Construction method and device of coal mine disaster prediction knowledge base and electronic equipment

Abstract

The invention provides a construction method and device of a coal mine disaster prediction knowledge base and electronic equipment. The method comprises the steps that historical disaster cases are obtained, the disaster types of the historical disaster cases are determined, and the historical disaster cases are text descriptions performed on occurred coal mine disasters; constructing a knowledge field text database corresponding to the disaster type, and extracting terminologies in the knowledge field text database; the technical terms are classified to obtain a plurality of term categories, object attributes and data attributes of each term category are defined, a prediction knowledge base corresponding to the disaster type is constructed, the object attributes are used for representing meanings of the term categories, the data attributes are used for representing data types of the term categories, and the object attributes are used for representing meanings of the term categories; the prediction knowledge base is used for predicting coal mine disasters of disaster types. By means of the method and device, the problem that in the prior art, unstructured data is difficult to store and process is solved.

Description

Technical Field

[0001] The present application relates to the technical field of coal mine rock burst knowledge base, and in particular, to a method, device, computer-readable storage medium and electronic device for constructing a coal mine disaster prediction knowledge base. Background Art

[0002] In recent years, with the deep mining of coal resources, impact ground pressure accidents have occurred frequently in coal mines, seriously threatening the safe and efficient production of coal mines and causing serious casualties and economic losses.

[0003] Rock burst is essentially a dynamic instability of deep rock engineering, which is instantaneous, destructive and uncertain. In order to effectively prevent and control rock burst, scholars have studied the formation mechanism, evolution law, prediction and early warning methods and prevention and control measures of rock burst. In recent years, with the development of Internet of Things technology, the theory of mine Internet of Things has gradually taken shape, and perception mines have become a hot topic in the field of mining research. In order to realize the perception of mines based on man-machine-environment-management to predict and prevent mine disasters, it is very necessary to build corresponding disaster prediction and early warning knowledge bases and other application platforms, analyze the dangerous precursors of rock burst accidents and make inferences and judgments.

[0004] In the field of coal mining, the coal mine data was initially stored mainly with the help of basic relational databases such as MySQL, SQL server, and Oracle. However, the existing coal mine data contains a large amount of text data such as geological reports and accident analysis reports. If such unstructured data is stored in the above basic relational databases, it is impossible to use these data to analyze and reason about the occurrence of related disasters; therefore, it is necessary to structure such unstructured data first. With the development of knowledge engineering and artificial intelligence, some coal mine disaster knowledge bases based on expert systems have emerged. The knowledge base is a product of combining traditional database technology and artificial intelligence technology. It can encode domain knowledge into a structure for accurate query and reasoning. This type of knowledge base can handle specific problems according to the ideas of experts, give certain answers to specific problems, and realize the intelligence of the knowledge base. However, the construction of expert systems requires a large number of experts, and can only be used to solve specific problems, resulting in a waste of resources. Summary of the invention

[0005] The main purpose of this application is to provide a method, device, computer-readable storage medium and electronic device for constructing a coal mine disaster prediction knowledge base, so as to at least solve the problem that unstructured data in the prior art is difficult to store and process.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for constructing a coal mine disaster prediction knowledge base is provided, comprising: obtaining historical disaster cases, determining the disaster type of the historical disaster cases, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred; constructing a knowledge domain text database corresponding to the disaster type, and extracting professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type; classifying the professional terms to obtain multiple term categories, and defining object attributes and data attributes of each of the term categories to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict coal mine disasters of the disaster type.

[0007] Optionally, extracting professional terms from the knowledge domain text database includes: using the formula Extract professional terms from the knowledge domain text database, where v i represents the i-th keyword node, d represents the damping coefficient, v j represents the jth keyword node, v k Indicates the kth keyword node, In(v i ) indicates pointing to keyword node v i The node out(v j ) indicates pointing to keyword v j All keyword nodes pointed to, w ji represents the weight of the edge from the jth keyword node to the ith keyword node, w jk Represents the weight of the edge from the jth keyword node to the kth keyword node.

[0008] Optionally, constructing a knowledge domain text database corresponding to the disaster type includes: obtaining basic geological concepts in the field of coal mine disasters, and obtaining prevention and control regulations for the disaster type, wherein the basic geological concepts represent text data describing the address of the coal mine; and constructing the knowledge domain text database based on the basic geological concepts and the prevention and control regulations.

[0009] Optionally, obtaining historical disaster cases includes: obtaining the location where the historical disaster case occurred, and obtaining the geological mining conditions at the location where the disaster occurred; obtaining the occurrence process and cause of the historical disaster case; and obtaining governance measures for the historical disaster case.

[0010] Optionally, the professional terms are classified to obtain a plurality of term categories, including: determining the number of occurrences of each professional term, and classifying the professional terms whose number of occurrences is greater than a predetermined number; and classifying the professional terms according to semantics to obtain a plurality of term categories.

[0011] Optionally, after defining the object attributes and data attributes of each of the term categories, the method further includes: defining a definition domain and a value range of the object attributes; and defining a data type of the data attributes.

[0012] Optionally, after constructing the prediction knowledge base corresponding to the disaster type, the method further comprises: detecting the syntax and semantics of the prediction knowledge base, and correcting the prediction knowledge base when the syntax and / or the semantics are wrong.

[0013] According to another aspect of the present application, a device for constructing a coal mine disaster prediction knowledge base is provided, comprising: a determination unit, used to obtain historical disaster cases and determine the disaster type of the historical disaster cases, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred; an extraction unit, used to construct a knowledge domain text database corresponding to the disaster type and extract professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type; a construction unit, used to classify the professional terms to obtain multiple term categories, and define object attributes and data attributes of each of the term categories to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, and the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict coal mine disasters of the disaster type.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods for constructing a coal mine disaster prediction knowledge base.

[0015] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for constructing a coal mine disaster prediction knowledge base for executing any one of the above-described methods.

[0016] Apply the technical solution of the present application to obtain historical disaster cases, determine the disaster types of historical disaster cases, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred; construct a knowledge domain text database corresponding to the disaster type, and extract professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and governance regulations formulated for disaster types; classify professional terms to obtain multiple term categories, and define object attributes and data attributes for each term category to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict the disaster type of coal mine disasters. The text database related to coal mine disasters is represented by data through historical disaster cases, and a corresponding disaster prediction knowledge base is established to facilitate disaster prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a mobile terminal for executing a method for constructing a coal mine disaster prediction knowledge base provided in an embodiment of the present application is shown;

[0019] Figure 2 A schematic diagram of a process for constructing a coal mine disaster prediction knowledge base provided in an embodiment of the present application is shown;

[0020] Figure 3 A schematic flow chart of a method for constructing a specific coal mine disaster prediction knowledge base provided in an embodiment of the present application is shown;

[0021] Figure 4 A schematic diagram of a specific coal mine disaster prediction knowledge base provided by an embodiment of the present application is shown;

[0022] Figure 5 A structural block diagram of a device for constructing a coal mine disaster prediction knowledge base provided in an embodiment of the present application is shown.

[0023] The above drawings include the following reference numerals:

[0024] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0025] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] As introduced in the background technology, unstructured data in the prior art is difficult to store and process. In order to solve the problem that unstructured data is difficult to store and process, the embodiments of the present application provide a method, device, computer-readable storage medium and electronic device for constructing a coal mine disaster prediction knowledge base.

[0029] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0030] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a method for constructing a coal mine disaster prediction knowledge base according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0031] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for constructing a coal mine disaster prediction knowledge base in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] In this embodiment, a method for constructing a coal mine disaster prediction knowledge base running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0033] Figure 2 FIG. 1 is a flow chart of a method for constructing a coal mine disaster prediction knowledge base according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0034] Step S201, obtaining historical disaster cases and determining the disaster type of the historical disaster cases, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred;

[0035] Specifically, historical disaster cases are obtained, and the knowledge representation of typical rock burst cases, i.e., case description, is performed. This application is explained by taking the rock burst disaster as an example. Historical disaster cases generally include sign information related to the occurrence of rock burst and description information of the basic geological conditions of the mine, and knowledge representation of rock burst cases that have occurred in the past is performed. The description of the rock burst case should include four aspects: geological mining conditions at the location of occurrence, rock burst occurrence process, causes of rock burst and lessons learned, and prevention and control measures. Rock burst prevention and control information mainly includes relevant rock burst prevention and control regulations and laws and regulations related to safe mining in coal mines. Constructing an ontology knowledge base can realize intelligent analysis and prediction of rock burst. On the basis of understanding the geological conditions, geological structures, and mining activities of coal mines, combined with the research results of dynamic disaster mechanisms, intelligent analysis of coal mine examples is carried out, and rock burst is evaluated through a variety of prediction methods, thereby realizing intelligent discrimination of rock burst occurrence.

[0036] Step S202, constructing a knowledge domain text database corresponding to the disaster type, and extracting professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type;

[0037] Specifically, when the disaster type is rock burst, the knowledge scope of the rock burst field is determined, and a knowledge domain text database in this field is constructed, which may include rock burst accident risk factors, rock burst accident prediction methods, rock burst prevention and control cases, rock burst accident occurrence from a time and space perspective, and rock burst safety evaluation ontology.

[0038] Step S203, classify the professional terms to obtain multiple term categories, and define the object attributes and data attributes of each term category to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict coal mine disasters of the disaster type.

[0039] Specifically, the professional terms are then classified into multiple different categories, such as the concept of the location of rock burst, the basic physical concepts involved, the concept of factors affecting rock burst, the concept of rock burst monitoring and early warning indicator system, the concept of prevention and control measures, and the concept of rock burst prediction. The non-hierarchical semantic relationship between classes is further described by setting object attributes. The numerical relationship between term concepts and non-term concepts is described by setting data attributes. Finally, a typical case of rock burst is created, and an ontology instance is constructed to complete the unified organization and formal expression of the rock burst case library.

[0040] Through this embodiment, historical disaster cases are obtained, and the disaster types of historical disaster cases are determined, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred; a knowledge domain text database corresponding to the disaster type is constructed, and professional terms in the knowledge domain text database are extracted, wherein the knowledge domain text database at least includes text data of prevention and governance regulations formulated for disaster types; professional terms are classified to obtain multiple term categories, and object attributes and data attributes of each term category are defined to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict the coal mine disaster of the disaster type. The text database related to coal mine disasters is represented by data through historical disaster cases, and a corresponding disaster prediction knowledge base is established to facilitate disaster prediction.

[0041] In the specific implementation process, the above step S202 extracts the professional terms in the knowledge domain text database, which can be achieved by the following steps: Step S2021: By formula Extract professional terms from the knowledge domain text database, where v i represents the i-th keyword node, d represents the damping coefficient, v j represents the jth keyword node, v k Indicates the kth keyword node, In(v i ) indicates pointing to keyword node v i The node out(v j ) indicates pointing to keyword v j All keyword nodes pointed to, w ji represents the weight of the edge from the jth keyword node to the ith keyword node, w jk Represents the weight of the edge from the jth keyword node to the kth keyword node.

[0042] Specifically, we first need to preprocess the text in the knowledge domain text database (word segmentation, removal of punctuation marks, English letters and spaces), filter stop words, and then use the TextRank algorithm to extract rock burst terms. The TextRank algorithm is a graph-based sorting algorithm.

[0043] In some optional implementations, the above step S202 constructs the knowledge domain text database corresponding to the disaster type, which can be implemented by the following steps: Step S2021: Acquire the basic geological concepts in the field of coal mine disasters, and acquire the prevention and control regulations of the disaster type, wherein the basic geological concepts represent text data describing the address of the coal mine; Step S2022: Construct the knowledge domain text database according to the basic geological concepts and the prevention and control regulations. The method constructs a database through the above steps, so that disaster prediction can be performed according to the constructed database.

[0044] Specifically, consider reusing existing ontologies and selectively reuse basic geological concepts in existing coal mine-related ontologies. This includes corpus preparation: various corpora designated by relevant departments; mine vocabulary in the classification thesaurus and vocabulary about mines; abstracts of literature related to rock burst; analysis reports on typical rock burst accidents in coal mines, etc. Based on the above information, a knowledge domain text database is constructed.

[0045] In some optional implementations, the above step S201 of obtaining historical disaster cases can be implemented by the following steps: Step S2011: obtaining the location of the historical disaster case and the geological mining conditions of the location; Step S2012: obtaining the occurrence process and cause of the historical disaster case; Step S2013: obtaining the governance measures of the historical disaster case. The method determines the historical disaster case through the above steps, so that a further knowledge base can be constructed based on the case.

[0046] In the specific implementation process, the description of rock burst cases, i.e. historical disaster cases, should include the geological mining conditions at the site of occurrence, the process of rock burst, the causes of rock burst, and may also include the lessons learned from the case, prevention and control measures, etc.

[0047] In some optional implementations, the above step S203 classifies the professional terms to obtain multiple term categories, which can be achieved by the following steps: step S2031: determine the number of occurrences of each professional term, and classify the professional terms whose number of occurrences is greater than a predetermined number; step S2032: classify the professional terms according to semantics to obtain multiple term categories. The method classifies through the above steps to obtain multiple categories, so as to further define the attributes of the class and facilitate the management of text data.

[0048] Specifically, define the hierarchical relationship between classes, and summarize the term concepts with higher frequency as modeling terms based on the domain concepts extracted by the previous Textrank algorithm and other knowledge sources. Specifically, the number of occurrences of each term can be counted. The number of occurrences greater than the predetermined number indicates a high frequency of application, which can be used as the basic term of the database, and the data with lower frequency of use can be filtered out before classification. Combined with the above domain knowledge and professional knowledge, classification is performed according to semantics, for example, the location of rock burst, the basic physical concepts involved, the factors affecting rock burst, the rock burst monitoring and early warning indicator system, prevention and control measures, and concepts related to rock burst prediction are classified, and the vocabulary that does not have an organizational system structure is organized according to the logical rules of domain knowledge to form a conceptual framework system of rock burst domain knowledge. Some of the terms selected through the above process are shown in Table 1.

[0049] Table 1. Glossary of some terms related to factors affecting rock burst

[0050] Disaster victims Fold Coal seam thickness Overburden density Technical staff Folds and undulations Coal seam stress concentration factor Impact tendency of the roof Safety Inspector Lane layout Coal seam properties Coal seam floor Rescue workers Layered mining Coal seam occurrence Coal seam depth Historical number of rock burst accidents High-cut mining Coal seam roof properties Basic top thickness Fault Fully mechanized caving mining Coal shock tendency Extractive activities Fault drop Coal seam inclination Bottom rock properties equipment

[0051] In some optional implementations, after defining the object attributes and data attributes of each term category, the method further includes the following steps: Step S204: defining the definition domain and value range of the object attribute; Step S205: defining the data type of the data attribute. The method further defines the data category through the above steps, so that the text data can be represented more accurately.

[0052] Specifically, the attributes of the rock burst class can include object attributes and data attributes; the non-hierarchical semantic relationship between classes is described by setting object attributes. For example, the coal mine instance can use the object attribute "take preventive measures" to connect the "preventive measures class" to indicate what measures the mine takes to prevent rock burst. In addition, the object attributes "separation" and "overlap" related to time constraints and space constraints are defined to indicate whether basic events have intersections in time. In addition, the numerical relationship between term concepts and non-term concepts is described by setting data attributes.

[0053] Define attribute constraints and restrictions. By setting the Domains and Ranges of the object attributes, the starting and ending points of the triples are established, allowing the object attributes to have multiple ranges. When defining data attributes, the main thing is to determine their data types, such as the data type of "basic top thickness" is set to "float".

[0054] In some optional implementations, after constructing the prediction knowledge base corresponding to the disaster type, the method further includes the following steps: detecting the syntax and semantics of the prediction knowledge base, and correcting the prediction knowledge base if the syntax and / or semantics are wrong. The method corrects the knowledge base through the above steps, so that the database can be continuously optimized.

[0055] In the specific implementation process, after the knowledge base is built, the semantic consistency check of rock burst ontology is carried out. After the ontology database model is built based on the Protégé tool, the semantic consistency check is completed using its built-in reasoning engine to detect possible semantic conflicts and errors in the ontology model and maintain the consistency of the ontology semantic logic.

[0056] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for constructing a coal mine disaster prediction knowledge base of the present application will be described in detail below in conjunction with specific embodiments.

[0057] This embodiment relates to a specific method for constructing a coal mine disaster prediction knowledge base. Figure 3 As shown, the following steps are included:

[0058] Step S1: rock burst body demand analysis;

[0059] Step S2: Determine the data source, which can be determined through expert experience, professional literature, rock burst cases, etc.;

[0060] Step S3: Design the ontology framework and conduct concept learning and auxiliary construction based on the Texttank algorithm;

[0061] Step S4: Protégé (tool) editing and building;

[0062] Step S5: Determine the scope of domain knowledge, consider reusing existing ontologies, list important terms in the domain, class definitions, attribute definitions, attribute constraint definitions, and create instances;

[0063] Step S6: Perform local storage and local consistency check.

[0064] Figure 4A specific coal mine disaster prediction knowledge base is proposed. The rock burst ontology library includes: mine locations include tunnels and working faces; prevention and control measures include regional prevention and control measures and local prevention and control measures; influencing factors may include multiple factors, which are not listed here one by one; prediction and evaluation categories include prediction and evaluation methods and classification of rock burst hazard levels, prediction and evaluation methods include static evaluation methods and dynamic evaluation methods, static evaluation methods include geological dynamic zoning method, multi-factor coupling method, possibility index diagnosis method, evaluation method based on quantitative theory, and comprehensive index method; dynamic evaluation methods include electromagnetic radiation method, charge induction method, microseismic monitoring method, geoacoustic monitoring method, drilling cuttings method and stress monitoring method; rock burst hazard levels include no rock burst hazard, weak rock burst hazard, moderate rock burst hazard, and strong rock burst hazard; time and space constraints include time category and space category; rock burst types include structural type, roof type, and coal pillar type.

[0065] The present application embodiment also provides a kind of coal mine disaster prediction knowledge base construction device, it should be noted that the coal mine disaster prediction knowledge base construction device of the present application embodiment can be used to execute the construction method for coal mine disaster prediction knowledge base provided by the present application embodiment. The device is used to implement the above-mentioned embodiment and preferred implementation mode, and the description has been made and will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0066] The following introduces the device for constructing a coal mine disaster prediction knowledge base provided in the embodiment of the present application.

[0067] Figure 5 Schematic diagram of a device for constructing a coal mine disaster prediction knowledge base according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0068] A determination unit 10 is used to obtain historical disaster cases and determine the disaster type of the historical disaster cases, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred;

[0069] Specifically, historical disaster cases are obtained, and the knowledge representation of typical rock burst cases, i.e., case description, is performed. This application is explained by taking the rock burst disaster as an example. Historical disaster cases generally include sign information related to the occurrence of rock burst and description information of the basic geological conditions of the mine, and knowledge representation of rock burst cases that have occurred in the past is performed. The description of the rock burst case should include four aspects: geological mining conditions at the location of occurrence, rock burst occurrence process, causes of rock burst and lessons learned, and prevention and control measures. Rock burst prevention and control information mainly includes relevant rock burst prevention and control regulations and laws and regulations related to safe mining in coal mines. Constructing an ontology knowledge base can realize intelligent analysis and prediction of rock burst. On the basis of understanding the geological conditions, geological structures, and mining activities of coal mines, combined with the research results of dynamic disaster mechanisms, intelligent analysis of coal mine examples is carried out, and rock burst is evaluated through a variety of prediction methods, thereby realizing intelligent discrimination of rock burst occurrence.

[0070] An extraction unit 20 is used to construct a knowledge domain text database corresponding to the disaster type and extract professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type;

[0071] Specifically, when the disaster type is rock burst, the knowledge scope of the rock burst field is determined, and a knowledge domain text database in this field is constructed, which may include rock burst accident risk factors, rock burst accident prediction methods, rock burst prevention and control cases, rock burst accident occurrence from a time and space perspective, and rock burst safety evaluation ontology.

[0072] The construction unit 30 is used to classify the professional terms to obtain multiple term categories, and define the object attributes and data attributes of each term category to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict coal mine disasters of the disaster type.

[0073] Specifically, the professional terms are then classified into multiple different categories, such as the concept of the location of rock burst, the basic physical concepts involved, the concept of factors affecting rock burst, the concept of rock burst monitoring and early warning indicator system, the concept of prevention and control measures, and the concept of rock burst prediction. The non-hierarchical semantic relationship between classes is further described by setting object attributes. The numerical relationship between term concepts and non-term concepts is described by setting data attributes. Finally, a typical case of rock burst is created, and an ontology instance is constructed to complete the unified organization and formal expression of the rock burst case library.

[0074] Through this embodiment, historical disaster cases are obtained, and the disaster types of historical disaster cases are determined, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred; a knowledge domain text database corresponding to the disaster type is constructed, and professional terms in the knowledge domain text database are extracted, wherein the knowledge domain text database at least includes text data of prevention and governance regulations formulated for disaster types; professional terms are classified to obtain multiple term categories, and object attributes and data attributes of each term category are defined to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict the coal mine disaster of the disaster type. The text database related to coal mine disasters is represented by data through historical disaster cases, and a corresponding disaster prediction knowledge base is established to facilitate disaster prediction.

[0075] In the specific implementation process, the above-mentioned extraction unit includes an extraction module for using the formula Extract professional terms from the knowledge domain text database, where v i represents the i-th keyword node, d represents the damping coefficient, v j represents the jth keyword node, v k Indicates the kth keyword node, In(v i ) indicates pointing to keyword node v i The node out(v j ) indicates pointing to keyword v j All keyword nodes pointed to, w ji represents the weight of the edge from the jth keyword node to the ith keyword node, w jk Represents the weight of the edge from the jth keyword node to the kth keyword node.

[0076] Specifically, we first need to preprocess the text in the knowledge domain text database (word segmentation, removal of punctuation marks, English letters and spaces), filter stop words, and then use the TextRank algorithm to extract rock burst terms. The TextRank algorithm is a graph-based sorting algorithm.

[0077] In some optional implementations, the extraction unit further includes a first acquisition module and a construction module, wherein the first acquisition module is used to acquire basic geological concepts in the field of coal mine disasters and to acquire the prevention and control regulations of the disaster type, wherein the basic geological concepts represent text data describing the address of the coal mine; and the construction module is used to construct the knowledge domain text database according to the basic geological concepts and the prevention and control regulations. The method constructs a database through the above steps, so that disaster prediction can be performed according to the constructed database.

[0078] Specifically, consider reusing existing ontologies and selectively reuse basic geological concepts in existing coal mine-related ontologies. This includes corpus preparation: various corpora designated by relevant departments; mine vocabulary in the classification thesaurus and vocabulary about mines; abstracts of literature related to rock burst; analysis reports on typical rock burst accidents in coal mines, etc. Based on the above information, a knowledge domain text database is constructed.

[0079] In some optional implementations, the determination unit includes a second acquisition module, a third acquisition module, and a fourth acquisition module. The second acquisition module is used to obtain the location of the historical disaster case and the geological mining conditions of the location; the third acquisition module is used to obtain the occurrence process and cause of the historical disaster case; and the fourth acquisition module is used to obtain the governance measures of the historical disaster case. The method determines the historical disaster case through the above steps, so that a further knowledge base can be constructed based on the case.

[0080] In the specific implementation process, the description of rock burst cases, i.e. historical disaster cases, should include the geological mining conditions at the site of occurrence, the process of rock burst, the causes of rock burst, and may also include the lessons learned from the case, prevention and control measures, etc.

[0081] In some optional implementations, the construction unit includes a first classification module and a second classification module, the first classification module is used to determine the number of occurrences of each professional term, and classify the professional terms whose number of occurrences is greater than a predetermined number; the second classification module is used to classify the professional terms according to semantics to obtain multiple term categories. The method performs classification through the above steps to obtain multiple categories, so as to further define the attributes of the class and facilitate the management of text data.

[0082] Specifically, define the hierarchical relationship between classes, and summarize the term concepts with higher frequency as modeling terms based on the domain concepts extracted by the previous Textrank algorithm and other knowledge sources. Specifically, the number of occurrences of each term can be counted. The number of occurrences greater than the predetermined number indicates a high frequency of application, which can be used as the basic term of the database, and the data with lower frequency of use can be filtered out before classification. Combined with the above domain knowledge and professional knowledge, classification is performed according to semantics, for example, the location of rock burst, the basic physical concepts involved, the factors affecting rock burst, the rock burst monitoring and early warning indicator system, prevention and control measures, and concepts related to rock burst prediction are classified, and the vocabulary that does not have an organizational system structure is organized according to the logical rules of domain knowledge to form a conceptual framework system of rock burst domain knowledge. Some of the terms selected through the above process are shown in Table 1.

[0083] In some optional implementations, after defining the object attribute and data attribute of each term category, the device further includes a first definition unit and a second definition unit, the first definition unit is used to define the definition domain and value range of the object attribute; the second definition unit is used to define the data type of the data attribute. The method further defines the data category through the above steps, so that the text data can be represented more accurately.

[0084] Specifically, the attributes of the rock burst class can include object attributes and data attributes; the non-hierarchical semantic relationship between classes is described by setting object attributes. For example, the coal mine instance can use the object attribute "take preventive measures" to connect the "preventive measures class" to indicate what measures the mine takes to prevent rock burst. In addition, the object attributes "separation" and "overlap" related to time constraints and space constraints are defined to indicate whether basic events have intersections in time. In addition, the numerical relationship between term concepts and non-term concepts is described by setting data attributes.

[0085] Define attribute constraints and restrictions. By setting the Domains and Ranges of the object attributes, the starting and ending points of the triples are established, allowing the object attributes to have multiple ranges. When defining data attributes, the main thing is to determine their data types, such as the data type of "basic top thickness" is set to "float".

[0086] In some optional implementations, after constructing the prediction knowledge base corresponding to the disaster type, the device further includes a correction unit for detecting the syntax and semantics of the prediction knowledge base, and correcting the prediction knowledge base when the syntax and / or semantics are wrong. The method corrects the knowledge base through the above steps, so that the database can be continuously optimized.

[0087] In the specific implementation process, after the knowledge base is built, the semantic consistency check of rock burst ontology is carried out. After the ontology database model is built based on the Protégé tool, the semantic consistency check is completed using its built-in reasoning engine to detect possible semantic conflicts and errors in the ontology model and maintain the consistency of the ontology semantic logic.

[0088] The device for constructing the coal mine disaster prediction knowledge base includes a processor and a memory, wherein the determination unit, extraction unit, and construction unit are stored in the memory as program units, and the processor executes the program units stored in the memory to realize the corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0089] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the knowledge base can be constructed by adjusting the kernel parameters.

[0090] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0091] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the method for constructing the coal mine disaster prediction knowledge base.

[0092] Specifically, the method for constructing a coal mine disaster prediction knowledge base includes:

[0093] Step S201, obtaining historical disaster cases and determining the disaster type of the historical disaster cases, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred;

[0094] Specifically, historical disaster cases are obtained, and the knowledge representation of typical rock burst cases, i.e., case description, is performed. This application is explained by taking the rock burst disaster as an example. Historical disaster cases generally include sign information related to the occurrence of rock burst and description information of the basic geological conditions of the mine, and knowledge representation of rock burst cases that have occurred in the past is performed. The description of the rock burst case should include four aspects: geological mining conditions at the location of occurrence, rock burst occurrence process, causes of rock burst and lessons learned, and prevention and control measures. Rock burst prevention and control information mainly includes relevant rock burst prevention and control regulations and laws and regulations related to safe mining in coal mines. Constructing an ontology knowledge base can realize intelligent analysis and prediction of rock burst. On the basis of understanding the geological conditions, geological structures, and mining activities of coal mines, combined with the research results of dynamic disaster mechanisms, intelligent analysis of coal mine examples is carried out, and rock burst is evaluated through a variety of prediction methods, thereby realizing intelligent discrimination of rock burst occurrence.

[0095] Step S202, constructing a knowledge domain text database corresponding to the disaster type, and extracting professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type;

[0096] Specifically, when the disaster type is rock burst, the knowledge scope of the rock burst field is determined, and a knowledge domain text database in this field is constructed, which may include rock burst accident risk factors, rock burst accident prediction methods, rock burst prevention and control cases, rock burst accident occurrence from a time and space perspective, and rock burst safety evaluation ontology.

[0097] Step S203, classify the professional terms to obtain multiple term categories, and define the object attributes and data attributes of each term category to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict coal mine disasters of the disaster type.

[0098] Specifically, the professional terms are then classified into multiple different categories, such as the concept of the location of rock burst, the basic physical concepts involved, the concept of factors affecting rock burst, the concept of rock burst monitoring and early warning indicator system, the concept of prevention and control measures, and the concept of rock burst prediction. The non-hierarchical semantic relationship between classes is further described by setting object attributes. The numerical relationship between term concepts and non-term concepts is described by setting data attributes. Finally, a typical case of rock burst is created, and an ontology instance is constructed to complete the unified organization and formal expression of the rock burst case library.

[0099] An embodiment of the present invention provides an electronic device, including a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, at least the following steps are implemented:

[0100] Step S201, obtaining historical disaster cases and determining the disaster type of the historical disaster cases, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred;

[0101] Specifically, historical disaster cases are obtained, and the knowledge representation of typical rock burst cases, i.e., case description, is performed. This application is explained by taking the rock burst disaster as an example. Historical disaster cases generally include sign information related to the occurrence of rock burst and description information of the basic geological conditions of the mine, and knowledge representation of rock burst cases that have occurred in the past is performed. The description of the rock burst case should include four aspects: geological mining conditions at the location of occurrence, rock burst occurrence process, causes of rock burst and lessons learned, and prevention and control measures. Rock burst prevention and control information mainly includes relevant rock burst prevention and control regulations and laws and regulations related to safe mining in coal mines. Constructing an ontology knowledge base can realize intelligent analysis and prediction of rock burst. On the basis of understanding the geological conditions, geological structures, and mining activities of coal mines, combined with the research results of dynamic disaster mechanisms, intelligent analysis of coal mine examples is carried out, and rock burst is evaluated through a variety of prediction methods, thereby realizing intelligent discrimination of rock burst occurrence.

[0102] Step S202, constructing a knowledge domain text database corresponding to the disaster type, and extracting professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type;

[0103] Specifically, when the disaster type is rock burst, the knowledge scope of the rock burst field is determined, and a knowledge domain text database in this field is constructed, which may include rock burst accident risk factors, rock burst accident prediction methods, rock burst prevention and control cases, rock burst accident occurrence from a time and space perspective, and rock burst safety evaluation ontology.

[0104] Step S203, classify the professional terms to obtain multiple term categories, and define the object attributes and data attributes of each term category to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict coal mine disasters of the disaster type.

[0105] Specifically, the professional terms are then classified into multiple different categories, such as the concept of the location of rock burst, the basic physical concepts involved, the concept of factors affecting rock burst, the concept of rock burst monitoring and early warning indicator system, the concept of prevention and control measures, and the concept of rock burst prediction. The non-hierarchical semantic relationship between classes is further described by setting object attributes. The numerical relationship between term concepts and non-term concepts is described by setting data attributes. Finally, a typical case of rock burst is created, and an ontology instance is constructed to complete the unified organization and formal expression of the rock burst case library.

[0106] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0107] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method described in each embodiment of the present application:

[0108] Step S201, obtaining historical disaster cases and determining the disaster type of the historical disaster cases, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred;

[0109] Specifically, historical disaster cases are obtained, and the knowledge representation of typical rock burst cases, i.e., case description, is performed. This application is explained by taking the rock burst disaster as an example. Historical disaster cases generally include sign information related to the occurrence of rock burst and description information of the basic geological conditions of the mine, and knowledge representation of rock burst cases that have occurred in the past is performed. The description of the rock burst case should include four aspects: geological mining conditions at the location of occurrence, rock burst occurrence process, causes of rock burst and lessons learned, and prevention and control measures. Rock burst prevention and control information mainly includes relevant rock burst prevention and control regulations and laws and regulations related to safe mining in coal mines. Constructing an ontology knowledge base can realize intelligent analysis and prediction of rock burst. On the basis of understanding the geological conditions, geological structures, and mining activities of coal mines, combined with the research results of dynamic disaster mechanisms, intelligent analysis of coal mine examples is carried out, and rock burst is evaluated through a variety of prediction methods, thereby realizing intelligent discrimination of rock burst occurrence.

[0110] Step S202, constructing a knowledge domain text database corresponding to the disaster type, and extracting professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type;

[0111] Specifically, when the disaster type is rock burst, the knowledge scope of the rock burst field is determined, and a knowledge domain text database in this field is constructed, which may include rock burst accident risk factors, rock burst accident prediction methods, rock burst prevention and control cases, rock burst accident occurrence from a time and space perspective, and rock burst safety evaluation ontology.

[0112] Step S203, classify the professional terms to obtain multiple term categories, and define the object attributes and data attributes of each term category to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict coal mine disasters of the disaster type.

[0113] Specifically, the professional terms are then classified into multiple different categories, such as the concept of the location of rock burst, the basic physical concepts involved, the concept of factors affecting rock burst, the concept of rock burst monitoring and early warning indicator system, the concept of prevention and control measures, and the concept of rock burst prediction. The non-hierarchical semantic relationship between classes is further described by setting object attributes. The numerical relationship between term concepts and non-term concepts is described by setting data attributes. Finally, a typical case of rock burst is created, and an ontology instance is constructed to complete the unified organization and formal expression of the rock burst case library.

[0114] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0115] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0116] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0119] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0120] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0121] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0122] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0123] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0124] 1) In the method for constructing the coal mine disaster prediction knowledge base of the present application, historical disaster cases are obtained, and the disaster types of the historical disaster cases are determined, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred; a knowledge domain text database corresponding to the disaster type is constructed, and professional terms in the knowledge domain text database are extracted, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type; the professional terms are classified to obtain multiple term categories, and the object attributes and data attributes of each term category are defined to construct a prediction knowledge base corresponding to the disaster type, wherein the object attributes are used to represent the meaning of the term category, the data attributes are used to represent the data type of the term category, and the prediction knowledge base is used to predict the disaster type of coal mine disasters. The text database related to coal mine disasters is represented by data through historical disaster cases, and a corresponding disaster prediction knowledge base is established to facilitate disaster prediction.

[0125] 2) In the device for constructing the coal mine disaster prediction knowledge base of the present application, historical disaster cases are obtained, and the disaster types of the historical disaster cases are determined, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred; a knowledge domain text database corresponding to the disaster type is constructed, and professional terms in the knowledge domain text database are extracted, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type; professional terms are classified to obtain multiple term categories, and object attributes and data attributes of each term category are defined to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict the disaster type of coal mine disasters. The text database related to coal mine disasters is represented by data through historical disaster cases, and a corresponding disaster prediction knowledge base is established to facilitate disaster prediction.

[0126] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for constructing a coal mine disaster prediction knowledge base, characterized in that: include: Acquire historical disaster cases and determine the disaster type of the historical disaster cases, wherein the historical disaster cases are text descriptions of coal mine disasters that have occurred; Constructing a knowledge domain text database corresponding to the disaster type, and extracting professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type; The professional terms are classified to obtain multiple term categories, and the object attributes and data attributes of each term category are defined to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict coal mine disasters of the disaster type.

2. The method for constructing a coal mine disaster prediction knowledge base according to claim 1, characterized in that: Extracting professional terms from the knowledge domain text database includes: By formula Extract professional terms from the knowledge domain text database, where v i represents the i-th keyword node, d represents the damping coefficient, v j represents the jth keyword node, v k Indicates the kth keyword node, In(v i ) indicates pointing to keyword node v i The node out(v j ) indicates pointing to keyword v j All keyword nodes pointed to, w ji represents the weight of the edge from the jth keyword node to the ith keyword node, w jk Represents the weight of the edge from the jth keyword node to the kth keyword node.

3. The method for constructing a coal mine disaster prediction knowledge base according to claim 1, characterized in that: Construct a knowledge domain text database corresponding to the disaster type, including: Obtaining basic geological concepts in the field of coal mine disasters and obtaining prevention and control regulations for the disaster type, wherein the basic geological concepts represent text data describing the address of the coal mine; The knowledge domain text database is constructed based on the basic geological concepts and the prevention and control regulations.

4. The method for constructing a coal mine disaster prediction knowledge base according to claim 1, characterized in that: Access historical disaster cases, including: Obtain the location where the historical disaster case occurred and the geological mining conditions at the location where the disaster occurred; Obtain the occurrence process and causes of the historical disaster cases; Obtain the governance measures for the historical disaster cases mentioned.

5. The method for constructing a coal mine disaster prediction knowledge base according to claim 1, characterized in that: The professional terms are classified to obtain multiple term categories, including: Determining the number of occurrences of each of the professional terms, and classifying the professional terms whose number of occurrences is greater than a predetermined number; The professional terms are classified according to semantics to obtain a plurality of term categories.

6. The method for constructing a coal mine disaster prediction knowledge base according to claim 1, characterized in that: After defining the object attributes and data attributes of each of the term categories, the method further comprises: Defining the domain and range of the object attribute; Defines the data type of the data attribute.

7. The method for constructing a coal mine disaster prediction knowledge base according to claim 1, characterized in that: After constructing the prediction knowledge base corresponding to the disaster type, the method further includes: The syntax and semantics of the prediction knowledge base are detected, and when the syntax and / or semantics are wrong, the prediction knowledge base is corrected.

8. A device for constructing a coal mine disaster prediction knowledge base, characterized in that: include: A determination unit, configured to obtain a historical disaster case and determine a disaster type of the historical disaster case, wherein the historical disaster case is a text description of a coal mine disaster that has occurred; An extraction unit, used to construct a knowledge domain text database corresponding to the disaster type and extract professional terms in the knowledge domain text database, wherein the knowledge domain text database at least includes text data of prevention and control regulations formulated for the disaster type; A construction unit is used to classify the professional terms to obtain multiple term categories, and define the object attributes and data attributes of each term category to construct a prediction knowledge base corresponding to the disaster type, wherein the object attribute is used to represent the meaning of the term category, the data attribute is used to represent the data type of the term category, and the prediction knowledge base is used to predict coal mine disasters of the disaster type.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for constructing a coal mine disaster prediction knowledge base as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for constructing a coal mine disaster prediction knowledge base as described in any one of claims 1 to 7.

Images