Data processing method for building structure model design

Abstract

The present invention relates to the technical field of image processing, and particularly to a data processing method for building structure model design. Obtain a plurality of historical product models and a current product design sketch, and respectively construct corresponding undirected graphs; take each node in the undirected graph of the current product design sketch as a first initial node, and obtain the path set of the first initial node; obtain the second initial node corresponding to the first initial node, and obtain the path set of the second initial node; obtain the similarity between the first initial node and each corresponding second initial node; arrange the part models corresponding to each second initial node to obtain a model recommendation sequence for the part type corresponding to the first initial node; obtain the model recommendation sequence for each part type in the current product design sketch for product model design. The present invention recommends the models of the parts in the current product design sketch through the attribute association between the parts in the historical products, making the establishment of the model more convenient.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a data processing method for building structure model design. Background Art

[0002] A building structure model is a type of product model. In industrial production, product models play an important role in the manufacturing industry. They help production personnel inspect the design rationality and accuracy of products. During the design process of product models, with the continuous development of computer technology, product models have gradually changed from being manually manufactured by production designers to being simulated using three-dimensional data models. This not only saves the production materials of product models but also helps improve the design efficiency of product models, making the product models more changeable during the design process, thereby improving the design efficiency of product models.

[0003] During the design process of a product, the rationality and reliability of the structural design are relatively important. At this time, it is necessary to design the product model more accurately and reasonably to facilitate production personnel in estimating the quality of the produced products. In the current product model design process, generally, a product design sketch is first drawn, and then the designer further designs the product three-dimensional model based on the two-dimensional design sketch. Since the parts are the units that make up the product, in order to improve the design efficiency of the designer, the parts composition of the product three-dimensional model is generally recommended. In the prior art, the recommendation of replaceable parts is usually carried out after the specific attributes of each part of the model are known. At the same time, when recommending parts in the prior art, only the attributes of the parts themselves are considered for model selection, and the combination relationship between parts is not taken into account. When replacing parts, each part is usually compared separately, which cannot play a good auxiliary role in the establishment of the product three-dimensional model and may even reduce the efficiency of the entire three-dimensional model establishment. Summary of the Invention

[0004] To solve the problem that in the prior art, when making part recommendations, only the attributes of the parts themselves are considered for model selection, the combination relationship between parts is not taken into account, and it is impossible to play a good auxiliary role in the establishment of the product three-dimensional model, the present invention provides a data processing method for building structure model design, including: obtaining a plurality of historical product models and the current product design sketch, and respectively constructing corresponding undirected graphs; taking each node in the undirected graph of the current product design sketch as the first initial node, and obtaining the path set of the first initial node; obtaining the second initial node corresponding to the first initial node, and obtaining the path set of the second initial node; obtaining the similarity between the first initial node and each corresponding second initial node; arranging the part models corresponding to each second initial node to obtain the model recommendation sequence of the part type corresponding to the first initial node; obtaining the model recommendation sequence of each part type in the current product design sketch for product model design. The present invention recommends the part models in the current product design sketch through the attribute association between parts in the historical products, making the establishment of the model more convenient.

[0005] The present invention adopts the following technical solutions. A data processing method for building structure model design includes:

[0006] Obtaining a plurality of historical product models, taking the model of each part type in each historical product model as a node, and constructing an undirected graph of each historical product model;

[0007] Obtaining the current product design sketch, taking each part type in the current product design sketch as a node, and constructing an undirected graph of the current product design sketch;

[0008] Respectively taking each node in the undirected graph of the current product design sketch as the first initial node, and grading the nodes in the undirected graph of the current product design sketch according to the first initial node;

[0009] Starting from the first initial node, sequentially connecting the next-level nodes until there are no secondary nodes in the next-level nodes, taking the next-level nodes without secondary nodes as the termination nodes, and obtaining the paths from the first initial node to each termination node to obtain the path set of the first initial node;

[0010] Obtaining the nodes in the undirected graph of each historical product model with the same part type as the first initial node as the second initial node corresponding to the first initial node; obtaining the path set of each second initial node;

[0011] According to the path set of the first initial node and the path sets of each corresponding second initial node, obtaining the similarity between the first initial node and each corresponding second initial node according to the number of nodes included in each path and the attribute correlation degree between two nodes in each path;

[0012] Arrange the part models corresponding to each second initial node in descending order according to the similarity between the first initial node and each second initial node, and obtain the model recommendation sequence of the part types corresponding to the first initial node in the current product design sketch;

[0013] Conduct product model design according to the model recommendation sequence of each part type in the current product design sketch.

[0014] Furthermore, a data processing method for building structure model design. The method for grading the nodes in the undirected graph of the current product design sketch according to the first initial node is as follows:

[0015] In the undirected graph of the current product design sketch, take the nodes directly connected to the first initial node as the first-level nodes;

[0016] In the undirected graph of the current product design sketch, take the ungraded nodes directly connected to each first-level node as the second-level nodes;

[0017] Gradually grade all the nodes in the undirected graph of the current product design sketch until all the nodes are completed with grade division.

[0018] Furthermore, a data processing method for building structure model design. The method for obtaining the paths from the first initial node to each terminal node is as follows:

[0019] Start from the first initial node and connect to each first-level node to obtain multiple first-node paths;

[0020] Obtain multiple second-node paths according to each first-level node connecting to the corresponding second-level node;

[0021] Connect downward in turn until the next-level node is the terminal node, obtain all the node paths between the first initial node and each terminal node, and get the paths from the first initial node to each terminal node.

[0022] Furthermore, a data processing method for building structure model design. The method for obtaining the path set of each second initial node is the same as the method for obtaining the path set of the first initial node.

[0023] Furthermore, a data processing method for building structure model design. The method for obtaining the attribute correlation degree between two adjacent nodes connected in sequence in each path is as follows:

[0024] According to the number of times each connection relationship between the part types corresponding to two adjacent nodes connected in sequence in each path appears in the historical product model, obtain the attribute correlation degree between two adjacent nodes connected in sequence in each path; where the connection relationships include attribute correlation connections and non-attribute correlation connections.

[0025] Further, for a data processing method for building structure model design, the method for obtaining the similarity between a first initial node and each second initial node is as follows:

[0026]

[0027] Among them, represents the similarity between the first initial node and the second initial node in the undirected graph of the p-th historical product model, represents the number of paths in the path set of the first initial node, represents the number of paths in the path set of the second initial node in the undirected graph of the p-th historical product model, represents the similarity between the i-th path of the first initial node and the j-th path of the second initial node in the undirected graph of the p-th historical product model.

[0028] Further, for a data processing method for building structure model design, the method for obtaining the similarity between the i-th path of the first initial node and the j-th path of the second initial node in the undirected graph of the p-th historical product model is as follows:

[0029]

[0030] Among them, represents the similarity between the i-th path of the first initial node and the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the maximum level of the termination node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the maximum level of the termination node in the i-th path of the first initial node, represents the level of the node, represents the -th node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the -th node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the attribute correlation degree between the -th node and the -th node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the -th node in the i-th path of the first initial node, represents the -th node in the i-th path of the first initial node, represents the The attribute correlation degree between the th node and the th node, indicating the part type corresponding to the th node in the jth path of the second initial node in the undirected graph of the pth historical product model, indicating the part type corresponding to the th node in the ith path of the first initial node, indicating the part type corresponding to the th node in the jth path of the second initial node in the undirected graph of the pth historical product model, indicating the part type corresponding to the th node in the ith path of the first initial node,

[0031] The beneficial effects of the present invention are as follows: First, the present invention establishes an undirected graph according to the part models in the historical product model, and then compares it with the undirected graph constructed by the part types in the current design sketch, which is an important basis for combining the use of parts in the present invention. The part types of unknown models in the current sketch are used to classify the nodes in the undirected graph, so as to specifically reflect the connection degree between each part and other parts, that is, it can reflect the part combination structure mainly based on each part, and find a similar structure in the undirected graph of the historical product model. Finally, the part models are sorted by the similarity value, so that each part in the current design sketch can obtain the best part model recommendation in the historical model on the basis of considering the combined information of the structure between parts, making the recommendation of part models more in line with the design logic of the model and improving the efficiency of three-dimensional model establishment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 It is a schematic flowchart of a data processing method for building structure model design according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0035] As Figure 1 shown, a schematic structural diagram of a data processing method for building structure model design according to an embodiment of the present invention is given, including:

[0036] 101. Obtain a plurality of historical product models and the current product design sketch, and respectively construct an undirected graph of each historical product model and an undirected graph of the current product design sketch;

[0037] The present invention first obtains a plurality of historical product models, and then analyzes the two-dimensional design sketches of each historical product model. Since the historical product models are already designed products, the information on the types of each part, the assembly connection information between parts, and the corresponding model information during part assembly can be obtained through the historical product models. To improve the efficiency of information recognition, the present invention uses a DNN network to recognize the two-dimensional design sketches of historical product models, trains the DNN network using the information on the types of each part, the assembly connection information between parts, and the corresponding model information during part assembly in the historical product models, and uses the trained DNN network to recognize the types of each part, the assembly connection information between parts, and the corresponding model information during part assembly; it should be noted that the DNN network used in the present invention is an existing recognition network, that is, any DNN network in the prior art for recognizing and obtaining information can be applied to the present invention. The specific training method of the DNN network can refer to the prior art, and the present invention does not make any restrictions or changes.

[0038] For the specific information of the parts in the current product design sketch, it is not necessary to obtain it through the DNN network. Since the current product design sketch only contains the assembly information between parts and the part types, in the present invention, it is necessary to compare with the information of the parts in the historical product models, so as to recommend the model through the similar part structures in the historical product models.

[0039] For the th part type For it, the connection and assembly methods used in model design between it and other types of part categories are generally divided into two types. One is non-attribute-associated connection, and the other is attribute-associated connection. Non-attribute-associated connection means that the connection method between two parts will not have mutual influence on attributes, such as welding, bonding, etc. This connection method means that regardless of the specifications and attributes of the two parts themselves, they will not affect each other. Therefore, when recommending part models, for parts with non-attribute-associated connections, the influence of their structural information on model recommendation is relatively low. The other is attribute-associated connection, which means that the connection method between two parts will have mutual influence on attributes, such as screwing. This connection method will unify the specifications and attributes of the two parts. For example, the inner diameter of a nut must be unified with the outer diameter of a bolt. Therefore, when the structural information between parts is attribute-associated connection, when recommending part models, the structural information between this part and other parts will be combined for recommendation. Therefore, by calculating the attribute association degree between different types of parts, the degree of mutual influence of the specifications and attributes between different part types can be measured. The specific calculation process is as follows:

[0040]

[0041] Among them, represents the category serial number of the part, that is, the corresponding part category when respectively represent the part categories and The number of times the connection relationship between the two is attribute-associated connection and non-attribute-associated connection in the historical product model. By represents the attribute association degree between the part categories and . It is a normalized data. The closer it is to 1, the more it indicates attribute association. The closer it is to 0, the more it indicates non-attribute association. It can be seen that the more times the non-attribute-associated connection between two parts, the more it indicates that there is no necessary connection between the model matching of these two parts, that is, there is no fixed model combination. Therefore, the attribute association degree between these two parts will be lower, and the influencing factors in subsequent part model recommendation will also be lower. On the contrary, the more times the attribute-associated connection between two parts, the more it indicates that there may be a fixed model combination between the two parts. That is, when the model of one part is selected, the model of the other part will probably be determined accordingly. Therefore, the influencing factors in subsequent part model recommendation will be higher.

[0042] For the historical product model, its part category is the part's own attribute. Since the present invention needs to recommend part models through the historical product model, the model of its part category is used as the node of the undirected graph, and the part category nodes with connection relationships are connected. The attribute association degree between the two corresponding part categories of the two nodes is used as the edge weight value between the nodes to construct the undirected graph of each historical product model.

[0043] For the current design sketch, since the specific model of each part cannot be directly obtained, such as the part type being a nut but without specific model information, the attributes of the parts themselves, that is, the type of each part, are used as the nodes of the undirected graph. Similarly, the nodes of the part types with connection relationships are connected, and the attribute correlation degree between the two corresponding part types of the nodes is used as the edge weight value between the nodes to construct the undirected graph corresponding to the current design sketch.

[0044] 102. Taking each node in the undirected graph of the current product design sketch as the first initial node, the nodes in the undirected graph of the current product design sketch are classified.

[0045] Since the design purpose of the present invention is to find an undirected graph structure similar to the undirected graph corresponding to the current design sketch from the undirected graphs of historical product models, so as to make specific part model recommendations, for the undirected graph corresponding to the design sketch it is necessary for the designer to select a part type node on it as the design node (i.e., the first starting node or the second starting node in the present invention). Then, the undirected graph structures with nodes having the same part type as the design node are screened out from the historical database as comparison data, and all the nodes on the undirected graphs in the comparison data (i.e., the undirected graphs of historical product models) with the same part type as the design node are used as reference nodes. At this time, the part type structure undirected graph corresponding to the design sketch has the same part type of the design node as the part types of the reference nodes of each undirected graph in the comparison data.

[0046] For the p-th undirected graph of the historical product model in the comparison data ( , is the total number of undirected graphs in the comparison data) and the undirected graph G of the current design sketch, taking the design node as the starting node, first calibrate the first-level nodes, the first-level nodes are the nodes directly connected to the design node. After calibrating the first-level nodes, continue to calibrate the second-level nodes, the second-level nodes are the uncalibrated nodes directly connected to the first-level nodes. After calibrating the second-level nodes, continue to calibrate the third-level nodes, the third-level nodes are the uncalibrated nodes directly connected to the second-level nodes, and so on until and all the nodes on are all calibrated, thus completing the classification of the nodes in the undirected graph.

[0047] The method for classifying the nodes in the undirected graph of the current product design sketch according to the first initial node is as follows:

[0048] Taking the nodes directly connected to the first initial node in the undirected graph of the current product design sketch as the first-level nodes;

[0049] In the undirected graph of the current product design sketch, the unclassified nodes directly connected to each first-level node are used as second-level nodes;

[0050] Classify all the nodes in the undirected graph of the current product design sketch in sequence until all the nodes are classified.

[0051] 103. Obtain the path set of the first initial node and the path sets of each second initial node;

[0052] After calibrating and all the nodes on, start from the design node to find secondary nodes, that is, start from the first starting node or the second starting node, find the first-level nodes, second-level nodes, and so on to form a node path until there are no connected secondary nodes around the node. At this time, stop searching and use the current node as the path termination node. At this time, a path containing the level order will be formed from the starting node to the path termination node. This path represents the connection characteristics of the first starting node or the second starting stage in the undirected graph. By searching and all the paths of the design nodes on, thus forming and the path sets corresponding to the design nodes on.

[0053] The method for obtaining the path from the first initial node to each termination node is as follows:

[0054] Start from the first initial node and connect each first-level node to obtain multiple first-node paths;

[0055] According to each first-level node connecting to the corresponding second-level node, obtain multiple second-node paths;

[0056] Connect downwards in sequence until the next-level node is the termination node, obtain all the node paths between the first initial node and each termination node, and get the path from the first initial node to each termination node.

[0057] The method for obtaining the path set of each second initial node is the same as the method for obtaining the path set of the first initial node.

[0058] 104. Obtain the similarity between the first initial node and each corresponding second initial node;

[0059] The method for obtaining the attribute correlation degree between two adjacent nodes connected in sequence in each path is as follows:

[0060] Obtain the attribute correlation degree between two adjacent nodes connected in sequence in each path according to the number of occurrences of each connection relationship between the part types corresponding to two adjacent nodes connected in sequence in each path in the historical product model; wherein, the connection relationships include attribute correlation connections and non-attribute correlation connections.

[0061] The method for obtaining the similarity between the i-th path of the first initial node and the j-th path of the second initial node in the undirected graph of the p-th historical product model is as follows:

[0062]

[0063] Wherein, represents the similarity between the i-th path of the first initial node and the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the maximum level number of the termination node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the maximum level number of the termination node in the i-th path of the first initial node, represents the level number of the node, represents the -th node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the -th node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the attribute correlation degree between the -th node and the -th node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the -th node in the i-th path of the first initial node, represents the -th node in the i-th path of the first initial node, represents the attribute correlation degree between the -th node and the -th node in the i-th path of the first initial node, represents the part type corresponding to the -th node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the part type corresponding to the -th node in the i-th path of the first initial node, represents the part type corresponding to the -th node in the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the part type corresponding to the th node in the i-th path of the first initial node,

[0064] represents the path and the path The product of the attribute correlation degrees between nodes at the same level. It indicates that if two nodes are more similar, that is, the node path on can be more referenced by the node path on And the condition for being referenceable is that the attribute correlation degrees between the part types corresponding to the two nodes should both tend to 1. That is, if the attribute correlation degrees of the two path segments are both small, it means that the corresponding model of the part type on the starting node is not greatly affected by the structure, that is, the reference degree is not high. Therefore, if is closer to 1, it indicates that the path and the path to on this path segment at the node level can be more referenced to each other. And and represent that the part types of the nodes on this path segment at the node level from to should be the same. If they are different, there is no reference, and if they are the same, it means it is meaningful.

[0065] The method for obtaining the similarity between the first initial node and each corresponding second initial node is as follows:

[0066]

[0067] Among them, represents the similarity between the first initial node and the second initial node in the undirected graph of the p-th historical product model, represents the number of paths in the path set of the first initial node, represents the number of paths in the path set of the second initial node in the undirected graph of the p-th historical product model, represents the similarity between the i-th path of the first initial node and the j-th path of the second initial node in the undirected graph of the p-th historical product model, is a normalized value, and the closer it is to 1, the more it indicates and The more similar, that is, by comprehensively considering the similarity of all paths of the same design nodes in the undirected graph of the current design sketch and the undirected graph of the historical product model, as the similarity between the first initial node in the undirected graph of the current design sketch and the second initial node in the undirected graph of the historical product model, so as to judge whether the part model corresponding to the second initial node in the undirected graph of the historical product meets the modeling requirements of the current design sketch.

[0068] It should be noted that if there are multiple nodes in a comparison data undirected graph that meet the conditions for being a reference node, the similarity between the two when each qualified node is used as a reference node shall be calculated respectively, and the reference node setting method with the largest similarity shall be selected as the final result.

[0069] 105. Obtain the model recommendation sequence of each part type in the current product design sketch for product model design.

[0070] Thus, by calculating the undirected graph of the current design sketch the similarity between each design node in it and the corresponding design node in the undirected graph of all comparison data (i.e., historical product models) is calculated, and then arranged in descending order of similarity, that is, the recommended ranking of the models corresponding to each part type in the historical product model is completed. When the designer selects a part model according to the ranking in the recommendation list for a part in the current design sketch, the next part model can be obtained in the same ranking in the model recommendation sequence, and certain part model adjustments can be made according to the specific situation, so as to realize the design of the entire product model.

[0071] The present invention first establishes an undirected graph based on the part models in the historical product model, so as to compare it with the undirected graph constructed by the part types in the current design sketch, which is an important basis for combining the combined use of parts in the present invention. The nodes in the undirected graph are classified according to the part types with unknown models in the current sketch, so as to specifically reflect the connection degree between each part and other parts, that is, it can reflect the part combination structure mainly composed of each part, and find a similar structure in the undirected graph of the historical product model. Finally, the part models are sorted by the similarity value, so that each part in the current design sketch can obtain the best part model recommendation in the historical model on the basis of considering the combined information of the part structures, making the recommendation of part models more in line with the design logic of the model and improving the efficiency of three-dimensional model establishment.

[0072] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data processing method for building structure model design, characterized in that: include: Acquire multiple historical product models, and construct an undirected graph of each historical product model by taking the model number of each part type in each historical product model as a node; Obtain the current product design sketch, and construct an undirected graph of the current product design sketch with each part type in the current product design sketch as a node; Taking each node in the undirected graph of the current product design sketch as a first initial node, and grading the nodes in the undirected graph of the current product design sketch according to the first initial nodes; Starting from the first initial node, sequentially connect the next level nodes until there is no secondary node in the next level node, take the next level node without a secondary node as the terminal node, obtain the path connecting the first initial node to each terminal node, and obtain the path set of the first initial node; Obtain a node in the undirected graph of each historical product model that has the same part type as that corresponding to the first initial node, as the second initial node corresponding to the first initial node; Get the path set of each second initial node; The similarity between the first initial node and each corresponding second initial node is obtained according to the number of nodes contained in each path and the attribute association between two nodes in each path in the path set of the first initial node and the path set corresponding to each second initial node; Arrange the part models corresponding to each second initial node from large to small according to the similarity between the first initial node and each corresponding second initial node, and obtain a model recommendation sequence of the part type corresponding to the first initial node in the current product design sketch; Design the product model according to the recommended model sequence of each part type in the current product design sketch; The method for obtaining the attribute association between two nodes connected in sequence in each path is as follows: According to the number of occurrences of each connection relationship between the part types corresponding to the two nodes connected in sequence in each path in the historical product model, the attribute association degree between the two nodes connected in sequence in each path is obtained; wherein the connection relationship includes attribute association connection and non-attribute association connection.

2. A data processing method for building structure model design according to claim 1, characterized in that: The method for grading the nodes in the undirected graph of the current product design sketch according to the first initial node is: In the undirected graph of the current product design sketch, the node directly connected to the first initial node is taken as a first-level node; In the undirected graph of the current product design sketch, the ungraded nodes directly connected to each first-level node are used as second-level nodes; All nodes in the undirected graph of the current product design sketch are graded in turn until all nodes have completed the grade division.

3. A data processing method for building structure model design according to claim 2, characterized in that: The method for obtaining the path connecting the first initial node to each terminal node is: Connect each first-level node starting from the first initial node to obtain multiple first-node paths; Multiple second node paths are obtained by connecting each first-level node to the corresponding second-level node; Connect downward in sequence until the next level node is a terminal node, obtain all node paths from the first initial node to each terminal node, and obtain the path from the first initial node to each terminal node.

4. A data processing method for building structure model design according to claim 1, characterized in that: The method for obtaining the path set of each second initial node is the same as the method for obtaining the path set of the first initial node.

5. The data processing method for building structure model design according to claim 1, characterized in that: The method for obtaining the similarity between the first initial node and each corresponding second initial node is: in, represents the similarity between the first initial node and the second initial node in the undirected graph of the p-th historical product model, represents the number of paths in the path set of the first initial node, represents the number of paths in the path set of the second initial node in the undirected graph of the p-th historical product model, Represents the similarity between the i-th path of the first initial node and the j-th path of the second initial node in the undirected graph of the p-th historical product model.

6. A data processing method for building structure model design according to claim 5, characterized in that: The method for obtaining the similarity between the i-th path of the first initial node and the j-th path of the second initial node in the undirected graph of the p-th historical product model is: in, represents the similarity between the i-th path of the first initial node and the j-th path of the second initial node in the undirected graph of the p-th historical product model, represents the maximum number of terminal nodes in the jth path from the second initial node in the undirected graph of the pth historical product model, represents the maximum degree of the terminal nodes in the ith path of the first initial node, represents the level of the node, The first path of the second initial node in the undirected graph of the pth historical product model nodes, The first path of the second initial node in the undirected graph of the pth historical product model nodes, The first path of the second initial node in the undirected graph of the pth historical product model The node and The attribute correlation between nodes, Indicates the first initial node in the i-th path nodes, Indicates the first initial node in the i-th path nodes, Indicates the first initial node in the i-th path The node and The attribute correlation between nodes, The first path of the second initial node in the undirected graph of the pth historical product model The part type corresponding to each node, Indicates the first initial node in the i-th path The part type corresponding to each node, The first path of the second initial node in the undirected graph of the pth historical product model The part type corresponding to each node, Indicates the first initial node in the i-th path The part type corresponding to each node, is the exclusive OR operator.

Images