CN111914100A - An ontology-based approach to knowledge representation for emergency decision-making in emergencies - Google Patents

Abstract

The invention relates to an ontology-based emergency decision-making knowledge representation method, and compared with the prior art, the defect that the emergency decision-making is not guided by technical data is solved. The present invention includes the following steps: determining an ontology model for emergency decision-making, and by analyzing emergency plans, emergency cases and emergency business rules, etc., to propose an ontology model for emergency decision-making knowledge; Construct. The present invention provides fast and efficient knowledge management for the intelligence of emergency decision-making by constructing the knowledge ontology of emergency decision-making and forming the corresponding relationship between knowledge nodes and data subclasses through the ontology based on attributes.

Description

An ontology-based approach to knowledge representation for emergency decision-making in emergencies

technical field

The invention relates to the technical field of data decision analysis, in particular to an ontology-based emergency decision-making knowledge representation method for emergencies.

Background technique

At present, the decision information accumulated in the emergency decision support system for emergencies is generally expressed in the form of structured and unstructured data such as traditional databases and file systems. The lack of semantic information makes it difficult for decision makers to obtain the semantic level in a short time. Therefore, it limits the improvement of emergency decision-making and command level.

SUMMARY OF THE INVENTION

The purpose of the present invention is to solve the defect of the prior art that emergency decision-making for emergencies has no technical data guidance, and to provide an ontology-based method for representing knowledge of emergency decision-making in emergencies to solve the above problems.

In order to achieve the above object, technical scheme of the present invention is as follows:

An ontology-based emergency decision-making knowledge representation method for emergencies, comprising the following steps:

Determine the ontology model of emergency decision-making, and propose a knowledge ontology model for emergency decision-making by analyzing emergency plans, emergency cases and emergency business rules;

Ontology construction based on emergency decision-making field.

The said ontology model for determining the emergency decision-making of emergencies is to assume that the ontology model of the emergency decision-making domain for emergencies is composed of quadruples,

Denoted as Ontology::=<Concepts,Relations,Individuals,Rules>,

in:

Concepts::={concept}, is a collection of concepts in the field of emergency decision-making, including social security, natural disasters and ecological environment and other emergencies elements collection, corresponding emergency plan collection, emergency case collection and emergency resource collection, etc.;

Relaitons::={r(c1,c2)|c1,c2∈Concepts, r is the name of the relationship}, is a set of binary relationships between concepts, concepts and attributes in the field of emergency decision-making, which represents The interaction between concepts and attributes in the field of emergency response;

Individuals::={individual|δ(individual)∈Concepts}, is a collection of concept instances in the field of emergency decision-making. An instance refers to a specific individual belonging to a concept class, such as an instance of the emergency case class "512 Wenchuan Earthquake" ;

Rules::={rule}, is a collection of emergency decision-making rules for emergencies, in the form of rules with an if...then...else... structure.

The ontology construction based on the emergency decision-making field for emergencies includes the following steps:

On the basis of analyzing and studying emergency management of emergencies, for emergency decision-making of emergencies, machine learning methods are used to extract information related to the field of emergency management from emergency plans, emergency management regulations and a large number of emergency cases. Terms and definitions, standard abbreviations, standard jargon, common synonyms, etc., to build a dictionary in the field of emergency management;

Based on these dictionaries, extracted from the national emergency response plan, the relevant departments of the State Council emergency plan, the relevant local people's government emergency plan, the emergency regional management agency and its dispatched agency emergency response plan, emergency rescue plan and other texts. Words included in the dictionary as domain concepts;

According to the subclass relationship and part relationship defined in the dictionary, the classification relationship is obtained to construct a multi-level concept tree of emergency decision-making ontology, and the domain is divided into the plan ontology and the basic ontology. Attributes and data attributes realize the description of non-classification relationships;

Based on the established ontology of emergency decision-making domain, the specific reasoning elements involved in emergency decision-making are determined through the extraction of ontology concepts, and reasoning rules are formed according to the elements.

beneficial effect

Compared with the prior art, an ontology-based emergency decision-making knowledge representation method of the present invention constructs a knowledge ontology for emergency decision-making based on attributes, and forms the corresponding relationship between knowledge nodes and data subclasses through ontology based on attributes. Provide fast and efficient knowledge management for the intelligence of emergency decision-making.

Description of drawings

FIG. 1 is a sequence diagram of the method of the present invention.

Detailed ways

In order to have a further understanding and understanding of the structural features of the present invention and the effects achieved, the preferred embodiments and accompanying drawings are used in conjunction with detailed descriptions, and the descriptions are as follows:

As shown in Figure 1, an ontology-based emergency decision-making knowledge representation method for emergencies described in the present invention includes the following steps:

The first step is to determine the ontology model of emergency decision-making. By analyzing emergency plans, emergency cases and emergency business rules, the knowledge ontology model of emergency decision-making is proposed.

To determine the ontology model of emergency decision-making for emergencies, it is assumed that the ontology model of the emergency decision-making domain for emergencies is composed of four-tuples,

Denoted as Ontology::=<Concepts,Relations,Individuals,Rules>,

in:

Concepts::={concept}, is a collection of concepts in the field of emergency decision-making, including social security, natural disasters and ecological environment and other emergencies elements collection, corresponding emergency plan collection, emergency case collection and emergency resource collection, etc.;

Relaitons::={r(c1,c2)|c1,c2∈Concepts, r is the name of the relationship}, is a set of binary relationships between concepts, concepts and attributes in the field of emergency decision-making, which represents The interaction between concepts and attributes in the field of emergency response;

Individuals::={individual|δ(individual)∈Concepts}, is a collection of concept instances in the field of emergency decision-making. An instance refers to a specific individual belonging to a concept class, such as an instance of the emergency case class "512 Wenchuan Earthquake" ;

Rules::={rule}, is a collection of emergency decision-making rules for emergencies, in the form of rules with an if...then...else... structure.

The second step is to construct the ontology based on the emergency decision-making field of emergencies. The specific steps are as follows:

(1) On the basis of analyzing and studying emergency management of emergencies, using machine learning methods for emergency decision-making in emergencies is extracted from emergency plans, emergency management regulations and a large number of emergency cases, including emergency management of emergencies. Domain-related terms and definitions, standard abbreviations, standard jargon, common synonyms, etc., to build a dictionary of the field of emergency management.

(2) Based on these dictionaries, from the national emergency response plan, the relevant departments of the State Council emergency plan, the relevant local people's government emergency plan, the emergency regional management agency and its dispatched agency emergency response plan, emergency rescue plan and other texts The words contained in the dictionary are extracted as domain concepts.

(3) According to the subclass relationship and part relationship defined in the dictionary, the classification relationship is obtained to construct a multi-level concept tree of emergency decision-making ontology, and the domain is divided into the plan ontology and the basic ontology. On the basis of the concept and its classification definition, The description of non-categorical relationships is achieved by defining object properties and data properties.

(4) On the basis of the established ontology of emergency decision-making domain, the specific reasoning elements involved in emergency decision-making are determined through the extraction of ontology concepts, and the reasoning rules are formed according to the elements.

Such as a fire and explosion emergency: it may cause more than 10 deaths, or more than 50 serious injuries (including acute industrial poisoning, the same below) or a direct economic loss of more than 10 million yuan, which is a Class I fire and explosion event, and the corresponding rules are as follows:

R1: Fire and explosion emergencies (?x)∧(((Number of deaths(?x,y)∧moreThan(?y,10))∨((Severe injuries(?x,y)∧moreThan(?y,50) )∨((direct economic loss (?x, y)∧moreThan(?y, 1000)))→Class I fire and explosion event (?x).

The foregoing has shown and described the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited by the above-mentioned embodiments. The above-mentioned embodiments and descriptions describe only the principles of the present invention. Without departing from the spirit and scope of the present invention, there are various Variations and improvements are intended to fall within the scope of the claimed invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims (3)

1. An ontology-based emergency decision knowledge representation method for emergencies is characterized by comprising the following steps:

11) determining an emergency decision ontology model, and providing an emergency decision knowledge ontology model by analyzing emergency plans, emergency cases, emergency business rules and the like;

12) and constructing an ontology based on the emergency decision field of the emergency.

2. The ontology-based emergency decision-making knowledge representation method of emergency events according to claim 1, wherein: the body model for determining the emergency decision-making domain of the emergency is formed by four tuples,

record as Ontology: : < Concepts, relationships, induviduals, Rules >,

wherein:

concept: : the system comprises a concept set, a concept set and a concept set, wherein the concept set is a set of concepts in the emergency decision field of an emergency, and comprises an emergency element set, a corresponding emergency plan set, an emergency case set, an emergency resource set and the like, wherein the emergency element set comprises social security, natural disasters, ecological environments and the like;

relaitons: : the system comprises a first set of relations in the emergency decision domain, a second set of relations in the emergency decision domain, and a third set of relations in the emergency decision domain, wherein the first set of relations is a binary relation set between Concepts in the emergency decision domain and between Concepts and attributes, and the second set of relations is { r (c1, c2) | c1, c2 ∈ Concepts, and r is a name of a relation }, and represents interaction between Concepts and attributes in the emergency decision domain;

indeviduals: { indevidual | (indevidual) ∈ Concepts }, which is a set of concept instances in the emergency decision field of an emergency event, where an instance refers to a specific individual belonging to a certain concept class, such as an instance of an emergency case class, "512 wenchuan earthquake";

rule: ═ rule, is a set of emergency decision Rules for emergencies, like the rule of if … the … else … structure.

3. The method as claimed in claim 1, wherein the ontology based emergency decision knowledge representation method for emergency decision domain comprises the following steps:

31) on the basis of analyzing and researching emergency management of the emergency, aiming at emergency decisions, extracting terms and definitions related to the emergency management field, standard abbreviations, standard jargon, common synonyms and the like from emergency plans, emergency management regulations and a large number of emergency cases by using a machine learning method, and constructing an emergency management field dictionary;

32) based on the dictionaries, words contained in the dictionaries are extracted from texts such as national disposal emergency plans, emergency plans of related departments of the state department, emergency plans of local people governments, emergency plans of emergency regional management organizations and their sending organizations, emergency plans of emergency rescue plans and the like as field concepts;

33) acquiring classification relations according to subclass relations and partial relations defined in a dictionary to construct a multilevel concept tree of an emergency decision body of an emergency incident, dividing the field into a plan body and a basic body, and realizing the description of non-classification relations by defining object attributes and data attributes on the basis of concepts and classification definitions thereof;

34) on the basis of the established emergency decision field ontology, specific reasoning elements involved in the emergency decision are determined through extraction of ontology concepts, and a reasoning rule is established according to the elements.

Images