Method and device for constructing multi-layer knowledge graph, and computer device

Abstract

The application discloses a multi-layer knowledge graph construction method and device, computer equipment and a storage medium. Specifically, the application discloses a multi-layer knowledge graph construction method, which comprises the following steps: constructing a hardware layer knowledge graph according to a target device; constructing a physical layer knowledge graph according to the target device; constructing an application layer knowledge graph according to a target scene; and connecting nodes in the hardware layer, the physical layer and the application layer in an interlayer corresponding manner. Through the above method, various logical relationships or hierarchical relationships in real production can be used to construct a knowledge graph according to hierarchical concepts, and then the whole knowledge graph structure is formed through connection, which is beneficial to the analysis of knowledge organization in a general manufacturing scene and the search for corresponding relationships between real objects or devices in different layers.

Description

Method, device, and computer equipment for constructing multi-layer knowledge graph Technical Field

[0001] The present application relates to the field of knowledge graphs, and specifically, to a method, apparatus, computer equipment, and storage medium for constructing a multi-layer knowledge graph. Background Art

[0002] With the growing demand for automated monitoring, processing, and decision-making in daily production activities, more and more people in the industrial sector are realizing the importance of logically organizing knowledge in production. At the same time, knowledge graphs (KGs), as a popular medium for storing, analyzing, and applying knowledge, are widely considered to be a key technological component in building future smart manufacturing or Industry 4.0.

[0003] Summary of the Invention

[0004] This summary is provided to introduce some selected concepts in a simplified form, which will be further described in the detailed description below. This summary is not intended to identify any key features or essential features of the claimed subject matter, nor is it intended to be used to help determine the scope of the claimed subject matter.

[0005] Based on this, an embodiment of the present application discloses a method for constructing a multi-layer knowledge graph, which includes: constructing a hardware layer knowledge graph based on the target device; constructing a physical layer knowledge graph based on the target device; constructing an application layer knowledge graph based on the target scenario; and connecting the nodes in the hardware layer, physical layer and application layer to corresponding layers.

[0006] Through the above method, various logical relationships or hierarchical relationships in real production can be constructed into a knowledge graph according to the hierarchical concept, and then connected to form an overall knowledge graph structure, which is conducive to analyzing data and finding the corresponding relationship between real objects or equipment at different layers.

[0007] Furthermore, the step of performing corresponding inter-layer connections between the nodes in the hardware layer, the physical layer, and the application layer includes:

[0008] The nodes in the application layer are connected to the nodes in the physical layer, and the connection with the nodes in the hardware layer is omitted.

[0009] Through the above method, the application layer can be flexibly connected to the physical layer and hardware layer.

[0010] Furthermore, constructing a physical layer knowledge graph based on the target device includes:

[0011] Nodes in the physical layer are constructed, wherein the nodes represent a plurality of identical products, and the products are physical entities.

[0012] Through the above method, during the construction of the physical layer, the construction of nodes can be simplified, important factors such as connection relationships can be highlighted, and duplication and redundancy can be avoided.

[0013] Furthermore, according to the target scenario, an application layer knowledge graph is constructed, including:

[0014] Construct the application layer knowledge graph, wherein the application layer knowledge graph serves as the external interface and algorithm interface of the multi-layer knowledge graph.

[0015] In this way, external algorithms can obtain the node information and connection relationships of the entire multi-layer knowledge graph through the application layer for model learning and calculation, which provides the basis and premise for analyzing knowledge in general manufacturing scenarios and understanding the relationship between real objects or real devices corresponding to different layers.

[0016] Based on this, an embodiment of the present application also provides a device for constructing a multi-layer knowledge graph, which includes: a hardware layer module, used to construct a hardware layer knowledge graph based on a target device; a physical layer module, used to construct a physical layer knowledge graph based on the target device; an application layer module, used to construct an application layer knowledge graph based on a target scenario; and a layer connection module, used to connect the nodes in the hardware layer, physical layer and application layer to corresponding layers.

[0017] The present application also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the above method when executing the computer program.

[0018] The present application also provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the above method when executed by a processor.

[0019] The present application also provides a computer program product, which is tangibly stored on a computer-readable medium and includes computer-executable instructions. When the computer-executable instructions are executed, the computer-executable instructions cause at least one processor to perform the method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Implementations of the present disclosure are illustrated by way of example and not limitation in the figures of the accompanying drawings in which like references indicate the same or similar parts.

[0021] FIG1 is a schematic diagram of the process of a method for constructing a multi-layer knowledge graph according to one embodiment of the present application.

[0022] Figure 2 is a schematic diagram of a device for constructing a multi-layer knowledge graph according to one embodiment of the present application.

[0023] Figure 3 is a schematic diagram of a computer device for constructing a multi-layer knowledge graph according to one embodiment of the present application.

[0024] FIG4 is a schematic diagram of a hardware layer according to an embodiment of the present application.

[0025] FIG5 is a schematic diagram of a physical layer according to an embodiment of the present application.

[0026] FIG6 is a schematic diagram of an application layer according to an embodiment of the present application.

[0027] FIG7 is a schematic diagram of connecting a multi-layer knowledge graph according to one embodiment of the present application.

[0028] The reference numerals are as follows: S101-S104 Step 200: Apparatus 201: Module 202: Module 203: Module 204: Module 300: Computer device 302: Processor 304: Memory DETAILED DESCRIPTION

[0029] In the following description, for the purpose of explanation, a large number of specific details are set forth. However, it is understood that the present invention can be implemented without these specific details. In other examples, well-known circuits, structures, and technologies are not shown in detail so as not to affect the understanding of the description.

[0030] References throughout this specification to "an implementation," "an implementation," "an exemplary implementation," "some implementations," "various implementations," etc., indicate that the implementations of the invention being described may include particular features, structures, or characteristics. However, it does not imply that every implementation must include those particular features, structures, or characteristics. Furthermore, some implementations may have some, all, or none of the features described for other implementations.

[0031] The main advantage of using a knowledge graph is that it can connect pieces of knowledge of different types or domains together, and then present this connection in an explicit way, or facilitate the discovery of potential hidden connections. However, the available connections require that the structures of certain subgraphs must be compatible, and how to design a standard and flexible knowledge graph structure remains an open problem.

[0032] Typically, knowledge graphs designed to solve specific problems are structured with specific data characteristics. For example, a knowledge graph used to track the quality of a batch of similar products requires each product to be set up as a separate entity or node, while a knowledge graph used to diagnose production line failures tends to merge all similar devices / units / products into a single entity or node. Therefore, without a universal design, it is difficult to merge small-scale, task-oriented knowledge graphs into a general large-scale knowledge graph, thus weakening the knowledge graph's greatest advantage: connectivity.

[0033] This embodiment of the application proposes a standardized knowledge graph structure that contains three independent but related layers to meet the needs of knowledge organization in common manufacturing scenarios. This structure will cover the requirements of as many different tasks as possible in the manufacturing process and maintain flexibility to support new requirements.

[0034] Furthermore, recent academic research has summarized some typical contents involved in knowledge graphs. These contents can be entity-based, following the definition of traditional ontologies or semantic web, or they can be increasingly text-rich in recent years, containing some more descriptive information - some previous work has also focused on how to capture this knowledge into graphs. At the same time, research is also conducted on dividing nodes into different groups according to their characteristics to facilitate multi-purpose applications or vivid demonstrations. In the embodiments of this application, it is recommended to standardize and expand the above concepts to define how to categorize functionality and versatility in industrial / manufacturing scenarios.

[0035] Based on this, this application discloses a method for constructing a multi-layer knowledge graph, which includes:

[0036] S101: Build a hardware layer knowledge graph based on the target device.

[0037] First, the hardware layer provides an abstract, accurate, and logical description of the physical layer. The hardware layer is concise, clearly illustrated, and clearly displays all the hardware involved in the production / manufacturing scenario. Most of the hardware layer nodes are typically entity-based. As the middle layer in the three-layer architecture, its nodes should be able to be mapped to the physical layer nodes using a one-to-many mapping mechanism.

[0038] As shown in Figure 4, building a hardware-layer knowledge graph includes:

[0039] In some embodiments, in the hardware layer, a basic hierarchical structure (hierarchical structure) and node connections of "Device->Module->Module Part" can be established, for example. It is emphasized that the above concept is a division of hardware, and can also be a concept from large to small, such as "system -> device -> module", "factory -> production line -> equipment", etc. The main role and significance of the hardware layer in this application is to clarify and establish the above hardware concepts, so as to facilitate subsequent adaptation, connection and application with other layers. In some embodiments, the temperature sensor (Temperature sensor) can be installed on Module B, and the vibration sensor (Vibration sensor) can be installed on Module Part A-2. Furthermore, Module Part C-1 and Module Part A-1 are actually the same functional components, but are installed on different modules. In the embodiments of the present application, only information related to failure root cause analysis is focused on, and a complete description of the hardware layer of a device should contain more information.

[0040] S102: Construct a physical layer knowledge graph based on the target device.

[0041] First, any node in the physical layer must exist physically. It can be a product, device, sensor, document, or other visible item, or it can be a gas, photoelectric signal, magnetic field, or other objectively existing but invisible substance. Regardless of the type, the node must satisfy the property of being physically locatable and identifiable. In some cases, a node can also be a batch or representative of multiple products, but only when the individual products in the batch are always considered to be the same. The purpose of this design is to ensure that any individual node in the physical layer is traceable, so that monitoring the node status is meaningful. In addition, through the above method, during the construction of the physical layer, the construction of the node can also be simplified, highlighting important factors such as connection relationships, and avoiding duplication and redundancy.

[0042] As shown in Figure 5, building a physical layer knowledge graph includes:

[0043] Two functionally identical devices operate in parallel: D01 and D02. They have the same hierarchical hardware structure. In some embodiments, D02 lacks a temperature sensor on its Module B (for example, D01-MB has an ST-115 sensor connected, but D02-MB has no connections). Furthermore, within the physical layer, there are some loose spare parts available, such as Reserve Part 1 and Reserve Part 2.

[0044] In the embodiment shown in FIG. 5 , a physical layer corresponding to a target device is constructed on the premise that the target device is the same as that of the above hardware layer.

[0045] S103: Build an application layer knowledge graph based on the target scenario.

[0046] First, the application layer flexibly organizes abstract knowledge related to selected applications. Specifically, the application layer has the following characteristics: In some embodiments, application layer nodes only directly connect to hardware layer nodes, and thus indirectly relate to physical layer nodes. However, in some cases, direct connections from the application layer to the physical layer are also permitted. This allows for flexible connections between the application layer, the physical layer, and the hardware layer.

[0047] In some embodiments, the nodes in the application layer are diverse and can be entity-based or text-rich. The application layer should serve as an interface for any algorithm running on the knowledge graph. In this way, external algorithms can obtain the node information and connection relationships of the entire multi-layer knowledge graph through the application layer for model learning and calculation, which provides the basis and premise for analyzing knowledge in general manufacturing scenarios and understanding the relationship between real objects or real devices corresponding to different layers.

[0048] In the embodiment shown in FIG6 , the application layer may have the following characteristics:

[0049] The root cause is the core information of the diagnostic application, and each root cause should be associated with a solution.

[0050] Root Causes are associated with Errors and Alarms, which may originate from Sensors or other undisclosed sources.

[0051] As shown in Figure 6, the potential path of this application scenario may be: (1) first receive a set of errors and alarms within a certain period of time; (2) secondly find the most likely root cause; (3) then propose a relevant solution; (4) resolve the failure event.

[0052] In addition, engineers and managers can be the actual personnel responsible for the maintenance of the device / module / component.

[0053] S104: Connect the nodes in the hardware layer, physical layer, and application layer to each other in a corresponding manner.

[0054] Figure 7 shows how knowledge in each layer or across different layers should theoretically be connected. For simplicity, Figure 7 only uses dotted lines to indicate a very small number of cross-layer connections and edges. However, in practice, there should be many more cross-layer connections and edges. As shown in Figure 7, the following cross-layer connection paths can be observed, most of which are continuous between adjacent layers:

[0055] - A specific sensor at the physical layer (e.g., SV-101) --> a vibration sensor at the abstract hardware layer (e.g., Sensor Vib) --> an error signal at the application layer (e.g., Error 10001)

[0056] -Root cause of a certain application layer (e.g., Root Cause A-1-alpha) -> Module Part related to the hardware layer (e.g., M_Part A-1) -> Detailed module part of the current work in the physical layer (e.g., D02-MA-P1)

[0057] - Spare part in the physical layer (e.g. Reserve Part 1) -> abstract general part in the hardware layer (e.g. Gen. Part 1)

[0058] - Engineer in the Application layer (e.g. Engineer Jeff) -> Detailed device in the Physical layer (e.g. D01), where the connection omits the intermediate hardware layer.

[0059] In summary, the three-layer knowledge graph structure proposed in the embodiment of the present application is very suitable for manufacturing scenarios and has the following advantages: the physical units in the physical layer and the abstract units in the hardware layer are clearly classified, distinguishing between theoretical problems related to abstract units and practical problems related to physical nodes. The same hardware structure can support various applications without causing confusion, making the functional expansion within the application layer simple and flexible. The three-layer structure itself is highly logical and easy to understand and explain. In this way, various logical relationships or hierarchical relationships in real production can be constructed into a knowledge graph according to the hierarchical concept, and then formed into an overall knowledge graph structure through connection, which is conducive to the analysis of knowledge organization in general manufacturing scenarios and finding the corresponding relationship between real objects or equipment at different layers.

[0060] It should be understood that although the various steps in the flowchart of FIG1 are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in FIG1 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0061] Figure 2 provides a device 200 for constructing a multi-layer knowledge graph. The device 200 includes: a hardware layer module 201 for constructing a hardware layer knowledge graph based on a target device; a physical layer module 202 for constructing a physical layer knowledge graph based on the target device; an application layer module 203 for constructing an application layer knowledge graph based on a target scenario; and a layer connection module 204 for connecting nodes in the hardware layer, physical layer, and application layer to each other.

[0062] Furthermore, the layer connection module 204 is used to: connect the nodes in the application layer with the nodes in the physical layer, and omit the connection with the nodes in the hardware layer.

[0063] Furthermore, the physical layer module 202 is used to: construct nodes in the physical layer, wherein the nodes represent multiple identical products, and the products are physical entities.

[0064] Furthermore, the application layer module 203 is used to: construct the application layer knowledge graph, wherein the application layer knowledge graph serves as the external interface and algorithm interface of the multi-layer knowledge graph.

[0065] It should be noted that the apparatus may include more or fewer modules to implement the described functionality. For example, at least one module in FIG. 2 may be further divided into a plurality of different submodules, each of which is configured to perform at least a portion of the operations described herein in conjunction with the corresponding module. Furthermore, in some examples, the apparatus 200 may further include additional modules for performing other operations already described in the specification. Furthermore, those skilled in the art will appreciate that the exemplary apparatus 200 may be implemented using software, hardware, firmware, or any combination thereof.

[0066] Figure 3 provides a computer device. According to one embodiment, the computer device 300 may include a processor 302, which executes a computer program stored in a memory 304. When the computer program is executed by the processor, the above method is implemented.

[0067] Those skilled in the art will understand that the structure shown in Figure 3 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0068] Those skilled in the art will appreciate that all or part of the processes in the methods for implementing the above-mentioned embodiments can be accomplished by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include processes for the implementation of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the various embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0069] The present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the above steps when the computer program is executed by a processor.

[0070] The present application also provides a computer program product, which is tangibly stored on a computer-readable medium and includes computer-executable instructions. When the computer-executable instructions are executed, the computer-executable instructions cause at least one processor to perform the above method.

[0071] Furthermore, the computer program can be stored and run in the cloud to perform the method. Furthermore, the components of the program can be deployed on multiple devices and the cloud. For example, the corresponding steps can be deployed and run on a local or local computer, or run on different cloud devices, and transmit signals through a communication connection, or can also be deployed and run on a local or local computer. This application does not limit the manner or method, and the corresponding technology can be flexibly deployed to make full use of equipment and technologies such as the cloud, big data, and supercomputing capabilities to execute and complete the method.

[0072] Some implementations of the present disclosure may include articles of manufacture. Articles of manufacture may include storage media for storing logic. Examples of storage media may include one or more types of computer-readable storage media capable of storing electronic data, including volatile or non-volatile memory, removable or non-removable memory, erasable or non-erasable memory, writable or rewritable memory, and the like. Examples of logic may include various software units, such as software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, processes, software interfaces, application program interfaces (APIs), instruction sets, computing codes, computer codes, code segments, computer code segments, words, values, symbols, or any combination thereof. In some implementations, for example, articles of manufacture may store executable computer program instructions that, when executed by a processor, cause the processor to perform the methods and / or operations described herein. Executable computer program instructions may include any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, and the like. Executable computer program instructions can be implemented according to a predefined computer language, method or syntax for commanding a computer to perform a specific function. The instructions can be implemented using any appropriate high-level, low-level, object-oriented, visual, compiled and / or interpreted programming language.

[0073] What has been described above includes examples of the disclosed architecture. It is, of course, not possible to describe every conceivable combination of components and / or methodologies, but those skilled in the art will appreciate that many other combinations and permutations are possible. Therefore, the novel architecture is intended to embrace all such alternatives, modifications, and variations that fall within the spirit and scope of the appended claims.

Claims

1. A method for constructing a multi-layer knowledge graph, wherein: include: Build a hardware-level knowledge graph based on the target device; Constructing a physical layer knowledge graph based on the target device; Build an application-layer knowledge graph based on the target scenario; The nodes in the hardware layer, physical layer and application layer are connected correspondingly between the layers.

2. The method according to claim 1, wherein The inter-layer corresponding connection of the nodes in the hardware layer, the physical layer, and the application layer includes: The nodes in the application layer are connected to the nodes in the physical layer, and the connection with the nodes in the hardware layer is omitted.

3. The method according to claim 1, wherein Based on the target device, a physical layer knowledge graph is constructed, including: Nodes in the physical layer are constructed, wherein the nodes represent a plurality of identical products, and the products are physical entities.

4. As claimed in claim 1, wherein According to the target scenario, build the application layer knowledge graph, including: Construct the application layer knowledge graph, wherein the application layer knowledge graph serves as the external interface and algorithm interface of the multi-layer knowledge graph.

5. A device (200) for constructing a multi-layer knowledge graph, wherein: include: The hardware layer module (201) is used to construct a hardware layer knowledge graph based on the target device; A physical layer module (202), configured to construct a physical layer knowledge graph based on the target device; The application layer module (203) is used to construct an application layer knowledge graph according to the target scenario; The layer connection module (204) is used to connect the nodes in the hardware layer, physical layer and application layer in a corresponding manner between the layers.

6. The device (200) of claim 5, wherein: The layer connection module (204) is used to: The nodes in the application layer are connected to the nodes in the physical layer, and the connection with the nodes in the hardware layer is omitted.

7. The device (200) of claim 5, wherein: The physical layer module (202) is configured to: Nodes in the physical layer are constructed, wherein the nodes represent a plurality of identical products, and the products are physical entities.

8. The apparatus (200) of claim 5, wherein: The application layer module (203) is used to: Construct the application layer knowledge graph, wherein the application layer knowledge graph serves as the external interface and algorithm interface of the multi-layer knowledge graph.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

11. A computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions which, when executed, cause at least one processor to perform the method according to any one of claims 1 to 4.

Images