Construction method and equipment of industrial knowledge graph, and storage medium

Abstract

The invention provides an industrial knowledge graph construction method and device and a storage medium, and is applied to the field of data intelligence. The method comprises the steps of obtaining industrial data corresponding to a target industrial chain, and determining a product logic relationship based on the industrial data; wherein the target industrial chain comprises N target products; n is a positive integer; constructing a product logic map based on the initial product code corresponding to the target product and the product logic relationship; reconstructing the product logic graph based on a preset reconstruction rule to generate an industrial knowledge graph; wherein the industrial knowledge graph comprises reconstructed product nodes. According to the method, the technical effect of improving the accuracy of industrial data structure construction is achieved.

Description

Technical Field

[0001] This application relates to the field of data intelligence, and particularly to a method, device, and storage medium for constructing an industrial knowledge graph. Background Art

[0002] With the advent of the big data era, data has become an important driving force for industrial innovation and development; as a representative application of big data, the industrial knowledge graph provides strong support for the intelligentization process of various industries.

[0003] In the existing product data management technology, the product data management of the actual industry is mainly realized through two technologies: big data applications and digital transformation; in data management, it is necessary to construct a data knowledge graph of relevant industrial data; regarding the construction of the industrial knowledge graph in the actual industry, the construction of the relevant data knowledge graph is mainly realized through a tree structure and a chain structure.

[0004] In the prior art, in the knowledge graph construction technology of relevant industrial data, the tree structure and the chain structure cannot truly reflect the real logical structure of industrial life in the actual industry; at the same time, due to the complexity of the relevant industrial structure, the processing solutions depending on the relevant industrial structure lack specific solutions that can be generalized and implemented; therefore, in the existing industrial knowledge graph construction technology, there is a technical problem of low accuracy in constructing the industrial data structure. Summary of the Invention

[0005] This application provides a method, device, and storage medium for constructing an industrial knowledge graph to solve the technical problem of low accuracy in constructing the industrial data structure in the existing industrial knowledge graph construction technology.

[0006] In a first aspect, this application provides a method for constructing an industrial knowledge graph, including:

[0007] Obtain industrial data corresponding to a target industrial chain, and determine product logical relationships based on the industrial data; wherein, the target industrial chain includes N target products; N is a positive integer;

[0008] Construct a product logic graph based on the initial product codes corresponding to the target products and the product logical relationships;

[0009] Reconstruct the product logic graph based on a preset reconstruction rule to generate an industrial knowledge graph; wherein, the industrial knowledge graph includes reconstructed product nodes.

[0010] Optionally, reconstructing the product logic graph based on a preset reconstruction rule to generate an industrial knowledge graph includes:

[0011] Determine a reconstruction value M based on the preset reconstruction rule; wherein, M is a positive integer greater than or equal to 2 and less than N;

[0012] Redefine the N initial product codes in the product logic map based on the reconstructed value M, and determine the P reconstructed product codes corresponding to the P reconstructed product nodes;

[0013] Generate an industrial knowledge map based on the P reconstructed product codes corresponding to the P reconstructed product nodes.

[0014] Optionally, redefining the N initial product codes in the product logic map based on the reconstructed value M to determine the P reconstructed product codes corresponding to the P reconstructed product nodes includes:

[0015] Determine the upstream and downstream order of the target product based on the product logic relationship, and determine the P reconstructed product codes based on the upstream and downstream order and the initial product codes; the reconstructed product codes include M consecutive initial product codes in the upstream and downstream order;

[0016] Based on the P reconstructed product codes, determine the P reconstructed product nodes.

[0017] Optionally, after generating the industrial knowledge map, it includes:

[0018] Determine a reconstructed node list based on the correction distance between any two reconstructed product nodes with an upstream and downstream relationship in the industrial knowledge map; where the correction distance is used to represent the difference in the upstream and downstream order of any two reconstructed product nodes with an upstream and downstream relationship;

[0019] Determine the corresponding order distance based on the arrangement order of the initial product codes in the reconstructed product codes, and determine the equal-order reconstructed product nodes and the equal-order hash table with a parallel relationship in the reconstructed product nodes;

[0020] Determine the reconstructed hash table based on the reconstructed node list, the equal-order reconstructed product nodes, and the equal-order hash table.

[0021] Optionally, after generating the industrial knowledge map, it includes:

[0022] In response to a product addition request for a product node to be added, obtain the industrial data of the product node to be added and update the product logic map;

[0023] Update the target reconstructed product code based on the updated product logic map to update the industrial knowledge map; where the target reconstructed product code refers to the reconstructed product code whose correction distance from the product node to be added is less than or equal to the reconstructed value M;

[0024] Update the reconstructed hash table based on the updated industrial knowledge map.

[0025] Optionally, after generating the industrial knowledge map, it includes:

[0026] In response to a product deletion request for a product node to be deleted, determine whether the product node to be deleted has a preceding product node;

[0027] If not, determine the product node number to be deleted based on the product node to be deleted, delete the product node number to be deleted in the product logic graph and the industrial knowledge graph, and determine the data set to be deleted corresponding to the product node to be deleted based on the reconstructed hash table, and update the reconstructed hash table based on the data set to be deleted.

[0028] Optionally, determining the data set to be deleted corresponding to the product node to be deleted based on the reconstructed hash table includes:

[0029] Determine the first data set to be deleted as the data including the product node number to be deleted in the reconstructed hash table;

[0030] Determine the sub-product nodes of the product node to be deleted based on the industrial knowledge graph, determine the reconstructed product code corresponding to the sub-product nodes as the sub-product code, and determine the data with a hierarchical distance of 2 of the sub-product code in the reconstructed hash table as the first set to be evaluated;

[0031] Based on the equivalent hash table, determine whether the sub-product node has a preceding product node. If so, determine the preceding product code based on the preceding product node, and determine the data with a hierarchical distance of 1 of the preceding product code in the reconstructed hash table as the second set to be evaluated;

[0032] Determine the intersection of the first set to be evaluated and the second set to be evaluated as the second data set to be deleted, and determine the data set to be deleted based on the first data set to be deleted and the second data set to be deleted.

[0033] In a second aspect, the present application provides a device for constructing an industrial knowledge graph, including:

[0034] An acquisition module, configured to acquire industrial data corresponding to a target industrial chain, and determine product logical relationships based on the industrial data; wherein, the target industrial chain includes N target products; N is a positive integer;

[0035] A first processing module, configured to construct a product logic graph based on the initial product code corresponding to the target product and the product logical relationship;

[0036] A second processing module, configured to reconstruct the product logic graph based on a preset reconstruction rule to generate an industrial knowledge graph; wherein, the industrial knowledge graph includes reconstructed product nodes.

[0037] Optionally, the device is further configured to:

[0038] Determine a reconstruction value M based on a preset reconstruction rule; wherein, M is a positive integer greater than or equal to 2 and less than N;

[0039] Redefine the N initial product codes in the product logic map based on the reconstructed value M, and determine the P reconstructed product codes corresponding to the P reconstructed product nodes;

[0040] Generate an industrial knowledge map based on the P reconstructed product codes corresponding to the P reconstructed product nodes.

[0041] Optionally, redefining the N initial product codes in the product logic map based on the reconstructed value M to determine the P reconstructed product codes corresponding to the P reconstructed product nodes includes:

[0042] Determine the upstream and downstream order of the target product based on the product logic relationship, and determine the P reconstructed product codes based on the upstream and downstream order and the initial product codes; the reconstructed product codes include M consecutive initial product codes in the upstream and downstream order;

[0043] Determine the P reconstructed product nodes based on the P reconstructed product codes.

[0044] Optionally, the device is also used for:

[0045] Determine a reconstructed node list based on the correction distance between any two reconstructed product nodes with an upstream and downstream relationship in the industrial knowledge map; where the correction distance is used to represent the difference in the upstream and downstream order of any two reconstructed product nodes with an upstream and downstream relationship;

[0046] Determine the corresponding order distance based on the arrangement order of the initial product codes in the reconstructed product codes, and determine the equivalent reconstructed product nodes and equivalent hash tables with a parallel relationship in the reconstructed product nodes;

[0047] Determine the reconstructed hash table based on the reconstructed node list, the equivalent reconstructed product nodes, and the equivalent hash tables.

[0048] Optionally, the device is also used for:

[0049] In response to a product addition request for a product node to be added, obtain the industrial data of the product node to be added and update the product logic map;

[0050] Update the target reconstructed product codes based on the updated product logic map to update the industrial knowledge map; where the target reconstructed product codes refer to the reconstructed product codes whose correction distance from the product node to be added is less than or equal to the reconstructed value M;

[0051] Update the reconstructed hash table based on the updated industrial knowledge map.

[0052] Optionally, the device is also used for:

[0053] In response to a product deletion request for a product node to be deleted, determine whether the product node to be deleted has a pre-product node;

[0054] If not, determine the product node number to be deleted based on the product node to be deleted, delete the product node number to be deleted in the product logic graph and the industrial knowledge graph, and determine the data set to be deleted corresponding to the product node to be deleted based on the reconstructed hash table, and update the reconstructed hash table based on the data set to be deleted.

[0055] Optionally, the device is further configured to:

[0056] Determine the data including the product node number to be deleted in the reconstructed hash table as the first data set to be deleted;

[0057] Determine the sub-product nodes of the product node to be deleted based on the industrial knowledge graph, determine the reconstructed product code corresponding to the sub-product nodes as the sub-product code, and determine the data with a hierarchical distance of 2 of the sub-product code in the reconstructed hash table as the first set to be evaluated;

[0058] Based on the equivalent hash table, determine whether the sub-product node has a pre-product node. If so, determine the pre-product code based on the pre-product node, and determine the data with a hierarchical distance of 1 of the pre-product code in the reconstructed hash table as the second set to be evaluated;

[0059] Determine the intersection of the first set to be evaluated and the second set to be evaluated as the second data set to be deleted, and determine the data set to be deleted based on the first data set to be deleted and the second data set to be deleted.

[0060] In a third aspect of the present application, there is provided a device for constructing an industrial knowledge graph, including:

[0061] A processor and a memory;

[0062] The memory stores computer-executable instructions;

[0063] The processor executes the computer-executable instructions stored in the memory, so that the device for constructing the industrial knowledge graph executes the method for constructing the industrial knowledge graph according to any one of the first aspects.

[0064] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the method for constructing an industrial knowledge graph according to any one of the first aspects.

[0065] A method, device, and storage medium for constructing an industrial knowledge graph provided by the present application. The method includes: obtaining industrial data corresponding to a target industrial chain, and determining product logical relationships based on the industrial data; wherein, the target industrial chain includes N target products; N is a positive integer; constructing a product logical graph based on the initial product codes corresponding to the target products and the product logical relationships; reconstructing the product logical graph based on a preset reconstruction rule to generate an industrial knowledge graph; wherein, the industrial knowledge graph includes reconstructed product nodes. By obtaining the industrial data of the target industrial chain and constructing a product logical graph according to the product logical relationships existing in the industrial data and the initial product codes of the target products, where the product logical graph represents the production relationships between the target products in the target industrial chain; reconstructing the production logical graph based on a preset reconstruction rule, reconstructing the initial product codes corresponding to the target products with upstream and downstream relationships in the production logical graph based on the preset reconstruction rule to determine the corresponding reconstructed product codes, and determining the industrial knowledge graph corresponding to the product logical graph based on the reconstructed product codes, thereby realizing the construction of the industrial knowledge graph. Compared with the prior art, the present application uses a graph structure as the data structure basis, uses the relationships between nodes in the graph structure to restore the product logical relationships between industrial data, and realizes the construction of the industrial knowledge graph through a preset reconstruction rule; thereby accurately representing the product logical relationships in the industrial data, and improving the modification efficiency of the product logical relationships through a simplified industrial knowledge graph; thereby achieving the technical effect of improving the accuracy of the construction of the industrial data structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0067] Figure 1 is the flow chart of the method for constructing an industrial knowledge graph provided by an embodiment of the present application Figure 1 ;

[0068] Figure 2 is the flow chart of the method for constructing an industrial knowledge graph provided by an embodiment of the present application Figure 2 ;

[0069] Figure 3 is the structure of the product logical graph provided by an embodiment of the present application Figure 1 ;

[0070] Figure 4 is the structure diagram of the industrial knowledge graph provided by an embodiment of the present application;

[0071] Figure 5 is the structure of the product logical graph provided by an embodiment of the present application Figure 2 ;

[0072] Figure 6 The structural schematic diagram of the construction device of the industrial knowledge graph provided by the embodiment of the present application;

[0073] Figure 7 The hardware structure diagram of the construction device of the industrial knowledge graph provided by the embodiment of the present application.

[0074] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0075] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0076] In the existing product data management technology, the product data management of the actual industry is mainly realized through two technologies: big data application and digital transformation; in data management, it is necessary to construct a data knowledge graph of relevant industrial data; regarding the construction of the industrial knowledge graph in the actual industry, the construction of the relevant data knowledge graph is mainly realized through a tree structure and a chain structure. In the prior art, in the knowledge graph construction technology of relevant industrial data, the tree structure and the chain structure cannot truly reflect the real logical structure of industrial life in the actual industry; at the same time, due to the complexity of the relevant industrial structure, the processing solutions depending on the relevant industrial structure lack specific solutions that can be generalized and implemented; therefore, in the existing industrial knowledge graph construction technology, there is a technical problem of low accuracy in constructing the industrial data structure.

[0077] A method, device, and storage medium for constructing an industrial knowledge graph provided by this application. The method includes: obtaining industrial data corresponding to a target industrial chain, and determining product logical relationships based on the industrial data; wherein the target industrial chain includes N target products; N is a positive integer; constructing a product logical graph based on the initial product codes corresponding to the target products and the product logical relationships; reconstructing the product logical graph based on a preset reconstruction rule to generate an industrial knowledge graph; wherein the industrial knowledge graph includes reconstructed product nodes. By obtaining the industrial data of the target industrial chain and constructing a product logical graph according to the product logical relationships existing in the industrial data and the initial product codes of the target products, where the product logical graph represents the production relationships between the target products in the target industrial chain; reconstructing the production logical graph based on a preset reconstruction rule, reconstructing the initial product codes corresponding to the target products with upstream and downstream relationships in the production logical graph based on the preset reconstruction rule to determine the corresponding reconstructed product codes, and determining the industrial knowledge graph corresponding to the product logical graph based on the reconstructed product codes, thereby realizing the construction of the industrial knowledge graph. Compared with the prior art, this application uses a graph structure as the data structure basis, uses the relationships between nodes in the graph structure to restore the product logical relationships between industrial data, and realizes the construction of the industrial knowledge graph through a preset reconstruction rule; thereby accurately representing the product logical relationships in the industrial data, and improving the modification efficiency of the product logical relationships through a simplified industrial knowledge graph; thereby achieving the technical effect of improving the accuracy of the construction of the industrial data structure, and solving the technical problem of low accuracy in the construction of the industrial data structure existing in the prior art.

[0078] The following uses specific embodiments to elaborate in detail on the technical solutions of this application and how the technical solutions of this application solve the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0079] Figure 1 The flow of the method for constructing an industrial knowledge graph provided by the embodiments of this application Figure 1 As Figure 1 shown, the method for constructing an industrial knowledge graph provided by the embodiments of this application includes:

[0080] S101. Obtain industrial data corresponding to a target industrial chain, and determine product logical relationships based on the industrial data;

[0081] In this embodiment, the target industrial chain includes N target products; N is a positive integer.

[0082] In this embodiment, the product logical relationship corresponding to industrial data is used to represent the production relationship between target products in the target industrial chain. For example, in the first exemplary case, there are five target products in the target industrial chain. The first product and the second product are combined to form the third product, and the third product can produce the fourth product and the fifth product. Then, the product logical relationship is determined based on the production relationship.

[0083] S102. Construct a product logic graph based on the initial product codes corresponding to the target products and the product logical relationship.

[0084] In this embodiment, in the first exemplary case, the product logical relationship is that the first product and the second product are combined to form the third product, and the third product can produce the fourth product and the fifth product. At the same time, based on the target products, the corresponding initial product codes are determined. One initial product code corresponds to one target product. Then, the corresponding first initial code, second initial code, third initial code, fourth initial code, and fifth initial code are determined. The product logic graph is as follows: Based on the target products, the corresponding initial nodes are determined. The first initial node corresponding to the first initial code and the second initial node corresponding to the second initial code are in a parallel relationship, and the first initial node and the second initial node are the upstream nodes of the third initial node corresponding to the third initial code. The fourth initial node corresponding to the fourth initial code and the fifth initial node corresponding to the fifth initial code are in a parallel relationship, and the third initial node is the upstream node of the fourth initial node and the fifth initial node.

[0085] S103. Reconstruct the product logic graph based on the preset reconstruction rules to generate an industrial knowledge graph.

[0086] In this embodiment, the industrial knowledge graph includes reconstructed product nodes.

[0087] In this embodiment, the preset reconstruction rule is to determine a reconstruction value M that is less than the number N of target products and ensure that M is greater than or equal to 2. Based on the product logic graph, M initial product codes with upstream and downstream relationships and that are consecutive are determined, and redefinition is performed to determine a corresponding reconstructed product code. The N target products and the corresponding product logical relationships can determine P reconstructed product codes. Based on the P reconstructed product codes, P reconstructed product nodes are determined, and the industrial knowledge graph is determined based on the reconstructed product nodes.

[0088] A method for constructing an industrial knowledge graph provided by this application. The method includes: obtaining industrial data corresponding to a target industrial chain, and determining product logical relationships based on the industrial data; wherein, the target industrial chain includes N target products; N is a positive integer; constructing a product logical graph based on the initial product codes corresponding to the target products and the product logical relationships; reconstructing the product logical graph based on a preset reconstruction rule to generate an industrial knowledge graph; wherein, the industrial knowledge graph includes reconstructed product nodes. By obtaining the industrial data of the target industrial chain and constructing a product logical graph according to the product logical relationships existing in the industrial data and the initial product codes of the target products, where the product logical graph represents the production relationships between the target products in the target industrial chain; reconstructing the production logical graph based on a preset reconstruction rule, reconstructing the initial product codes corresponding to the target products with upstream and downstream relationships in the production logical graph based on the preset reconstruction rule to determine the corresponding reconstructed product codes, and determining the industrial knowledge graph corresponding to the product logical graph based on the reconstructed product codes, thereby realizing the construction of the industrial knowledge graph. Compared with the prior art, this application uses a graph structure as the data structure basis, uses the relationships between nodes in the graph structure to restore the product logical relationships between industrial data, and realizes the construction of the industrial knowledge graph through a preset reconstruction rule; thereby accurately representing the product logical relationships in industrial data, and improving the modification efficiency of product logical relationships through a simplified industrial knowledge graph; thereby achieving the technical effect of improving the accuracy of industrial data structure construction, and solving the technical problem of low accuracy in industrial data structure construction existing in the prior art.

[0089] Figure 2 The flow of the method for constructing an industrial knowledge graph provided by an embodiment of this application Figure 2 , Figure 3 The structure of the product logical graph provided by an embodiment of this application Figure 1 ; Figure 4 The structure diagram of the industrial knowledge graph provided by an embodiment of this application; Figure 5 The structure of the product logical graph provided by an embodiment of this application Figure 2 As Figure 2 shown, the method for constructing an industrial knowledge graph provided by an embodiment of this application includes:

[0090] S201. Obtain industrial data corresponding to a target industrial chain, and determine product logical relationships based on the industrial data; construct a product logical graph based on the initial product codes corresponding to the target products and the product logical relationships;

[0091] In this embodiment, the target industrial chain includes N target products; N is a positive integer.

[0092] In this embodiment, the initial product code is a code of any length, and the code lengths of each initial product are the same. The product logic map is a relational graph constructed based on the graph structure and product logic relationships. The connection relationships between the initial product nodes in the product logic map are determined depending on the product logic relationships.

[0093] S202. Determine the reconstruction value M based on a preset reconstruction rule;

[0094] In this embodiment, M is a positive integer greater than or equal to 2 and less than N.

[0095] S203. Determine the upstream and downstream order corresponding to the target product based on the product logic relationships, and determine P reconstructed product codes based on the upstream and downstream order and the initial product code; the reconstructed product codes include M consecutive initial product codes in the upstream and downstream order.

[0096] In this embodiment, in the second exemplary example as Figure 3 shown, the initial product nodes corresponding to the target product are represented by the initial product code. The number N corresponding to the target product is 9; the length of the initial product code is 1, and the initial product codes are respectively: {A, B, C, D, E, F, G, H, I, J}, and the product logic relationships are: {A->B, (B, C, D)->E, E->F, (F, G)->H, H->(I, J)}. It is expressed as: the target product with the initial product code A generates the target product with the initial product code B; the target products with the initial product code B, the initial product code C, and the initial product code D are combined to generate the target product with the initial product code E; the target product with the initial product code E generates the target product with the initial product code F; the target products with the initial product code F and the initial product code G are combined to generate the target product with the initial product code H; the target product with the initial product code H can produce the target products with the initial product code I and the initial product code J.

[0097] In this embodiment, in the second exemplary example, the reconstruction value is 3, and based on the reconstruction value and the upstream and downstream order of the product logic relationships, 9 corresponding reconstructed product codes are determined: {ABE, BEF, CEF, DEF, EFH, EFI, FHJ, GHI, GHJ}.

[0098] In this embodiment, the number P of reconstructed product codes is related to the product logical relationship, the number N of target products and the reconstruction number M, and the size of P changes according to the changes in the product logical relationship, the number N of target products and the reconstruction number M; the reconstructed product code must be determined by M original product codes that have upstream and downstream relationships and are continuous; the reconstructed product code can be reconstructed by merging M original product codes; it can also be the original product code that is redefined to determine the iconic code and merged to determine; the reconstructed product code needs to indicate the upstream and downstream relationship between the M original product codes.

[0099] S204, based on the P reconstructed product codes, determining P reconstructed product nodes; generating an industry knowledge graph based on the P reconstructed product codes corresponding to the P reconstructed product nodes;

[0100] In this embodiment, Figure 4 In the second example shown, the reconstructed product code is used to represent the reconstructed product nodes and the connection relationship between the reconstructed product nodes. P is 9, and the 9 reconstructed product codes determine the corresponding 9 reconstructed product nodes; the connection relationship between the reconstructed product nodes is: {ABE->BEF, (BEF, CEF, DEF)->EFH, EFH->(FHI, FHJ), GHI, GHJ}.

[0101] S205, determining a reconstructed node list based on the corrected distance between any two reconstructed product nodes that have an upstream and downstream relationship in the industrial knowledge graph; determining a corresponding order distance based on the arrangement order of the initial product code in the reconstructed product code, and determining equal-order reconstructed product nodes and equal-order hash tables that have a parallel relationship in the reconstructed product nodes based on the order distance; determining a reconstructed hash table based on the reconstructed node list, the equal-order reconstructed product nodes and the equal-order hash table;

[0102] In this embodiment, the corrected distance is used to represent the difference between the upstream and downstream orders of any two reconstructed product nodes that have an upstream and downstream relationship.

[0103] In this embodiment, when the modified distance is 1, it can be determined that there is a direct upstream and downstream relationship between the two reconstructed product nodes. Figure 4In the second exemplary embodiment shown, it can be determined that the nodes with a correction relationship of 1 in the reconstructed product nodes are: between ABE and BEF, between (BEF, CEF, DEF) and EFH, and between EFH and (FHI, FHJ); and a reconstructed node list is determined: {ABE, BEF, CEF, DEF, EFH, EFI, FHJ, GHI, GHJ}. Based on the arrangement order of the initial product codes in the reconstructed product codes, the corresponding order distance is determined, and then the equivalent reconstructed product nodes are determined: (BEF, CEF, DEF), (EFI, FHJ, GHI, GHJ); the corresponding equivalent hash table is determined: {E: [B, C, D], H: [F, G]}; based on the equivalent hash table, the reconstructed node list, and the equivalent reconstructed product nodes, a reconstructed hash table is determined. The reconstructed hash table is: {(A, 1): [ABE], (B, 1): [BEF], (C, 1): [CEF], (D, 1)[DEF], (E, 1): [EFH], (F, 1): [FHI, FHJ], (G, 1): [GHI, GHJ], (B, 2): [ABE], (E, 2): [BEF, CEF, DEF], (F, 2): [EFH], (H, 2): [FHI, FHJ, GHI, GHJ], (E, 3): [ABE], (F, 3): [BEF, CEF, DEF], (H, 3): [EFH], (I, 3): [FHI, GHI], (J, 3): [FHJ, GHJ]}. The reconstructed hash table represents the reconstructed product nodes corresponding to each initial product code when the order distance is fixed.

[0104] S206. In response to a product addition request for a product node to be added, obtain the industrial data of the product node to be added and update the product logic map; update the target reconstructed product code based on the updated product logic map to update the industrial knowledge map; update the reconstructed hash table based on the updated industrial knowledge map;

[0105] In this embodiment, the target reconstructed product code refers to the reconstructed product code whose correction distance from the product node to be added is less than or equal to the reconstruction value M;

[0106] In this embodiment, such as Figure 5In the third exemplary embodiment shown, the initial product code is used to represent the initial product node corresponding to the target product and the corresponding connection relationship. The initial product code of the node to be newly added is K, and the product logic relationship corresponding to the node to be newly added is: the target product corresponding to the initial product code E generates the target product corresponding to the node to be newly added K, and the target product corresponding to the node to be newly added K generates the target product with the initial product code H. Then, the newly added target reconstruction product codes corresponding to the node to be newly added are: {BEK, CEK, DEK, EKH, KHI, KHJ}, and they are determined as the newly added node list; add the newly added node list to the reconstructed node list, and the newly added reconstructed node list is: {ABE, BEF, BEK, CEK, DEK, EKH, KHI, KHJ, CEF, DEF, EFH, EFI, FHJ, GHI, GHJ}. Add the order distance corresponding to the newly added node list to the reconstructed hash table, and the updated reconstructed hash table is: {(A,1):[ABE], (B,1):[BEF,BEK], (C,1):[CEF,CEK], (D,1)[DEF,DEK], (E,1):[EFH,EKH], (F,1):[FHI,FHJ], (K,1):[KHI,KHJ], (G,1):[GHI,GHJ], (B,2):[ABE], (E,2):[BEF,CEF,DEF,BEK,CEK,DEK], (K,2):[EKH], (F,2):[EFH], (H,2):[FHI,FHJ,GHI,GHJ,KHI,KHJ], (E,3):[ABE], (K,3):[BEK,CEK,DEK], (F,3):[BEF,CEF,DEF], (H,3):[EFH,EKH], (I,3):[FHI,GHI,KHI], (J,3):[FHJ,GHJ,KHJ]}.

[0107] S207. In response to a product deletion request for the product node to be deleted, determine whether the product node to be deleted has a pre-product node; if not, determine the product node number to be deleted based on the product node to be deleted, and delete the product node number to be deleted in the product logic graph and the industrial knowledge graph;

[0108] In this embodiment, in the fourth exemplary case, the reconstructed node list is: {ABE, BEF, CEF, DEF, EFH, EFI, FHJ, GHI, GHJ}. The equivalent hash table is: {E: [B, C, D], H: [F, G]}. The reconstructed hash table is: {(A, 1): [ABE], (B, 1): [BEF], (C, 1): [CEF], (D, 1)[DEF], (E, 1): [EFH], (F, 1): [FHI, FHJ], (G, 1): [GHI, GHJ], (B, 2): [ABE], (E, 2): [BEF, CEF, DEF], (F, 2): [EFH], (H, 2): [FHI, FHJ, GHI, GHJ], (E, 3): [ABE], (F, 3): [BEF, CEF, DEF], (H, 3): [EFH], (I, 3): [FHI, GHI], (J, 3): [FHJ, GHJ]}. The initial product code corresponding to the product node to be deleted is G. Based on the product logic graph, it is determined that the product node to be deleted does not have a pre-product node; then the relevant nodes in the product logic graph and the industrial knowledge graph are deleted.

[0109] S208. Determine the data including the product node number to be deleted in the reconstructed hash table as the first set of data to be deleted; determine the sub-product nodes of the product node to be deleted based on the industrial knowledge graph, determine the reconstructed product code corresponding to the sub-product nodes as the sub-product code, and determine the data with a hierarchical distance of 2 for the sub-product code in the reconstructed hash table as the first set of data to be evaluated;

[0110] In the fourth exemplary case, the first set of data to be deleted determined based on the initial product code G and the reconstructed hash table is: GHI and GHJ; determine the sub-product nodes of the product node to be deleted based on the industrial knowledge graph. The sub-product node of G is H, then the reconstructed product codes corresponding to the sub-product nodes are: {FHI, FHJ, GHI, GHJ, EFH}; and determine them as the sub-product codes, and determine the data with a hierarchical distance of 2 corresponding to H as the first set of data to be evaluated: {FHI, FHJ, GHI, GHJ}; the purpose is to determine the pre-nodes for generating the target product H.

[0111] S209. Judge whether the sub-product node has a pre-product node based on the equivalent hash table. If so, determine the pre-product code based on the pre-product node, and determine the data with a hierarchical distance of 1 for the pre-product code in the reconstructed hash table as the second set of data to be evaluated; determine the intersection of the first set of data to be evaluated and the second set of data to be evaluated as the second set of data to be deleted, and determine the set of data to be deleted based on the first set of data to be deleted and the second set of data to be deleted; update the reconstructed hash table based on the set of data to be deleted.

[0112] In the fourth exemplary embodiment, based on the equal-order hash table lookup, the pre-product nodes of the sub-product node H include G and F; the data with a rank distance of 1 for the pre-product codes in the reconstructed hash table is determined as the second set of data to be evaluated: {FHI, FHJ, GHI, GHJ}; the first set of data to be evaluated and the second set of data to be evaluated are intersected to determine the second set of data to be deleted: {FHI, FHJ, GHI, GHJ}; the set of data to be deleted {FHI, FHJ, GHI, GHJ} is determined based on the first set of data to be deleted and the second set of data to be deleted; wherein, if the product node G is deleted, the product node H cannot be generated normally, and the product logic relationship for generating the product node H by the product node F needs to be deleted simultaneously.

[0113] In this embodiment, the pre-product nodes of the sub-product node are determined, and the pre-product codes corresponding to the pre-product nodes with a rank distance of 1 are determined. Thereby, the reconstructed product node codes corresponding to the other pre-product nodes used to merge with the product node to be deleted to generate the sub-product node are determined; a complete deletion of the product node is achieved.

[0114] By executing S201 to S09, the knowledge graph construction of industrial data is realized by using the graph structure, and the update of industrial data is realized by using the hash table corresponding to the graph structure, thereby achieving the technical effect of improving the accuracy of the construction of the industrial data structure.

[0115] A method for constructing an industrial knowledge graph provided by the present application. The method includes: obtaining industrial data corresponding to a target industrial chain, and determining product logical relationships based on the industrial data; wherein, the target industrial chain includes N target products; N is a positive integer; constructing a product logical graph based on the initial product codes corresponding to the target products and the product logical relationships; reconstructing the product logical graph based on a preset reconstruction rule to generate an industrial knowledge graph; wherein, the industrial knowledge graph includes reconstructed product nodes. Obtain the corresponding industrial data through the target industrial chain, and construct a corresponding product logical graph according to the product logical relationships of the industrial data and the initial product codes of the target products; wherein the product logical graph reflects the production relationships between the target products; determine the reconstruction quantity through the preset reconstruction rule, and redefine the original product codes corresponding to the target products based on the reconstruction quantity to determine the reconstructed product codes; determine the corresponding reconstructed product nodes based on the reconstructed product codes, and construct the corresponding industrial knowledge graph; wherein the reconstructed product codes contain the initial product codes and the corresponding arrangement order; determine the corresponding reconstructed node list, equivalent hash table, and reconstructed hash table based on the industrial knowledge graph and the product logical graph; for realizing the update of industrial data. Compared with the prior art, the present application completely represents the product logical relationships in industrial data through a graph structure, and at the same time represents the relationships between each node in the graph structure based on the corresponding reconstructed node list, equivalent hash table, and reconstructed hash table, and realizes the addition and deletion of industrial data, achieving efficient data update while maintaining the stability of the industrial data structure, thereby achieving the technical effect of improving the accuracy of constructing the industrial data structure and solving the technical problem of low accuracy in constructing the industrial data structure in the prior art.

[0116] Figure 6 The structure diagram of the device for constructing an industrial knowledge graph provided by an embodiment of the present application. The device in this embodiment can be in the form of software and / or hardware. As Figure 6 shown, an industrial knowledge graph construction device 600 provided by an embodiment of the present application includes: an acquisition module 601, a first processing module 602, and a second processing module 603,

[0117] The acquisition module 601 is configured to obtain industrial data corresponding to a target industrial chain, and determine product logical relationships based on the industrial data; wherein, the target industrial chain includes N target products; N is a positive integer;

[0118] The first processing module 602 is configured to construct a product logical graph based on the initial product codes corresponding to the target products and the product logical relationships;

[0119] The second processing module 603 is configured to reconstruct the product logical graph based on a preset reconstruction rule to generate an industrial knowledge graph; wherein, the industrial knowledge graph includes reconstructed product nodes.

[0120] In a possible implementation, the device is further configured to:

[0121] Determine a reconstruction value M based on a preset reconstruction rule; where M is a positive integer greater than or equal to 2 and less than N;

[0122] Redefine the N initial product codes in the product logic map based on the reconstruction value M, and determine P reconstruction product codes corresponding to P reconstruction product nodes;

[0123] Generate an industrial knowledge map based on the P reconstruction product codes corresponding to the P reconstruction product nodes.

[0124] In a possible implementation, redefining the N initial product codes in the product logic map based on the reconstruction value M to determine P reconstruction product codes corresponding to P reconstruction product nodes includes:

[0125] Determine the upstream and downstream order of the target product based on the product logic relationship, and determine P reconstruction product codes based on the upstream and downstream order and the initial product codes; the reconstruction product codes include M consecutive initial product codes in the upstream and downstream order;

[0126] Determine P reconstruction product nodes based on the P reconstruction product codes.

[0127] In a possible implementation, the device is further configured to:

[0128] Determine a reconstruction node list based on the correction distance between any two reconstruction product nodes with an upstream and downstream relationship in the industrial knowledge map; where the correction distance is used to represent the difference in the upstream and downstream order of any two reconstruction product nodes with an upstream and downstream relationship;

[0129] Determine the corresponding order distance based on the arrangement order of the initial product codes in the reconstruction product codes, and determine the equivalent reconstruction product nodes and equivalent hash table with a parallel relationship in the reconstruction product nodes;

[0130] Determine a reconstruction hash table based on the reconstruction node list, the equivalent reconstruction product nodes, and the equivalent hash table.

[0131] In a possible implementation, the device is further configured to:

[0132] In response to a product addition request for a product node to be added, obtain the industrial data of the product node to be added and update the product logic map;

[0133] Update the target reconstruction product code based on the updated product logic map to update the industrial knowledge map; where the target reconstruction product code refers to the reconstruction product code whose correction distance from the product node to be added is less than or equal to the reconstruction value M;

[0134] Update the reconstructed hash table based on the updated industrial knowledge graph.

[0135] In a possible implementation, the device is further configured to:

[0136] In response to a product deletion request for a product node to be deleted, determine whether the product node to be deleted has a pre-product node;

[0137] If not, determine the product node number to be deleted based on the product node to be deleted, delete the product node number to be deleted in the product logic graph and the industrial knowledge graph, and determine the data set to be deleted corresponding to the product node to be deleted based on the reconstructed hash table, and update the reconstructed hash table based on the data set to be deleted.

[0138] In a possible implementation, the device is further configured to:

[0139] Determine the first data set to be deleted that includes the product node number to be deleted in the reconstructed hash table;

[0140] Determine the sub-product nodes of the product node to be deleted based on the industrial knowledge graph, determine the reconstructed product code corresponding to the sub-product node as the sub-product code, and determine the data with a hierarchical distance of 2 of the sub-product code in the reconstructed hash table as the first set to be evaluated;

[0141] Determine whether the sub-product node has a pre-product node based on the equal-level hash table. If so, determine the pre-product code based on the pre-product node, and determine the data with a hierarchical distance of 1 of the pre-product code in the reconstructed hash table as the second set to be evaluated;

[0142] Determine the intersection of the first set to be evaluated and the second set to be evaluated as the second data set to be deleted, and determine the data set to be deleted based on the first data set to be deleted and the second data set to be deleted.

[0143] An apparatus for constructing an industrial knowledge graph provided by this application. The apparatus includes: an acquisition module, configured to acquire industrial data corresponding to a target industrial chain and determine product logical relationships based on the industrial data; wherein the target industrial chain includes N target products; N is a positive integer; a first processing module, configured to construct a product logical graph based on the initial product codes corresponding to the target products and the product logical relationships; a second processing module, configured to reconstruct the product logical graph based on a preset reconstruction rule to generate an industrial knowledge graph; wherein the industrial knowledge graph includes reconstructed product nodes. The industrial data corresponding to the target industrial chain is acquired, and a corresponding product logical graph is constructed according to the product logical relationships of the industrial data and the initial product codes of the target products; wherein the product logical graph reflects the production relationships between the target products; the reconstruction quantity is determined by the preset reconstruction rule, and the original product codes corresponding to the target products are redefined based on the reconstruction quantity to determine the reconstructed product codes; the reconstructed product nodes corresponding to the reconstructed product codes are determined, and the corresponding industrial knowledge graph is constructed; wherein the reconstructed product codes include the initial product codes and the corresponding arrangement order; the corresponding reconstructed node list, equivalent hash table, and reconstructed hash table are determined based on the industrial knowledge graph and the product logical graph; which is used to implement the update of industrial data. Compared with the prior art, this application completely represents the product logical relationships in industrial data through a graph structure, and at the same time represents the relationships between each node in the graph structure based on the corresponding reconstructed node list, equivalent hash table, and reconstructed hash table, and realizes the addition and deletion of industrial data, achieving efficient data update while maintaining the stability of the industrial data structure, thereby achieving the technical effect of improving the accuracy of industrial data structure construction and solving the technical problem of low accuracy in industrial data structure construction existing in the prior art.

[0144] Figure 7 The hardware structure diagram of the apparatus for constructing an industrial knowledge graph provided by an embodiment of this application. As Figure 7 shown, the apparatus 700 for constructing an industrial knowledge graph includes:

[0145] A processor 701 and a memory 702;

[0146] The memory stores computer execution instructions;

[0147] It should be understood that the above-mentioned processor 701 may be a central processing unit (CPU for short), or other general-purpose processors, digital signal processors (DSP for short), application specific integrated circuits (ASIC for short), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly implemented by the execution of the hardware processor, or implemented by the combination of hardware and software modules in the processor. The memory 702 may include a high-speed random access memory (RAM for short), and may also include non-volatile memory (NVM for short), such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disc, etc.

[0148] The processor executes the computer execution instructions stored in the memory 702, so that the device for constructing the industrial knowledge graph executes the method for constructing the industrial knowledge graph as described above.

[0149] The embodiment of the present application correspondingly further provides a computer-readable storage medium, in which computer execution instructions are stored, and when the computer execution instructions are executed by the processor, they are used to implement the method for constructing the industrial knowledge graph.

[0150] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, some steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0151] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential either, but can be executed alternately or in rotation with at least some of the other steps or sub-steps or stages of the other steps.

[0152] It should be understood that the above device embodiments are illustrative only, and the devices of the present application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0153] In addition, unless otherwise specified, in each embodiment of the present application, each functional unit / module can be integrated in one unit / module, or each unit / module can exist physically alone, or two or more units / modules can be integrated together. The above integrated unit / module can be implemented in the form of hardware or in the form of a software program module.

[0154] When the integrated unit / module is implemented in the form of hardware, the hardware can be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory RRAM (Resistive Random Access Memory), dynamic random access memory DRAM (Dynamic Random Access Memory), static random access memory SRAM (Static Random-Access Memory), enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), high-bandwidth memory HBM (High-Bandwidth Memory), hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0155] When the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. And the aforementioned memory includes: various media such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0156] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0157] Those skilled in the art will readily think of other implementation schemes of this application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptive changes of this application, which follow the general principles of this application and include the common general knowledge or conventional technical means in the technical field not disclosed in this application. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of this application are pointed out by the following claims.

[0158] It should be understood that this application is not limited to the exact structure already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is only limited by the appended claims.

Claims

1. A method for constructing an industrial knowledge graph, characterized in that Including: Obtain industrial data corresponding to the target industrial chain, and determine product logical relationships based on the industrial data; wherein, the target industrial chain includes N target products; N is a positive integer; Construct a product logical graph based on the initial product codes corresponding to the target products and the product logical relationships; Reconstruct the product logical graph based on a preset reconstruction rule to generate the industrial knowledge graph; wherein, the industrial knowledge graph includes reconstructed product nodes.

2. The method according to claim 1, wherein The reconstructing the product logical graph based on a preset reconstruction rule to generate the industrial knowledge graph includes: Determine a reconstruction value M based on the preset reconstruction rule; wherein, M is a positive integer greater than or equal to 2 and less than N; Redefine the N initial product codes in the product logical graph based on the reconstruction value M to determine P reconstructed product codes corresponding to P reconstructed product nodes; Generate the industrial knowledge graph based on the P reconstructed product codes corresponding to the P reconstructed product nodes.

3. The method according to claim 2, wherein The redefining the N initial product codes in the product logical graph based on the reconstruction value M to determine P reconstructed product codes corresponding to P reconstructed product nodes includes: Determine the upstream and downstream order corresponding to the target products based on the product logical relationships, and determine the P reconstructed product codes based on the upstream and downstream order and the initial product codes; the reconstructed product codes include M initial product codes with consecutive upstream and downstream order; Determine the P reconstructed product nodes based on the P reconstructed product codes.

4. The method according to claim 3, wherein After generating the industrial knowledge graph, it includes: Determine a reconstructed node list based on the correction distance between any two reconstructed product nodes with an upstream and downstream relationship in the industrial knowledge graph; wherein, the correction distance is used to represent the difference in the upstream and downstream order of any two reconstructed product nodes with an upstream and downstream relationship; Determine the corresponding order distance based on the arrangement order of the initial product codes in the reconstructed product codes, and determine the equal-order reconstructed product nodes and the equal-order hash table with a parallel relationship among the reconstructed product nodes based on the order distance; Determine a reconstructed hash table based on the reconstructed node list, the equal-order reconstructed product nodes, and the equal-order hash table.

5. The method according to claim 4, wherein After generating the industrial knowledge graph, it includes: In response to a product addition request for a product node to be added, obtain the industrial data of the product node to be added and update the product logical graph; Update the target reconstructed product codes based on the updated product logical graph to update the industrial knowledge graph; wherein, the target reconstructed product codes refer to the reconstructed product codes whose correction distance from the product node to be added is less than or equal to the reconstruction value M; Update the reconstructed hash table based on the updated industrial knowledge graph.

6. The method according to claim 4, wherein After generating the industrial knowledge graph, it includes: In response to a product deletion request for a product node to be deleted, determine whether the product node to be deleted has a pre-product node; Otherwise, determine the product node number to be deleted based on the product node to be deleted, delete the product node number to be deleted in the product logic graph and the industrial knowledge graph, determine the data set to be deleted corresponding to the product node to be deleted based on the reconstructed hash table, and update the reconstructed hash table based on the data set to be deleted.

7. The method according to claim 6, wherein Determining the data set to be deleted corresponding to the product node to be deleted based on the reconstructed hash table includes: Determine the first data set to be deleted as the data including the product node number to be deleted in the reconstructed hash table; Based on the industrial knowledge graph, determine the sub-product nodes of the product node to be deleted, determine the reconstructed product code corresponding to the sub-product nodes as the sub-product code, and determine the data with a hierarchical distance of 2 for the sub-product code in the reconstructed hash table as the first data set to be evaluated; Based on the equal-rank hash table, determine whether the sub-product node has the pre-product node. If so, determine the pre-product code based on the pre-product node, and determine the data with a hierarchical distance of 1 for the pre-product code in the reconstructed hash table as the second data set to be evaluated; Determine the intersection of the first data set to be evaluated and the second data set to be evaluated as the second data set to be deleted, and determine the data set to be deleted based on the first data set to be deleted and the second data set to be deleted.

8. An apparatus for constructing an industrial knowledge graph, characterized in that, Including: An acquisition module, configured to acquire industrial data corresponding to a target industrial chain, and determine a product logic relationship based on the industrial data; wherein, the target industrial chain includes N target products; N is a positive integer; A first processing module, configured to construct a product logic graph based on the initial product code corresponding to the target product and the product logic relationship; A second processing module, configured to reconstruct the product logic graph based on a preset reconstruction rule to generate the industrial knowledge graph; wherein, the industrial knowledge graph includes reconstructed product nodes.

9. An apparatus for constructing an industrial knowledge graph, characterized in that, Including: A processor, and a memory communicatively connected to the processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory to implement the data graph construction method based on industrial data according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Computer execution instructions are stored in the computer-readable storage medium, and when the computer execution instructions are executed by a processor, they are used to implement the data graph construction method based on industrial data according to any one of claims 1 to 7.

Images