A method, system and device for digital twin of events

Abstract

This application discloses a method, system, and device for event digital twin generation, relating to the field of digital twin technology. The method includes: constructing a digital twin model of an event; creating a horizontally scalable non-relational database; acquiring multiple pieces of information about each object in the event in real time and storing them in the non-relational database as an array; treating each object and each piece of information about each object in the non-relational database as an entity, extracting entity relationships, and constructing a knowledge graph for the event; mapping the multiple pieces of information about each object acquired in real time to the digital twin model; and optimizing the mapped digital twin model based on the event's knowledge graph to obtain a real-time digital twin model of the event. This application can optimize the digital twin model based on the changing relationships between objects, continuously improving the universality and accuracy of the digital twin model mapping.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital twinning, in particular to an event digital twinning method, system and device. BACKGROUND

[0002] Digital twinning is a simulation process integrating multi-discipline, multi-physical quantity, multi-scale and multi-probability, which is completed in a virtual space by making full use of physical models, sensor updates, operation history and other data. Digital twinning establishes a combined, associated and unified query platform for existing data.

[0003] At present, the digital twinning method can feed back the state of the event in real time, but cannot reflect the full change relationship between objects in the development process of the event. When the development changes exceed the original system setting boundary, the description system will be difficult or impossible to realize under the original system, affecting the universality and accuracy of the digital twinning model. SUMMARY

[0004] The purpose of the present application is to provide an event digital twinning method, system and device, which can optimize the digital twinning model according to the change relationship between objects and objects, and continuously improve the universality and accuracy of the digital twinning model mapping.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In a first aspect, the present application provides an event digital twinning method, comprising: building a digital twinning model of an event; creating a horizontally expandable non-relational database; acquiring multiple pieces of information of each object contained in the event in real time, and storing the multiple pieces of information in an array form to the non-relational database; extracting entity relationships by taking each object in the non-relational database and each piece of information of each object as an entity, and constructing a knowledge graph of the event; mapping the multiple pieces of information of each object acquired in real time to the digital twinning model; and optimizing the mapped digital twinning model according to the knowledge graph of the event, to obtain a real-time digital twinning model of the event.

[0007] In a second aspect, the present application provides an event digital twinning system, comprising: a non-relational database, a processing unit and a human-computer interaction unit; the human-computer interaction unit and the processing unit are connected with the non-relational database; the human-computer interaction unit is configured to record multiple pieces of information of each object contained in an event in real time, and store the multiple pieces of information to the non-relational database; the processing unit is configured to build a digital twinning model of the event, and extract relationships between entities by taking each object in the non-relational database and each piece of information of each object as an entity, to construct a knowledge graph of the event; map the multiple pieces of information of each object acquired in real time to the digital twinning model according to the knowledge graph of the event, to obtain a real-time digital twinning model of the event; and the human-computer interaction unit is further configured to display the real-time digital twinning model of the event.

[0008] In a third aspect, the present application provides a computer device, comprising a memory, a processing unit, and a computer program stored in the memory and executable on the processing unit, wherein the processing unit executes the computer program to implement the event digital twin method according to any one of the above.

[0009] According to the specific embodiments provided in the present application, the present application has the following technical effects:

[0010] The present application provides an event digital twin method, system and device, creates a non-relational database supporting horizontal expansion, and stores objects and information in the form of arrays to the non-relational database. Since the non-relational database can be dynamically horizontally expanded according to actual needs, it can adapt to various application scenarios and data needs. By regarding each object in the non-relational database and each piece of information of each object as an entity, extracting entity relationships, and constructing a knowledge graph of the event, the knowledge graph connects the associations between entities in the form of edges, thereby reflecting the development and change process of objects and information in the event through entity nodes and edges, adjusting and optimizing the mapped digital twin model, and continuously improving the generality and accuracy of the digital twin model mapping. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0012] Figure 1 An application environment diagram of an event digital twin method according to an embodiment of the present application;

[0013] Figure 2 A flowchart of an event digital twin method according to an embodiment of the present application;

[0014] Figure 3 A structural diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0016] The above purposes, features and advantages of the present application will be more apparent and understandable, and the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0017] The event digital twin method provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104. The data storage system can be separately arranged, or integrated on the server 104, or placed on a cloud or other server. The terminal 102 can send multiple pieces of information of each object contained in an event to the server 104. After receiving the multiple pieces of information of each object contained in the event, the server 104 builds a digital twin model of the event for the multiple pieces of information of each object contained in the event; creates a non-relational database supporting horizontal expansion; obtains the multiple pieces of information of each object contained in the event in real time, and stores the multiple pieces of information in an array form to the non-relational database; extracts entity relationships by taking each object and each piece of information of each object in the non-relational database as an entity, and constructs a knowledge graph of the event; maps the multiple pieces of information of each object obtained in real time to the digital twin model according to the knowledge graph of the event, and obtains a real-time digital twin model of the event. The server 104 can feed back the obtained real-time digital twin model of the event to the terminal 102. In addition, in some embodiments, the event digital twin method can also be implemented by the server 104 or the terminal 102 alone, for example, the terminal 102 can directly perform event digital twin for the multiple pieces of information of each object contained in the event, or the server 104 can obtain the multiple pieces of information of each object contained in the event from the data storage system, and perform event digital twin for the multiple pieces of information of each object contained in the event.

[0018] The terminal 102 can be, but is not limited to, various desktop computers, notebook computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0019] In an exemplary embodiment, as shown in Figure 2 An event digital twin method is provided, which is executed by a computer device, specifically, can be executed by a terminal or a server, or both, in the embodiments of the present application, taken as an example of the server 104 in Figure 1 The method includes the following steps 201 to 206.

[0020] Step 201: build a digital twin model of the event.

[0021] Step 202: create a non-relational database supporting horizontal expansion.

[0022] Step 203: obtain multiple pieces of information of each object contained in the event in real time, and store them in an array form in the non-relational database.

[0023] Step 204: extract entity relationships by taking each object and each piece of information of each object in the non-relational database as an entity, and build a knowledge graph of the event.

[0024] Step 205: map the multiple pieces of information of each object obtained in real time to the digital twin model.

[0025] Step 206: optimize the mapped digital twin model according to the knowledge graph of the event, and obtain a real-time digital twin model of the event.

[0026] The steps 201 to 206 are implemented to create a non-relational database supporting horizontal expansion, and objects and information are stored in an array form in the non-relational database. Since the non-relational database can be dynamically expanded horizontally according to actual needs, it can adapt to various application scenarios and data requirements. By taking each object and each piece of information of each object in the non-relational database as an entity, extracting entity relationships, and building a knowledge graph of the event, the knowledge graph connects the associations between entities in the form of edges, thereby reflecting the development and change process of objects and information in the event through entity nodes and edges, adjusting and optimizing the mapped digital twin model, and continuously improving the generality and accuracy of the digital twin model mapping.

[0027] In another exemplary embodiment of the present application, the non-relational database supporting horizontal expansion built in the above step 202 does not need to define a data structure in advance, and can adapt to various application scenarios and data requirements.

[0028] In another exemplary embodiment of the present application, the event in the above step 201 is the most basic form of nature and human society. The most basic form of nature and human society can be people, land, events, objects, and organizations, etc.

[0029] In another exemplary embodiment of the present application, in the above step 202, multiple pieces of information of each object contained in the event are obtained in real time, which can include: associated object number, relationship description, relationship explanation, relationship start and end time, entry time, entry person, remarks, etc.

[0030] In another example embodiment of the present application, each piece of information of each object contained in the real-time acquired event is classified and described in a scene language (non-standard or metadata) in the non-relational database. For example, when the object is a certain person, if the certain person speaks in a dialect, the dialect is still stored in the non-relational database. Then, when the knowledge graph is constructed, different languages expressing the same meaning need to be divided into the same category.

[0031] In another example embodiment of the present application, in order to clarify the object relationship and the development process, the integrity and correlation of the event can be revealed by constructing the knowledge graph. Then, the above step 204 can be replaced by the following steps 301-303:

[0032] Step 301: Each object and each piece of information of each object in the non-relational database is taken as an entity, and two entities form an entity pair.

[0033] Step 302: Extract the relationship of the entity pair.

[0034] Step 303: Map the entity to a node, and map the extracted entity pair relationship to an edge to obtain the knowledge graph of the event.

[0035] The knowledge graph is a technical method for describing knowledge and modeling the correlation between all things in the world by using a graph model. The knowledge graph is composed of nodes and edges. The node can be an entity, such as a person, a book, etc., or an abstract concept, such as artificial intelligence, etc. The edge can be an attribute of the entity, such as a name, a book name, or a relationship between entities, such as a friend.

[0036] Through the boundaryless storage of the non-relational database, and then mapping the stored data to the knowledge graph, the full change relationship between the objects in the development process of the event can be found in the knowledge graph.

[0037] In another example embodiment of the present application, the knowledge graph can be dynamically updated, and then after the above step 204, the method can further include the following steps 401-403. Among them:

[0038] Step 401: Convert the newly entered object or information into structured data.

[0039] Step 402: Extract and tokenize the structured data.

[0040] Step 403: Mine the relationship between the tokenized entity and the entity in the current knowledge graph, and generate an edge to obtain the latest knowledge graph of the event.

[0041] The knowledge graph is constantly updated with the update of the data.

[0042] In another example embodiment of the present application, the knowledge graph describes concepts, entities and their relationships in the objective world in a structured form, and can be applied in the fields of search, recommendation, intelligent question answering, etc. The knowledge graph-based search includes semantic search, relationship search, and structured presentation, etc. After step 204, the method can further query nodes and paths in the knowledge graph of the event according to the search request.

[0043] In another example embodiment of the present application, the knowledge graph can be logically divided into two levels of schema layer and data layer. The data layer is mainly composed of a series of facts, and the knowledge is stored in units of facts. If the fact is expressed by a triple (entity 1, relationship, entity 2), (entity, attribute, attribute value), a graph database can be selected as the storage medium, such as the open source Neo4j, Twitter's FlockDB, sones' GraphDB, etc. After step 204, the method can further extract triple data from the non-relational database and store the triple data in the graph database. For example, the Neo4j graph database is used to store data in the form of a directed graph.

[0044] According to the knowledge graph of the event, the mapped digital twin model can be optimized to restore the change process of each object contained in the event. The digital twin can realize real-time monitoring and analysis of the event by integrating with the knowledge graph knowledge. The system of the digital twin model of the present application theoretically has a boundaryless normalized digital twin management architecture. When the development and change exceed the original system boundary, it can still be realized under the original system.

[0045] Based on the same inventive concept, the present application also provides an event digital twin system for implementing the event digital twin method described above. The implementation scheme of the system for solving the problem is similar to the implementation scheme described in the above method, so the specific limitations in one or more event digital twin system embodiments provided below can refer to the limitations of the event digital twin method in the above, which will not be repeated here.

[0046] In an example embodiment, an event digital twin system is provided, comprising a non-relational database, a processing unit and a human-computer interaction unit. The human-computer interaction unit and the processing unit are connected with the non-relational database; the human-computer interaction unit is configured to record in real time a plurality of pieces of information of each object contained in an event and store the plurality of pieces of information into the non-relational database; the processing unit is configured to build a digital twin model of the event, extract the relationship between entities by taking each object and each piece of information of each object in the non-relational database as the entity, and construct a knowledge graph of the event; map the plurality of pieces of information of each object acquired in real time to the digital twin model; optimize the mapped digital twin model according to the knowledge graph of the event to obtain a real-time digital twin model of the event; and the human-computer interaction unit is further configured to display the real-time digital twin model of the event.

[0047] As an optional implementation, the event digital twin system further comprises a graph database. The graph database is configured to store the knowledge graph of the event.

[0048] In an example embodiment, a computer device is provided, which can be a server or a terminal. An internal structure diagram of the computer device can be as shown in Figure 3 The computer device comprises a processing unit, a memory, an input / output interface (I / O) and a communication interface. The processing unit, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processing unit of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store a real-time digital twin model of an event. The input / output interface of the computer device is configured to exchange information between the processing unit and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processing unit to implement an event digital twin method.

[0049] Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can comprise more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an example embodiment, a computer device is provided, comprising a memory and a processing unit, the memory storing a computer program, and the processing unit implementing the steps in the above method embodiments when executing the computer program.

[0050] Any combination of the technical features in the above embodiments can be made. For the sake of brevity, the foregoing description has not described all possible combinations of the technical features in the above embodiments, however, it is understood that any combination of the technical features is within the scope of the present disclosure as long as there is no contradiction.

[0051] The principles and implementation manners of the present application are described herein by using specific examples, and the above embodiments are only used to help understand the method and core idea of the present application; meanwhile, according to the idea of the present application, the specific implementation manners and application range can be changed by those skilled in the art. In conclusion, the content of the present description should not be understood as a limitation of the present application.

Claims

1. An event digital twin method, characterized in that, The method comprises the following steps: building a digital twin model of the event; creating a non-relational database supporting horizontal expansion; obtaining in real time a plurality of pieces of information of each object included in the event and storing the plurality of pieces of information in an array form in the non-relational database; each piece of information is classified and described in a scene language in the non-relational database; the scene language includes non-standard or metadata; each object and each piece of information in the non-relational database is taken as an entity, two entities form an entity pair, the entity relationship is extracted, and a knowledge graph of the event is constructed; mapping the plurality of pieces of information of each object obtained in real time to the digital twin model; optimizing the mapped digital twin model according to the knowledge graph of the event to obtain a real-time digital twin model of the event; storing the data in the non-relational database, and then mapping the stored data to the knowledge graph to find the full change relationship between the objects in the development process of the event in the knowledge graph; the system in which the digital twin model is located has a theoretically unlimited normalized digital twin management architecture, and the development change can still be realized in the original system when the development change exceeds the boundary set by the original system.

2. The event digital twin method of claim 1, wherein, The event includes the most basic forms of nature and human society.

3. The event digital twin method of claim 1, wherein, The method for constructing the knowledge graph of the event by taking each object and each piece of information of the object in the non-relational database as an entity and extracting the entity relationship comprises the following steps: taking each object and each piece of information of the object in the non-relational database as an entity, and forming an entity pair with two entities; extracting the relationship of the entity pair; mapping the entity to a node and the extracted relationship of the entity pair to an edge to obtain the knowledge graph of the event.

4. The event digital twin method of claim 1, wherein, The method for constructing the knowledge graph of the event by taking each object and each piece of information of the object in the non-relational database as an entity and extracting the entity relationship further comprises the following steps: transforming the newly recorded object or information into structured data; extracting and dividing the structured data; mining the relationship between the divided entity and the entity in the current knowledge graph, and generating an edge to obtain the latest knowledge graph of the event.

5. The event digital twin method of claim 1, wherein, The method for constructing the knowledge graph of the event by taking each object and each piece of information of the object in the non-relational database as an entity and extracting the entity relationship further comprises the following steps: querying the node and the path in the knowledge graph of the event according to a search request.

6. The event digital twin method of claim 1, wherein, The method for constructing the knowledge graph of the event by taking each object and each piece of information of the object in the non-relational database as an entity and extracting the entity relationship further comprises the following steps: extracting triple data from the non-relational database and storing the triple data in a graph non-relational database.

7. An event digital twin system, characterized in that, The event digital twin system is used to implement the event digital twin method in any one of claims 1-6, and the event digital twin system comprises a non-relational database, a processing unit and a human-computer interaction unit. The human-computer interaction unit and the processing unit are connected with the non-relational database. The human-computer interaction unit is used to record in real time a plurality of pieces of information of each object included in the event and store the plurality of pieces of information in the non-relational database. The processing unit is configured to build a digital twin model of the event, extract the relationship between entities by taking each object in a non-relational database and each piece of information of each object as an entity, and construct a knowledge graph of the event; map the multiple pieces of information of each object obtained in real time to the digital twin model; and optimize the mapped digital twin model according to the knowledge graph of the event to obtain a real-time digital twin model of the event. The human-computer interaction unit is further configured to display the real-time digital twin model of the event.

8. The event digital twin system of claim 7, wherein, The event digital twin system further comprises a graph database. The graph database is configured to store the knowledge graph of the event.

9. A computer device comprising: A memory, a processing unit, and a computer program stored on the memory and executable on the processing unit, wherein the processing unit executes the computer program to implement the event digital twin method of any one of claims 1-6.

Images