KR20210054109A - Method and system for managing grade of risk alarm - Google Patents

Abstract

An emergency alert level management method and a system thereof are disclosed. The emergency alert level management method comprises the steps of: the emergency alert level management system receiving disaster state occurrence information; the emergency alert level management system specifying the kind of disaster based on the received disaster state occurrence information and determining information on spreadability to be collected on the basis of the specified kind of disaster; the emergency alert level management system acquiring the determined information on spreadability; and the emergency alert level management system determining the emergency alert level of the disaster state on the basis of alert level considering information including the acquired information on spreadability. The present invention can rapidly issue an emergency alert and provide consistency of the emergency alert level.

Description

Method and system for managing grade of risk alarm}

The present invention relates to a risk warning level management method and system thereof.

More specifically, it relates to a method and system that enables rapid crisis response and appropriate response to the level of crisis warning by automatically determining the level of crisis warning in a disaster situation.

In the event of a disaster (defined in the broader meaning of disaster/disaster/accident), appropriate response is required according to the crisis level of the disaster. Especially, in the case of a large disaster, the level of crisis warning according to the situation of the disaster is determined in advance. There are cases where it is defined. For example, the Basic Act on Disaster and Safety Management stipulates that a crisis alert can be issued by comprehensively judging the risk level and possibility of occurrence, and the Act categorizes crisis alerts into interest, caution, caution, and seriousness. I'm doing it.

In addition, the level of response such as response procedures and response personnel may also vary depending on the level of crisis warning.

In the event of a disaster, even though efforts are made to perform crisis alerts by level and respond appropriately, in the past, when a disaster occurs, situation information of the disaster site is collected, and after confirming the collected information, situation judgment meetings are held. As a result, relevant personnel determine the level of crisis warning through meetings or artificial judgments.

And even if a disaster situation occurs due to this type of problem, it is a reality that the issuance of a crisis warning is relatively delayed due to the demand for a procedural or factual judgment process at the crisis level of the disaster situation.

The problem of delaying the issuance of crisis alerts or determining the level of crisis alerts is an obstacle to establishing an immediate response system or an accurate and appropriate level of response in the event of a disaster.

Korean Patent Registration No. 100800023 "Disaster Response Resource Management System and Method"

The present invention is an invention conceived to solve the problems of the prior art, and provides a method and system for quickly and quickly determining and managing a crisis level when a disaster occurs.

A method for managing a crisis level according to an aspect of the present invention includes the steps of receiving, by a crisis level management system, information about occurrence of a disaster situation, and specifying the type of the disaster based on the information about occurrence of a disaster situation received by the crisis level management system. And determining the spreadability information to be collected based on the specific type of disaster, obtaining the determined spreadability information by the crisis warning level management system, and the spreadability information obtained by the crisis warning level management system. And determining the crisis level of the disaster based on the alert level consideration information including a.

The crisis warning level management method further comprises the step of storing, by the crisis warning level management system, a disaster spread factor table defining disaster spread factors for each disaster type, and determining the spreadability information to be collected based on the type of the disaster. The step of doing may include determining the spreadability information based on the disaster spread factor table.

The crisis warning level management method further comprises the step of obtaining social trend information corresponding to the disaster situation, and based on the warning level consideration information including the spreadability information obtained by the crisis warning level management system. The determining of the crisis warning level of the situation may include determining the crisis warning level of the disaster situation based on the warning level consideration information further including the social trend information.

The step of acquiring social trend information corresponding to the disaster situation includes acquiring press content corresponding to the disaster situation or user content corresponding to the disaster situation, the alert level further comprising the social trend information The determining of the crisis warning level of the disaster situation based on the consideration information may determine the crisis warning level of the disaster situation based on the frequency of the media content or the user content.

The step of determining the crisis warning level of the disaster situation based on the warning level consideration information further including the social trend information is to perform a sentiment analysis of the press content or the user content, and the sentiment analysis performed. It may include the step of determining the crisis warning level of the disaster situation based on the result of.

The determining of the crisis warning level of the disaster situation based on the warning level consideration information further including the social trend information includes determining the crisis warning level as the frequency of the media content or user content included in the social trend information increases. The level index may be improved as the result of the sentiment analysis of the press content or the user content has more negative reactions.

The step of determining the crisis warning level of the disaster situation based on the warning level consideration information including the spreadability information obtained by the crisis warning level management system may further determine the number of casualties, the number of victims, or the degree of damage in the disaster situation. It may include the step of determining a crisis warning level of the disaster situation based on the included warning level consideration information.

The step of determining the crisis warning level of the disaster situation based on the warning level consideration information including the spreadability information obtained by the crisis warning level management system includes the warning according to a detailed level classified by each warning level consideration information. The crisis warning level may be determined by a step of determining a detailed index for each level consideration information and by synthesizing the determined detailed index for each warning level consideration information.

A method for managing a crisis level according to another aspect includes the steps of receiving, by a crisis level management system, information on occurrence of a disaster situation, obtaining, by the crisis level management system, information on social trends corresponding to the situation, and The level management system may include determining, by the level management system, a crisis alert level of the disaster situation based on alert level consideration information including the social trend information.

The above methods may be implemented by a computer program stored in a computer-readable recording medium.

A crisis warning level management system according to another aspect of the present invention includes a processor and a storage device in which a program driven by the processor is stored, and a program driven by the processor receives disaster situation occurrence information and receives the received disaster. An alert level that specifies the type of disaster based on the situation occurrence information, determines the probability of spreading information to be collected based on the type of the specific disaster, obtains the determined spreadability information, and includes the obtained spreadability information Based on the consideration information, the level of crisis warning in the above disaster situation is judged.

The program driven by the processor may further acquire social trend information corresponding to the disaster situation, and determine the crisis alert level of the disaster situation based on the warning level consideration information further including the social trend information. .

A crisis warning level management system according to another aspect includes a processor and a storage device in which a program driven by the processor is stored, and a program driven by the processor receives information on occurrence of a disaster situation, and corresponds to the disaster situation. It is possible to obtain the social trend information, and determine the crisis alert level of the disaster situation based on the alert level consideration information including the obtained social trend information.

According to an embodiment of the present invention, by adaptively and systematically determining the level of crisis warning of a disaster situation according to a predetermined standard and type of disaster when a disaster occurs, the promptness of issuance of the crisis and the consistency of the level of crisis warning are improved. It can be provided, and accordingly, there is an effect of securing the promptness of the response and the appropriateness of the level of response.

In addition, it is not limited to the existing physical environment, and reflects social trends (press, public opinion, etc.) in the judgment of the level of crisis warning, thereby enabling adaptive and appropriate crisis response according to national interests.

A brief description of each drawing is provided in order to more fully understand the drawings cited in the detailed description of the present invention.
1 is a diagram schematically showing a system configuration for implementing a crisis alert level management method according to an embodiment of the present invention.
2 is a diagram schematically showing the configuration of a crisis warning level management system according to an embodiment of the present invention.
3 is a diagram illustrating a crisis warning level and a criterion for determination.
4 is a diagram illustrating an example of a table of disaster spread factors for each type of disaster according to an embodiment of the present invention.
5 is a diagram for explaining collection of social trend information according to an embodiment of the present invention.
6 and 7 are diagrams for explaining an example of social trend information according to an embodiment of the present invention.
8 is a diagram for explaining a method of determining a crisis alert level according to an embodiment of the present invention.

Since the present invention can apply various transformations and have various embodiments, specific embodiments are illustrated in the drawings and will be described in detail in the detailed description. However, this is not intended to limit the present invention to a specific embodiment, it should be understood to include all conversions, equivalents, and substitutes included in the spirit and scope of the present invention. In describing the present invention, when it is determined that a detailed description of a related known technology may obscure the subject matter of the present invention, a detailed description thereof will be omitted.

Terms such as first and second may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another component.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise.

In the present specification, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and one or more other It is to be understood that the presence or addition of features, numbers, steps, actions, components, parts, or combinations thereof, does not preclude the possibility of preliminary exclusion.

In addition, in the present specification, when one component'transmits' data to another component, the component may directly transmit the data to the other component, or through at least one other component. This means that the data may be transmitted to the other component. Conversely, when one component'directly transmits' data to another component, it means that the data is transmitted from the component to the other component without passing through the other component.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings, focusing on embodiments of the present invention. The same reference numerals shown in each drawing indicate the same members.

1 is a diagram schematically showing a system configuration for implementing a crisis alert level management method according to an embodiment of the present invention.

Referring to FIG. 1, in order to implement a method for managing a crisis level according to an embodiment of the present invention, a crisis level management system 100 may be provided.

The crisis warning level management system 100 may refer to a system that performs a function of automatically determining the crisis warning level of the disaster when a disaster situation occurs according to the technical idea of the present invention.

In the present specification, the term “disaster” includes natural disasters and accidents, as well as accidents caused by humans, and may mean comprehensively including situations requiring crisis management and response.

In addition, the fact that the crisis warning level management system 100 automatically determines the crisis warning level means only the case where the crisis warning level determined by the crisis warning level management system 100 according to the technical idea of the present invention is final. It is not, and a person or organization finally determines the level of crisis warning based on the judgment of the crisis level management system 100, or the judgment of the risk level management system 100 and the judgment of the person or organization are combined to warn of a crisis. It may mean that the level is finally determined.

In the case of a disaster, the level of crisis warning was determined by collecting information on the situation of the disaster site and checking the collected information. In this method, the collection of information on a wide range of related factors other than the situation information of the disaster site is done manually by humans, so it takes time and the breadth of the information is inevitably limited. It takes time, and there is a problem in that the judgment result is inconsistent due to an artificial judgment by a person.

In order to solve this problem, the crisis warning level management system 100 according to the technical idea of the present invention not only quickly collects element information to be considered in determining the crisis warning level, but also information that has not been previously considered (for example, Social trend information, etc.) are reflected in the determination of the level of crisis warning, thereby providing an effect that adaptive disaster response can be performed reasonably according to the public's social interests.

To this end, the crisis warning level management system 100 includes a manager terminal 200, an information channel 300, and/or a social channel 400 to collect risk warning level consideration factors defined according to the technical idea of the present invention. And communication.

The manager terminal 200 may be artificially collected at the disaster site, such as the occurrence of a disaster situation and/or disaster site information (eg, type of disaster, current progress, degree of damage, number of casualties, number of requested persons, etc.). It may be a terminal for inputting information. The manager terminal 200 may mean a terminal used by a predetermined manager who responds to and manages a disaster situation, and can communicate with the crisis alert level management system 100 such as a computer, a mobile phone, and a smart pad. An average expert in the technical field of the present invention can easily infer that it can be implemented with any type of data processing device.

The information channel 300 may refer to various and formal information collection routes capable of automatically collecting factors that may be considered in determining a crisis alert level. For example, the information channel 300 may be a system of a related institution, such as the Meteorological Administration, the National Police Agency, the Fire and Disaster Prevention Administration, the Ministry of Public Administration and Security, the local government, etc. Does not.

The information collected through the information channel 300 may be element information to be considered in determining the crisis level, that is, standardized information, such as weather information, traffic information, geographic information, regional information, and the like, among warning level consideration information. Therefore, any channel capable of collecting standardized information among warning level consideration information may be included in the information channel 300.

One of the important warning level consideration information collected through the information channel 300 may be information on the possibility of spreading a disaster situation. The likelihood of proliferation is to determine the level of crisis warning depending on whether or not a disaster can spread further, and in the past, there have been many cases of relying on artificial judgments of those involved in the likelihood of spreading.

However, according to the technical idea of the present invention, factors that can determine the probability of spreading according to the type of disaster, that is, the factors of disaster spread, are specified in advance, and the specified factors are automatically collected and then used to determine the level of crisis warning. By reflecting it, it has the effect of making quick and consistent judgments.

Disaster spread factors may include factors that affect the spread of the disaster itself as well as factors that affect the spread of damage caused by the disaster.

For example, if the type of disaster is a fire, information that may affect the spread of the fire itself (e.g., wind speed, humidity, etc.) may be specified as a disaster spread factor, and factors that may affect the spread of damage. (For example, local information such as building density at a fire site, population density, traffic situation information, etc.) may exist.

In addition, when the type of disaster is a maritime accident, marine weather information such as the flow rate and visibility of the tide can be a disaster spread factor, and the number of ships that can be rescued in the vicinity may be further included in the disaster spread factor if necessary.

As described above, when a disaster spread factor is specified in advance for each disaster, when a disaster occurs, such disaster spread factors are quickly collected through the information channel 300, and then the risk warning level is determined in consideration of the probability of the spread of the disaster according to the collected results. Compared to this, it has the effect of being able to make a reliable judgment of the level of crisis warning based on a quick, consistent and wide range of information.

Meanwhile, the social channel 400 may mean an information collection channel capable of collecting social trend information included in the alert level consideration information according to the technical idea of the present invention. Such social trend information is information that has not been considered at all in determining the crisis warning level in the prior art, but may be information that can be further considered in a system for determining an automated and consistent crisis warning level as in the technical idea of the present invention.

The social trend information may mean unstructured information capable of confirming the attitudes or reactions of users, that is, citizens or local residents to a disaster situation.

As social trend information is considered in the risk warning level consideration information, it is possible to respond more and more appropriately and promptly by the relevant organizations according to the trend of reaction to the public's interest.

Such social trend information may include media content (e.g., a press article) corresponding to a disaster situation and/or user content including direct social reactions of people or local residents. The social response may be meant to include any information including a user's response to a disaster situation, such as content directly generated by a user (national or local, etc.), such as blogs, cafes, videos, or comments on them.

Accordingly, the social channel 400 may include a media company system or a predetermined SNS channel (eg, Facebook, Instagram, cafe, blog, etc.).

According to an example, the social trend information collected by the crisis warning level management system 100 may be an analysis target such as, for example, the frequency of media content or user content, or a result of sentiment analysis. That is, the media content or user content corresponding to the disaster situation may refer to the content mentioning the disaster. And this frequency can be used as an indicator of the degree of interest of the media or the public. According to an example, the higher the frequency, the higher the level of crisis warning or the same level of crisis warning can be reflected in the detailed level.

Sentiment Analysis may mean analyzing a user's sentiment to a disaster situation expressed in media content or user content.

This sentiment analysis is also called opinion mining, and conventionally, a method of classifying polarity detection reactions such as positive, negative, neutral, etc. from text through traditional machine learning techniques (e.g., Naive Bayes method) Can be used.

In addition, in recent years, more advanced sentiment analysis has become possible through deep learning. This deep learning method learns a number of data (social reactions) labeled with predetermined reactions with a deep learning-based natural language processing model, and responds to data input to the learned model by one or more of the predetermined reactions. It can be implemented as a kind of classification model that performs classification.

In addition, when implementing such a deep learning-based sentiment analysis model, it is possible to classify various reactions according to the labeling result of learning data in addition to simple classification as positive, negative, and neutral.

For example, reactions may be classified as very positive, somewhat positive, neutral, somewhat negative, and very negative, or may be classified as depression, anxiety, displeasure, sadness, disappointment, relief, joy, and happiness, as will be described later. In this case, reactions of depression, anxiety, discomfort, sadness, and disappointment may be classified as negative reactions and positive reactions. Accordingly, there is an effect that the determination of the crisis warning level and the adaptive determination of the response level according to the determined crisis warning level can be made.

Since the implementation of a machine learning or deep learning model for such emotion analysis is well known, a detailed description of the specific emotion analysis model will be omitted in this specification.

As described above, according to the technical idea of the present invention, information on the possibility of spreading a disaster and/or social trend information may be used for warning level consideration information. Such information may be transmitted to the crisis warning level management system 100 through the manager terminal 200 and/or the information channel 300.

In addition, the information on the crisis warning level determined by the crisis warning level management system 100 is transferred to a system or terminal of a person involved in crisis response, such as a system of various related organizations or a responder terminal performing a response, that is, a crisis response system 500. Of course it can be transmitted.

Depending on the embodiment, the crisis alert level management system 100 may further transmit meaningful information such as a predetermined response manual according to the crisis alert level to the crisis response system 500.

A schematic configuration of the crisis warning level management system 100 for implementing this technical idea may be as shown in FIG. 2.

2 is a diagram schematically showing the configuration of a crisis warning level management system according to an embodiment of the present invention.

2, the crisis warning level management system 100 according to the technical idea of the present invention includes a memory 120 in which a program for implementing the technical idea of the present invention is stored, and a program stored in the memory 120. A processor 110 for execution may be provided.

An average expert in the technical field of the present invention can easily infer that the processor 110 may be named by various names such as CPU and mobile processor, depending on the implementation example of the crisis warning level management system 100. . In addition, the platform providing system 100 may be implemented by organically combining a plurality of physical devices. In this case, the processor 110 is provided with at least one for each physical device to provide the platform providing system 100 of the present invention. That it can be implemented will be easily inferred by an average expert in the technical field of the present invention.

The memory 120 stores the program, and may be implemented as any type of storage device that the processor can access to drive the program. In addition, according to a hardware implementation example, the memory 120 may be implemented as a plurality of storage devices instead of a single storage device. In addition, the memory 120 may include not only a main memory device but also a temporary memory device. Also, it may be implemented as a volatile memory or a nonvolatile memory, and may be defined as including all types of information storage means implemented so that the program can be stored and driven by the processor.

The crisis warning level management system 100 may be a system operated and implemented by a government agency, a local government, or an authority in charge of disaster response according to an embodiment, and may be implemented in various ways, such as a web server and a computer. , It may be defined as including any type of data processing device capable of performing the functions defined in the present specification.

In addition, various peripheral devices (peripheral devices 1 to N) may be further provided according to an embodiment of the crisis warning level management system 100. For example, an average expert in the technical field of the present invention can easily infer that a keyboard, a monitor, a graphic card, a communication device, etc. may be further included in the crisis warning level management system 100 as peripheral devices.

Hereinafter, it is an average expert in the technical field of the present invention that the function or process of the crisis warning level management system 100 defined in the present specification can be implemented by the processor 110 driving a program stored in the memory 120. Can be easily deduced.

3 is a diagram illustrating a crisis warning level and a criterion for determination.

The crisis warning level and determination standard shown in FIG. 3 exemplarily illustrate the large-scale fire crisis alarm determination standard of a conventional multi-dense facility.

As shown in FIG. 3, the conventional crisis warning level is largely divided into four levels: interest, caution, warning, and seriousness.

The general criteria for determining the level of crisis warning can be as follows.

The level of interest may have signs, but the level of expansion is low, and the possibility of developing a national crisis within the near period is relatively low.

Attention level refers to a state in which symptom activity is relatively active and a certain level of tendency to develop into a national crisis appears, and warning level refers to a state where symptom activity is very active and development of Songdo is remarkable, and there is a possibility of development into a national crisis. It means a rich state, and the severity level can be defined as a state in which the occurrence of a crisis is certain as the symptom activity is very active and the development speed and tendency are serious.

In addition, the criterion for defining the level of crisis alerting as concretely as possible for each type of disaster may be the level of risk alerting and the criterion for determining each level as shown in FIG. 3.

However, as shown in FIG. 3, even if specific criteria for each type of disaster are previously defined, these criteria may be quite conceptual and ambiguity, and there are cases in which the contents of the general criteria are not reflected in detail.

Therefore, when a large fire actually occurs in a multi-dense facility based on the judgment criteria shown in Fig. 3, when determining the crisis level of the current disaster situation through a meeting of related organizations, different judgments depending on the participants and the timing. There are cases in which this is achieved or the clarity of the judgment is poor.

In order to solve this problem, according to the technical idea of the present invention, the factors to be reflected when considering the crisis level are specifically defined, and these factors, that is, the alert level consideration information are collected as much as possible so that the determination of the alert level is as clear and prompt as possible. Making it possible can be its main purpose and effect.

According to the technical idea of the present invention, it is possible to determine the alarm level based on the clear standard defined by the present invention, that is, the alarm level consideration information, not the ambiguous judgment standard as shown in FIG. 3.

As such a criterion for determination, the clear criterion defined by the present invention, that is, the alert level consideration information, includes information on the possibility of spreading a disaster and/or social trend. In addition, according to an embodiment, the number of casualties, the number of victims, and the degree of damage may be further included as warning level consideration information.

In addition, a detailed grade can be divided for each warning level consideration information, and a detailed grade can be evaluated for each warning level consideration information for the current disaster situation. In addition, the level of warning of a disaster can be determined by comprehensively considering these detailed grades.

For example, FIG. 8 is a diagram for explaining a method of determining a crisis alert level according to an embodiment of the present invention. As shown in FIG. 8, the crisis alert level management system 100 includes each alert level consideration information. It is possible to classify detailed grades (eg, high, medium, low), and define a predetermined detailed index for each detailed grade.

In addition, criteria for belonging to each subclass can be defined in advance for each type of disaster.

For example, in the case of a fire, a specific criterion (eg, what is the wind speed, what is the population density of the corresponding region information, etc.) for classifying the probability of spread into high, medium, and low subclasses may be predefined.

Similarly, specific criteria (eg, how often the frequency is, the ratio of negative sentiment analysis results, etc.) to be classified as high, medium, or low in the social trend information may be predefined.

In the same way, specific criteria for classifying into high, medium, and low detailed levels for each warning level consideration information (eg, the number of casualties, the number of victims, the degree of damage, etc.) may be predefined.

In addition, a certain detailed index can be assigned to each detailed grade, and the total disaster index can be calculated comprehensively according to the detailed index for each warning level consideration information.

Of course, in order to calculate the overall overall index, the same level of contribution (or weight factor) is assigned for each warning level consideration information, and can be simply determined by the sum of the detailed indexes. An index may be calculated, and various embodiments are possible.

In addition, it goes without saying that a specific criterion for classifying a detailed grade may also have a range defined in various ways according to exemplary embodiments.

In any case, if such a criterion is clearly defined, in the event of a disaster situation, the detailed index for each warning level consideration information and the total index can be clearly and quickly determined according to the defined criterion.

In this way, the detailed grade, the judgment standard for each detailed grade, and the detailed index shown in FIG. 8 may be predefined for each type of disaster.

Meanwhile, an example for determining the possibility of spreading, which is one of important warning level consideration information for determining the crisis level according to the technical idea of the present invention, is shown in FIG. 4.

4 is a diagram illustrating an example of a table of disaster spread factors for each type of disaster according to an embodiment of the present invention.

Referring to FIG. 4, the crisis warning level management system 100 may predefine a disaster spread factor, which is an factor affecting the spreading probability of a corresponding disaster, as shown in FIG. 4 for each type of disaster. In this specification, the defined information will be referred to as a disaster spread factor table for each type of disaster.

This disaster spread factor table is collected to determine the possibility of the spread of a disaster in addition to the information that can be checked at the disaster site through the information channel 300 when the disaster situation occurrence information is input to the crisis warning level management system 100. It may be a collection object to do.

For example, the crisis warning level management system 100 may receive information on occurrence of a disaster situation from the manager terminal 200. The disaster situation occurrence information may include only basic information such as, for example, the type of disaster and the location of the disaster. Depending on the embodiment, the disaster situation occurrence information may additionally include additional information that can be checked through the disaster site, such as the number of requested persons and the number of casualties, and such information may be used as warning level consideration information.

In any case, the crisis warning level management system 100 may specify the type of disaster based on the information on the occurrence of the disaster situation. Then, which disaster spread factors to be collected according to the type of disaster can be specified based on the disaster spread factor table for each disaster type.

Of course, in some cases, some of the information defined in the disaster spread factor table for each disaster type may be included in the disaster situation occurrence information, and in this case, only the remaining disaster spread factor information may be collected.

When a disaster spread factor is specified according to the type of disaster, the crisis warning level management system 100 may collect the specified disaster spread factor through the information channel 300. Of course, such collection may be performed through a protocol or API previously agreed upon with the information channel 300.

For example, in the case of a fire, wind speed, wind direction, local information (population density, arrangement of buildings, etc.), humidity, etc. can be previously defined as factors of disaster spread, and in the case of a flood, geographic information including information on topography, Various information, such as predicted precipitation and atmospheric pressure, can be defined as factors of disaster spread. In the case of a traffic accident, fog or visibility information, traffic information such as traffic volume or width of a road in a nearby area may be previously defined as a disaster spread factor.

As described above, when the disaster spread factors are previously defined for each type of disaster, and the information channel 300 capable of collecting the defined disaster spread factors is specified in advance, the crisis warning level management system 100 provides information on the occurrence of disaster situations. When inputted, information on the disaster spreading factor according to the type of disaster may be immediately collected through the information channel 300.

In addition, it can be calculated by indexing the degree of the probability of spreading as described in FIG. 8 according to the collected disaster spreading factors.

Meanwhile, an example of collecting and determining social trend information defined as important alert level consideration information according to the technical idea of the present invention will be described with reference to FIGS. 5 to 7.

5 is a diagram for explaining collection of social trend information according to an embodiment of the present invention, and FIGS. 6 and 7 are diagrams for explaining an example of social trend information according to an embodiment of the present invention.

First, referring to FIG. 5, the crisis warning level management system 100 is capable of confirming the trends of the media and/or user reactions from various media companies, social channels (eg, SNS, etc.), and/or systems of various related organizations. Various contents can be crawled.

Such crawling may be performed immediately upon receipt of the disaster situation occurrence information, that is, when the crisis warning level management system 100 recognizes that a disaster situation has occurred, and may be continuously performed at regular intervals rather than a one-time collection.

The trend of the reaction analysis results obtained from the social trend information is checked continuously, and not only the simple reaction analysis result but also the change trend of the reaction analysis result is reflected in determining the detailed grade or index of the warning level consideration information called social trend information. can do.

As described above, the response analysis result of the social trend information may include the frequency of the content corresponding to the disaster situation included in the media content and/or the user content or the emotional analysis result.

Therefore, when the crisis warning level management system 100 uses or considers the social trend information to determine the crisis warning level, it may mean that the reaction analysis result of the social trend information is used or considered.

An example for determining the frequency of content corresponding to a disaster situation may be as illustrated in FIG. 6.

The crisis warning level management system 100 can analyze the number of specific disasters mentioned, that is, the frequency, in various predetermined social channels (eg, Twitter, blog, community, Instagram, etc.), as shown in FIG. 6. have. In addition, the frequency of media content (eg, news) may be separately analyzed as shown in FIG. 6.

When this frequency is derived from the reaction analysis result of the social trend information, the reaction analysis result as shown in FIG. 6 is transmitted to the manager terminal 200 so that the manager can check it in real time.

In addition, depending on the embodiment, the index of the total frequency may be calculated by assigning a weight to the calculation of the frequency for each channel for collecting media content or user content.

The high frequency index or index can be regarded as an index that indirectly indicates that the national or social interest in the disaster is high or serious. Accordingly, the higher the frequency, the higher the warning level. Rules or algorithms can be designed.

The fact that the warning level can be raised may mean not only raising the crisis warning level itself according to the frequency, but also raising the detailed rating for each warning level consideration information called social trend information, as described above.

In order to calculate the frequency response analysis result, the crisis warning level management system 100 counts the content mentioning the disaster situation from a plurality of random contents collected from social channels, or crawls only the content mentioning the disaster situation. An average expert in the technical field of the present invention can easily infer that an embodiment is possible.

Meanwhile, the response analysis result analyzed by the crisis warning level management system 100 through the social trend information may be the result of sentiment analysis as shown in FIG. 7.

The sentiment analysis result may mean a result of classifying the sentiment of the content creator as described above, and the crisis warning level management system 100 may include a sentiment analysis engine for sentiment analysis. In addition, the classification classification for each content may vary according to which classifications the emotion analysis engine included in the crisis warning level management system 100 learns to classify the contents.

For example, the exemplary emotion analysis result shown in FIG. 7 shows an example in which contents are classified into emotions such as depression, anxiety, displeasure, sadness, disappointment, relief, joy, and happiness.

However, depending on the embodiment, the crisis warning level management system 100 may be implemented to simply classify it into three sensibilities of positive, negative, and neutral, and strong positive, weak positive, strong negative, weak negative, neutral, etc. It can also be implemented so as to classify it into five sensibilities.

Depending on the embodiment, emotions may be classified in various ways, and the emotion analysis engine may be trained to classify content into any one of pre-classified emotions.

Embodiments for implementing such an emotion analysis engine have been widely known. For example, at least one of a pure Bayesian classification (Naive Bayes), a random forest, a support vector machine, or a deep learning method may be used.

For example, the deep learning method uses a context sensitive natural language processing model (e.g., Google BERT, etc.) to label a plurality of media content or user content with one of predetermined emotions, Learning can be performed on a plurality of labeled contents as learning data.

The learned emotion analysis engine may perform a function of classifying the input content into one of predetermined emotions when new content is input.

The specific implementation method of the sentiment analysis engine is well known, and in any case, the crisis warning level management system 100 equipped with the sentiment analysis engine summarizes and analyzes how the media or users react to the current disaster situation. Can play a role.

In addition, by actively using the results of this analysis when determining the level of crisis warning, even informal elements (the level of media or public interest) can be used to determine the level of disaster response.

For example, according to an embodiment, the crisis warning level management system 100 may determine that the alert level is improved as a result of the sentiment analysis results in a negative reaction rate higher. Negative reaction may mean a reaction that can be treated as a negative reaction among a variety of emotional components, as well as that there is a negative in the classification of emotion itself. For example, in the example illustrated in FIG. 7, depression, anxiety, displeasure, sadness, disappointment, etc. may be negative reactions.

In addition, depending on the embodiment, among the negative reactions, the average expert in the technical field of the present invention can easily distinguish whether it is a strong negative reaction or a weak negative reaction and use it as a differential influence factor in determining the alarm level. You will be able to infer.

As a result, according to the technical idea of the present invention, it is possible to quickly and consistently determine the crisis warning level according to the unique warning level consideration information defined in the present invention, and by using this, there is an effect of enabling a quick and appropriate crisis response. .

Meanwhile, according to an implementation example, the crisis warning level management system 100 may include a processor and a memory storing a program executed by the processor. The processor may include a single-core CPU or a multi-core CPU. The memory may include high-speed random access memory and may include non-volatile memory such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid state memory devices. Access to memory by the processor and other components can be controlled by the memory controller. Here, when the program is executed by a processor, the crisis warning level management system 100 according to the present embodiment may perform the above-described method for providing an intelligent disaster response training system.

Meanwhile, the crisis warning level management method according to an embodiment of the present invention may be implemented in the form of a computer-readable program command and stored in a computer-readable recording medium. The program may also be stored in a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system.

The program instructions recorded on the recording medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in the software field.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and floptical disks. Hardware devices specially configured to store and execute program instructions such as magneto-optical media and ROM, RAM, flash memory, and the like are included. In addition, the computer-readable recording medium is distributed over a computer system connected through a network, so that computer-readable codes can be stored and executed in a distributed manner.

Examples of program instructions include not only machine language codes such as those produced by a compiler, but also devices that process information electronically using an interpreter, for example, high-level language codes that can be executed by a computer.

The above-described hardware device may be configured to operate as one or more software modules to perform the operation of the present invention, and vice versa.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that other specific forms can be easily modified without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. .

Claims (13)

Receiving, by the crisis warning level management system, disaster situation occurrence information;
Specifying the type of the disaster based on the disaster situation occurrence information received by the crisis warning level management system, and determining spreadability information to be collected based on the specific type of the disaster;
Obtaining, by the crisis warning level management system, information about the determined spreadability; And
And determining a crisis warning level of the disaster situation based on the warning level consideration information including the spreadability information obtained by the crisis warning level management system.
The method of claim 1, wherein the crisis warning level management method comprises:
The crisis warning level management system further comprises the step of storing a disaster spread factor table defining disaster spread factors for each disaster type,
The step of determining the spreadability information to be collected based on the type of the disaster,
And determining the spreadability information based on the disaster spread factor table.
The method of claim 1, wherein the crisis warning level management method comprises:
Further comprising the step of obtaining social trend information corresponding to the disaster situation,
The step of determining the crisis warning level of the disaster situation based on the warning level consideration information including the spreadability information obtained by the crisis warning level management system,
And determining a crisis warning level of the disaster situation based on the warning level consideration information further including the social trend information.
The method of claim 3, wherein obtaining social trend information corresponding to the disaster situation,
Comprising the step of acquiring media content corresponding to the disaster situation or user content corresponding to the disaster situation,
The step of determining the crisis warning level of the disaster situation based on the warning level consideration information further including the social trend information,
A crisis warning level management method for determining a crisis warning level of the disaster situation based on the frequency of the media content or the user content.
The method of claim 4, wherein the step of determining a crisis warning level of the disaster situation based on the warning level consideration information further comprising the social trend information,
And performing a sentiment analysis of the media content or the user content, and determining a crisis alert level of the disaster situation based on a result of the sent sentiment analysis.
The method of claim 3, wherein the determining of the crisis level of the disaster situation based on the alert level consideration information further comprising the social trend information comprises:
The higher the frequency of the media content or user content included in the social trend information, the higher the level index for determining the crisis warning level, or the higher the negative reaction result of the sentiment analysis of the media content or the user content, the higher the level index. How to manage the level of crisis warning to improve.
The method of claim 1, wherein the determining of the crisis level of the disaster situation based on the alert level consideration information including the spreadability information obtained by the crisis level management system comprises:
And determining a crisis warning level of the disaster situation based on the warning level consideration information further including the number of casualties, the number of victims, or the degree of damage in the disaster situation.
The method of claim 1, wherein the determining of the crisis level of the disaster situation based on the alert level consideration information including the spreadability information obtained by the crisis level management system comprises:
Determining a detailed index for each alarm level consideration information according to a detailed grade classified for each alarm level consideration information; And
And determining the crisis alert level by synthesizing the determined detailed indices for each alert level consideration information.
Receiving, by the crisis warning level management system, disaster situation occurrence information;
Obtaining, by the crisis warning level management system, social trend information corresponding to the disaster situation;
And determining, by the crisis alert level management system, a crisis alert level of the disaster situation based on alert level consideration information including the social trend information.
A computer program installed in a data processing apparatus and stored on a computer-readable recording medium for performing the method according to any one of claims 1 to 9.
Processor;
A storage device in which a program driven by the processor is stored,
The program driven by the processor,
Receiving the disaster occurrence information, specifying the type of disaster based on the received disaster occurrence information, determining the spreadability information to be collected based on the specific disaster type, and obtaining the determined spreadability information, A crisis warning level management system that determines a crisis level of the disaster based on the acquired information regarding the level of warning including the information about the possibility of spreading.
The method of claim 11, wherein the program driven by the processor,
A crisis alert level management system that further acquires social trend information corresponding to the disaster situation, and determines a crisis alert level of the disaster situation based on the alert level consideration information further including the social trend information.
Processor;
A storage device in which a program driven by the processor is stored,
The program driven by the processor,

A crisis warning level that receives disaster occurrence information, obtains social trend information corresponding to the disaster situation, and determines the crisis warning level of the disaster situation based on the alert level consideration information including the obtained social trend information. Management system.

Images