment array corresponding to the first group of optimized spatial collaborative operation nodes (assuming that in this example the posture adjustment array represents related information such as the angle between the cutting tool and the wood surface, and remains unchanged).

[0088] Finally, the position adjustment array (x-axis is 10.5 meters, etc.), operation state parameters (5.2 kilowatts) and posture adjustment array corresponding to the first group of optimized spatial collaborative operation nodes of the target digital factory production line are output as the optimized operation data corresponding to the first group of optimized spatial collaborative operation nodes. For the standard spatial collaborative operation nodes corresponding to the furniture component processing process (a = 2) and the furniture assembly process (a = 3), the server also uses the corresponding operation mapping parameter data to fuse the basic operation data of the basic spatial collaborative operation nodes in the same way, and obtains the optimized operation data corresponding to the second and third groups of optimized spatial collaborative operation nodes respectively. These optimized operation data will be further used in subsequent operations to optimize the production process of the furniture production line and improve production efficiency and product quality.

[0089] In a possible implementation, the standard mapping operation nodes corresponding to the first group of standard space collaborative operation nodes are the first group of standard space collaborative operation nodes, the standard mapping operation nodes corresponding to the bth group of standard space collaborative operation nodes are the b-1th group of standard space collaborative operation nodes, the first group of standard space collaborative operation nodes are extracted from the earliest enabled standard production process data among the X standard production process data, the activation time of the standard production process data corresponding to the b-1th group of standard space collaborative operation nodes is before the activation time of the standard production process data corresponding to the bth group of standard space collaborative operation nodes, and b is an integer greater than 1 and not greater than X.

[0090] Step S131 may also include: optimizing the optimized operation data corresponding to the basic space collaborative operation nodes based on the operation mapping parameter data corresponding to the first group of standard space collaborative operation nodes, and generating optimized operation data corresponding to the first group of optimized space collaborative operation nodes of the target digital factory production line.

[0091] Based on the operation mapping parameter data corresponding to the bth group of standard space collaborative operation nodes, the optimized operation data corresponding to the b-1th group of optimized space collaborative operation nodes are updated to generate the optimized operation data corresponding to the bth group of optimized space collaborative operation nodes of the target digital factory production line.

[0092] In this embodiment, it is further assumed that X is 3, which represents three standard production process data, namely, the wood pre-processing process, the furniture parts processing process and the furniture assembly process.

[0093] The first is the first set of standard spatial collaborative operation nodes, which are the nodes corresponding to the wood pre-processing process. The first set of standard spatial collaborative operation nodes corresponds to the standard mapping operation node itself. The server will optimize the optimized operation data corresponding to the basic spatial collaborative operation nodes based on the operation mapping parameter data corresponding to the first set of standard spatial collaborative operation nodes, thereby generating the optimized operation data corresponding to the first set of optimized spatial collaborative operation nodes of the target digital factory production line.

[0094] For example, for the cutting equipment in the basic spatial collaborative operation node, its basic operation data includes the position adjustment array (assuming that the initial position of the cutting equipment in the production line is x = 10 meters, y = 5 meters, z = 0 meters) and the operation state parameters (assuming that the initial power of the equipment is 5 kilowatts and the operation mode is continuous operation). The operation mapping parameter data corresponding to the first set of standard spatial collaborative operation nodes includes the position offset array (assuming that the offset is 0.5 meters in the x-axis direction), the operation state offset parameters (assuming that the power needs to be increased by 0.2 kilowatts) and the posture adjustment array (assuming the initial angle between the cutting tool and the wood surface and other related information). The server fuses the position offset array with the position adjustment array in the basic operation data to obtain the optimized position adjustment array (x = 10.5 meters, y = 5 meters, z = 0 meters); fuses the operation state offset parameters with the operation state parameters in the basic operation data to obtain the optimized operation state parameters (the power becomes 5.2 kilowatts); the posture adjustment array directly adopts the posture adjustment array corresponding to the first set of standard spatial collaborative operation nodes. In this way, the optimized operation data corresponding to the first set of optimized spatial collaborative operation nodes of the target digital factory production line are generated, which will serve as the basis for subsequent operations.

[0095] Next, for b = 2, that is, the second group of standard spatial collaborative operation nodes corresponding to the furniture parts processing process. The standard mapping operation nodes corresponding to the second group of standard spatial collaborative operation nodes are the first group of standard spatial collaborative operation nodes (nodes corresponding to the wood pre-processing process). At this time, the server needs to update the optimized operation data corresponding to the first group of optimized spatial collaborative operation nodes based on the operation mapping parameter data corresponding to the second group of standard spatial collaborative operation nodes to generate the optimized operation data corresponding to the second group of optimized spatial collaborative operation nodes.

[0096] For example, the operation mapping parameter data corresponding to the second group of standard spatial collaborative operation nodes include the position offset array (assuming an offset of -0.3 meters in the y-axis direction, which is the position relationship relative to the first group of standard spatial collaborative operation nodes), the operation state offset parameters (assuming the parameter changes corresponding to the need to reduce the operating speed of the equipment by a certain value), and the posture adjustment array (assuming the adjustment information related to the contact angle between the polishing equipment and the wooden board). For the position adjustment array (x = 10.5 meters, y = 5 meters, z = 0 meters) in the optimized operation data corresponding to the first group of optimized spatial collaborative operation nodes, the server merges the position offset array corresponding to the second group of standard spatial collaborative operation nodes with it (here it is assumed that it is a simple coordinate addition) to obtain the updated position adjustment array (x = 10.5 meters, y = 4.7 meters, z = 0 meters); for the operation state parameters, the operation state offset parameters corresponding to the second group of standard spatial collaborative operation nodes are merged with the operation state parameters corresponding to the first group of optimized spatial collaborative operation nodes (the calculation method determined according to equipment performance and production requirements) to obtain the updated operation state parameters; the posture adjustment array directly adopts the posture adjustment array corresponding to the second group of standard spatial collaborative operation nodes. Through such an update operation, the optimized operation data corresponding to the second group of optimized spatial collaborative operation nodes of the target digital factory production line are generated.

[0097] When b = 3, i.e., the third group of standard spatial collaborative operation nodes corresponding to the furniture assembly process, the standard mapping operation nodes corresponding to the third group of standard spatial collaborative operation nodes are the second group of standard spatial collaborative operation nodes (nodes corresponding to the furniture component processing process). The server again updates the optimized operation data corresponding to the second group of optimized spatial collaborative operation nodes based on the operation mapping parameter data corresponding to the third group of standard spatial collaborative operation nodes, and generates the optimized operation data corresponding to the third group of optimized spatial collaborative operation nodes.

[0098] Assume the position offset array (for example, 0.2 meters offset in the z-axis direction, relative to the position relationship corresponding to the second group of standard space collaborative operation nodes), operation state offset parameters (assuming the parameter change corresponding to the torque adjustment of the connector installation device) and posture adjustment array (assuming the connection installation angle related adjustment information) in the operation mapping parameter data corresponding to the third group of standard space collaborative operation nodes. For the position adjustment array (x = 10.5 meters, y = 4.7 meters, z = 0 meters) in the optimized operation data corresponding to the second group of optimized space collaborative operation nodes, the server fuses the position offset array corresponding to the third group of standard space collaborative operation nodes with it (according to the established fusion rules) to obtain the updated position adjustment array (x = 10.5 meters, y = 4.7 meters, z = 0.2 meters); for the operation state parameters, the operation state offset parameters corresponding to the third group of standard space collaborative operation nodes are fused with the operation state parameters corresponding to the second group of optimized space collaborative operation nodes (according to the method determined by the equipment and production logic) to obtain the updated operation state parameters; the posture adjustment array directly adopts the posture adjustment array corresponding to the third group of standard space collaborative operation nodes. In this way, the optimized operation data corresponding to the third group of optimized spatial collaborative operation nodes of the target digital factory production line are obtained.

[0099] In this way, the optimization operation data corresponding to the previous group of optimization space collaborative operation nodes are updated step by step based on the operation mapping parameter data corresponding to different groups of standard space collaborative operation nodes, and finally the optimization operation data associated with each of the X groups of optimization space collaborative operation nodes of the target digital factory production line are generated. These optimization operation data fully consider the association and sequence between various production processes, and can effectively improve the overall efficiency and product quality of the home furnishing production line. For example, the optimized cutting equipment position and parameters can cut wood more accurately, providing more suitable raw materials for subsequent furniture component processing; the optimized furniture component processing equipment data can better process parts that meet the requirements, and then provide high-quality components for furniture assembly, making the entire home furnishing production process smoother, more efficient and with more guaranteed product quality.

[0100] In a possible implementation, the optimization operation data includes operation state parameters, a position adjustment array, and a posture adjustment array.

[0101] Step S136 includes:

[0102] Step S1361, fusing the position adjustment array corresponding to the c-th group of optimized space collaborative operation nodes and the posture adjustment array corresponding to the c-th group of optimized space collaborative operation nodes to generate a conversion array corresponding to the c-th group of optimized space collaborative operation nodes;

[0103] Step S1362, based on the conversion array corresponding to the c-th group of optimized spatial collaborative operation nodes, mapping processing is performed on the operation state parameters corresponding to the c-th group of optimized spatial collaborative operation nodes to generate initial mapping operation data of the c-th group of planar collaborative operation nodes of the target digital factory production line;

[0104] Step S1363, based on the relative position relationship between the cth adaptation reference point and the cth group of optimized spatial collaborative operation nodes, the initial mapping operation data of the cth group of plane collaborative operation nodes of the target digital factory production line is updated to generate mapping operation data of the cth group of plane collaborative operation nodes of the target digital factory production line.

[0105] In this embodiment, taking the furniture production mentioned above as an example, assuming X = 3, when c = 1, the first group of optimized spatial collaborative operation nodes corresponding to the wood pre-processing process. The optimized operation data of the first group of optimized spatial collaborative operation nodes includes operation state parameters, position adjustment arrays, and posture adjustment arrays.

[0106] First, the position adjustment array and the attitude adjustment array corresponding to the first group of optimized spatial collaborative operation nodes are fused to generate the transformation array corresponding to the first group of optimized spatial collaborative operation nodes. For example, in the wood cutting process, the position adjustment array represents the position of the cutting tool relative to the wood, assuming that x = 10 meters, y = 5 meters, and z = 0 meters, and the attitude adjustment array represents the attitude information such as the angle between the tool and the wood surface, such as the angle between the tool and the wood surface is 30 degrees. During the fusion process, the position information and attitude information are combined to form a transformation array according to a specific algorithm (this algorithm may be defined based on the process requirements and equipment characteristics of home furnishing production). This transformation array may not only be a simple numerical combination, but also contain a new data representation of the relationship between position and attitude, which reflects information such as the effective position of the tool relative to a reference point in this specific attitude.

[0107] Next, based on the conversion array corresponding to the first group of optimized spatial collaborative operation nodes, the operation state parameters corresponding to the first group of optimized spatial collaborative operation nodes are mapped to generate the initial mapping operation data of the first group of plane collaborative operation nodes of the target digital factory production line. For example, the cutting tool speed in the operation state parameter is 3000 revolutions per minute. According to the position and posture relationship reflected by the conversion array, the speed is mapped to the initial mapping operation data of the plane collaborative operation node through a specific mapping function (this function is predetermined based on the performance curve and process requirements of the production equipment). This initial mapping operation data may change the actual meaning of the speed in the plane operation, such as converting it into the number of revolutions of the tool per unit distance on the plane, etc., to meet the needs of plane collaborative operation.

[0108] Then, based on the relative positional relationship between the first adaptation reference point and the first group of optimized spatial collaborative operation nodes, the initial mapping operation data of the first group of plane collaborative operation nodes of the target digital factory production line are updated to generate the mapping operation data of the first group of plane collaborative operation nodes of the target digital factory production line. Assuming that the first adaptation reference point is at the center of the wood cutting area, the first group of optimized spatial collaborative operation nodes has a certain distribution relationship around this adaptation reference point. If some parameters in the initial mapping operation data are set based on the average situation of the entire cutting area, and the actual positions of each operation node relative to the adaptation reference point are different, it is necessary to adjust according to this relative positional relationship. For example, the cutting operation close to the adaptation reference point may require higher precision, then the corresponding rotation speed (the number of tool rotations per unit distance) in the initial mapping operation data may need to be further increased, and the operation far from the adaptation reference point may need to reduce the rotation speed to ensure the consistency of the overall cutting effect. Through such adjustments, the mapping operation data of the first group of plane collaborative operation nodes are generated, which are more in line with the specific needs of each operation node on the plane in actual production.

[0109] When c = 2, for the second group of optimized spatial collaborative operation nodes corresponding to the furniture component processing flow. Similarly, the position adjustment array and posture adjustment array corresponding to the second group of optimized spatial collaborative operation nodes are fused to generate a conversion array. For example, in the polishing process of furniture components, the position adjustment array represents the position of the polishing equipment relative to the component, and the posture adjustment array represents the contact angle between the polishing equipment and the surface of the component and other information. The conversion array obtained after the fusion process can accurately reflect the effective position relationship of the polishing equipment relative to the component in this posture.

[0110] Based on this conversion array, the operation state parameters corresponding to the second group of optimized spatial collaborative operation nodes are mapped to generate the initial mapping operation data of the second group of plane collaborative operation nodes. For example, the moving speed of the grinding equipment in the operation state parameters is converted into the effective grinding speed for different areas of the component on the plane through the mapping function according to the position and posture relationship reflected by the conversion array, which takes into account factors such as the shape of the component, the starting and ending positions of grinding, and forms the initial mapping operation data.

[0111] Then, the initial mapping operation data is updated based on the relative position relationship between the second adaptation reference point (assuming it is a key positioning point in the component processing area) and the second group of optimized spatial collaborative operation nodes. If a grinding operation node is close to the adaptation reference point, it may require more refined grinding, so the grinding speed in the initial mapping operation data may need to be further adjusted to a slower value; if the distance is far and the area has little impact on the overall situation, the grinding speed can be appropriately increased. In this way, the mapping operation data of the second group of plane collaborative operation nodes is generated, so that the grinding operation on the plane is more in line with the actual needs of component processing.

[0112] When c = 3, for the third group of optimized spatial collaborative operation nodes corresponding to the furniture assembly process, the position adjustment array and the posture adjustment array corresponding to the third group of optimized spatial collaborative operation nodes are fused so that in the furniture assembly process, such as in the connector installation operation, the position adjustment array represents the position of the connector installation device relative to the furniture component, and the posture adjustment array represents the angle of the connector installation. The conversion array is obtained through the fusion process, and this conversion array accurately reflects the effective operating position relationship of the installation device relative to the component in a specific posture.

[0113] Based on the conversion array, the operation state parameters corresponding to the third group of optimized spatial collaborative operation nodes are mapped and processed to generate the initial mapping operation data of the third group of plane collaborative operation nodes. For example, the torque of the connector installation device in the operation state parameter is converted into the effective torque value at different assembly positions on the plane through the mapping function according to the position and posture relationship represented by the conversion array, and the initial mapping operation data is formed by taking into account the stability requirements of the furniture structure and the assembly sequence.

[0114] Finally, the initial mapping operation data is updated based on the relative position relationship between the third adaptation reference point (assuming it is the center of the assembly area or the key structural positioning point) and the third group of optimized spatial collaborative operation nodes. The installation of connectors close to the adaptation reference point may require higher torque to ensure the firmness of key parts, while the area far from the adaptation reference point can adjust the torque value appropriately according to the force distribution of the overall structure. Through such an update, the mapping operation data of the third group of plane collaborative operation nodes is generated, so that the furniture assembly operation on the plane is more scientific and reasonable, and the overall quality and stability of the furniture are improved.

[0115] Through the above operations for different groups (c takes different values), the server generates the mapping operation data of the cth group of planar collaborative operation nodes of the target digital factory production line according to the position adjustment array, posture adjustment array and operation state parameters in the optimized operation data, combined with the relative position relationship between the adaptation reference point and the optimized space collaborative operation node. These data are helpful to further optimize the planar operations of each link in the home furnishing production line and improve production efficiency and product quality.

[0116] In a possible implementation, step S140 includes:

[0117] Step S141, using a graph autoencoder to encode the X reference production line optimization data to generate encoding representation vectors associated with each of the X reference production line optimization data;

[0118] Step S142, generating guiding feature data including a characterization vector of the target digital factory production line in the production line operation configuration data;

[0119] Step S143, adding interference to the coded representation vectors associated with the X reference production line optimization data, to generate interference coded representation vectors associated with the X reference production line optimization data;

[0120] Step S144, using the self-focusing unit of the production line activation estimation network, performing a weighting operation on the interference code representation vectors associated with each of the X reference production line optimization data of the target digital factory production line, to generate a weighted interference code representation vector associated with each of the X reference production line optimization data of the target digital factory production line;

[0121] Step S145, using the interactive focusing unit of the production line activation estimation network, based on the guiding feature data, performing interference removal on the weighted interference coded representation vectors associated with each of the X reference production line optimization data of the target digital factory production line, to generate interference removal coded representation vectors associated with each of the X reference production line optimization data of the target digital factory production line;

[0122] Step S146, using the timing unit of the production line activation estimation network, based on the activation time associated with each of the X reference production line optimization data, adjusting the interference removal coding representation vectors associated with each of the X reference production line optimization data of the target digital factory production line, and generating coding representation vectors associated with each of the X estimated production line optimization data of the target digital factory production line;

[0123] Step S147: using a decoder, decoding and representing the coded representation vectors associated with each of the X estimated production line optimization data of the target digital factory production line, and generating target production line activation data of the target digital factory production line.

[0124] In detail, the graph autoencoder is a neural network model for data encoding and decoding. The graph autoencoder can learn the intrinsic representation of data and convert it into a more compact and abstract encoding form. In production line optimization, the graph autoencoder can be used to extract and optimize the features of production process data. The production line activation estimation network is a neural network model for estimating and predicting the effect of production line optimization. The model can generate optimized production line activation data based on the input production line configuration and operation data, and evaluate its performance and effect.

[0125] In this embodiment, first, the graph autoencoder is used to encode and represent X reference production line optimization data, and generate encoding representation vectors associated with each of the X reference production line optimization data. Taking X = 3 in the previously mentioned furniture production as an example, these three reference production line optimization data correspond to the wood pre-processing, furniture component processing and furniture assembly processes respectively. For the reference production line optimization data of the wood pre-processing process, the graph autoencoder will encode the many operation-related data contained therein, such as the optimized position of the cutting equipment, the speed of the cutting tool, the cutting angle and other information. This encoding process is to convert these complex data with specific structures into a more compact and abstract encoding representation vector. For example, the position information of the cutting equipment may be converted into a specific vector value, and its position in this vector space represents the relative relationship of the cutting equipment in the entire production line layout and the collaborative relationship with other equipment. Similarly, for the grinding equipment operation data, the punching equipment operation data in the reference production line optimization data of the furniture component processing process, and the connector installation operation data in the furniture assembly process, the graph autoencoder will perform similar encoding operations to generate encoding representation vectors associated with each of the three reference production line optimization data.

[0126] Next, guide feature data including the characterization vector of the target digital factory production line in the production line operation configuration data is generated. In the home furnishing production line, the characterization vector in the production line operation configuration data contains some key characteristics of the production line as a whole. For example, the production capacity of the production line (the number of furniture that can be produced per hour), the overall layout of the equipment (the impact of the relative position relationship of each equipment in the production workshop on the production process), the energy consumption of the production line (the total energy consumption of different equipment and the optimization potential), etc. This information is integrated to form the guide feature data, which will serve as an important reference for subsequent operations to ensure that the generated target production line activation data meets the overall planning and requirements of the production line.

[0127] Then, interference is added to the code representation vectors associated with each of the three reference production line optimization data to generate interference code representation vectors associated with each of the three reference production line optimization data. In the actual furniture production environment, there are many unpredictable factors, such as slight wear of equipment, slight differences in raw materials, etc. Interference addition is to simulate the impact of these factors on the data. For example, for the code representation vector corresponding to the wood pre-processing process, a small interference value may be added to the vector component representing the speed of the cutting tool. This interference value may be determined based on the statistical data of the impact of tool wear on the speed in previous production. Similar operations are performed on the code representation vectors corresponding to the furniture component processing process and the furniture assembly process to generate their own associated interference code representation vectors.

[0128] Afterwards, the self-focusing unit of the production line activation estimation network is used to perform weighting operations on the interference coding representation vectors associated with the three reference production line optimization data of the target digital factory production line, and generate weighted interference coding representation vectors associated with the three reference production line optimization data of the target digital factory production line. The self-focusing unit will assign weights according to the importance and relevance of the data. In furniture production, the interference coding representation vectors corresponding to the data that have a greater impact on product quality and production efficiency are given higher weights. For example, in the early wood processing process, the speed and cutting accuracy of the cutting tool have a great impact on the subsequent furniture component processing and the final product quality, so the interference coding representation vectors associated with these data will be given higher weights. For the key operations in the furniture component processing process, such as the data related to the position accuracy of the punching and the surface quality of the polished surface, and the data related to the firmness of the installation of the connectors in the furniture assembly process, the corresponding interference coding representation vectors will also be given corresponding weights according to their importance, thereby generating weighted interference coding representation vectors associated with the three reference production line optimization data.

[0129] Then, the interactive focusing unit of the production line activation estimation network is used to remove interference from the weighted interference coding representation vectors associated with the three reference production line optimization data of the target digital factory production line based on the guided feature data, and generate interference removal coding representation vectors associated with the three reference production line optimization data of the target digital factory production line. The interactive focusing unit identifies and removes interference factors that do not meet the overall requirements of the production line by interacting with the guided feature data. For example, if a component in the weighted interference coding representation vector conflicts with the production capacity of the production line in the guided feature data (it may be that the interference causes the value of this component to make the production capacity unable to meet expectations), then this component will be adjusted to remove the interference. Similar processing is also performed on other conflicting parts related to guided feature data such as equipment layout and energy consumption, so as to ensure that the interference removal coding representation vector corresponding to each reference production line optimization data meets the overall planning and requirements of the production line.

[0130] Next, the interference removal coding representation vectors associated with the three reference production line optimization data of the target digital factory production line are adjusted based on the activation time associated with the three reference production line optimization data, and the coding representation vectors associated with the three estimated production line optimization data of the target digital factory production line are generated. In the furniture production line, the operations of different processes have a sequence, and the activation time is an important factor. For example, the wood pre-processing process must precede the furniture component processing process, and the furniture component processing process must precede the furniture assembly process. The timing unit will adjust the interference removal coding representation vector according to this sequence relationship. If an operation is performed at an inappropriate time, it may affect the entire production process. For example, processing furniture components before the wood is completely dried may cause the components to deform. The timing unit will adjust the coding representation vector according to this time relationship to ensure that the operations of each process are performed in the correct time sequence, thereby generating the coding representation vectors associated with the three estimated production line optimization data.

[0131] Finally, the decoder is used to decode the coded representation vectors associated with the three estimated production line optimization data of the target digital factory production line, and generate the target production line activation data of the target digital factory production line. The decoder restores the coded representation vector obtained after a series of processing to data that can actually be used for production line operation. For example, for the wood pre-processing process, the decoded target production line activation data will clarify the final position of the cutting equipment, the actual speed of the cutting tool, the precise cutting angle and other operating parameters. For the furniture parts processing process, the operating parameters of the grinding equipment and the precise operating data of the punching equipment will be obtained. For the furniture assembly process, the specific operating parameters of the connector installation and the assembly order will be obtained. These target production line activation data will be applied to the home furnishing production line to ensure that the production line operates efficiently and stably according to the optimized plan and produces high-quality home furnishing products.

[0132] In a possible implementation, the method further includes:

[0133] Step A110, obtaining the example production line operation configuration data of the example digital factory production line and Y example production line optimization data from the basic production line activation data. Y is a positive integer;

[0134] Step A120, using an initial graph autoencoder, encoding the mapping operation data of the Y groups of plane cooperative operation nodes associated with each of the Y example production line optimization data, to generate a coding representation vector associated with each of the Y example production line optimization data;

[0135] Step A130, using the initial production line activation estimation network, taking the representation vector of the example digital factory production line in the example production line operation configuration data as a restriction basis, and based on the encoding representation vectors associated with each of the Y example production line optimization data, generating encoding representation vectors associated with each of the Y estimated production line optimization data of the example digital factory production line;

[0136] Step A140, based on the coded representation vectors associated with each of the Y example production line optimization data, determining the collaborative operation logic area associated with each of the Y example production line optimization data, based on the collaborative operation logic area associated with each of the Y example production line optimization data, determining the operation identification array associated with each of the Y example production line optimization data, fusing the operation identification array associated with each of the Y example production line optimization data with the coded representation vectors associated with each of the Y example production line optimization data, and generating the operation node features associated with each of the Y example production line optimization data;

[0137] Step A150, fusing the operation identification arrays associated with the Y example production line optimization data and the coded representation vectors associated with the Y estimated production line optimization data to generate operation node features associated with the Y estimated production line optimization data, performing feature distance calculation on the operation node features associated with the Y example production line optimization data and the operation node features associated with the Y estimated production line optimization data to generate a first training error;

[0138] Step A160, determining a second training error based on the coded representation vectors associated with each of the Y example production line optimization data and the coded representation vectors associated with each of the Y estimated production line optimization data, and performing a fusion calculation on the first training error and the second training error to generate a global training error;

[0139] Step A170, when the global training error is greater than a threshold value, updating the neuron weight information in the initial production line activation estimation network and the neuron weight information in the initial graph autoencoder based on the global training error;

[0140] Step A180, when the global training error obtained based on the updated initial production line activation estimation network and the updated initial graph autoencoder is not greater than the threshold value, the updated initial production line activation estimation network is output as the production line activation estimation network, and the updated initial graph autoencoder is output as the graph autoencoder.

[0141] In this embodiment, first, the example production line operation configuration data of the example digital factory production line and Y example production line optimization data are obtained from the basic production line activation data. Assuming that Y is 3, these three example production line optimization data correspond to different optimization scenarios in home furnishing production. Taking the example production line operation configuration data as an example, it contains the overall layout information of the example production line, such as the specific location of different production equipment (such as cutting equipment, grinding equipment, assembly equipment, etc.) in the workshop, the model and specifications of the equipment, and other information. At the same time, each example production line optimization data contains optimization operation-related data for different production processes. For example, the example production line optimization data for the wood pre-processing process will include the optimized wood cutting size, cutting angle, drying temperature and duration, etc.; the example production line optimization data for the furniture parts processing process will include grinding pressure, sandpaper model, punching size and spacing, etc.; the example production line optimization data for the furniture assembly process will include the type of connector, assembly sequence, torque requirements, etc.

[0142] Next, the initial graph autoencoder is used to encode the mapping operation data of the three groups of plane collaborative operation nodes associated with the three example production line optimization data, and generate the encoding representation vectors associated with the three example production line optimization data. Taking the mapping operation data of the plane collaborative operation nodes corresponding to the wood pre-processing process as an example, these data contain information such as the operation trajectory of the cutting tool on the plane, the cutting order, and the collaborative relationship with other auxiliary equipment on the plane. The initial graph autoencoder will convert these complex plane collaborative operation data into encoding representation vectors according to the pre-set encoding rules. This encoding process is an abstract representation that maps specific operation data into a vector space so that the position of the data in this space can reflect the relationship and characteristics between the operations. For the mapping operation data of the plane collaborative operation nodes corresponding to the furniture component processing process and the furniture assembly process, the initial graph autoencoder will also perform the same encoding operation to obtain the encoding representation vectors associated with the three example production line optimization data.

[0143] Then, using the initial production line activation estimation network, taking the representation vector of the example digital factory production line in the example production line operation configuration data as the restriction basis, based on the coded representation vectors associated with the three example production line optimization data, the coded representation vectors associated with each of the three example production line optimization data are generated. The representation vector in the example production line operation configuration data contains comprehensive information such as the overall performance indicators, layout rationality, and production efficiency of the production line. The initial production line activation estimation network processes the coded representation vector of the example production line optimization data according to the overall requirements represented by this representation vector. For example, if high production efficiency is emphasized in the representation vector, then when generating the coded representation vector of the estimated production line optimization data, those operating data that can improve the production speed (such as the fast cutting mode of the cutting equipment, the efficient assembly process of the assembly equipment, etc.) will be weighted or adjusted to generate the coded representation vector of the estimated production line optimization data that meets the requirements.

[0144] Based on the encoding representation vectors associated with the three exemplary production line optimization data, the collaborative operation logic areas associated with the three exemplary production line optimization data are determined. In furniture production, taking the wood pre-processing process as an example, the collaborative operation logic area may be the operation area around the cutting equipment. There is a logical association between the operations in this area, such as the operation of the cutting tool and the wood feeding operation. There is a collaborative relationship between them, and they together constitute a collaborative operation logic area. For the furniture component processing process, the operation area around the grinding equipment and the punching equipment and the collaborative relationship between their operations constitute the collaborative operation logic area; for the furniture assembly process, the operations around the assembly workbench and the collaborative relationship between the assembly sequence of different components constitute the collaborative operation logic area. Based on these collaborative operation logic areas, the operation identification arrays associated with the three exemplary production line optimization data are determined. The operation identification array may include identification of information such as the operation type, operation sequence, and operation importance in each collaborative operation logic area. For example, in the operation identification array of the wood pre-processing process, it may be identified that the cutting operation is a key operation, and the order of cutting is long edge cutting first and short edge cutting later. Then, the operation identification arrays associated with the three example production line optimization data and the coding representation vectors associated with the three example production line optimization data are fused to generate the operation node features associated with the three example production line optimization data. This fusion process combines the identification information in the operation identification array with the operation data information in the coding representation vector, so that the operation node features contain both specific operation data and the logical identification of the operation, which can more comprehensively describe the operation on the production line.

[0145] The operation identification arrays associated with the three example production line optimization data and the encoding representation vectors associated with the three estimated production line optimization data are fused to generate the operation node features associated with the three estimated production line optimization data. Then, the feature distance calculation is performed on the operation node features associated with the three example production line optimization data and the operation node features associated with the three estimated production line optimization data to generate the first training error. This feature distance calculation is a way to measure the difference in operation node features between the example production line optimization data and the estimated production line optimization data. For example, for the wood pre-processing process, if the cutting operation in the example production line optimization data is identified as high-precision cutting in the operation node features, and the cutting operation in the estimated production line optimization data is identified as ordinary precision cutting in the operation node features, then this difference will be considered when calculating the feature distance. By comparing and calculating the operation node features of all processes (wood pre-processing, furniture component processing, furniture assembly), a comprehensive first training error is obtained.

[0146] Based on the coded representation vectors associated with the three example production line optimization data and the coded representation vectors associated with the three estimated production line optimization data, the second training error is determined. This second training error mainly measures the difference between the example production line optimization data and the estimated production line optimization data from the perspective of the coded representation vector. For example, if a component in the coded representation vector of the example production line optimization data represents the optimal speed of the cutting equipment, and the speed represented by the corresponding component in the coded representation vector of the estimated production line optimization data has a large deviation from the optimal speed, then this deviation will be considered when calculating the second training error. The first training error and the second training error are fused and calculated to generate a global training error. This fusion calculation may be based on a pre-set weight, and the first training error and the second training error are added in a certain proportion to obtain a global training error.

[0147] When the global training error is greater than the threshold value, the neuron weight information in the initial production line activation estimation network and the neuron weight information in the initial graph autoencoder are updated based on the global training error. If the global training error is large, it means that the performance of the current initial production line activation estimation network and the initial graph autoencoder is not ideal enough, and the neuron weight information needs to be adjusted to improve the accuracy. For example, if the global training error indicates that the punching operation prediction in the furniture component processing process is inaccurate, then when updating the neuron weight information, the neuron weights related to the punching operation will be adjusted so that the model can better predict and optimize this operation. When the global training error obtained based on the updated initial production line activation estimation network and the updated initial graph autoencoder is not greater than the threshold value, the updated initial production line activation estimation network is output as the production line activation estimation network, and the updated initial graph autoencoder is output as the graph autoencoder. This means that the adjusted model has reached the expected accuracy requirements and can be used in the actual home production line optimization operation. It can more accurately generate the target production line activation data and improve the efficiency and quality of home production.

[0148] Figure 2 The cloud platform 100 shown includes: a processor 1001 and a memory 1003. The processor 1001 and the memory 1003 are connected, such as through a bus 1002. Optionally, the cloud platform 100 may also include a transceiver 1004, which may be used for data interaction between the server and other servers, such as data transmission and / or data reception. It should be noted that the transceiver 1004 is not limited to one in actual scheduling, and the structure of the cloud platform 100 does not constitute a limitation on the embodiments of the present application.

[0149] Processor 1001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 1001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0150] The bus 1002 may include a path to transmit information between the above components. The bus 1002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 1002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0151] The memory 1003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage medium, other magnetic storage devices, or any other medium that can be used to carry or store program code and can be read by a computer, without limitation herein.

[0152] The memory 1003 is used to store program codes for executing the embodiments of the present application, and the execution is controlled by the processor 1001. The processor 1001 is used to execute the program codes stored in the memory 1003 to implement the steps shown in the above method embodiments.

[0153] In addition, an embodiment of the present application also provides a readable storage medium, in which computer executable instructions are pre-installed. When the processor executes the computer executable instructions, the business data management method based on the process industry digital factory as described above is implemented.

[0154] Similarly, it should be noted that in order to simplify the description disclosed in this application, thereby helping to understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present application, multiple features are sometimes combined into one embodiment, drawings, or descriptions thereof. Similarly, it should be noted that in order to simplify the description disclosed in this application, thereby helping to understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present application, multiple features are sometimes combined into one embodiment, drawings, or descriptions thereof.

Claims

1. A business data management method based on a process industry digital factory, characterized in that: The method comprises: obtaining X standard production process data and production line operation configuration data of a target digital factory production line from a process industry digital factory; X is a positive integer, and each standard production process data contains predefined production operation data; extracting operation drive instruction data associated with each of X groups of standard space collaborative operation nodes from the X standard production process data, and extracting basic operation data corresponding to the basic space collaborative operation nodes of the target digital factory production line from the production line operation configuration data; one standard production process data corresponds to a group of operation drive instruction data of standard space collaborative operation nodes; based on the operation drive instruction data associated with each of the X groups of standard space collaborative operation nodes and the basic space collaborative operation The X sets of standard spatial collaborative operation nodes are used to map the predefined production operation data associated with each of the X standard production process data to the production line operation configuration data to generate X reference production line optimization data for the target digital factory production line; the characterization vector of the target digital factory production line in the production line operation configuration data is used as a restriction basis, and based on the X reference production line optimization data, the target production line activation data for the target digital factory production line is generated; based on the operation drive instruction data associated with each of the X sets of standard spatial collaborative operation nodes and the basic operation data corresponding to the basic spatial collaborative operation nodes, the predefined production operation data associated with each of the X standard production process data is mapped to the production line operation configuration data to generate X reference production line optimization data for the target digital factory production line; The method comprises: obtaining, from the X groups of standard spatial collaborative operation nodes, standard mapping operation nodes corresponding to each group of standard spatial collaborative operation nodes; determining operation mapping parameter data corresponding to each group of standard spatial collaborative operation nodes based on operation driving instruction data of each group of standard spatial collaborative operation nodes and operation driving instruction data of corresponding standard mapping operation nodes; optimizing basic operation data corresponding to the basic spatial collaborative operation nodes based on operation mapping parameter data respectively associated with the X groups of standard spatial collaborative operation nodes, and generating optimized operation data respectively associated with the X groups of optimized spatial collaborative operation nodes of the target digital factory production line. operation data; the optimized operation data of a group of optimized spatial collaborative operation nodes correspond to the predefined production operation data in a standard production process data; extract the spatial attention collaborative operation nodes in the c-th group of optimized spatial collaborative operation nodes; c is a positive integer not greater than X; according to the radiation area of ​​the spatial attention collaborative operation nodes in the c-th group of optimized spatial collaborative operation nodes, determine the c-th adaptation reference point; based on the relative position relationship between the c-th adaptation reference point and the c-th group of optimized spatial collaborative operation nodes, perform dimension adaptation processing on the optimized operation data corresponding to the c-th group of optimized spatial collaborative operation nodes, and generate the mapping operation data of the c-th group of plane collaborative operation nodes of the target digital factory production line;From each group of plane collaborative operation nodes of the target digital factory production line, screen out plane collaborative operation nodes reflecting key operation areas for the target digital factory production line; based on the plane collaborative operation nodes extracted from each group of plane collaborative operation nodes, determine X reference production line optimization data of the target digital factory production line. ; 2. The business data management method based on process industry digital factory according to claim 1 is characterized in that: The operation drive instruction data includes a position adjustment array, a posture adjustment array and an operation state parameter; the operation drive instruction data based on each group of standard space collaborative operation nodes and the operation drive instruction data of the corresponding standard mapping operation nodes are used to determine the operation mapping parameter data corresponding to each group of standard space collaborative operation nodes, including: performing a deviation operation on the position adjustment array of each group of standard space collaborative operation nodes and the position adjustment array of the corresponding standard mapping operation nodes to generate a position offset array corresponding to each group of standard space collaborative operation nodes; performing a deviation operation on the operation state parameters of each group of standard space collaborative operation nodes and the operation state parameters of the corresponding standard mapping operation nodes to generate the operation state offset parameters corresponding to each group of standard space collaborative operation nodes; and outputting the operation state offset parameters, position offset array and posture adjustment array corresponding to each group of standard space collaborative operation nodes as the operation mapping parameter data corresponding to each group of standard space collaborative operation nodes.

3. The business data management method based on process industry digital factory according to claim 1 is characterized in that: The standard mapping operation nodes associated with each of the X groups of standard space collaborative operation nodes are all the first group of standard space collaborative operation nodes, and the first group of standard space collaborative operation nodes are extracted from the earliest enabled standard production process data among the X standard production process data; the operation mapping parameter data includes an operation state offset parameter, a position offset array, and a posture adjustment array; The basic operation data includes a position adjustment array and an operation state parameter; the optimizing the basic operation data corresponding to the basic space collaborative operation node based on the operation mapping parameter data associated with each of the X groups of standard space collaborative operation nodes to generate the optimized operation data associated with each of the X groups of optimized space collaborative operation nodes of the target digital factory production line includes: fusing and calculating the position offset array corresponding to the a-th group of standard space collaborative operation nodes and the position adjustment array corresponding to the basic space collaborative operation node to generate the position adjustment array corresponding to the a-th group of optimized space collaborative operation nodes of the target digital factory production line; a is a positive integer not greater than X; fusing and calculating the operation state offset parameters corresponding to the a-th group of standard space collaborative operation nodes and the operation state parameters corresponding to the basic space collaborative operation nodes to generate the operation state parameters corresponding to the a-th group of optimized space collaborative operation nodes; outputting the posture adjustment array corresponding to the a-th group of standard space collaborative operation nodes as the posture adjustment array corresponding to the a-th group of optimized space collaborative operation nodes; outputting the position adjustment array, the operation state parameter and the posture adjustment array corresponding to the a-th group of optimized space collaborative operation nodes of the target digital factory production line as the optimized operation data corresponding to the a-th group of optimized space collaborative operation nodes.

4. The business data management method based on process industry digital factory according to claim 1 is characterized in that: The standard mapping operation nodes corresponding to the first group of standard space collaborative operation nodes are the first group of standard space collaborative operation nodes, the standard mapping operation nodes corresponding to the bth group of standard space collaborative operation nodes are the b-1th group of standard space collaborative operation nodes, the first group of standard space collaborative operation nodes are extracted from the earliest enabled standard production process data among the X standard production process data, the activation time of the standard production process data corresponding to the b-1th group of standard space collaborative operation nodes is before the activation time of the standard production process data corresponding to the bth group of standard space collaborative operation nodes, and b is an integer greater than 1 and not greater than X; the operation mapping parameter data associated with each of the X groups of standard space collaborative operation nodes is used to determine the basic The method optimizes the basic operation data corresponding to the spatial collaborative operation nodes to generate the optimized operation data associated with each of the X groups of optimized spatial collaborative operation nodes of the target digital factory production line, including: optimizing the optimized operation data corresponding to the basic spatial collaborative operation nodes based on the operation mapping parameter data corresponding to the first group of standard spatial collaborative operation nodes to generate the optimized operation data corresponding to the first group of optimized spatial collaborative operation nodes of the target digital factory production line; and updating the optimized operation data corresponding to the b-1th group of optimized spatial collaborative operation nodes based on the operation mapping parameter data corresponding to the bth group of standard spatial collaborative operation nodes to generate the optimized operation data corresponding to the bth group of optimized spatial collaborative operation nodes of the target digital factory production line.

5. The business data management method based on process industry digital factory according to claim 1 is characterized in that: The optimized operation data includes operation state parameters, position adjustment arrays and posture adjustment arrays; the optimization operation data corresponding to the c-th group of optimized space collaborative operation nodes are dimensionally adapted based on the relative position relationship between the c-th adaptation reference point and the c-th group of optimized space collaborative operation nodes, and the mapping operation data of the c-th group of plane collaborative operation nodes of the target digital factory production line are generated, including: fusing the position adjustment arrays corresponding to the c-th group of optimized space collaborative operation nodes and the posture adjustment arrays corresponding to the c-th group of optimized space collaborative operation nodes to generate the c-th group of optimized space collaborative operation nodes. a conversion array corresponding to the same operation node; based on the conversion array corresponding to the cth group of optimized space collaborative operation nodes, mapping the operation state parameters corresponding to the cth group of optimized space collaborative operation nodes to generate the initial mapping operation data of the cth group of plane collaborative operation nodes of the target digital factory production line; based on the relative position relationship between the cth adaptation reference point and the cth group of optimized space collaborative operation nodes, updating the initial mapping operation data of the cth group of plane collaborative operation nodes of the target digital factory production line to generate the mapping operation data of the cth group of plane collaborative operation nodes of the target digital factory production line.

6. The business data management method based on process industry digital factory according to claim 1 is characterized in that: The method of generating target production line activation data of the target digital factory production line based on the X reference production line optimization data and taking the characterization vector of the target digital factory production line in the production line operation configuration data as a restriction basis comprises: using a graph autoencoder to encode and represent the X reference production line optimization data to generate encoding representation vectors associated with each of the X reference production line optimization data; generating guiding feature data including the characterization vector of the target digital factory production line in the production line operation configuration data; performing interference addition on the encoding representation vectors associated with each of the X reference production line optimization data to generate interference encoding representation vectors associated with each of the X reference production line optimization data; using a self-focusing unit of a production line activation estimation network to perform a weighting operation on the interference encoding representation vectors associated with each of the X reference production line optimization data of the target digital factory production line to generate encoding representation vectors associated with each of the X reference production line optimization data of the target digital factory production line. The invention relates to a method for generating a weighted interference coding representation vector associated with each of the X reference production line optimization data of the target digital factory production line by using an interactive focusing unit of the production line activation estimation network; performing interference removal on the weighted interference coding representation vector associated with each of the X reference production line optimization data of the target digital factory production line based on the guiding feature data, so as to generate an interference removal coding representation vector associated with each of the X reference production line optimization data of the target digital factory production line; performing adjustment on the interference removal coding representation vector associated with each of the X reference production line optimization data of the target digital factory production line based on the activation time associated with each of the X reference production line optimization data, so as to generate a coding representation vector associated with each of the X estimated production line optimization data of the target digital factory production line; and performing decoding representation on the coding representation vector associated with each of the X estimated production line optimization data of the target digital factory production line by using a decoder, so as to generate target production line activation data of the target digital factory production line.

7. The business data management method based on process industry digital factory according to claim 6 is characterized in that: The method further includes: obtaining example production line operation configuration data and Y example production line optimization data of the example digital factory production line from the basic production line activation data; Y is a positive integer; using an initial graph autoencoder, encoding the mapping operation data of the Y groups of plane collaborative operation nodes associated with each of the Y example production line optimization data, and generating a coded representation vector associated with each of the Y example production line optimization data; using an initial production line activation estimation network, taking the representation vector of the example digital factory production line in the example production line operation configuration data as a restriction basis, based on the coded representation vector associated with each of the Y example production line optimization data , generate the coded representation vectors associated with the Y estimated production line optimization data of the example digital factory production line; determine the collaborative operation logic area associated with the Y example production line optimization data based on the coded representation vectors associated with the Y example production line optimization data; determine the operation identification array associated with the Y example production line optimization data based on the collaborative operation logic area associated with the Y example production line optimization data; fuse the operation identification array associated with the Y example production line optimization data with the coded representation vectors associated with the Y example production line optimization data to generate the Y example production line optimization data. According to the operation node features associated with each of the Y example production line optimization data; the operation identification arrays associated with each of the Y example production line optimization data and the coding representation vectors associated with each of the Y estimated production line optimization data are fused to generate the operation node features associated with each of the Y estimated production line optimization data; the feature distance calculation is performed on the operation node features associated with each of the Y example production line optimization data and the operation node features associated with each of the Y estimated production line optimization data to generate a first training error; based on the coding representation vectors associated with each of the Y example production line optimization data and the coding representation vectors associated with each of the Y estimated production line optimization data, a second training error is determined; the first training error and the second training error are fused to generate a global training error; when the global training error is greater than a threshold value, based on the global training error, the neuron weight information in the initial production line activation estimation network and the neuron weight information in the initial graph autoencoder are updated; when the global training error obtained according to the updated initial production line activation estimation network and the updated initial graph autoencoder is not greater than the threshold value, the updated initial production line activation estimation network is output as the production line activation estimation network, and the updated initial graph autoencoder is output as the graph autoencoder.

8. A business data management system based on a process industry digital factory, characterized in that: The invention comprises a cloud platform and a process industry digital factory connected to the cloud platform in communication; the cloud platform is specifically used to: obtain X standard production process data and production line operation configuration data of a target digital factory production line from the process industry digital factory; X is a positive integer, and each standard production process data contains predefined production operation data; from the X standard production process data, extract X groups of operation drive instruction data associated with each of the standard space collaborative operation nodes, and from the production line operation configuration data, extract basic operation data corresponding to the basic space collaborative operation node of the target digital factory production line; one standard production process data corresponds to a group of operation drive instruction data of the standard space collaborative operation node; Based on the operation drive instruction data associated with each of the X groups of standard space collaborative operation nodes and the basic operation data corresponding to the basic space collaborative operation nodes, the predefined production operation data associated with each of the X standard production process data are mapped to the production line operation configuration data to generate X reference production line optimization data of the target digital factory production line; Taking the characterization vector of the target digital factory production line in the production line operation configuration data as a restriction basis, based on the X reference production line optimization data, generating target production line activation data of the target digital factory production line; The method includes mapping the predefined production operation data associated with each of the X standard production process data to the production line operation configuration data based on the operation drive instruction data associated with each of the X groups of standard space collaborative operation nodes and the basic operation data corresponding to the basic space collaborative operation nodes to generate X reference production line optimization data for the target digital factory production line, including: acquiring the standard mapping operation nodes corresponding to each group of standard space collaborative operation nodes from the X groups of standard space collaborative operation nodes; determining the operation mapping parameter data corresponding to each group of standard space collaborative operation nodes based on the operation drive instruction data associated with each of the X groups of standard space collaborative operation nodes and the operation drive instruction data of the corresponding standard mapping operation nodes; optimizing the basic operation data corresponding to the basic space collaborative operation nodes based on the operation mapping parameter data associated with each of the X groups of standard space collaborative operation nodes to generate the optimized operation data associated with each of the X groups of optimized space collaborative operation nodes for the target digital factory production line; and generating the optimized operation data associated with each of the X groups of optimized space collaborative operation nodes for the target digital factory production line. The optimization operation data of the operation node corresponds to the predefined production operation data in a standard production process data; extract the spatial attention collaborative operation nodes in the cth group of optimized spatial collaborative operation nodes; c is a positive integer not greater than X; determine the cth adaptation reference point according to the radiation area of ​​the spatial attention collaborative operation nodes in the cth group of optimized spatial collaborative operation nodes; take the relative position relationship between the cth adaptation reference point and the cth group of optimized spatial collaborative operation nodes as the conversion basis, perform dimension adaptation processing on the optimization operation data corresponding to the cth group of optimized spatial collaborative operation nodes, and generate the mapping operation data of the cth group of plane collaborative operation nodes of the target digital factory production line; from each group of plane collaborative operation nodes of the target digital factory production line, screen out the plane collaborative operation nodes reflecting the key operation area for the target digital factory production line; based on the plane collaborative operation nodes extracted from each group of plane collaborative operation nodes, determine X reference production line optimization data of the target digital factory production line.

9. A cloud platform, characterized in that: The cloud platform includes a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions, and the machine-executable instructions are loaded and executed by the processor to implement the business data management method based on a process industry digital factory as described in any one of claims 1-7.

Images