KR-20260065684-A - Electronic apparatus for automatically classifying the scale of human casualties and control method for automatically classifying the scale of human casualties using the same

KR20260065684AKR 20260065684 AKR20260065684 AKR 20260065684AKR-20260065684-A

Abstract

An electronic device is disclosed. The electronic device includes an interface for receiving data regarding human casualties, a memory for storing a neural network model and instructions, and at least one processor. The processor performs text preprocessing based on the data regarding human casualties, inputs the text-preprocessed human casualties data into a neural network model to obtain sentiment words, classifies the obtained sentiment words into negative sentiment words and positive sentiment words, calculates sentiment scores for the human casualties data based on the classified sentiment words, and classifies and provides risk levels for the human casualties data by grade based on the calculated sentiment scores.

Inventors

김철홍
성유기

Assignees

미래아이티(주)

Dates

Publication Date: 20260511
Application Date: 20241101

Claims (12)

In an electronic device for automatically classifying the scale of casualties based on data regarding casualties, Interface for receiving data regarding the above-mentioned casualties; Memory for storing neural network models and instructions; and It includes at least one processor; and The above processor is, Text preprocessing is performed based on the data regarding the aforementioned casualties, and The human casualty data, on which the above text preprocessing has been performed, is input into the above neural network model to obtain emotion words, and the obtained emotion words are classified into negative emotion words and positive emotion words, and Calculate emotional scores for human casualty data based on classified emotional words, and An electronic device that classifies and provides risk levels for human casualty data by grade based on calculated assessment scores.
In paragraph 1, The above processor is, Based on the data regarding the aforementioned casualties, tokenization is performed to separate the text into sentences and words, and An electronic device that performs stopword removal by removing meaningless words from data based on tokenized data.
In paragraph 1, The above neural network model is, Based on a pre-configured emotion dictionary, emotion words are obtained from the data regarding the aforementioned human casualties, and An electronic device that classifies the said emotion words based on preset negative emotion words and positive emotion words.
In paragraph 3, The above processor is, An electronic device that calculates the ratio of positive and negative emotional words to the total emotional words included in the data regarding human casualties based on classified emotional words, and calculates the emotional score based on the calculated ratio of emotional words.
In paragraph 3, The above processor is, Based on classified sentiment words, text patterns for phrases or multi-word expressions (MWE) related to casualties are extracted from the above casualty data, and Calculate an sentiment score for each pattern of the above text patterns, and An electronic device that obtains a total emotional score by summing the emotional score for each pattern to the emotional score calculated based on the above-mentioned emotional words.
In paragraph 1, The above processor is, Using a supervised learning algorithm, emotion words are obtained based on the data regarding the aforementioned human casualties with emotion labels, and An electronic device that classifies data regarding human casualties according to a preset grade using a machine learning classifier based on emotion words obtained using the above supervised learning.
In paragraph 1, The above processor is, An electronic device that classifies emotion words by performing context-based sentiment analysis of data regarding the aforementioned human casualties based on a deep learning model.
A control method for an electronic device for automatically classifying the scale of human casualties based on data regarding human casualties, A step of collecting data on the above-mentioned casualties; A step of performing text preprocessing based on the above data regarding casualties; A step of obtaining emotion words by inputting the human casualty data, on which the above text preprocessing has been performed, into a neural network model; A step of classifying acquired emotion words into negative emotion words and positive emotion words; A step of calculating an emotional score of human casualty data based on classified emotional words; and A control method comprising the step of classifying and providing risk levels for human casualty data by grade based on calculated emotional scores.
In paragraph 8, The step of performing the above text preprocessing is, A tokenization step for separating text into sentences and words based on the data regarding the aforementioned casualties; Stopword Removal step of removing meaningless words from data based on tokenized data; A stemming and lemmatization step that standardizes the form of words based on the above tokenized data to consistently process similar words; and A control method comprising a normalization step that converts text into a consistent format by unifying uppercase letters and punctuation based on the above-mentioned tokenized data.
In paragraph 8, The step of calculating the assessment score of the above human casualty data is, A step of calculating the ratio of positive and negative emotional words to the total emotional words included in the data on human casualties based on classified emotional words; and A control method comprising the step of calculating the emotion score based on the ratio of calculated emotion words.
In Paragraph 10, The step of calculating the assessment score of the above human casualty data is, A step of extracting text patterns for phrases or multi-word expressions (MWE) related to human casualties from the human casualty data based on the above-described classified emotion words; A step of calculating an emotion score for each pattern of the above text pattern; and A control method comprising the step of obtaining a total emotional score by summing the emotional score for each pattern to the emotional score calculated based on the above emotional words.
A computer-readable recording medium comprising a program for executing a control method for an electronic device for automatically classifying the scale of casualties based on data regarding casualties, The above control method is, A step of collecting data on the above-mentioned casualties; A step of performing text preprocessing based on the above data regarding casualties; A step of obtaining emotion words by inputting the human casualty data, on which the above text preprocessing has been performed, into a neural network model; A step of classifying acquired emotion words into negative emotion words and positive emotion words; A step of calculating an emotional score of human casualty data based on classified emotional words; and A computer-readable recording medium comprising the step of classifying and providing risk levels for human casualty data by grade based on calculated assessment scores.

Description

Electronic apparatus for automatically classifying the scale of human casualties and control method for automatically classifying the scale of human casualties using the same The present disclosure relates to an electronic device for automatically classifying the scale of human casualties and a control method for automatically classifying the scale of human casualties using the same, and more specifically, to an electronic device for automatically classifying the scale of human casualties based on data related to human casualties of a major social disaster and a control method for automatically classifying the scale of human casualties using the same. A disaster refers to an event caused by natural phenomena or man-made accidents that inflicts significant social or economic damage. Disasters can be classified into natural disasters, which occur naturally, and social disasters, which occur man-made. Natural disasters may include damage caused by typhoons or storms, flooding and landslides due to torrential rain, damage caused by heavy snowfall, meteorological disasters caused by weather factors such as floods and tsunamis, and geological disasters caused by earthquakes or volcanic activity. Social disasters may include fires, explosions of hazardous materials, radioactive leaks at nuclear power plants, and traffic accidents (e.g., car accidents, ship sinkings, aircraft accidents). Meanwhile, damages resulting from social disasters may include property damage and loss of life. Among these, loss of life is of paramount importance as it directly relates to human life; therefore, it is necessary to promptly classify and provide the scale of damage associated with the accident. FIG. 1 is a block diagram showing the configuration of an electronic device according to various embodiments of the present disclosure. FIGS. 2 and 3 are flowcharts for explaining a method of controlling an electronic device according to various embodiments of the present disclosure. The terms used in this specification will be briefly explained, and the present disclosure will be described in detail. The terms used in the embodiments of this disclosure have been selected to be as widely used as possible, taking into account their functions within this disclosure; however, these terms may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant explanatory section of this disclosure. Therefore, terms used in this disclosure should be defined not merely by their names, but based on their meanings and the overall content of this disclosure. In this specification, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of such features (e.g., numerical values, functions, operations, or components such as parts) and do not exclude the presence of additional features. In the present disclosure, expressions such as “A or B,” “at least one of A or/and B,” or “one or more of A or/and B” may include all possible combinations of items listed together. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” may refer to cases including (1) at least one A, (2) at least one B, or (3) both at least one A and at least one B. Expressions such as "first," "second," "first," or "second" used in this specification may modify various components regardless of order and/or importance, and are used only to distinguish one component from another and do not limit said components. Where it is stated that a component (e.g., Component 1) is "operatively or communicatively coupled with/to" or "connected to" another component (e.g., Component 2), it should be understood that the component may be directly connected to the other component or connected through the other component (e.g., Component 3). The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "consisting of" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. In the present disclosure, a "module" or "part" performs at least one function or operation and may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of "modules" or a plurality of "parts" may be integrated into at least one module and implemented by at least one processor (not shown), except for a "module" or "part" that needs to be implemented in specific hardware. An embodiment of the present disclosure will be described in more detail below with reference to the