BIM-based knowledge graph system

Abstract

Embodiments of the present application disclose a BIM-based knowledge graph system. A specific implementation of the method includes: a data acquisition module configured to acquire and parse data of a coal preparation plant information system; a data governance module configured to govern the data acquired by the data acquisition module, and to obtain an entity topic of a knowledge graph by correlating and aggregating entities under a BIM business scenario of the coal preparation plant; a knowledge graph construction module configured to construct the knowledge graph by extracting entity attributes and combining relationships between entities according to the entity topic; and a knowledge graph intelligent application module configured to provide data intelligent application based on the knowledge graph obtained by the knowledge graph construction module. The implementation provides an automated process from data acquisition, parsing, and governance to knowledge graph construction and application, thereby improving the knowledge utilization efficiency of the coal preparation plant.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of computer, and particularly relate to a knowledge graph system based on BIM. BACKGROUND

[0002] BIM(Building Information Modeling) is a new tool for architecture, engineering and civil engineering. The technology is a data tool applied to engineering design, construction and management. Through this three-dimensional modeling technology, data modeling of coal preparation plant can be completed, that is, data of business is realized to build a three-dimensional visual management platform.

[0003] Knowledge graph(Knowledge Graph) is also known as knowledge domain visualization or knowledge field mapping map in the field of library and information. It is a series of various graphs that display the development process and structural relationship of knowledge. It uses visualization technology to describe knowledge resources and their carriers, and excavates, analyzes, constructs, draws and displays knowledge and their mutual relationships.

[0004] At present, there are deficiencies in the construction and application of the knowledge graph of the coal preparation plant, and there is a lack of a process from data collection, analysis, governance to knowledge graph construction and application that fits the business scene of the coal preparation plant. SUMMARY

[0005] Embodiments of the present application propose a knowledge graph system based on BIM. The system comprises: a data collection module configured to collect and analyze data of an information system of a coal preparation plant; a data governance module configured to govern the data collected by the data collection module, and to obtain entities of a knowledge graph based on association and aggregation of entities under a BIM business scene of the coal preparation plant; a knowledge graph construction module configured to construct the knowledge graph based on entity attribute extraction and relationships between entities according to the entity monograph; and a knowledge graph intelligent application module configured to provide data intelligent application based on the knowledge graph obtained by the knowledge graph construction module.

[0006] In some embodiments, the system further comprises a retrieval module configured to provide a knowledge graph digital archive retrieval service.

[0007] In some embodiments, the retrieval module is further configured to implement multi-index full-text retrieval and fuzzy query matching of the graph database based on an index function of a Nebula Graph graph database improved through an ElasticSearch search engine.

[0008] In some embodiments, the data governance module is further configured to govern the data collected by the data collection module based on the data resource pool, and the data resource pool of the informatization system of the coal preparation plant includes an original data area, a standard data area, a data theme area, and an application theme area.

[0009] In some embodiments, the entity theme includes a coal entity theme, a device entity theme, a space entity theme, a personnel entity theme, a time entity theme, an event entity theme, a process entity theme, and a business entity theme.

[0010] In some embodiments, the system further includes an entity and relationship extraction module configured to automatically extract entities and relationships of the BIM knowledge graph of the coal preparation plant based on natural language processing technology.

[0011] In some embodiments, the knowledge graph construction module is configured to realize cross-knowledge graph data fusion and update based on knowledge graph fusion technology.

[0012] In some embodiments, the data intelligent application includes a coal preparation plant device health state classification, and the knowledge graph intelligent application module is further configured to perform data processing on the device original data in the knowledge graph to obtain a continuous data set, perform instantaneous feature extraction, periodic feature extraction, and basic model fitting on the continuous data set, and integrate to obtain a device historical baseline model, and train the device historical baseline model to obtain a coal preparation plant device health state classification model.

[0013] In some embodiments, the data intelligent application includes a coal preparation plant device fault early warning monitoring, and the knowledge graph intelligent application module is further configured to perform data classification and aggregation on the device original data in the knowledge graph to obtain a first target data set, integrate a fault prediction model constructed based on an association algorithm, a fault time and probability prediction model constructed based on a probability distribution, and a fault time and probability prediction model constructed based on an HSMM to obtain a coal preparation plant device fault prediction model.

[0014] In some embodiments, the data intelligent application includes a coal preparation plant device safety risk assessment, and the knowledge graph intelligent application module is further configured to perform data classification and aggregation on the device original data in the knowledge graph to obtain a second target data set, obtain a feature set of the second target data set by constructing a general evaluation domain and a special evaluation domain, extract main features from the feature set to obtain a main feature set, and train and optimize a logistic regression model based on the main feature set to obtain a coal preparation plant device safety risk assessment model.

[0015] The BIM-based knowledge graph system provided by the embodiment of the application provides an automatic process from data collection, analysis and management to knowledge graph construction and application, and improves the knowledge utilization efficiency of the coal preparation plant. BRIEF DESCRIPTION OF DRAWINGS

[0016] Other features, objects and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments, made with reference to the attached drawings:

[0017] Figure 1 is a structural schematic diagram of the BIM-based knowledge graph system of the application;

[0018] Figure 2 is a schematic diagram of the entity relationship of the coal preparation plant in the embodiment of the application;

[0019] Figure 3 is a schematic diagram of the function architecture of the knowledge graph system of the coal preparation plant in the embodiment of the application;

[0020] Figure 4A is a schematic diagram of the equipment health state classification model of the coal preparation plant in the embodiment of the application;

[0021] Figure 4B is a schematic diagram of the equipment fault prediction model of the coal preparation plant in the embodiment of the application;

[0022] Figure 4C is a schematic diagram of the equipment safety risk assessment model of the coal preparation plant in the embodiment of the application;

[0023] Figure 5 is a schematic diagram of the technical route of the knowledge graph system of the coal preparation plant in the embodiment of the application;

[0024] Figure 6 is a structural schematic diagram of a computer system suitable for implementing some embodiments of the application. DETAILED DESCRIPTION

[0025] The application will be further described in detail below with reference to the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related application, and not to limit the application. In addition, it should be noted that only the parts related to the application are shown in the drawings for ease of description.

[0026] It should be noted that the embodiments in the application and the features in the embodiments can be combined with each other without conflict. The application will be described in detail below with reference to the drawings and embodiments.

[0027] REFERENCE Figure 1FIG. 1 shows the structure 100 of one embodiment of the BIM-based knowledge graph system according to the present application. The BIM-based knowledge graph system comprises the following modules:

[0028] Module 101, a data collection module, is configured to collect and parse data of the coal preparation plant information system.

[0029] In this embodiment, the data collection module can collect and parse data of the coal preparation plant information system according to the data collection task or according to the set data collection rules in response to obtaining the data collection task. The parsing can be to structure the unstructured data or semi-structured data through protocols or machine learning methods. In addition, when encountering cross-system and cross-database situations, the data collection module also needs to perform protocol adaptation for data collection. The data collection module can provide data support for the BIM full life cycle management of the coal preparation plant.

[0030] Module 102, a data governance module, is configured to govern the data collected by the data collection module and to obtain the entity special topic of the knowledge graph according to the association and aggregation of the entities in the BIM business scenario of the coal preparation plant.

[0031] In this embodiment, governing the data can include data cleaning and processing, standardization and other operations. In addition, considering the particularity of the BIM business scenario of the coal preparation plant, when planning the equipment entity of the coal preparation plant, the production and operation attributes, online monitoring attributes, digital archive attributes, VR maintenance and repair attributes, and intelligent analysis attributes around the equipment entity can be sorted out, and the equipment can be fully managed in the BIM full life cycle from design, modeling, production, and transportation.

[0032] In some optional implementations of this embodiment, the data governance module is further configured to govern the data collected by the data collection module based on the data resource pool. The data resource pool of the coal preparation plant information system comprises an original data area, a standard data area, a data theme area, and an application special topic area. The data in the data source can be directly stored in or stored in the original data area after being structured. The original data area is cleaned and processed, and the data is standardized according to the pre-set standard to obtain the data of the standard data area. The data of the standard data area is sorted, divided, and / or associated and aggregated to obtain the data of the data theme area. The data of the data theme area is field screened and / or associated and aggregated to obtain the data of the application special topic area.

[0033] Here, the data resource pool can be a resource pool of a big data platform such as CPIM (Certified in Planning & Inventory Management), and by adopting the idea of data hierarchical management, the multi-source heterogeneous data of the information system of the coal preparation plant is divided into the original area, the standard area, the theme area and the special theme area, which can improve the management efficiency and data reusability of the knowledge graph special theme data, and guarantee the data support of the BIM knowledge graph construction of the coal preparation plant.

[0034] In some optional implementations of the present embodiment, the entity special theme can include: a coal entity special theme, a device entity special theme, a space entity special theme, a personnel entity special theme, a time entity special theme, an event entity special theme, a process entity special theme and a business entity special theme. The specific special theme division can be performed according to actual needs, for example, the event entity special theme can be further divided into a fault event entity special theme and a safety event entity special theme.

[0035] Module 103, knowledge graph construction module, is configured to extract entity attributes according to entity special themes and construct a knowledge graph combining the relationships between entities.

[0036] In the present embodiment, the knowledge graph construction module can utilize the fusion analysis module function of a big data platform such as CPIM to respectively complete the following work: knowledge graph schema design of the coal preparation plant, business entity relationship analysis of the coal preparation plant, device entity attribute extraction of the coal preparation plant, knowledge graph data storage of the coal preparation plant and accumulation of domain knowledge experts of the coal preparation plant. See Figure 2 , Figure 2 A schematic diagram of the entity relationship of the coal preparation plant.

[0037] In addition, in some optional implementations of the present embodiment, the system further includes an entity and relationship extraction module, which is configured to realize automatic extraction of the BIM knowledge graph entities and relationships of the coal preparation plant based on natural language processing technology.

[0038] In some optional implementations of the present embodiment, the knowledge graph construction module is configured to realize cross-knowledge graph data fusion and update based on knowledge graph fusion technology.

[0039] Module 104, knowledge graph intelligent application module, is configured to provide data intelligent application based on the knowledge graph obtained by the knowledge graph construction module.

[0040] See Figure 3 , Figure 3An example of the function architecture of the knowledge graph system of the coal preparation plant is shown in FIG. 1. The intelligent application module of the knowledge graph can provide data intelligent applications such as the safety risk management analysis application of the coal preparation plant, the digital archive management retrieval application of the construction of the coal preparation plant, the equipment state monitoring and fault early warning application of the coal preparation plant, the BIM+ production system integrated management application of the coal preparation plant, and the BIM+ VR equipment virtual maintenance application of the coal preparation plant to the upper layer of the coal washing engineering digital construction center application system and the coal preparation plant digital management application system through the business decision engine, the intelligent recommendation engine, the full-text retrieval engine, and the visualization service engine provided by the fusion analysis module of the CPIM big data platform. In addition, the graph vectorization analysis and mining of the BIM knowledge graph of the coal preparation plant can be realized based on deep learning.

[0041] In some optional implementations of the present embodiment, the data intelligent application includes the health state classification of the equipment of the coal preparation plant, and the intelligent application module of the knowledge graph is further configured to: perform data processing on the original data of the equipment in the knowledge graph to obtain a continuous data set; perform instantaneous feature extraction, periodic feature extraction, and basic model fitting on the continuous data set to obtain an equipment historical baseline model; and train the equipment health state classification model based on the equipment historical baseline model. Referring to FIG. 2, the data processing can include data aggregation, data cleaning, pre-fusion, pre-processing, and the like, and the equipment health state classification model of the coal preparation plant can be trained by a support vector machine or other classification model. Figure 4A

[0042] In some optional implementations of the present embodiment, the data intelligent application includes the fault early warning monitoring of the equipment of the coal preparation plant, and the intelligent application module of the knowledge graph is further configured to: perform data classification and aggregation on the original data of the equipment in the knowledge graph to obtain a first target data set; integrate a fault prediction model based on an association algorithm, a fault time and probability prediction model based on a probability distribution, and a fault time and probability prediction model based on a hidden semi-Markov model (Hiddensemi-Markov models, HSMM) to obtain a fault prediction model of the equipment of the coal preparation plant. Referring to FIG. 3, the data classification can be a grouping classification of the equipment, and then the HSMM parameter estimation model based on the modified particle swarm optimization (MPSO) can be constructed and assumed to perform fault rate calculation model construction and conditional reliability calculation model construction, and the fault time and probability prediction model based on the HSMM can be obtained from the two. Compared with a single model, the three models can obtain a more effective fault prediction model. Figure 4B

[0043] ​​In some optional implementations of the embodiment, the data intelligent application includes a coal preparation plant equipment safety risk assessment; and the knowledge graph intelligent application module is further configured to: perform data classification and aggregation on the equipment original data in the knowledge graph to obtain a second target data set; obtain a feature set of the second target data set through the constructed general evaluation domain and the special evaluation domain; perform main feature extraction on the feature set to obtain a main feature set; and perform logic regression model training and optimization based on the main feature set to obtain a coal preparation plant equipment safety risk assessment model. See Figure 4C The data classification can be grouping and classification of the equipment. The above three implementations propose a coal preparation plant equipment safety risk assessment model, an equipment historical baseline health model, and an equipment fault early warning monitoring model by analyzing the particularity of the coal preparation plant business scenario, thereby enriching the intelligent attribute dimension of the knowledge graph construction based on BIM.

[0044] See Figure 5 , Figure 5 is a schematic diagram of a technical route of the coal preparation plant knowledge graph system. The technical roadmap of the data intelligent application construction is divided into four stages. The core task in the first stage is to sort out the entities and relationships of the coal preparation plant knowledge graph. The core task in the second stage is to construct the knowledge graph special library of the CPIM big data platform data resource pool. The core task in the third stage is to implement and construct the five intelligent application scenarios of the coal preparation plant. The core task in the last stage is to plan the function modules of the digital management application system of the coal preparation plant, and to truly implement the digital intelligent application from planning and implementation to the coal preparation plant application landing, so as to realize the closed loop of business data, data asset, asset service, and service scenario.

[0045] In some optional implementations of the embodiment, the system further includes a retrieval module configured to provide a knowledge graph digital archive retrieval service. The knowledge graph digital archive retrieval service can be realized through an open source search engine.

[0046] In some optional implementations of the embodiment, the retrieval module is further configured to realize multi-index full-text retrieval and fuzzy query matching of the graph database based on the index function of the Nebula Graph graph database improved through the ElasticSearch search engine. Elasticsearch is a search server based on Lucene. It provides a distributed multi-user full-text search engine based on the RESTful web interface. Nebula Graph is an open source distributed graph database with horizontal expansion, strong data consistency, high availability, and a SQL-like query language.

[0047] The method provided by the above embodiments of the present application is configured to collect and parse data of the information system of the coal preparation plant through a data collection module; configured to govern the data collected by the data collection module, and to obtain an entity special topic of a knowledge graph according to correlation and aggregation of entities under a BIM business scenario of the coal preparation plant; configured to construct the knowledge graph according to entity attribute extraction of the entity special topic and the relationship between entities; and configured to provide data intelligent application based on the knowledge graph obtained by the knowledge graph construction module, thereby providing an automatic process from data collection, parsing and governance to knowledge graph construction and application, and improving knowledge utilization efficiency of the coal preparation plant.

[0048] Reference will be made to the following Figure 6 which shows a structural diagram of a computer system 600 suitable for implementing embodiments of the present application. Figure 6 The computer system shown is merely an example and should not impose any limitation on the functions and use range of embodiments of the present application.

[0049] As shown in Figure 6 , the computer system 600 includes a central processing unit (CPU) 601 which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or loaded from a storage portion 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the system 600 are also stored in the RAM 603. The CPU 601, the ROM 602 and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0050] The following components can be connected to the I / O interface 605: an input portion 606 including, for example, a keyboard, a mouse, etc.; an output portion 607 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including, for example, a hard disk, etc.; and a communication portion 609 including, for example, a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as necessary. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 610 as necessary, so that a computer program read therefrom is installed in the storage portion 608 as necessary.

[0051] In particular, the processes described above with reference to the flow charts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for performing the methods illustrated by the flow charts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-described functions defined in the methods of the present application are performed. It should be noted that the computer readable medium described in the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable medium may, for example, be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples of the computer readable medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer readable program code is carried. Such a propagated data signal can take a variety of forms, including but not limited to, an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium that can be used to carry or store a program for use by or in connection with an instruction execution system, apparatus or device. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to, wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the above.

[0052] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0053] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0054] The modules described in the embodiments of the present application can be implemented in the form of software, or can be implemented in the form of hardware. The described modules can also be arranged in a processor, for example, can be described as: a processor includes a data acquisition module, a data governance module, a knowledge graph construction module, and a knowledge graph intelligent application module. Among them, the names of these modules do not constitute a limitation on the modules themselves in some cases, for example, the data acquisition module can also be described as: "a module configured to acquire and parse the data of the information system of the coal preparation plant".

[0055] The above description is only the preferred embodiment of the present application and the explanation of the technical principles. It should be understood by those skilled in the art that the scope of the protection of the present application is not limited to the technical solutions formed by the specific combinations of the above technical features. It should also cover other technical solutions formed by the combinations of the above technical features or their equivalent features without departing from the concept of the present application. For example, the technical solutions formed by the mutual replacement of the above features and the technical features with similar functions disclosed (but not limited to) in the present application.

Claims

1. A BIM-based knowledge graph system, comprising: a data collection module configured to collect and parse data of a coal preparation plant information system; a data governance module configured to govern the data collected by the data collection module, and to obtain entity topics of a knowledge graph by correlating and aggregating entities under a BIM business scenario of a coal preparation plant; a knowledge graph construction module configured to construct a knowledge graph by extracting entity attributes according to the entity topics and combining relationships between the entities; the knowledge graph construction module utilizes a fusion analysis module function of a CPIM big data platform to respectively complete knowledge graph mode design of a coal preparation plant, business entity relationship analysis of the coal preparation plant, equipment entity attribute extraction of the coal preparation plant, knowledge graph data storage of the coal preparation plant, and accumulation of domain knowledge of the coal preparation plant; a knowledge graph intelligent application module configured to provide data intelligent applications based on the knowledge graph obtained by the knowledge graph construction module; the data intelligent applications include coal preparation plant equipment health state classification, and the knowledge graph intelligent application module is further configured to: perform data processing on original data of equipment in the knowledge graph to obtain a continuous data set; perform instantaneous feature extraction, periodic feature extraction, and basic model fitting on the continuous data set to obtain an equipment historical baseline model; train a coal preparation plant equipment health state classification model based on the equipment historical baseline model; the data intelligent applications include coal preparation plant equipment fault early warning monitoring, and the knowledge graph intelligent application module is further configured to: perform data classification and aggregation on original data of equipment in the knowledge graph to obtain a first target data set; integrate a fault prediction model constructed based on a correlation algorithm, a fault time and probability prediction model constructed based on a probability distribution, and a fault time and probability prediction model constructed based on a hidden semi-Markov model (HSMM) to obtain a coal preparation plant equipment fault prediction model; the data intelligent applications include coal preparation plant equipment safety risk assessment, and the knowledge graph intelligent application module is further configured to: perform data classification and aggregation on original data of equipment in the knowledge graph to obtain a second target data set; obtain a feature set of the second target data set by constructing a general evaluation domain and a specific evaluation domain; perform main feature extraction on the feature set to obtain a main feature set; perform logistic regression model training and optimization based on the main feature set to obtain a coal preparation plant equipment safety risk assessment model.

2. The system of claim 1, wherein: the system further comprises a retrieval module configured to: provide a knowledge graph digital archive retrieval service.

3. The system of claim 2, wherein: the retrieval module is further configured to: based on an index function of a Nebula Graph graph database improved by an ElasticSearch search engine, implement multi-index full-text retrieval and fuzzy query matching of the graph database.

4. The system of claim 1, wherein: the data governance module is further configured to: Based on the hierarchical management of the data resource pool, the data collected by the data collection module, the data resource pool of the coal preparation plant information system includes the original data area, the standard data area, the data theme area and the application theme area.

5. The system of claim 1, wherein, The entity theme includes: coal entity theme, equipment entity theme, space entity theme, personnel entity theme, time entity theme, event entity theme, process entity theme and business entity theme.

6. The system of claim 1, wherein, The system further comprises an entity and relationship extraction module, which is configured to: Based on natural language processing technology, the BIM knowledge graph entity and relationship of the coal preparation plant are automatically extracted.

7. The system of claim 1, wherein, The knowledge graph construction module is configured to: Based on the knowledge graph fusion technology, the data fusion update across the knowledge graphs is realized.

Images